Page 6 (data 151 to 180 of 351) | Displayed ini 30 data/page
<< PREV 1 2 3 4 5 6 7 8 9 10 11 12 NEXT >>

151	Topic B: Applications of Remote Sensing	ABS-350
Multi-Nutrient Mapping in Oil Palm Using Sentinel-2 and Random Forest: A Cost-Efficient Approach for Precision Agriculture Wiratmoko, D. (a*) and Diana, S.R.(b) a) Indonesian Oil Palm Research Institute, Medan, Indonesia *dhimaswiratmoko[at]iopri.org and wiratmoko2nd[at]gmail.com b) Research Organisation for Governance, Economy, and Public Welfare, PRKP, National Research and Innovation Agency (BRIN), Indonesia Abstract Efficient and accurate assessment of leaf nutrient content is essential for optimizing fertilizer use and ensuring sustainable oil palm production. Conventional methods that rely on extensive field sampling and laboratory analysis are costly, labor-intensive, and have limited spatial and temporal coverage. Advances in remote sensing and cloud-based analytics have offered opportunities for efficient, scalable, and timely nutrient mapping. However, research integrating multi-nutrient prediction in oil palms using satellite imagery and machine learning, particularly within the Google Earth Engine (GEE) platform, remains scarce. This study developed and evaluated a cost-efficient method to map multiple essential leaf nutrients, including nitrogen (N), phosphorus (P), potassium (K), and magnesium (Mg), using Sentinel-2 multispectral imagery and a Random Forest (RF) algorithm in GEE. Field sampling was conducted in oil palm plantations in North Sumatra, Indonesia, and nutrient concentrations were determined by laboratory analysis. Sentinel-2 spectral features, including vegetation indices and reflectance bands, were extracted as predictor variables for RF classification. Model performance was evaluated using the overall accuracy, kappa coefficient, producer accuracy, and user accuracy. The results showed high classification performance, with overall accuracies of 91.13% (N), 91.60% (P), 91.48% (K), and 92.18% (Mg) and kappa values between 0.873 and 0.917. Producer accuracies exceeded 90% for all nutrients, indicating reliable detection, while user accuracies were consistently above 89%, confirming classification stability. Compared with traditional approaches, this method can reduce operational costs by up to 60% and significantly shorten the processing time, enabling large-scale and frequent nutrient monitoring. By linking nutrient mapping to precision agriculture, the proposed approach supports site-specific fertilizer recommendations, minimizes environmental risks from over-fertilization, and enhances plantation management decision-making. The integration of Sentinel-2 imagery, RF modelling, and cloud-based processing is a practical, scalable, and economically viable solution for sustainable oil palm cultivation. Keywords: Cost-efficient monitoring, oil palm, precision agriculture, random forest, remote sensing Share Link | Plain Format | Corresponding Author (Dhimas Wiratmoko)

152	Topic B: Applications of Remote Sensing	ABS-95
Spatio-Temporal Variation of Diatom Blooms along the Singapore Coasts from Multispectral Imagery Amihan Yson Manuel (a*), Ryan Tan (a), Chenguang Hou (a), Soo Chin Liew (a), Chee Yew Sandric Leong (b) a) Centre for Remote Imaging Processing and Sensing, National University of Singapore *aymanuel[at]nus.edu.sg b) Tropical Marine Science Institute, National University of Singapore Abstract Recent incidences of massive fish kill events and the constant presence of toxic species in Singapore waters have been a rising cause of concern especially for our aquaculture industry. While government and research sectors are intensifying efforts to mitigate the threat of harmful algal blooms, current monitoring methods lack the frequency and spatial coverage needed to help better characterize how these blooms develop and spread through time. Remote sensing addresses this gap by providing a panoramic view of bloom extents with sufficient revisit times to bridge information in between field data collection times. Field surveys were conducted from January 2024 to March 2025 in Singapore coastal waters. Phytoplankton community analyses across monsoon seasons revealed diatoms as the dominant group, driving the blooms observed during the sampling period. In this study, we review and apply different diatom abundance indicators such as combining the backscatter signature with the red band ratio, and other spectral indices to map diatom blooms from Sentinel-2 images. Bio-optical models for Singapore coastal waters were developed from the field survey data that included measurements of absorption and backscattering coefficients. We have good results in the retrieval of inherent optical properties with machine learning algorithms on multispectral images, and we are also currently investigating the feasibility of deriving relative diatom fraction from these results. In addition to providing insights vital for monitoring and early detection of blooms, the results from this study may also aid in identifying diatom bloom hotpots throughout the straits of Singapore. Keywords: diatoms, algae blooms, machine learning, spectral indices Share Link | Plain Format | Corresponding Author (Amihan Yson Manuel)

