Page 5 (data 121 to 150 of 351) | Displayed ini 30 data/page
<< PREV 1 2 3 4 5 6 7 8 9 10 11 12 NEXT >>

121	Topic B: Applications of Remote Sensing	ABS-319
Satellite Imagery-Based PM10 Air Parameter Analysis in Makassar City Nurul Masyiah Rani Harusi1,2*, Rizieq Akbar Mubarak 1,2 , Sumarni Hamid Aly1,2, Mitani Yasuhiro3 , Khaerul Amru4,2 1Department of Environmental Engineering, Facutly of Engineering, University of Hasanuddin, St. Poros Malino KM. 6, Bontomarannu, Gowa, South Sulawesi, 92172, Indonesia 2 Transportation and Air Quality Research Group, University of Hasanuddin, St. Perintis Kemerdekaan No. KM. 10, Makassar, South Sulawesi, 90245, Indonesia 3Department of Civil Engineering, Faculty of Engineering, University of Kyushu, Fukuoka, 819-0395, Japan 4Research Center for Environmental and Clean Technology, National Research, and Innovation Agency (BRIN), Geotech Building 820, Puspuptek Sorong, South Tangerang, Indonesia Abstract Air pollution caused by particulate matter (PM10) remains a pressing environmental issue in major urban centers, particularly in Makassar City, where rapid population growth and the increasing number of vehicles significantly contribute to deteriorating air quality. Conventional monitoring methods are constrained by the limited coverage of Air Quality Monitoring Stations, which fail to capture the spatial variability of pollutants. This study applies remote sensing techniques using Landsat 8 Operational Land Imager (OLI) data to estimate PM10 concentrations across Makassar. Two established algorithms were implemented: Othman (2010), which utilizes visible bands (Blue, Green, Red), and Mozafari (2019), which employs coastal/aerosol, green, and red bands combined with the Normalized Difference Vegetation Index (NDVI) to account for vegetation effects. Data preprocessing, atmospheric correction, and algorithmic modeling were performed on the Google Earth Engine platform. Spatial analysis revealed elevated concentrations along major road corridors and commercial-industrial areas, particularly on 6/2 divided and 4/2 divided roads, where traffic volumes are highest. In contrast, residential and green spaces exhibited relatively lower values, confirming the influence of land use and road type on particulate distribution. The integration of remote sensing with GIS-based analysis successfully highlights pollution hotspots, demonstrating the potential of satellite-based monitoring as a complementary tool to conventional air quality networks. Keywords: Air quality, Particulate Matter, Landsat 8, Remote sensing, Makassar Metropolitan City Share Link | Plain Format | Corresponding Author (Nurul Masyiah Rani Harusi)

122	Topic B: Applications of Remote Sensing	ABS-320
Assessing the performance of recognized ML approaches on remote sensing data for sowing progress detection in Kazakhstan Alfarabi Imashev (a*,b), Nurali Khamitov (b) a) Nazarbayev University, Astana 010000, Kazakhstan * alfarabi.imashev[at]nu.edu.kz b) LLP SkyTerra, Astana 010000, Kazakhstan n.khamitov[at]skyterra.ai Abstract Remote sensing fundamentally entails the acquisition of data about the Earth^s surface using satellites, drones, or sensors placed on airplanes, without direct interaction with the terrain. Remote sensing has revolutionized industrial agriculture, providing farmers and researchers with effective tools to observe and manage crops with greater effectiveness and sustainability. This technology enables monitoring of vast agricultural areas, assisting in the evaluation of crop vitality, soil moisture levels, insect invasions, and nutritional deficits. Several main applications encompass: - Multispectral and thermal imaging, when used for crop identification and monitoring, can identify plant stress before it becomes visible to the unaided eye. - Irrigation management: sensors optimize water use by detecting arid areas. - Remote sensing enhances the accuracy of agricultural yield estimations and predictions via the analysis of vegetation indices, including NDVI, GNDVI, EVI, and the Canola Index (EAYI), among others. - Early identification of pathogens and pests facilitates the implemen- tation of targeted measures, which minimizes chemical use. Recent advances, including the use of machine learning and cloud computing, have made remote sensing more accessible and accurate than ever before. It is particularly advantageous in precision agriculture, where data-informed choices can enhance yield while reducing environmental impact. This paper delineates the second iteration of testing machine learning approaches to detect the tentative sowing process beginning date (with the admissible margin of error of +/- 2 days) and to monitor subsequent sowing progress in Kazakhstan, which was requested by the Kazakstani National Space Agency to explore the possibility of using ML solutions for monitoring tasks. Keywords: Remote sensing, Satellite Imagery, Machine Learning, Computer Vision Share Link | Plain Format | Corresponding Author (Alfarabi Imashev)

123	Topic B: Applications of Remote Sensing	ABS-321
Urban Growth Dynamics Using Cloud-Based Geospatial Analysis in Google Earth Engine: Udaipur, India Dr. Urmi Sharma Assistant Professor, Department of Geography, Mohanlal Sukhadia University Udaipur, India Abstract Urbanization is a major anthropogenic driver of land use land cover change, with impervious surface mapping serving as a robust proxy for settlement expansion. In India, the urban population has risen from 17 percent in 1951 to nearly 35 percent in 2021, and Udaipur exemplifies this transformation. Classified as a Tier-2 city, its Urban Agglomeration spans 109.4 sq km and has grown from 474,531 inhabitants in 2011 to an estimated 692,000 in 2025 (46 percent growth). Its strategic location, economic profile, and rapid population growth driven by tourism and migration make it a critical case for studying spatial expansion in medium sized Indian cities. This study examines built-up expansion in the Udaipur Development Area (UDA) from 1988 to 2018 using the Tsinghua FROM-GLC Year of Change to Impervious Surface dataset (30 m resolution, greater than 90 percent accuracy) processed in Google Earth Engine (GEE). Ancillary datasets-OpenStreetMap roads and lakes, SRTM DEM, and UDA boundaries-were integrated. Built-up maps for 1988, 1998, 2008, and 2018 were generated, with density classes (high, moderate, low, dispersed) derived using r.neighbour in QGIS. Elevation zonation and proximity to transport networks were assessed through GIS overlay and zonal statistics. Results reveal a twelvefold increase in built-up area from 4.91 sq km (1988) to 61.67 sq km (2018), with 78 percent of growth between 500-600 m MSL. Peripheral zones shifted from low to moderate densities, reflecting peri-urban transformation and integration into the metropolitan core. Expansion is constrained by the surrounding Aravalli hills, limiting higher elevation development. The availability of ready-to-use, high-accuracy, multi-temporal datasets in GEE enabled efficient, reproducible analysis using open-source tools. Extending such high-resolution datasets beyond 2018 is essential for predictive urban growth modelling to support sustainable planning in rapidly growing cities. Keywords: Urban expansion, Google Earth Engine, QGIS, Udaipur Share Link | Plain Format | Corresponding Author (Urmi Sharma)

124	Topic B: Applications of Remote Sensing	ABS-322
Satellite-Powered Crop Insurance to Protect Rice Farmers from Climate Risk in the Philippines Raviz J.V.1*, De La Cruz I.Q. 2, Gutierrez M.A.R. 1, Alosnos E.D. 3, Garcia C.A1, Villano L. S. 1, Hellin J. 1 and Laborte A.G. 1 1International Rice Research Institute, Laguna, Philippines 2Philippine Crop Insurance Corporation, Quezon City, Philippines 3Philippine Rice Research Institute, Nueva Ecija, Philippines *j.raviz[at]cgiar.org Abstract Smallholder rice farmers in the Philippines face increasing losses from climate hazards. Conventional indemnity-based crop insurance, while available at no cost to smallholder farmers in the Philippines, suffers from slow claims processing, subjective damage assessments and limited coverage. This study presents the development and simulation of the Area-Based Yield index insurance (ARBY) product, an innovative and scalable crop insurance solution that leverages the Philippine Rice Information System (PRISM). PRISM integrates remote sensing and crop modeling to generate monthly and seasonal estimates of rice area, planting date, and yield estimates, which are used to define homogeneous insurance zones (IZ) and estimate seasonal yields. Using six-year historical baselines (2018-2023), we parameterized the mean and variance of yields per IZ and conducted simulations for the 2023-2024 rice crop seasons in six municipalities in the Philippines. Two coverage options (80% and 90% of historical mean yield) were evaluated to balance affordability and protection. Results show that 80% coverage was cost-effective for moderate-risk areas, while 90% coverage delivered greater protection in high-risk zones, at higher premiums. ARBY demonstrates significant potential to reduce financial losses from climate-induced yield shortfalls, with benefits amplified by farmer education, local government engagement, targeted subsidy schemes and continuous refinement of yield models. This study illustrates how remote sensing-based yield estimation can overcome key limitations of traditional crop insurance and strengthen climate resilience and food security in rice-based systems By replacing costly and time-consuming farm-level loss adjustment with satellite-derived yields, ARBY addresses core limitations of traditional schemes and can improve the speed, transparency, and scale of financial protection. Keywords: Area yield index insurance, climate risk, crop insurance, food security, Philippines Share Link | Plain Format | Corresponding Author (Jeny Villaluz Raviz)