153	Topic B: Applications of Remote Sensing	ABS-97
Deep Learning Based Semantic Segmentation and Explianability Analysis for Building Footprint Extraction Using High Resolution Remote Sensing Imagery Kavzoglu, T., Yilmaz, E.O., Teke, A. Gebze Technical University, Turkey Abstract Building extraction from remote sensing imagery is pivotal across multiple research domains, including urban planning, land management, transportation planning, and disaster monitoring. Although deep learning has demonstrated premise in building extraction, significant challenges remain, due to the variations in building types and the presence of complex backgrounds. Progress in building footprint extraction directly supports two Sustainable Development Goals: Sustainable Cities and Communities (SDG 11), which promotes planned and sustainable urban development, and Climate Action (SDG 13), which is critical for identifying buildings located within disaster prone areas. In this study, the extraction of building footprints was conducted using two widely used deep learning based semantic segmentation models, namely DeepLabV3plus and PSPNet. A high-resolution SPOT dataset covering a study site in the Pyrenees-Orientales region of France was constructed and utilized. The performances of the pretrained models were compared using IoU, F-score, accuracy, precision, and recall metrics. Additionally, decision making processes of the models were analyzed for explainability using the GradientSHAP technique. Results showed that the DeepLabV3plus model achieved an IoU score of 0.9541 and an accuracy rate of 0.9762, whereas the PSPNet model achieved an IoU score of 0.9463 and an accuracy rate of 0.9720. As a result, it was found that the DeepLabV3plus architecture was more effective for large and regular building types. Moreover, GradientSHAP maps produced for the DeepLabV3plus model showed greater sensitivity to building boundaries, and decisions were focused more specifically on the building structure. On the other hand, the PSPNet model focuses more scattered and widespread. In summary, the DeepLabV3plus model resulted in more reliable outputs in terms of both quantitative performance and the explainability perspective. Keywords: Building segmentation, SPOT satellite image, DeepLabV3plus, PSPNet, deep learning Share Link | Plain Format | Corresponding Author (TASKIN KAVZOGLU)

154	Topic B: Applications of Remote Sensing	ABS-353
Relative Spatial Poverty Analysis using Remote Sensing and Points of Interest Elysabeth Nindy Nasing1*, Agung Budi Harto2,3, and Anjar Dimara Sakti2,3 1. Master Program in Geodesy and Geomatics Engineering, Institut Teknologi Bandung, 2. Sains and Technology Information Geographics, Faculty of Earth Science and Technology, Institut Teknologi Bandung, Indonesia, 3. Center for Remote Sensing, Institut Teknologi Bandung, Indonesia *nasingnindy[at]gmail.com Abstract Poverty mapping is a crucial aspect in designing targeted policy interventions. However, conventional approaches based on household surveys are often constrained by high costs. This study proposes the development of a Relative Spatial Poverty Index (RSPI) derived from multisource geospatial data, including nighttime light intensity (NTL), Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), and accessibility to Points of Interest (POI). Variable weighting was performed objectively using Principal Component Analysis (PCA) on a 1.5 x 1.5 km spatial grid to estimate poverty levels on Timor Island, East Nusa Tenggara. Furthermore, hotspot analysis using the Getis-Ord Gi method was used to identify poverty clusters, while model validation was performed using simple linear regression. The results showed that the RSPI performed strongly, with a high correlation to official poverty data from the Central Statistics Agency (BPS) (Pearsons Correlation Coefficient = 0.84- R^2 = 0.70) with an RMSE of 19.65. Morans I analysis confirmed the presence of significant positive spatial autocorrelation (Morans I Index = 0.924). The spatial pattern revealed shows a concentration of poverty in rural and urban areas. Overall, this study offers an effective methodological framework for more granular spatial poverty mapping, which can be the basis for formulating more targeted intervention policies. Keywords: relative poverty, remote sensing, PCA, hotspot mapping Share Link | Plain Format | Corresponding Author (Elysabeth Nindy Nasing)

155	Topic B: Applications of Remote Sensing	ABS-354
Contribution of Satellite Data for Renewable Energy Claire NICODEME EDF power solutions Abstract Energy providers have long used satellite data for occasional applications. However, they were limited by the data^s spatial and temporal resolutions, as well as their high prices. New Space development opens doors to a multitude of new use cases. With so many actors on the market, and their number still rising, there is a profusion of satellites and associated data. In addition, the standardization of components and software strongly reduces costs and increase fiability. Last but not least, new service-based economical models make data accessible and affordable. Therefor, satellite data becomes a legitimate information source for industries, offering short revisit time, worldwide coverage and high resolution. In particular, Earth Observation data starts to compete with on-site or aerial acquisition. Indeed, both classical methods are costly either to install and maintain or because of the mandatory expertise and equipment. The coverage is often limited, homogeneity across data sources is not always possible, and some areas are just impossible to reach. Satellites address these issues. The range of applications for Energy providers, especially renewables, is extensive. This paper aims to evaluate the impact of Low Earth Orbit (LEO) micro and nano-satellites for industrials. We will discuss how they may increase knowledge about and reduce the environmental impact of powerplants, from the site selection to its end-of-life. It includes for example historical data analysis and site modeling, construction work and soil stability monitoring, habitats mapping and evolution studying, etc. Finally, satellite imagery may also help prevent and better respond to disasters. Let us note that satellite imagery mostly comes as an additional information source, and rarely replace classical solutions. Keywords: Renewable energy, Earth Observation, Monitoring, Environmeent modeling Share Link | Plain Format | Corresponding Author (Claire NICODEME)

156	Topic B: Applications of Remote Sensing	ABS-355
Predictive Ability of Delft3D-Based Storm Surge Forecasts Using Historical and Forecasted Typhoon Tracks Christine B. Mata, Clein Winslee Duquez, Olivia C. Cabrera, tristan Janryll A. Mata, Nathaniel R. Alibuyog Mariano Marcos State University Abstract The DELFT3D Flexible Mesh (D3D FM) model with an unstructured grid extending up to 10 m elevation above mean sea level inland was generated to simulate storm surge in coastal areas of Northwestern Luzon (NWL), Philippines. The objective of this research is to examine the forecasting ability of the model at different lead times during extreme events by using historical versus forecasted data. Three events were selected: Super Typhoon Mangkhut (2018), Tropical Storm Pankhar (2017), and Typhoon Hato (2017). Two sea-level stations were used to validate the model: Currimao (CM) and San Fernando (SF) stations. The model^s performance revealed an average NSE = 0.834, RMSE = 7.8 cm, and MAE = 6.2 cm, indicating very good agreement between observed and simulated water levels at both CM and SF stations. Using forecasted tracks of the same events by the Japan Meteorological Agency (JMA), the average RMSE at 72-, 48-, and 24-hr lead times are 5.6 cm, 7.5 cm, and 10.6 cm, respectively, while the average MAE is 4.3 cm, 6.9 cm, and 8.9 cm, respectively. The forecasting ability of the model performs very high and indicates suitability for operational surge forecasting, although it becomes less reliable closer to landfall, especially for intense typhoons with rapid structural changes. Model performance is generally better for moderate typhoons with simpler wind and pressure fields. Overall, the model can be readily used to support disaster preparedness and early warning systems in coastal communities. Keywords: storm surge, typhoon track, lead time, sea level, forecast Share Link | Plain Format | Corresponding Author (Christine B. Mata)

157	Topic B: Applications of Remote Sensing	ABS-101
Spatio-Temporal Analysis of Inundation Exposure and Soil Heat Stress in Paddy Fields Using Multi-Sensor Remote Sensing in the MADA Region Maizatuldura Mohd Isa1, Hana Mohamad Jamil1, Mohd Arif Shahdan Azmi1, Mckreddy Yaban1, Nurul Suliana Ahmad Hazmi1 And Mohd Shahrizal Bin Mohd Noor2 1 Maizatuldura Mohd Isa: Research Officer, Malaysian Space Agency (MYSA), Malaysia 2 Mohd Shahrizal Bin Mohd Noor: Head of Research and Statistics Branch, Muda Agricultural Development Authority, Malaysia Abstract Paddy cultivation in Malaysia MADA granary area is increasingly threatened by climate induced extremes such as flash floods and elevated soil temperatures. To address these challenges, the Malaysian Space Agency, MYSA and the Muda Agricultural Development Authority, MADA collaborated on a study to assess the spatial and temporal impacts of inundation and soil heat stress on rice production using integrated multi-sensor satellite remote sensing. Inundation patterns were mapped using Sentinel1 Synthetic Aperture Radar, SAR imagery during key crop growth stages. Land Surface Temperature, LST data from Landsat8 and Sentinel-3 were employed to monitor thermal stress throughout the planting season. Vegetation dynamics and stress responses were analyzed using Normalized Difference Vegetation Index, NDVI profiles derived from Sentinel-2 under both hydrological and thermal stress conditions. Initial findings indicate that paddy plots subjected to more than three consecutive days of flooding or LST values exceeding 35C during the flowering stage exhibited significant vegetation stress and potential yield reductions. This spatio-temporal analysis provides critical insights to support precision agriculture, enhance irrigation strategies, and strengthen climate resilience in rice-growing ecosystems. Keywords: Paddy field, flood mapping, soil heat stress, land surface temperature (LST), Sentinel-1 and NDVI Share Link | Plain Format | Corresponding Author (MAIZAITOLDURA MOHD ISA)

158	Topic B: Applications of Remote Sensing	ABS-358
Tidal Flooding Assessment in Balikpapan Coastline using Modified Coastal Vulnerability Index (CVI) Nabila Luthfiani (a), Muhammad Aldila Syariz (b*) Institut Teknologi Sepuluh Nopember (ITS), Surabaya 60111, Indonesia *aldilasyariz[at]its.ac.id Abstract Coastal zones are foundational in supporting economic and ecological activities, yet are increasingly exposed to tidal flooding due to sea-level rise and climate variability. Indonesia, as the world^s largest archipelagic nation, faces heightened risk with extensive low-lying coastlines and rapid urban development. Balikpapan, a coastal city in East Kalimantan and a strategic node near the new national capital, experiences frequent tidal inundation events that threaten industrial infrastructure, fisheries, and coastal tourism. This study aims to assess the physical vulnerability of Balikpapan^s coast to tidal flooding by applying a modified Coastal Vulnerability Index (CVI) using remote sensing and geospatial data. Landsat 8 imagery, Sentinel 2A and secondary datasets were used to extract seven key parameters: geomorphology, shoreline change rate, coastal slope, significant wave height, relative sea-level rise, mean tidal range, and mangrove width. Each parameter was ranked and integrated within a GIS-based CVI framework to produce spatial vulnerability map at sub-district level. The result shows that 21.43% of sub-districts are not vulnerable, 28.58% exhibit low to moderate vulnerability, 35.71% are classified as vulnerable, and 14.29% as highly vulnerable. The findings can inform local authorities and stakeholders in prioritizing mitigation efforts and developing sustainable coastal management strategies for Balikpapan and similar regions across Asia. Keywords: Tidal Flood, Coastal Resilience, Climate Adaptation, SDGs. Share Link | Plain Format | Corresponding Author (Nabila Luthfiani)