125	Topic B: Applications of Remote Sensing	ABS-323
Mapping and Classification of Crystallization Ponds in Pangasinan Salterns Using LandSat Imagery for Salt Production Estimation Rodel T. Utrera(1), Nadine Sharinette R. Bravo(2), Julius Jonar L. Butay(3), Nathaniel R. Alibuyog(4) and Lord Ian R. Galano(5) (1)Research Directorate, Mariano Marcos State University, rtutrera[at]mmsu.edu.ph (2)Research Directorate, Mariano Marcos State University, nrbravo[at]mmsu.edu.ph (3)Planning Directorate, Mariano Marcos State University, jbutay[at]mmsu.edu.ph (4)College of Engineering, Mariano Marcos State University, nralibuyog[at]mmsu.edu.ph (5)Research Directorate, Mariano Marcos State University, lrgalano[at]mmsu.edu.ph Abstract Crystallization ponds are the final and most essential component of solar salt production systems, where salt precipitates and is harvested after successive evaporation stages. Mapping the spatial extent of these ponds is crucial not only for monitoring salt farm infrastructure but also for estimating potential salt production output. By accurately identifying and delineating crystallization ponds, it becomes possible to project salt yields across wider areas, providing valuable data to support the revitalization and planning of the salt industry throughout the Philippines. This study focused on classifying and mapping crystallization ponds within existing salterns in Pangasinan using remote sensing and GIS-based techniques. LandSat eight (8) satellite imagery was processed using the Supervised Classification tool in ArcGIS to extract crystallization pond features based on their unique spectral characteristics. A refined training dataset enabled distinction from similar land uses such as evaporation ponds, fishponds, and agricultural fields. To evaluate classification accuracy, a total of 151 validation points were collected through extensive ground truthing, including field visits and drone-assisted aerial surveys. Among these, 124 points were correctly classified, resulting in an overall accuracy of 82.12%. This reliable classification demonstrates the potential of integrating remote sensing, GIS, and field validation to generate high-quality spatial datasets. The delineation revealed a total crystallization pond area of 430.52 hectares, with individual pond sizes ranging from 0.058 ha to 36.806 ha The resulting maps serve as a foundation for estimating salt production potential by correlating pond area with yield estimates. This approach can be scaled nationally, offering a cost-effective method for identifying underutilized salt farming areas and informing data-driven policies for sustainable salt industry development in the Philippines. Keywords: Crystallization Ponds, Remote Sensing, Supervised Classification, Geospatial Analysis, Salt Production Mapping Share Link | Plain Format | Corresponding Author (Rodel Tolosa Utrera)

126	Topic B: Applications of Remote Sensing	ABS-324
Importance of Monitoring Sea Ice with GOSAT-GW/AMSR3 Kohei Cho 1*, Kazuhiro Naoki 1 , Misako Kachi 2, Rigen Shimada 2, and Josefino Comiso 1 Tokai University, japan 2 JAXA , Japan 3 NASA, USA * kohei.cho[at]tokai.ac.jp Abstract JAXA has successfully launched the Global Observing SATellite for Greenhouse gases and Water cycle (GOSAT-GW) on June 29, 2025 (JST). GOSAT-GW carries two sensors, which are Advanced Microwave Scanning Radiometer 3 (AMSR3) and Total Anthropogenic and Natural emissions mapping SpectrOmeter-3 (TANSO-3). AMSR3 is the follow on of AMSR2 onboard GCOM-W which was launched in 2012 and is still under operation. Microwave radiometers on board satellites such as AMSR3 can penetrate clouds and can observe the global sea ice distribution on daily basis. Ice concentration (IC) is one of the most important parameters of sea ice which can be calculated from brightness temperatures measured by the passive microwave radiometers. The IC data is used for calculating the global sea ice extent, and the historical sea ice extents observed by the passive microwave radiometers onboard satellites are used to monitor the trend of global sea ice distribution. In this paper, the trend of the dramatical sea ice extent reduction of the Arctic derived from those sensors are presented. The initial result of AMSR3 for sea ice monitoring will also be presented. Keywords: passive microwave radiometer- GCOM-W- AMSR2- sea ice extent- global warming Share Link | Plain Format | Corresponding Author (Kohei Cho)

127	Topic B: Applications of Remote Sensing	ABS-71
Remote Identification of Wildlife Species Richness Along Linear Disturbance Corridors in Endau-Rompin (Peta) National Park, Johor, Malaysia. Kugan RAJU. 1* and Noordyana HASSAN. 1,2* 1 Department of Geoinformation, Faculty of Built Environment and Surveying, Universiti Teknologi Malaysia (UTM), 81310 UTM Skudai, Johor, Malaysia 2 Geoscience and Digital Earth Centre (INSTeG), Research Institute of Sustainable Environment (RISE), Universiti Teknologi Malaysia (UTM), 81310 UTM Skudai, Johor, Malaysia. Abstract Ecotourism and forest management activities have caused an increase in the number of linear disturbance corridors, such as roads, trails, and logging routes within protected rainforests. Species richness near these types of corridors is crucial because these areas may influence wildlife presence due to environmental factors. While previous studies have examined detection rates and diel activity of wildlife, there are less studies that have investigated how natural and anthropogenic factors influence species richness using remote sensing. Therefore, in the present study, we identify the species richness of wildlife and examine the influence of natural and anthropogenic factors on species richness along linear disturbance corridors in Endau-Rompin (Peta) National Park, Malaysia by using camera traps and remote sensing derived information. Camera trap data were collected along paved and unpaved roads inside the national park with each unit operating continuously over 250 days. Species richness was calculated using the Habitat and Biodiversity Modeler (HBM). Natural and anthropogenic variables were extracted using Sentinel-2 data. Additionally, human activity indexes extracted from camera traps at each location were used as direct field-based indicators for anthropogenic variables. The relationship between environmental factors and species richness was computed using statistical analyses. The result is expected to show that species richness varied across paved and unpaved roads. Locations with higher vegetation productivity exhibited higher species richness while locations with higher human activity had lower species richness. Species richness was slightly high at locations near unpaved road compared to paved road which indicate anthropogenic factors influence wildlife diversity along linear disturbance corridors. In conclusion, both natural and anthropogenic factors significantly influence wildlife species richness along linear disturbance corridors within protected rainforests. The results obtained from this study would be useful for the Department of Wildlife and National Parks (DWNP) to inform conservation planning within protected areas. Keywords: alpha diversity, remote sensing, species richness. Share Link | Plain Format | Corresponding Author (Kugan Raju)

128	Topic B: Applications of Remote Sensing	ABS-72
Building and Analysis of Spectral Library for Durian Varieties in Malaysia Khoo Soh Teng (a*), Noordyana Binti Hassan (b) (a)Department of Geoinformation, Faculty of Built Environment and Surveying, Universiti Teknologi Malaysia(UTM), 81310 UTM Skudai,Johor,Malaysia (b) Geoscience and Digital Earth Centre (INSTeG), Research Institute of Sustainable Environment(RISE), Universiti Teknologi Malaysia, 81310 UTM Skudai,Johor,Malaysia Abstract Traditional methods for manually evaluating durian species in agriculture are time-intensive and prone to human error. This study investigates the spectral characteristics of durian species in Malaysia, focusing on constructing a spectral library using spectral reflectance values. A spectroradiometer was utilized to measure the spectral reflectance of various durian species, including durian jungle (kampung) and cultivated durian varieties. Leaf samples were collected from Dusun UTM for analysis. Through this research, a comprehensive spectral library, encompassing a set of spectral reflectance values, was developed. Spectral separability techniques such as first, second, and third derivatives were employed to distinguish between durian species. The spectral reflectance data predominantly falls within the visible, near infrared, and short-wave infrared regions. The result show that spectral separability region for durian cultivars and kampung are green, yellow and red edge band. Vegetation indices such as NDVI, NDRE, GNDVI, and EVI were calculated using the spectral reflectance values, with results visualized on a dedicated Durian Dashboard. The spectral library will be significant for horticulturists and agriculturists, environmental scientists, remote sensing professionals, and GIS professionals. For example, use for durian mapping, monitor crop plants health and optimal optimizing growth conditions. In conclusion, the best band for separating the different durian varieties within inter species for durian kampung and durian cultivars are green, yellow, and red edge region wavelength. Reject the null hypothesis which means the comparison between inter species for durian kampung and durian cultivars are the different. The generated spectral library is anticipated to support future research and practical field applications. This study contributes to the advancement of accurate and efficient durian species identification methods, addressing the limitations of manual agricultural evaluation. Keywords: Durian, remote sensing, spectral library, spectroradiometer Share Link | Plain Format | Corresponding Author (SOH TENG KHOO)

129	Topic B: Applications of Remote Sensing	ABS-329
Integrating Multi-Scale Remote Sensing and Ground-Sampling to Map Seagrass Blue Carbon Stocks in Phu Quoc Island, Vietnam Xuan Truong Trinh (a*), Van Cong Doan (b,c), Quang-Loc Nguyen (d), Masahiko Nagai (e) (a) Faculty of Engineering, Yamaguchi University, Japan *trinh[at]yamaguchi-u.ac.jp (b) Department of Life Sciences and Systems Biology, University of Turin, Italy (c) Center for Climate Change Adaptation Research and Community Development Support, Tra Vinh University, Viet Nam (d) Institute for Circular Economy Development, VNU-HCMC, Vietnam (e) Yamaguchi University Center for Research and Application of Satellite Remote Sensing, Yamaguchi University, Japan Abstract Seagrass meadows are pivotal blue carbon ecosystems that play a critical role in climate change mitigation by sequestering atmospheric CO2 and trapping organic carbon in sediments. While Vietnam once supported over 36,000 hectares of seagrass, a significant decline to 17,000 hectares has been driven by rapid coastal development and aquaculture. The extensive 9,600-hectare seagrass meadow around Phu Quoc island, however, remains a crucial national asset. This study provides the first spatially explicit, high-resolution assessment of seagrass biomass and sediment carbon stocks for this vital ecosystem. Ultra high resolution UAV imagery was collected across the intertidal flat and classified using an object-based random forest approach. Ground surveys provided quadrat-level measurements of seagrass density, species composition and canopy height to calibrate UAV derived cover and biomass estimates. To characterise blue carbon stocks, eighteen aboveground and belowground biomass samples and eighteen sediment cores were collected across a gradient of seagrass densities. In the laboratory, samples were dried and processed using the Loss on Ignition method to determine organic matter and carbon content. Models were built to estimate seagrass biomass and carbon stocks based on their density, which was in turn used to generate continuous maps of seagrass biomass and carbon stocks across the 9,600 ha meadow. The resulting dataset establishes a fundamental baseline for blue carbon accounting in Vietnam and provides essential, data-driven insights for conservation management and policy. This research directly supports the Sustainable Development Goals (SDGs) by contributing to climate action, protecting life below water, and informing strategies for sustainable coastal development. Keywords: Biomass, Loss on Ignition (LOI), Multi-scale analysis, Climate change mitigation, UAV Share Link | Plain Format | Corresponding Author (Xuan Truong Trinh)

130	Topic B: Applications of Remote Sensing	ABS-74
Unmanned Aerial Vehicle-Based Carbon Sink Estimation in Bamboo and Urban Forests Zhan Y.X.(a), Zhang Y.J. (b), Chen J.C. (c*), Wei C.H. (d), Shiau Y. (e), Huang W.H. (e), Hsu I.N. (e), Chang C.Y. (e), and Lai J.C. (e) a) Lecturer-level Researcher, R&D Center / Ph.D. Student, Doctoral Program in Bioresources, National Pingtung University of Science and Technology (NPUST), Taiwan b) Research Assistant, Department of Forestry / College of Agriculture, NPUST, Taiwan c) Professor, Department of Forestry / College of Agriculture, NPUST, Taiwan d) Associate Professor, Department of Forestry / College of Agriculture, NPUST, Taiwan e) Department of Network Technology, Telecommunication Training Institute, Chunghwa Telecom Co., Ltd., Taiwan, R.O.C. *Correspondence: janchang17[at]gmail.com Abstract In this study, we focus on two types of landscape, urban forest and bamboo forest, carbon sink potential assessment. We combined UAV remote sensing techniques and ground survey to establish carbon storage estimation model. We aim bamboo forest in Fuxing District, Taoyuan City and urban forest in Chunghwa Telecom Academic Kaohsiung. We set up ground survey plots to measure diameter at breast height (DBH), tree height and tree species identification in these two places to establish procedure and model feasibility. We use drone (Matrice 300 RTK) with optical sensor payload by Structure from Motion (SFM) and Multi View Stereo (MVS) methods to build Canopy Height Model (CHM). We combine above ground biomass (AGB) and aerial forest stocking model by spatial location georeferencing to retrieve estimation value. Further, we estimate carbon storage with IPCC conversion factors and assess regression verification and model bias. The results display urban forest investigating 532 trees and brushes with 64.58 t C (236.79 t CO&#8322-) and Phyllostachys makinoi bamboo forest demonstrating 4,299 bamboos with ABG 1,262.02 t and carbon storage 567.91 t C by 30 ground survey plots. We can save the investigation cost by using drones and it still shows good accuracy and practicality. That means UAV can be a good assist tool to estimate carbon sink value. Keywords: UAV, carbon storage, bamboo forest, urban forest, Structure from Motion Share Link | Plain Format | Corresponding Author (Yu Xuan Zhan)

131	Topic B: Applications of Remote Sensing	ABS-330
An improved LOD3 through photogrammetry for generating digital twins Saruul Altankhuyag1, Bilguuntugs Tovuusuren1, Bolorchuluun Chogsom2 1 Monmap LLC, Mongolia 2Department of Geography, National University of Mongolia, Mongolia Abstract Digital twin technology creates an integrated spatial system in a virtual environment that represents real-world objects and systems, ensuring their interconnection through the use of geographic information systems (GIS). This system connects to real-time data derived from generated datasets, enabling monitoring, analysis, and improved decision-making. This study aims to explore the potential for generating base data for a Level of Detail 3 (LOD3) digital twin model using stereophotogrammetry and GIS, with a pilot implementation in the 100 Ail area of Ulaanbaatar, Mongolia. This area was selected because it contains a diverse mix of ger districts, built-up zones, bridge structures, rivers, and green spaces. As base data, aerial imagery captured in 2023 by MonMap LLC^s WingtraOne GEN II unmanned aerial vehicle was used. The aerial photographs were processed using stereophotogrammetric methods to create a 3D spatial model. Orthophotos, a digital surface model (DSM), and a digital terrain model (DTM) were produced, with the aim of developing both schematic and high-precision 3D models of buildings and structures. As a result of the study, an LOD3 3D model was created. Spatial elements such as buildings, roads, and green areas were represented in 2D form, while the models accurately reflected roof shapes, facade structures, and heights. This enhances the potential applications of digital twin systems in urban planning, building monitoring, and smart city analytics, among other fields. Keywords: Digital Twin, LOD3, Stereophotogrammetry, GIS, Spatial Base Data Model Share Link | Plain Format | Corresponding Author (Saruul Altankhuyag)