159	Topic B: Applications of Remote Sensing	ABS-110
BPA-Based InSAR for High-Resolution DEM Generation Using UAV and Airborne Platforms Sangho An, Duk-jin Kim, Junwoo Kim School of Earth and Environmental Science, Seoul National University, Seoul, Republic of Korea Future Innovative Institute, Seoul National University, Siheung, Republic of Korea Abstract Backprojection (BPA) imaging offers a flexible alternative to conventional frequency-domain methods in synthetic aperture radar (SAR) systems, particularly for low-altitude platforms such as unmanned aerial vehicles (UAVs) and light aircraft. However, its application in interferometric SAR (InSAR) has remained limited due to challenges in phase consistency, co-registration, and precise motion compensation. This study presents a complete processing framework for BPA-based InSAR, enabling high-resolution digital elevation model (DEM) generation by addressing these limitations through both theoretical and practical contributions. We analyse the phase behavior specific to BPA and demonstrate that, by constructing a common imaging grid, flat-earth phase components can be inherently cancelled, eliminating the need for separate co-registration and flattening steps. A high-precision antenna trajectory estimation technique is implemented by integrating differential GPS, inertial measurements, and lever-arm correction to model both translational and rotational motions, ensuring sub-wavelength phase alignment. Experimental data were acquired using airborne and UAV platforms over Yongnuni Oreum in Jeju Island and Baegot Park in Siheung, respectively. The airborne result was validated against TanDEM-X data and corner reflector measurements, while the UAV result was compared to a photogrammetry-derived DEM and ground-deployed reflectors. The proposed method produces interferometric results with stable phase characteristics and accurate elevation output, comparable to those from frequency-domain InSAR. This framework enables coherent processing of BPA-generated single-look complex (SLC) images and offers a practical tool for topographic mapping using flexible SAR systems, with potential applications in local terrain monitoring and geohazard assessment. Keywords: Airborne SAR, UAV SAR, Backprojection, InSAR, DEM Share Link | Plain Format | Corresponding Author (Sangho An)

160	Topic B: Applications of Remote Sensing	ABS-366
Urban Expansion and Carbon Footprint in Selangor: Remote Sensing and GIS Applications for Sustainable Cities and Climate Action Nur Hidayah Zakaria, Nur Atiqah Hazali, Siti Aekbal Salleh, Nurul Amirah Isa, Nini Nurdiana Johari, Arnis Asmat, Nurafiqah Wahid, Kamri Ahmad Faculty of Built Environment (FBE), Kompleks Tahir Majid, Universiti Teknologi MARA, 40450 Shah Alam, Selangor Darul Ehsan, Malaysia. Geospatial Science & Technology College, Level 2 & 3, Wisma Lembaga Jurukur Tanah (LJT, Lorong Perak, Taman Melawati, 53100 Kuala Lumpur, Selangor,Malaysia. Faculty of Asia Built Environment and Surveying, Universiti Geomatika Malaysia, Lot 5-5-7, 5th Floor, Prima Peninsular, Jalan Setiawangsa 11, Setiawangsa, 54200 Kuala Lumpur, Federal Territory of Kuala Lumpur, Malaysia. Institute for Biodiversity and Sustainable Development (IBSD), Universiti Teknologi MARA School of Chemistry and Enviroment, Faculty of Applied Science, Universiti Teknologi MARA, 40450 Shah Alam, Selangor Darul Ehsan,Malaysia Abstract Rapid urbanization and land use transformation are major agents of rising carbon dioxide (CO2) emissions, which compromise natural carbon sinks and exacerbate climate concerns. Selangor, Malaysia^s most urbanized and industrialized state, is the prime example, whereby population growth, industrialization, and deforestation fuel emissions while reducing biomass storage. This study employs remote sensing and Geographic Information Systems (GIS) to map and quantify CO2 emissions across Selangor for 2015 and 2025 using Landsat 8 Operational Land Imager (OLI) data. Land cover and land use (LULC) were derived through supervised classification, with the aid of Normalized Difference Vegetation Index (NDVI) in helping with Above Ground Biomass (AGB), carbon stock, and emission level estimation. Findings show extensive land cover alterations, where urban land cover expanded from 38% to 42% between 2015 and 2025, while forest cover reduced from 32% to 28%. High NDVI areas (>0.6) reduced from 27% to 23%, as well as high AGB (>100 t/ha) from 24% to 20% and carbon stock (>24 t C/ha) from 25% to 20%. Concurrently, high-emission zones (>100 tCO2/ha) expanded from 22% to 28%, and carbon sequestering zones (<0 tCO2/ha) declined from 15% to 12%, particularly in Hulu Selangor and Sabak Bernam. This indicates a net reduction in carbon sequestration capacity, raising the doubt as to whether Selangor is likely to achieve its Low Carbon City 2030 target. The integration of remote sensing and GIS is effective in monitoring spatial carbon dynamics and provides actionable information for interventions such as urban greening, sustainable land use, and forest conservation, directly aiding Malaysia^s efforts for SDG 11 and SDG 13 Keywords: Carbon Emissions, Remote Sensing, GIS, Sustainable Urban Planning Share Link | Plain Format | Corresponding Author (Nur Hidayah Zakaria)