132	Topic B: Applications of Remote Sensing	ABS-75
Retrieval of cloud base height and cloud geometric thickness based on PARASOL oxygen A band Huazhe Shang State Key Laboratory of Remote Sensing and Digital Earth, Aerospace Information Research Institute, Chinese Academy of Sciences Abstract The base heights and geometric thicknesses of clouds are important cloud characteristics and are highly important for climate, weather, and aviation safety. The current measurement methods have limitations: ground-based observations have limited ranges, active remote sensing has insufficient spatiotemporal coverage, and passive remote sensing cannot directly retrieve cloud base information. Therefore, a new cloud base height retrieval method, which is a cloud base height retrieval method based on the PARASOL oxygen A-band (OA), is proposed in this paper. On this basis, multiangle polarization can be used to obtain the top heights of clouds with high precision. Then, by combining the top height of a cloud with its base height, the geometric thickness of the cloud can be acquired. Simulation experiments involving radiative transfer models indicate that the OA exhibits regular sensitivity to the CBH . Within the OA, the ratio of narrow-channel (763 nm) to wide-channel (765 nm) radiation intensities increases as the CBH increases. Owing to the uniform distribution of oxygen in the atmosphere, the OA remains relatively stable. Additionally, the wealth of information derived from multiangle remote sensing can further increase the accuracy of retrievals. Therefore, the multiangle OA is incorporated into the model training process. CBHs obtained from CloudSat are used as the true values. The longitude, latitude, and multiangle OA information obtained from PARASOL Level 1 is utilized to retrieve the CBHs. After several machine learning algorithms are compared, the deep neural network (DNN) model with the best accuracy is selected as the retrieval model. The method of CBH reversal based on multiangle OA remote sensing and the DNN has a mean absolute error (MAE) of 0.78 km, a bias of 0.22 km, and a correlation coefficient (R) of 0.82. By integrating machine learning with the multiangle OA, this method offers a novel approach for CBH retrieval. Keywords: multi-angle,oxygen A band,cloud base height,cloud geometric thickness,PARASOL,CloudSat Share Link | Plain Format | Corresponding Author (Huazhe Shang)

133	Topic B: Applications of Remote Sensing	ABS-332
Flood Identification Using Sentinel 1 SAR Imagery in Bila Walanae Watershed Syaeful Rahmat(a*), Sigit Herlambang Asmorojati(b), Andang Suryana Soma(b,c) a) Study Programs Remote Sensing and Geographic Information System, Faculty of Vocational, Hasanuddin University, Makassar, Indonesia b) Watershed Management Laboratory, Faculty of Forestry Hasanuddin University, Makassar Indonesia c) Forest Hidrology and Watersheds Management Research Group, Faculty of Forestry Hasanuddin University Abstract Indonesia is a tropical climate with a high rainfall intensity, so almost all areas in Indonesia have the potential to be affected by flood disasters. Bila-Walanae watershed is included in WS Walanae - Cenranae which is a National Strategic River Area. The strategic issue that occurs in the watershed when Walanae shallowing lake Tempe due to sedimentation that empties into lake Tempe and more than half of the area is flat-roofed and sloping with land closures in the form of forests that leave 15.47% of the total watershed area, thus increasing the potential for flooding in this region. This study aims to identify flooded areas in the Bila Walanae Watershed using Sentinel-1 SAR imagery data before and at the time of the flood event on July 19, 2020. Identify floods using the Normalized Difference Sigma Index method. The number of samples in the study was used as many as 102 samples used for reference data. Simple random sampling techniques are used for sampling methods. Results from the Normalized Difference Sigma Index analysis identified floodwaters covering an area of 36,593.51 ha with an accuracy rate of 90.2%. Floodwaters spread to seven sub-districts in Wajo Regency, five sub-districts in Sidenreng Rappang Regency, two sub-districts in Soppeng regency, and three sub-districts in Bone regency. The results of the analysis showed that the elevation and Digital Elevation Model were very influential on the identification of flooded areas by using sentinel-1 imagery in the Bila Walanae watershed. Flood identification using Sentinel 1 imagery should be used in open land-covered areas to avoid factors that can affect the backscatter, namely double-bounce vegetation layer and lookalikes. Keywords: Flood, NDSI, Sentinel-1 SAR, Watershed Share Link | Plain Format | Corresponding Author (Syaeful Rahmat)

134	Topic B: Applications of Remote Sensing	ABS-77
Detection of Illegal Waste Dumping via Satellite Imagery using U-Net and Open-Source Tools Welly Anak Numpang (1*), Noryusdiana Mohamad Yusoff (1), Siti Muazah Md Zin (1), Muhammad Hazrul Haiqal Abdul Wahab (4), Nurul Izza Zainal (1), Siti Nor Afzan Abdul Habib (2) and Kamaruzzaman Wahid (3) (1) Research Officer, Strategic Application Division, Malaysian Space Agency (MYSA), Malaysia (2) Research Officer, ICT Development and Geoinformatics Division, MYSA, Malaysia (3) Director, Strategic Application Division, MYSA, Malaysia (4) Protege, Strategic Application Division, MYSA, Malaysia *welly[at]mysa.gov.my Abstract Global solid waste generation is projected to increase from 2.24 to 3.88 billion tonnes by 2050, with more than one third currently mismanaged through open dumping or burning, posing severe environmental and public health risks. In Malaysia, nearly 39,000 tonnes of waste are produced daily, and many landfills are already at full capacity, resulting in widespread illegal dumping. Traditional monitoring methods, which rely on manual surveys and visual interpretation of satellite images, are time-consuming, resource-intensive, and highly dependent on the expertise of analysts. Malaysian Space Agency (MYSA) began applying satellite imagery to detect illegal waste dumping sites in 2019, following the Kim-Kim River incident, using SPOT-6/7 (1.5 m) and Pleiades (0.5 m) for visual interpretation. With recent advances in Artificial Intelligence (AI), particularly Machine Learning (ML) and Deep Learning (DL), MYSA has transitioned towards automated detection of illegal waste dumping using Pleiades Neo imagery (0.3 m). In this study, a U-Net architecture with a ResNet34 backbone was implemented in open-source software and trained on 2,213 image chips. The model achieved a final accuracy of 99.96% with no signs of overfitting, and was further validated through field deployment in Penang, where verification accuracy reached 96.86%. The model successfully improved overall accuracy by eliminating misclassified outliers, particularly those arising from cemetery areas. By integrating advanced DL and remote sensing technologies, manpower requirements were reduced by up to 99%, leading to a corresponding reduction in labor costs of approximately 93%, significantly enhancing operational efficiency. Looking ahead, MYSA will operationalize the model through the Sistem Pemantauan Potensi Lokasi Pelupusan Sisa (e-Sisa) to support local enforcement and improve waste management. This initiative, aligned with the Malaysia Space Exploration 2030 (MSE2030) Action Plan. Keywords: deep learning, Pleiaides Neo, remote sensing, illegal waste, u-net Share Link | Plain Format | Corresponding Author (Welly Anak Numpang)

135	Topic B: Applications of Remote Sensing	ABS-78
Forest Regeneration Status To Support Forest Health In Panti Forest Reserve Using Machine Learning Approach Ashleza Ahmad (1*), Noordyana Hassan (2) 1) Department of Geoinformation, Faculty of Built Environment and Surveying, Universiti Teknologi Malaysia (UTM), 81310 UTM Skudai, Johor, Malaysia 2) Geoscience and Digital Earth Centre (INSTeG), Research Institute of Sustainable Environment (RISE), Universiti Teknologi Malaysia (UTM), 81310 UTM Skudai, Johor, Malaysia Abstract Remote sensing has now acquired a crucial role for mapping forest changes, understanding ecosystem dynamics, and monitoring both deforestation and natural regeneration. It significantly contributes forest management, biodiversity conservation and habitat monitoring since it provides extensive information on spatial data. In the past, Panti Forest Reserve, located in Kota Tinggi, Johor, Malaysia, experienced scheduled logging, which led to habitat loss and a decline in wildlife presence, as the Sustainable Forest Management (SFM) was not employed anymore in this area to encourage forest regeneration. However, recent observations suggest that the forest is regenerating, with increasing signs of wildlife returning. This observation raises important questions about the drivers of habitat reoccupation and the spatial conditions that support wildlife return. This study aims to analyse land use and land cover (LULC) changes in Panti Forest Reserve for the years 2015, 2020, and 2025 using SPOT satellite imagery and the Random Forest classification. Key environmental variables such as elevation, slope, distance from water sources, and distance from forest edges will be analysed to explore their influence on wildlife return. Statistical analysis will be conducted to identify the impact of forest regeneration on wildlife presence in the area. The findings of this study will contribute to the Forestry Department of Peninsular Malaysia and the Department of Wildlife and National Parks (PERHILITAN) by supporting forest management and wildlife conservation planning. Keywords: Forest regeneration, land cover change, Random Forest classification, wildlife return Share Link | Plain Format | Corresponding Author (BINTI AHMAD ASHLEZA)

136	Topic B: Applications of Remote Sensing	ABS-334
Deep Learning Framework for Large-Scale Precision Mapping of Brick Kilns to Support Sustainable Policy in the Indo-Gangetic Plain Yamini Agrawal1,2,*, Hina Pande1, Poonam Seth Tiwari1, Shefali Agrawal1, Prakash Chauhan3 1 Indian Institute of Remote Sensing, Indian Space Research Organisation, Dehradun, Uttarakhand, India 2 Department of Civil Engineering, Indian Institute of Technology Roorkee, Roorkee, Uttarakhand, India 3 National Remote Sensing Centre, Indian Space Research Organisation, Hyderabad, Telangana, India Abstract The urban population in South Asia is projected to grow by 250 million by 2030, driving an expansion of built-up areas and escalating demand for raw construction materials, particularly fired clay bricks. Currently, the region produces approximately 310 billion bricks annually, contributing substantially to particulate matter emissions. However, the absence of a documented, spatially explicit survey of active brick kilns limits policymakers ability to assess and mitigate the sectors environmental impacts. This study applies a novel deep learning-based detection-segmentation approach to map brick kilns in the entire northern Indo-Gangetic Plains (IGP), which contains a high density of kilns on alluvial, sandy, clayey, and loamy soils. A deep learning model was trained, fine-tuned using hyperparameter tuning and tested on multi-sensor optical satellite imagery to detect and segment kiln structures. On the validation set, the model achieved mAP >= 0.50, mask mAP >= 0.87, with inference throughput exceeding 15 frames s-1, demonstrating suitability for large-scale, near real-time applications. Final results yielded an average precision, recall, and F1-score of 0.881, 0.827, and 0.853, respectively, identifying kilns in the study area. Post segmentation, Normalized Difference Vegetation Index (NDVI) and Short-Wave Infrared (SWIR) spectral indices were derived from multi-temporal satellite imagery to track interseasonal and annual dynamical changes, enabling discrimination between active and abandoned brick kilns. Segmentation output provided accurate boundary delineations, enabling estimation of kiln footprint area, potential brick production capacity, and associated carbon footprint. The findings highlight the potential of advanced object detection-segmentation frameworks for automated and scalable environmental monitoring and generating comprehensive spatial inventories. This approach can directly inform regulatory compliance, and support emission-reduction strategies. Keywords: Brickkiln, deep learning, detection, environment, urban Share Link | Plain Format | Corresponding Author (Yamini Agrawal)

137	Topic B: Applications of Remote Sensing	ABS-79
A Fire Scene Reconstruction System Integrating Fire Dynamics and Structural Analysis Models Yen-Jung Chen(a) , Chih-Yuan Huang(b), Wen-Shuo Liang(c), Jun-Yi Wu(d), Wei-Hsuan Lin(d) (a)Master^s Student, Department of Civil Engineering, National Central University (b)Associate Professor, Center for Space and Remote Sensing Research, National Central University (c)Research Assistant, Center for Space and Remote Sensing Research, National Central University (d)Satellite Survey Center, Department of Land Administration, Ministry of the Interior, Taiwan Abstract On January 20, 2015, a catastrophic fire occurred at a bowling alley in Xinwu District, Taoyuan City, Taiwan, resulting in the tragic deaths of six firefighters. This incident remains one of the most severe firefighter casualty events in recent Taiwanese history. The building^s complex interior layout, and limited access to structural and fire-related information significantly hindered real-time decision-making during the response. The lack of structural safety assessment prior to firefighter entry ultimately contributed to fatalities caused by structural collapse. This study aims to reconstruct the fire scene of this incident by developing an integrated framework that couples fire dynamics simulation with structural analysis in a bidirectional manner. The proposed method aims at reproducing the fire development and structural degradation processes, identify high-risk zones within the building and support post-event analysis. The proposed system integrates two computational tools: Fire Dynamics Simulator (FDS) and ABAQUS. By setting up fire source locations, material properties, ventilation openings, and boundary conditions, FDS is used to simulate the fire-induced thermal changes and smoke spread. The temperature time series data generated by FDS are then translated into thermal loads for the structural model in ABAQUS to simulate structure degradation, deformation, and potential failure zones under elevated temperatures. The structural response results, including collapse patterns, is subsequently fed back into the fire model to update boundary conditions and rerun the fire simulation. Through iteratively coupling fire and structural simulations, the proposed system can capture the evolving interaction between fire development and structural behavior more accurately. This enhances the reliability of fire scene reconstructions and provides a scientific basis for risk assessment, training, and safety planning in future fire incidents. Keywords: Fire simulation, structural analysis, fire scene reconstruction, FDS, ABAQUS Share Link | Plain Format | Corresponding Author (YEN JUNG CHEN)

138	Topic B: Applications of Remote Sensing	ABS-80
CoSIA and FLAIR-HUB: multi-source AI models for land cover mapping Bookjans E. , Garioud A., Marchand G., Vo Quang A., Dekeyne F. and Masse A. Institut national de l^information geographique et forestiere (IGN), France IGNFI, France Abstract The French Mapping Agency (IGN) has invested in deep learning methods and technologies to accelerate the production of high-resolution land cover maps to better monitor the evolution of the French territory, i.e. to map the Anthopocene. This initiative, named CoSIA (Land Cover by Artificial Intelligence), is crucial for monitoring the evolution of the French territory and improving land management. More than 2,800 km2 of aerial imagery have been annotated by image analysts, enabling IGN to train a robust semantic segmentation AI model applicable at the national scale. In parallel, the IGN launched the FLAIR (French Land cover Aerospace ImagRy) challenges to help improve its AI land cover models. To support continued innovation, experimentation and encourage collaboration, the IGN has not only made this dataset and its AI models publicly available but has recently augmented it with multi-modal data: FLAIR-HUB also contains satellite images, historical aerial images (1950s) and crop type annotations (23 agricultural classes). The resulting land cover maps CoSIA find a wide range of applications in environmental monitoring, land use planning and resource management (e.g., change detection, forestry, hydrology, agriculture). The IGN already exploits CoSIA for several different applications, including quantification of artificial surfaces, identification of green spaces in cities, and monitoring agricultural features like hedges.. In summary, CoSIA and FLAIR-HUB provide geospatial communities with valuable resources and tools allowing for a better overall land management in the face of the current technological, socio-economic and environmental challenges. In complement, IGNFI, the international subsidiary of IGN, is providing for close to 40 years expertise and services to help decision-makers around the world, including Indonesia, to fully own and take advantage of the potential of geographical information, including Land Cover Mapping. Results will be presented during Keywords: Land Cover Mapping, Deep Learning, Aerial Imagery, Satellite imagery, CoSIA Share Link | Plain Format | Corresponding Author (Antoine Masse)

139	Topic B: Applications of Remote Sensing	ABS-81
Validating AI-Based Depth Estimation for Road Scene Reconstruction Using Dashcam Images and Low-Cost LiDAR Bilguunmaa Myagmardulam, Kazuyoshi Takahashi Toyama Prefectural University, Toyama, Japan. Nagaoka University of Technology, Niigata, Japan. Abstract Monocular depth estimation powered by deep learning has the potential to significantly reduce the cost and complexity of 3D scene reconstruction in mobile applications. In this study, we conduct a foundational evaluation of the VGGT model^s performance using low-cost Mobile Mapping System (MMS) data, focusing on snow-free urban road environments. The MMS setup consists of a dashcam, GNSS/IMU, and 3D LiDAR sensor, enabling both image capture and 3D point cloud generation at low cost. Lens distortion in dashcam images was corrected using MATLAB-calculated camera parameters before inputting the data into the VGGT depth estimation model. The resulting 3D structures were compared with LiDAR-based point clouds in CloudCompare to assess spatial accuracy. Structure-from-Motion (SfM) outputs from VGGT model were also used for cross-validation. Our results show that, even under non-snowy conditions, monocular depth estimation can generate meaningful 3D structures for road scenes. These findings support the broader application of such models to regular road monitoring and infrastructure inspection. With further refinement, especially regarding accuracy thresholds acceptable to field operators, this approach could enable low-cost road patrol systems where only critical areas are followed up with high-end equipment. Future work will extend this validation to snow-covered scenes. Keywords: Monocular Depth Estimation, VGGT, Low-Cost MMS, LiDAR, SfM, Dashcam, Road Scene Reconstruction, Snow Monitoring Share Link | Plain Format | Corresponding Author (Bilguunmaa Myagmardulam)