161	Topic B: Applications of Remote Sensing	ABS-112
Evaluating the Impact of Surface Deformation on Building Damage During the 2022 Cianjur Earthquake Using Remote Sensing Silmi Afina Aliyan*1, Mochammad Rifqi Naufal Alfayyadh1, Jupri Sains Informasi Geografi, Fakultas Pendidikan Ilmu Pengetahuan Sosial, Universitas Pendidikan Indonesia Abstract An earthquake measuring 5.6 on the Magnitude scale occurred in Cianjur Regency in 2022, which was caused by the activity of the newly discovered Cugenang fault. The type of fault, based on the focal mechanism analysis by the Meteorology, Climatology, and Geophysics Agency (BMKG), is categorized as a dextral strike-slip fault with a strike direction of N347oE and a dip of 82 degrees. The relatively shallow depth of the earthquake at 60 km below the surface caused surface deformation around the area traversed by the fault. Much damage occurred to buildings and infrastructure- the distribution of damage needs to be identified to determine the factors influencing the damage. This study aims to analyze surface deformation and its impact on building and infrastructure damage due to the 2022 Cianjur earthquake. The method used in this study is quantitative and descriptive, with a Python-based Remote Sensing approach and statistical analysis to determine the relationship between building damage and the deformation conditions that occurred. The results show that the implications of the presence of the Cugenang Fault in the 2022 Cianjur earthquake resulted in two deformation phenomena. The northern area of the Cugenang Fault showed a maximum land surface rise of 38.14 millimeters. In the eastern area of the Cugenang Fault, a maximum land surface subsidence of 35.04 millimeters was observed. The correlation between surface deformation and the level of building damage shows a weak relationship. The results of a simple linear regression analysis indicate that building damage during the Cianjur earthquake was not influenced by surface deformation. The coefficient of determination yielded a value of 0.05, or only 5%. This means that deformation only affected 5% of the total damage, while the remaining 95% was influenced by other factors not examined in this study. Keywords: Surface Deformation, Cugenang Fault, Remote Sensing, Building Damage Assessment, Python-Based Geospatial Analysis Share Link | Plain Format | Corresponding Author (Silmi Afina Aliyan)

162	Topic B: Applications of Remote Sensing	ABS-369
Revealing Bare-Soil Texture using GLCM and Multispectral Indicators: Applications to Sustainable Agricultural Land-Use Planning in Enrekang Nurfadila JS 1*, Syaeful Rahmat 2, Rismaneswati 3 1. Agricultural Sciences Study Program, Post-Graduate School, Hasanuddin University, Makassar, Indonesia 2. Remote Sensing and Geographic Information Systems Study Program, Faculty of Vocational Studies, Hasanuddin University, Makassar, Indonesia 3. Soil Science Study Program, Faculty of Agriculture, Hasanuddin University, Makassar, Indonesia Abstract Remote sensing provides a scalable pathway to characterize soil texture in data-sparse tropical landscapes, but the signal is indirect and highly conditioned by surface state. This study develops a PlanetScope based workflow to reveal bare-soil texture patterns in Enrekang for sustainable agricultural land-use planning. We construct dry season, low vegetation composites to isolate bare soil, apply atmospheric and topographic corrections, and compute Gray Level Co-occurrence Matrix (GLCM) metrics on red-edge and near-infrared channels within moving windows. Texture features are fused with multispectral soil indicators and terrain covariates to enhance separability under variable illumination and micro relief. Field and laboratory observations guide model development and spatially aware validation. Qualitatively, the resulting maps delineate coherent zones aligned with landform and management gradients, distinguishing five dominant texture classes without relying on quantitative thresholds: sandy clay loam, silt loam, clay, silty clay loam , and clay loam. Red-edge and NIR texture metrics consistently emerge as the most informative cues under bare soil, dry conditions, while terrain variables stabilize transitions across slope positions. Principal limitations residual vegetation, surface moisture, iron oxide coatings, and tillage imprints are mitigated through strict masking and multi-date compositing. The workflow is repeatable, low cost, and transferable, offering decision support for site selection, crop and tillage choices, irrigation prioritization, erosion control, and targeted ground sampling across smallholder agroecosystems. Keywords: GLCM, PlanetScope, soil texture, bare soil, Enrekang Share Link | Plain Format | Corresponding Author (NURFADILA JS)

163	Topic B: Applications of Remote Sensing	ABS-115
A Preliminary Study on Remote Sensing-Based Detection of Vacant Houses in Urban Areas Shota Tsujino (1)*, Kiichiro Kumagai (1),Kazuki Hatao (2) (1) Setsunan University, Japan (2) HawksMap Co., Ltd., Japan Abstract In Japan, the population is declining at a rapid pace due to a sharp drop in the birth rate and the progression of an aging society. As a result, the importance of continuously monitoring urban structures, living environments, and related social dynamics over the long term has increased significantly. Among various influencing factors, accurately identifying the spatial distribution of vacant houses is expected to be an effective and practical means of observing underutilized, low-utilized, or abandoned spaces in diverse urban environments. However, in field surveys aimed at accurately identifying vacant houses, various issues such as physical access restrictions, obstructed views due to adjacent buildings or vegetation, safety concerns, and legal privacy restrictions often make it difficult or impossible to visually confirm the exterior of buildings. To comprehensively address these challenges, we have focused on aerial images captured by unmanned aerial vehicles (UAVs, commonly known as drones) and proposed a method to effectively identify the condition of the surrounding environment of residential properties as an objective and quantitative indicator of vacant or underutilized residential properties by leveraging deep learning techniques for image recognition. Considering the potential application of satellite imagery for large-scale and efficient monitoring, this study first performed interpolation processing on UAV images as a preliminary step and compared the differences in identification results due to variations in spatial resolution. Furthermore, image-based classification was performed on all buildings within the designated field survey area, and the classification results of the original high-resolution UAV images and the interpolated low-resolution images were compared in detail. Through this detailed comparison, this study verified the impact of image resolution on classification accuracy and confirmed the potential of this approach as an expandable and cost-effective method for supporting large-scale identification and continuous monitoring of vacant house distribution. Keywords: Vacant houses,UAV imagery,Deep learning,Spatial resolution,Image recognition Share Link | Plain Format | Corresponding Author (Shota Tsujino)

164	Topic B: Applications of Remote Sensing	ABS-116
Detection and analysis of forest fire damaged areas using Sentinel-2 imagery in Gyeongsangbuk-do Province, Korea Mohamed, S.Y.1, Yoon, H.S.2, Lee, S.Y.3, Choung Y.J.4, and Jo M.H.*5 1Researcher, Geo C&I Co., Ltd., South Korea 2Researcher, Geo C&I Co., Ltd., South Korea 3Emerits professor, Geo C&I Co., Ltd., South Korea 4Researcher, Geo C&I Co., Ltd., South Korea 5Director, Geo C&I Co., Ltd., South Korea Abstract Forest fires pose substantial threats to both ecological systems and economic stability, particularly in regions with vulnerable natural environments. The ability to accurately and rapidly assess the extent of fire damage is essential for implementing timely and effective recovery strategies. This study aims to detect and map forest fire damage in Gyeongsangbuk-do Province, Korea, where significant fire activity occurred between March 22 and March 29, 2025. To achieve this, high-resolution Sentinel-2 satellite imagery was utilized, capitalizing on its spectral capabilities and frequent revisit times. The methodology combined supervised classification techniques with the difference Normalized Burn Ratio (dNBR), a widely accepted index for identifying burn severity and extent. Supervised classification was applied to distinguish burned and unburned areas based on spectral signatures. The dNBR was then calculated by subtracting the post-fire NBR values from the pre-fire NBR values. The analysis revealed that the estimated burned area was 690.19 km2 based on supervised classification and 774.31 km2 using dNBR. Compared to the actual damaged area reported by the Korea Forest Service (902.89 km), the dNBR-based estimate more closely approximates the true extent of the fire-affected region. This suggests that dNBR offers higher accuracy in capturing the full spatial extent of burn severity. While supervised classification is useful for delineating obvious fire damage. Overall, the study demonstrates that the use of freely available satellite data, combined with well-established image processing techniques, offers a cost-effective and efficient solution for forest fire damage assessment. This methodology can be applied in other forest fire-prone regions to support environmental monitoring, disaster response, and long-term ecological recovery planning. Keywords: Difference Normalized Burn Ratio (dNBR), Forest fire damage assessment, Gyeongsangbuk-do Province, Sentinel-2 imagery, Supervised classification Share Link | Plain Format | Corresponding Author (Samar Youssef Sayed Mohamed)

165	Topic B: Applications of Remote Sensing	ABS-117
Tree Height Estimation Using Sentinel-1/2 and LiDAR Data: A Case Study in the Dalseong Wetlands, South Korea Baek, G.H..1, Mohamed, S.Y.2, Jang, H.K.3, Choung Y.J. 4, and Jo M.H.5* 1Researcher, Geo C&I Co., Ltd., South Korea 2Researcher, Geo C&I Co., Ltd., South Korea 3Researcher, Geo C&I Co., Ltd., South Korea 4Researcher, Geo C&I Co., Ltd., South Korea 5Director, Geo C&I Co., Ltd., South Korea Abstract Accurate estimation of tree height is fundamental to forest resource management, carbon stock assessment, and ecological monitoring. This study presents a remote sensing-based approach to estimate tree height by integrating multi-source satellite data with machine learning, using the Dalseong Wetlands in Daegu, South Korea as a case study area. The region is characterised by heterogeneous forest cover within a protected wetland ecosystem, offering a suitable testbed for evaluating forest height modelling techniques. We utilised Sentinel-2-derived NDVI, Sentinel-1 SLC backscatter (VV and VH), and a DSM generated from Sentinel-1 InSAR imagery as predictor variables. The target variable, reference tree height, was extracted from a LiDAR-derived normalised digital surface model (nDSM). A Random Forest regression model was developed using both original and derived features, including NDVI-DSM interaction, DSM squared, logarithmic and square root DSM, square root VH, and the VV/VH backscatter ratio. After removing invalid or noisy pixels and standardising the features, the model was trained on 80% of the data and tested on the remaining 20%. The model achieved a root mean square error (RMSE) of 2.0527 metres and a coefficient of determination (R2) of 0.6161 when compared to LiDAR-based tree heights. The final tree height predictions were exported as a georeferenced raster map, which may serve as a valuable baseline for long-term monitoring of forest structure, biomass estimation, and habitat mapping in wetland regions. This research demonstrates the effectiveness of combining freely available SAR and optical satellite data with LiDAR and machine learning to estimate forest parameters in ecologically sensitive or data-scarce areas. Keywords: Dalseong Wetlands, LiDAR, Random forest, Sentinel-1/2, Tree height estimation. Share Link | Plain Format | Corresponding Author (Samar Youssef Sayed Mohamed)

166	Topic B: Applications of Remote Sensing	ABS-118
XGBoost-Based Predictive Modeling Using Sentinel-2 Satellite Imagery and Empirical Data of Jakarta River Water Quality Rijaldi R.M. (1), Prayoga G. (1)*, Faskayana Y.S. (1,2), and Firmansyah F.S. (1) 1) Center for Environmental Research, IPB University, Indonesia 2) The Graduate School of Agriculture, Tokyo University of Agriculture and Technology, Japan *gatotprayoga16[at]gmail.com Abstract Machine learning methods have shown strong potential in estimating water quality parameters. Satellite remote sensing provides an efficient approach for monitoring water quality over extended periods and spatial variations, thereby reducing reliance on resource-intensive field monitoring. Therefore, this study aims to develop a predictive approach using XGBoost regression and Sentinel-2 satellite imagery to estimate river water quality. Dataset from 60 river monitoring stations across 12 river sections, collected over 16 periods between 2021 and 2024, was used as empirical data and then paired with harmonized data from Sentinel-2. The dataset paired in-situ measurements with reflectance values from relevant Sentinel-2 bands for model training. Using Google Earth Engine (GEE), reflectance values from Sentinel-2 bands were extracted for each sampling point and acquisition date. The derived spectral features were then used to train XGBoost regression models for each water quality parameter. The models showed moderate predictive performance, with R square values of 0.65 (turbidity), 0.61 (TSS), 0.58 (TDS), 0.63 (color), and 0.67 (transparency). Corresponding RMSE values were 8.7 NTU (turbidity), 45.2 mg/L (TSS), 60.4 mg/L (TDS), 25.8 Pt-Co units (color), and 6.3% (transparency), indicating a fair level of accuracy with room for improvement across parameters. This study demonstrates the possibility of estimating river water quality using remote sensing. This approach could enhance the effectiveness and efficiency of water quality management, particularly in challenging and remote areas. However, several significant limitations, such as the limited availability of Sentinel-2 imagery that coincided precisely with the in situ sampling dates, may have introduced some temporal discrepancies in the dataset. Keywords: water quality parameters- remote sensing- machine learning- XGBoost- Jakarta Share Link | Plain Format | Corresponding Author (Gatot Prayoga)