140	Topic B: Applications of Remote Sensing	ABS-337
Seeing Health from Above: Remote Sensing and GIS Evidence for Bridging Primary Health Care Access Inequities Fedri Ruluwedrata Rinawan (a*), Salma Ziani Nazwa Mulyana (b), Fidya Meditia Putri (c) a) Department of Public Health, Faculty of Medicine, Universitas Padjadjaran Jalan Ir. Soekarno No.KM. 21, Hegarmanah, Jatinangor, Sumedang Regency, West Java 45363 *f.rinawan[at]unpad.ac.id b) Undergraduate Study Program, Faculty of Medicine, Universitas Padjadjaran Jalan Ir. Soekarno No.KM. 21, Hegarmanah, Jatinangor, Sumedang Regency, West Java 45363 c) Department of Dental Public Health, Faculty of Dentistry, Universitas Padjadjaran Jalan Ir. Soekarno No.KM. 21, Hegarmanah, Jatinangor, Sumedang Regency, West Java 45363 Abstract Access to Primary Health Care (PHC) remains a fundamental challenge in achieving Universal Health Coverage (UHC). In Indonesia, the National Health Insurance (Jaminan Kesehatan Nasional/JKN) aims to ensure equitable access to first-level health facilities (Fasilitas Kesehatan Tingkat Pertama/FKTP). However, disparities persist, particularly in rapidly urbanizing areas. Our case study in Citeureup Subdistrict, Cimahi, West Java, used Geographic Information System (GIS) analysis to assess spatial accessibility for JKN participants. By applying both buffer and network analyses, we measured the distance from patient residences to the nearest FKTP and classified locations as near (<1 km) or far (>1 km). Findings revealed that a substantial proportion of residents live beyond the optimal service radius, with road network patterns further limiting access. These results highlight geographic proximity as a key factor influencing facility selection, alongside perceived quality and service availability. Building on these local insights, we extended the research through a systematic literature review (SLR) examining how remote sensing (RS) can enhance the measurement of PHC accessibility. The SLR, conducted according to PRISMA guidelines, synthesized global evidence on RS-derived variables-such as built-up density, road quality, elevation, vegetation indices, hydrological barriers, and climatic conditions-and their integration into health access models. Studies demonstrated that RS data improve travel-time modeling, identify underserved populations, and inform more accurate facility placement, especially when combined with GIS-based spatial analysis. By linking a ground-level case study with a global evidence synthesis, this research offers a dual perspective: detailed local diagnosis and broader methodological context. The approach underscores the potential of integrating RS and GIS to guide infrastructure planning, optimize facility distribution, and address inequities in PHC access. These findings are relevant for policymakers, public health planners, and researchers aiming to design data-driven strategies that bridge gaps in essential health services. Keywords: Primary Health Care, accessibility, remote sensing, GIS, systematic review Share Link | Plain Format | Corresponding Author (Fedri Ruluwedrata Rinawan)

141	Topic B: Applications of Remote Sensing	ABS-82
Sentinel-3 SAR Altimetry for Accurate Water Level Retrieval in Small Tropical Reservoirs Mohd Adha Abdul Majid (a,b), Nurul Hazrina Idris (c*,d), Mohd Nadzri Md Reba (d) a) Department of Geoinformation, Faculty of Built Environment and Surveying, Universiti Teknologi Malaysia, Malaysia b) Strategic Application Division, Malaysian Space Agency, Malaysia c) Tropical Resource Mapping Research Group, Department of Geoinformation, Faculty of Built Environment and Surveying, Universiti Teknologi Malaysia, Malaysia. *nurulhazrina[at]utm.my d) Geoscience and Digital Earth Centre, Research Institute for Sustainability and Environment, Universiti Teknologi Malaysia, Malaysia Abstract Monitoring water surface elevation (WSE) is essential for effective water resource management in tropical regions with strong monsoonal influences. However, traditional in-situ methods and conventional satellite altimetry often lack the spatial resolution and reliability needed for small, remote reservoirs with complex topography. This study examines the feasibility of using Sentinel-3 synthetic aperture radar (SAR) altimetry to retrieve WSE in small tropical reservoirs by testing tailored geophysical and atmospheric correction strategies in three inland reservoirs in Peninsular Malaysia - Kenyir (326.4 km2), Temengor (137.3 km2), and Chenderoh (8.6 km2). Three correction configurations were evaluated, and altimetry-derived WSE was validated against in-situ gauge data. Among them, Model Set 1 - integrating European Centre for Medium-Range Weather Forecasts (ECMWF)-based atmospheric corrections (dry at zero altitude, wet at measured altitude), the Finite Element Solution Release Year 2014 (FES 2014) tide model, and the European Improved Gravity Model of the Earth by New Techniques (EIGEN6C4) geoid - consistently delivered the best performance. Kenyir, with its large surface area and stable terrain, showed minimal sensitivity to correction models, achieving a correlation coefficient of 0.99, root mean square error (RMSE) between 42 cm and 46 cm, and mean absolute error (MAE) between 34 cm and 37 cm. Temengor performed best under Set 1, with a correlation coefficient of 0.99, RMSE of 20 cm, and MAE of 13 cm. Despite Chenderoh^s smaller size and likely influence of narrow-channel hydrodynamics, fair accuracy was achieved, with a correlation coefficient of 0.84, RMSE of 26 cm, and MAE of 22 cm. These findings confirm that Sentinel-3 SAR altimetry, when paired with site-specific correction strategies, enables reliable WSE monitoring in small tropical reservoirs, supporting hydrological modelling, reservoir management, and climate-resilient planning in scarce-data regions. Keywords: SAR altimetry, Water surface elevation, Small reservoirs, Sentinel-3, Tropical hydrology Share Link | Plain Format | Corresponding Author (Mohd Adha Abdul Majid)

142	Topic B: Applications of Remote Sensing	ABS-84
Time-Series InSAR Monitoring of Ground Deformation along the Baribis Fault Using LiCSBAS Muhammad Rakha Fadhila, Dwi Lestari a) Undergraduate Student, Geodetic Engineering, Universitas Gadjah Mada, Indonesia *muhammad.rakha1803[at]mail.ugm.ac.id b) Associate Professor, Geodetic Engineering, Universitas Gadjah Mada, Indonesia Abstract The Baribis Fault a significant seismic threat running through Javas densely populated northern regions has yet to be mapped with a comprehensive 2D deformation analysis combining both ascending and descending InSAR data To better understand this risk our study uses time-series Interferometric Synthetic Aperture Radar InSAR to create a detailed map of its surface deformation We analysed Sentinel-1 imagery from 2017 to 2023 using the Small Baseline Subset SBAS technique within the open-source LiCSBAS platform with further analysis performed in Jupyter Notebook By combining data from ascending and descending satellite paths we decomposed the line-of-sight displacement into true vertical and horizontal East-West ground motion The accuracy of our results was then confirmed by comparing them against measurements from two nearby CORS stations CBTU and CTGR yielding a Root Mean Square Error between 509 and 534 cm Our analysis reveals complex ground motion vertical displacement rates range from -864 to 32 mmyr showing uplift in the north and nearly subsidence in the south while horizontal velocities range from -86 to 106 mmyr indicating a clear left-lateral strike-slip pattern Beyond providing the first comprehensive 2D deformation map for this critical fault this research highlights the practical power of a fully open-source workflow It shows how community-driven tools and free satellite data make advanced geodetic monitoring more accessible empowering local institutions to conduct their vital hazard assessments This work ultimately demonstrates how collaborative open science in remote sensing can directly contribute to building more resilient communities Keywords: Baribis Fault, Deformation, InSAR, LiCSBAS, Open Science, SBAS Share Link | Plain Format | Corresponding Author (Muhammad Rakha Fadhila)

143	Topic B: Applications of Remote Sensing	ABS-86
Soil Salt Content Inversion Using Novel Salinity Indices Based on a Stacking Model Yufei Lan,Ruiyin Tang,Guohong Li,Xuqing Li,Yancang Wang,Haizhou Chen,Tingxuan Wang North China Institute of Aerospace Engineering School of Remote Sensing and Information Engineering, Langfang 065000- Hebei Province Collaborative Innovation Center for Space Remote Sensing Information Processing and Application, Langfang 065000- Abstract Soil salinization is a major threat to land and agriculture in coastal regions, particularly in China Coastal New Areas, including Tangshan, Cangzhou, and Qinhuangdao. Due to its coastal geography and climate, this region faces severe soil salinity issues, impacting agricultural productivity and environmental sustainability. Traditional field sampling is time-consuming and limited in coverage, inadequate for large-scale monitoring. While remote sensing is widely used, existing salinity indices, such as S1 and SI1, show low correlation in this region due to complex soil and environmental conditions, limiting prediction accuracy. This study develops new three-band salinity indices and integrates advanced stacking regression models to enhance soil salinity monitoring accuracy.Using 2025 Sentinel-2 multispectral imagery and 95 field-measured soil salinity samples via conductivity, six bands-Blue, Green, Red, NIR, SWIR1, SWIR2-were selected to construct novel three-band salinity indices through addition, subtraction, ratios, and power operations. The results confirm the superiority of the novel indices. The best-performing index achieved a maximum Pearson correlation coefficient of 0.60 with soil EC, a substantial improvement over the 0.41 from the most effective existing index. The Stacking model yielded an outstanding validation coefficient of determination of 0.870. This performance not only surpassed that of high-performing individual models like RF (R2=0.773) and XGBoost (R2=0.768), but also substantially exceeded the traditional Partial Least Squares Regression (PLSR) model (R2=0.526). The success of the Stacking model highlights its ability to effectively fuse the predictive strengths of its diverse base learners, enhancing overall robustness and accuracy. This research presents a robust methodology for regional soil salinity estimation, providing critical decision-making support for sustainable land management in the China Coastal Areas and other similar regions. Keywords: Soil salinity, Sentinel-2, Indices constructions, Machine Learning, Stacking Regression Share Link | Plain Format | Corresponding Author (Ruiyin Tang)

144	Topic B: Applications of Remote Sensing	ABS-87
Estimating Cultivated Land Quality in Sugarcane Planting Areas Using Remote Sensing and Machine Learning in Guangxi, China Zhihe Hu1,Xuqing li1,2*,Ruiyin Tang1,2,Guohong li1,2,Yancang Wang1,2,Zekun zhang1 1North China Institute of Aerospace Engineering, Langfang 065000, China 2Hebei Province Collaborative Innovation Center for Space Remote Sensing Information Processing and Application, Langfang 065000, China Abstract Guangxi is a pivotal sugarcane region in China, where cultivated land quality underpins high yields and sustainable production. Traditional assessments relying on labor-intensive field sampling and manual interpretation are time-consuming, spatially constrained, and ill-suited to rapid regional evaluations. To overcome these limitations, we develop an integrated pipeline that fuses high-resolution remote sensing, deep learning-based semantic segmentation, and machine learning to estimate a comprehensive Cultivated Land Quality Index (CLQI). Using GF-6 multispectral imagery, we generated RGB composites from the visible bands and curated a segmentation dataset from authoritative sugarcane distribution records and expert-annotated samples to train OCRNet. The trained model accurately delineated sugarcane parcels in Nanning and Chongzuo, yielding a fine-grained distribution map and an estimated sugarcane area of 3,785.48 km^2. Representative sample points were selected, and the comprehensive Cultivated Land Quality Index (CLQI) was computed in accordance with national standards, integrating historical soil data. On Google Earth Engine, spectral indices (e.g., NDVI, EVI, VARI, NDWI) were derived- Spearman rank correlation then screened predictors, retaining NIR, DGSI, DRSI, and DVI as most informative. Two estimators were trained: Random Forest (RF) achieved R2_train=0.798, R2_test=0.687, RMSE=0.016- XGBoost achieved R2_train=0.833, R2_test=0.707, RMSE=0.019. Thus, XGBoost achieved a higher test-set R2 (0.707) with a comparable RMSE, indicating stronger predictive power and generalization for CLQI than RF. The framework provides operational evidence and a technical reference for precision land management and broader agricultural land quality assessments across Guangxi. Keywords: Cultivated Land Quality- Remote Sensing- Sugarcane fields- Semantic Segmentation Share Link | Plain Format | Corresponding Author (li xuqing)

145	Topic B: Applications of Remote Sensing	ABS-343
Rapid Land Cover Change Detection with Optical and SAR Satellite Data after Tropical Cyclone Seroja - Case Study in Dili, Timor-Leste Pedro Junior Fernandes (a*), Masahiko Nagai (b) Yamaguchi University Abstract This study utilizes optical PlanetScope imagery and Synthetic Aperture Radar (SAR) data from Sentinel-1 to assess land cover changes in Dili, Timor-Leste, following Tropical Cyclone Seroja. The primary aim is to investigate how combining these data types enhances disaster monitoring and response in areas affected by flooding. Using the Random Forest classifier, known for its effectiveness with high-dimensional and noisy datasets, we categorized land cover into six classes: vegetation, water, built-up areas, bare soil, clouds, and shadows. This categorization was conducted across pre-disaster, post-disaster, and recovery phases using Google Earth Engine (GEE). To improve the delineation of water bodies, we applied binary segmentation through Otsu thresholding on the SAR images. The classification achieved impressive accuracy, with overall accuracy scores ranging from 97% to 98.7% and Kappa indices between 0.947 and 0.968, indicating strong model performance. Notably, the study revealed a significant increase in water bodies, considerable damage to vegetation and built-up areas after the disaster, and a gradual recovery over time. However, challenges were encountered in urban classification, especially in distinguishing between built-up and bare soil areas. This research emphasizes the value of integrating optical and SAR data with machine learning techniques for effective land cover monitoring in post-disaster contexts, contributing to enhanced disaster preparedness, improved recovery planning, and vital insights for managing flood impacts in regions like Timor-Leste, where technical resources and data may be limited. Keywords: land cover change- change detection- disaster monitoring- Random Forest classifier- Otsu Thresholding- SAR data- optical imagery- Timor-Leste Share Link | Plain Format | Corresponding Author (PEDRO JUNIOR FERNANDES)

146	Topic B: Applications of Remote Sensing	ABS-88
Stability Analysis and Case Study for Fire Smoke Removal of Sentilel-2 Satellite Images Using Fuzzy Classification Yi-Hsin Chung(a*), Yu-Wen Li(b) and Li-Yu Chang (c) a) Engineering Assistant, Taiwan Space Agency 8F, 9 Prosperity 1st Road, Hsinchu Science Park, HsinChu City 300, Taiwan *yihsinchung[at]tasa.org.tw b) Engineering Assistant, Taiwan Space Agency c) Engineer, Taiwan Space Agency Abstract Satellite imagery allows for the identification of wildfire locations and potential spread. However, smoke generated by fires often blocks the penetration of visible and near-infrared (VNIR) radiance, making it difficult to recognize surface features by satellite images. In contrast, shortwave infrared (SWIR) radiance can penetrate smoke particles, thereby improving the visibility of surface information and providing the possiblity of wildfire monitoring for the smoke affected areas. A previous study, ^Using Sentinel-2 SWIR to Remove Forest Fire Smoke^ (ACRS), primarily employed fuzzy classification-developed based on fuzzy set theory-offers a soft classfier approach to combine multiple linear functions in the SWIR to VNIR mapping and improves upon the results obtained using a single linear relationship. This method provides better correspondence between the SWIR and VNIR bands in smoke removal applications. However, in the fuzzy classification process, the number of classes must be defined prior to processing, and this parameter significantly affects both computational efficiency and the quality of results. Using fewer classes (e.g., 3 to 5) may have better efficiency in performance, but it often leads to poor outcomes due to an inability to resolve complex land cover types within the image. Conversely, using too many classes (e.g., more than 30) requires a high number of iterations and substantial processing time to achieve convergence, while yielding only limited improvements in classification accuracy. This study investigates how the number of fuzzy classification classes affects the accuracies across different wildfire case images. Based on the results, the study will offer practical recommendations for optimal class settings in future wildfire monitoring applications using Sentinel-2 satellite images. Keywords: Sentinel-2- Forest Fire Smoke- SWIR- VNIR- fuzzy classification Share Link | Plain Format | Corresponding Author (YI-HSIN CHUNG)