167	Topic B: Applications of Remote Sensing	ABS-375
Spatiotemporal Analysis of Land Surface Temperature, Vegetation, and Water Index Correlations Using MODIS Data (2003-2024) (Case Study: Palangkaraya City, Indonesia) Soni Darmawan, Rika Hernawati, Muhammad Faiza Abdurrahman, Lintan Bening Nurulhakim Institut Teknologi Nasional Bandung Abstract Rapid urbanization and land cover transformation have led to increased land surface temperatures (LST), particularly in dense city areas, contributing to the Urban Heat Island (UHI) phenomenon. This study investigates the spatiotemporal patterns and correlations between Land Surface Temperature (LST), Normalized Difference Vegetation Index (NDVI), and Normalized Difference Water Index (NDWI) in Palangkaraya City from 2003-2024 using MODIS satellite data and Google Earth Engine. We used an 8-day composite MODIS dataset (MOD11A2 for LST, MOD13A2 for NDVI, and MYD09A1 for NDWI calculations) covering the period 2003 to 2024. Data preprocessing included cloud masking, data filtering, and gap filling using temporal interpolation. The dataset was then clustered into annual averages using Google Earth Engine over the administrative area of Palangkaraya City. Time series analysis was performed to detect temporal trends, while spatial analysis used distribution mapping and Pearson correlation analysis through scatter plots to quantify relationships between variables. Over the 21-year period, Palangkaraya City showed significant LST increase of 0.3 degrees Celcius, concurrent with declining vegetation cover (NDVI: -0.02) and water content (NDWI: -0.002). Correlation analysis revealed a moderate negative relationship between LST and NDVI with r = -0.54, and strong negative correlation between LST and NDWI with r = -0.87. Keywords: Land Surface Temperature- NDVI- NDWI- MODIS- Urban Heat Island- Google Earth Engine- Palangkaraya Share Link | Plain Format | Corresponding Author (Soni Darmawan)

168	Topic B: Applications of Remote Sensing	ABS-121
Spatiotemporal Flood Characterization and Early Warning System Development in the Rokan Watershed Using Sentinel-1 SAR and Water Level Data Rijaldi R.M.(1*), Sidik R.F.(1), Liyantono.(1), Setiawan Y.(1) and Faskayana Y.S.(2) 1) Center for Environmental Research, IPB University, Indonesia 2) The Graduate School of Agriculture, Tokyo University of Agriculture and Technology, Japan *rizkirijaldi44[at]gmail.com Abstract The Rokan watershed in Sumatra, frequently experiences flood inundation with the most extensive event recorded between late 2023 and early 2024 that last for over three months. Despite this, the long-term spatiotemporal characteristic of floods in this watershed remain unstudied and the early warning system has not been developed yet to mitigate its impacts. This study aims to characterize flood dynamics over a 10-year period (2014-2024) and provide a foundation for a flood early warning system in the Rokan Watershed. Flood extent was identified using Sentinel-1 synthetic aperture radar (SAR) data, applying a -19 dB threshold to VH-polarized imagery. Unlike optical sensors, Sentinel-1 SAR can penetrate cloud cover and is not affected by sunlight enabling reliable and consistent flood mapping under all weather conditions. The threshold-based classification was implemented using Google Earth Engine through Google Colab, enabling rapid and consistent mapping across multiple time periods. Validation using 439 ground reference points within 100-meter buffer yielded an overall detection accuracy of 83.8%. Detection results revealed the extensive inundation that occured in 2014, 2018, 2019, and especially during the 2023-2024 period, indicating an increasing trend in flood severity and spatial extent. The results were compared with water level observation data from BWSS III monitoring stations to explore temporal relationships between hydrological conditions and flood onset. The comparison highlights potential time lag between upstream water levels and flood inundation. Based on data from Lubuk Bendahara Station, when the water level reaches 220 cm during the rainy season at the end of the year, increased vigilance is necessary within 2 to 5 days due to the potential risk of flooding in Bonai Village. These findings can enhance flood preparedness and support early warning system development in the Rokan Watershed. Keywords: flood dynamics- Sentinel-1 SAR- early warning systems- Google Earth Engine Share Link | Plain Format | Corresponding Author (Rizki Moch Rijaldi)