147	Topic B: Applications of Remote Sensing	ABS-89
Dissolved Oxygen Estimation in Freshwater Aquaculture Ponds from UAV Multispectral Imagery via Coupled Transfer Learning Strategies Wenxu Lv (1, 2), Peng Cheng (1, 2), Guohong Li (1, 2*), Ruiyin Tang (1, 2*), Yancang Wang (1, 2*), Xuqing Li (1, 2) 1) North China Institute of Aerospace Engineering, Langfang 065000, China. 2) Aerospace Remote Sensing Information Processing and Application Collaborative Innovation Center of Hebei Province, Langfang 065000, China Abstract Dissolved oxygen is a key indicator of aquatic environmental health. Its dynamic changes directly reflect water quality conditions. In recent years, the integration of UAV multispectral imagery and machine learning algorithms has emerged as a research hotspot for accurately estimating water quality parameters. However, the temporal adaptability and stability of such models remain major challenges limiting their broader application. This study proposes a transfer learning based approach for dynamic monitoring of dissolved oxygen, aiming to enhance the temporal generalization ability of remote sensing estimation models. Data in 2023 were used as the training and validation sets, while data from 2024 were employed as the test set. Three machine learning algorithms, RF, XGBoost, and LightGBM, were used to construct estimation models. Three transfer learning strategies, including instance reweighting (IR), maximum mean discrepancy (MMD), and a hybrid method combining both, were applied to improve the models^ temporal generalization performance. The results show that first, compared with baseline models, instance reweighting increased the coefficient of determination by an average of 12 percent, and reduced RMSE and MAE by 4 percent and 4.5 percent, respectively. MMD improved the coefficient of determination by 32 percent, with average reductions of 11 percent in RMSE and 15 percent in MAE. Second, the hybrid transfer learning strategy combining IR and MMD yielded the most significant improvements, increasing the coefficient of determination by 38 percent, and decreasing RMSE and MAE by 18 percent and 21 percent, respectively. The hybrid RF based transfer learning model achieved the best performance on the test set, with a coefficient of determination of 0.58, RMSE of 3.01 mg/L, and MAE of 2.77 mg/L. These findings demonstrate that transfer learning strategies can effectively mitigate the impact of temporal variability on remote sensing based water quality estimation. Keywords: Transfer learning- temporal generalization- UAV multispectral imagery- freshwater aquaculture-dissolved oxygen Share Link | Plain Format | Corresponding Author (Guohong Li)

148	Topic B: Applications of Remote Sensing	ABS-348
Mapping of Landslide Hazards Using Remote Sensing and GIS in Gandaki Province, Nepal Nabaraj Neupane*1, Bikash Sherchan2, Krishna Prasad Bhandari3 and Sujan Subedi3 *1 Department of Civil Engineering, Pashchimanchal Campus, Tribhuvan University, Nepal 2Department of Geomatics Engineering, Pashchimanchal Campus, Tribhuvan University, Nepal 3Center for Space Science and Geomatics Studies, Pashchimanchal Campus, Tribhuvan University, Nepal Abstract Because of the the rugged topography, fragile geology and heavy rain precipitation pattern, landslide hazards pose a major threat in the Himalayan Region. Gandaki Province experiences the highest rainfall in Nepal and its fragile geology alleviate the probability of landslide occurance every year. The aim of this study is to analyze the landslide hazard and to present the results using a Geographic Information System (GIS) based on hazard risk zonation applying Analytical Hierarchy Process (AHP) techniques in Gandaki Province, Nepal. Hazard risk mapping was performed based on twelve conditioning parameters under four groups i.e., topographic factors (Elevation, Slope, Land Use Land Cover, and Profile curvature), hydrological factors (Proximity to stream, Precipitation, Flow Accumulation, Drainage Density, and Topographic Wetness Index), geological factors (Geology and Fault lines) and infrastructure factor (Proximity to road). Hazard risk maps were then classified into five classes: very low, low, moderate, high, and very high risks. The result then analyzed using GIS based on applying AHP technique. The historical date of landslides were validate by overlaying to the hazard risk map. The validity and accuracy were tested by. The calculated AUC (Areas Under the Curve) value 0.792 in the ROC (Receiver Operating Characteristic curve) indicating good accuracy during validation. The hazard risk maps were produced and were classified into five classes: very low, low, moderate, high, and very high risks. The Landslide Risk Map is used for disaster risk reduction, land use planning, and early warning systems. Keywords: AHP, GIS, Hazards, Remote Sensing, Risk Zone Share Link | Plain Format | Corresponding Author (Nabaraj Neupane)

149	Topic B: Applications of Remote Sensing	ABS-93
Flood Estimation with Application of Surface Water and Ocean Topography (SWOT) satellite data in Gandaki River Basin, Nepal Sherchan B (a) and Bhandari K P (b) (a) and (b) Department of Geomatics Engineering, Institute of Engineering, Tribhuvan University, Nepal Abstract Quantifying flood magnitudes is an important aspect of river basin management, particularly related to harnessing of the water resources (for various uses like drinking water, irrigation, hydropower, inland navigation, etc.), management of water induced disaster, and for planning and design of infrastructures that are supposed to be built across the river and on either side the river. However, there is a huge gap in field data in Nepal, resulting in poor level of planning, management and implementation of water related facilities, causing significant loss of lives and properties. Remote sensing data such as Ka-band radar interferometer (KaRIn) under SWOT mission provides direct measurements of water surface elevation (WSE), width and water surface slope of a river which were used to derive the discharge data for the year 2023. Discharge data derived in such a way have been validated with the directly observed data acquired from the Department of Hydrology and Meteorology (DHM). The results correlate with the observed data implying that the satellite data acquired from SWOT mission are are very useful to fulfill the spatial and temporal data gap in the areas such as Gandaki Basin. The research is ongoing and provided the recent data are available the research will continue for the year 2024 and 2025. Keywords: SWOT, flood, interferometer, discharge Share Link | Plain Format | Corresponding Author (Bikash Sherchan)

150	Topic B: Applications of Remote Sensing	ABS-94
Multi-Satellite Detection and Analysis of the 2024 Mt. Lewotobi Eruption using Himawari-9 and Sentinel-5P Mukhamad Adib Azka (a*), Rif^at Darajat (a), Alpon Sepriando (a) a) Satellite Imagery Team, Meteorology, Climatology, and Geophysics Agency, Indonesia *mukhamad.azka[at]bmkg.go.id Abstract Satellite remote sensing provides the observation of all changes on the Earth^s surface, including monitoring volcanic activities, especially for remote regions. Monitoring methods mostly rely on a single satellite independently for analyzing, but nowadays, volcanic hazard mitigation needs to enhance the models to improve the affected areas of eruption accurately. This study investigates the 2024 eruption of Mt. Lewotobi in East Flores, Indonesia, by comparing volcanic ash and gas dispersion products derived from Himawari-9 and Sentinel-5P satellites. Himawari-9^s multispectral observations are used to detect thermal anomalies and ash clouds through a three-band RGB composite method, utilizing selected infrared channels. In contrast, Sentinel-5P data, obtained from the TROPOMI instrument, provide measurements of sulfur dioxide (SO&#8322-) and aerosol index values, which are used to track gas dispersion in the upper troposphere. Several eruptive events are analyzed to assess the spatial and temporal differences in ash and SO&#8322- plume detection between the two platforms. These combined techniques demonstrate the capability for swift volcanic ash dispersion recognition, thereby providing valuable support for decision-making in national disaster management Keywords: remote sensing, himawari-9, sentinel-5p, mt. Lewotobi, volcanic ash Share Link | Plain Format | Corresponding Author (Mukhamad Adib Azka)

Page 5 (data 121 to 150 of 351) | Displayed ini 30 data/page
<< PREV 1 2 3 4 5 6 7 8 9 10 11 12 NEXT >>

Powered By Konfrenzi Ultimate 1.832M-Build8 © 2007-2025 All Rights Reserved