169	Topic B: Applications of Remote Sensing	ABS-378
Characteristics of Spectral Values and Spatial Distribution of Oil Palm Health in Relation to Productivity at PT Kayung Agro Lestari Plantation Atysatya Prawira Adjas (a), Masita Dwi Mandini Manessa (a), Iqbal Putut Ash Shidiq (a), a. Department Geography, Faculty Mathematic and Science, Universitas Indonesia, Indonesia Abstract Oil palm plantations support the non-oil and gas economy in Indonesia, but in business practice oil palm plantations still face challenges in maintaining the health of oil palm plants. Currently, one of the main problems is the large number of unhealthy trees that can directly affect neighboring trees. If an overview of the plantation area can be identified quickly and in detail, this information can be integrated into advanced planning in oil palm planta-tion management. To address this problem, this research presents a system for detecting the health of oil palm plants by utilizing deep learning tech-niques in collaboration with UAV orthophotos and descriptive analysis to see the relationship to the productivity of the oil palm fruit produced. The appli-cation of semantic segmentation using the U-net algorithm aims to identify the palm tree canopy, eliminate the bias between the tree canopy and the ob-jects below it and facilitate the classification of plant health. In the next stage, the algorithm used is a support vector machine (SVM) for accurate plant health classification with a fairly high value. The evaluation results of the classification of oil palm plant health gave satisfactory results with F1-score values in blocks D52 and D53 of 71.4% and in blocks E58 and E59 reaching 81.3%. It is known that the difference in the value of the F1-score results is influenced by the quality of the multispectral aerial photographs used. In multispectral aerial photographs in blocks D52 and D53 there is some noise that makes the difference in the value obtained. The relationship between oil palm plant health conditions and oil palm fruit productivity is carried out using productivity data in oil palm plant blocks with vulnerable months from January to June in 2024. The relationship between oil palm health conditions and productivity shows a tendency that the number of un-healthy trees correlates with decreased productivity, as seen in blocks D52 and E58. Conversely, blocks with fewer unhealthy trees, such as D53, show increased productivity. Although pests and diseases have been shown to have a significant impact, productivity is also influenced by other factors, such as land characteristics, climate, and harvest management, so a holistic approach is needed for optimal management. Keywords: Health Mapping- Oil Palm Plants- Productivity- Semantic Segmentation. Share Link | Plain Format | Corresponding Author (Masita Dwi Mandini Manessa)

170	Topic B: Applications of Remote Sensing	ABS-123
Thermal Mapping and Land Cover Correlation to Support Heat Island Mitigation in Jombang Regency Using Remote Sensing Data Tarisa Fadilah, Luisa Febrina Amalo, Novia Ramadhani Center for Environmental Research, IPB University, Bogor, Indonesia Conservation of Forest Resources and Ecotourism Study Program, Faculty of Forestry and Environment, IPB University, Bogor, Indonesia Abstract Land cover change in semi-urban areas can affect the increase of surface temperature, thus contributing to the formation of the urban heat island phenomenon. This study aims to analyse the spatial relationship between land surface temperature (LST), normalised difference vegetation index (NDVI), and normalised difference built-up index (NDBI) in Jombang Regency, East Java Province, Indonesia, during the dry season of 2024. Data were obtained from Landsat 8 and Sentinel-2 satellite images that had been filtered based on cloud cover levels of less than 20%. The researchers analyzed the data to calculate surface temperature values, vegetation density measurements, and built-up area intensity measurements. The results showed that the average surface temperature is 29.86 degrees Celsius with a minimum value of 15.02 degrees Celsius and a maximum of 44.68 degrees Celsius. The NDVI value of 0.35 indicated moderate vegetation control, but the NDBI value of -0.097 showed undeveloped land as the main land feature. The Pearson correlation analysis showed that vegetation index values had a small negative relationship with surface temperature readings (r = -0.20) and built-up index values had a small positive relationship with surface temperature readings (r = +0.25). A very strong negative correlation was found between vegetation index and built-up index (r = -0.85), indicating the conversion of vegetative land into built-up areas. These results suggest that although vegetation cover exists throughout Jombang District, the spatial arrangement of green infrastructure may not be suitable for reducing surface heat. The research shows that green open spaces require deliberate planning to achieve their full potential in reducing heat and enhancing climate resilience within urban development areas. Keywords: built-up index, remote sensing, surface temperature, vegetation index Share Link | Plain Format | Corresponding Author (Tarisa Fadilah)

171	Topic B: Applications of Remote Sensing	ABS-381
Deep Learning Framework for Automated Detection and Parameter Estimation of Internal Solitary Waves from Sentinel-1 SAR Imagery in the Lombok Strait, Indonesia Chonnaniyah (1*), Toshikazu Samura (2), Abd. Rahman As-syakur (3) and Takahiro Osawa(2) 1) Environmental Engineering Program, Institute of Science and Technology Nahdlatul Ulama Bali (ISTNUBA), Denpasar, Bali 80119, Indonesia 2) Center for Research and Application of Satellite Remote Sensing (YUCARS), Yamaguchi University, Ube, Yamaguchi 755-8611, Japan 3) Marine Science Department, Faculty of Marine and Fisheries, Udayana University, Bukit Jimbaran Campus, Bali 80361, Indonesia Abstract Keywords: Deep learning, internal solitary waves, oceanography, remote sensing, Sentinel-1 Share Link | Plain Format | Corresponding Author (Chonnaniyah Chonnaniyah)

172	Topic B: Applications of Remote Sensing	ABS-382
Deep Learning Framework for Automated Detection and Parameter Estimation of Internal Solitary Waves from Sentinel-1 SAR Imagery in the Lombok Strait, Indonesia Chonnaniyah (1*), Toshikazu Samura (2), Abd. Rahman As-syakur (3) and Takahiro Osawa (2) 1) Environmental Engineering Program, Institute of Science and Technology Nahdlatul Ulama Bali (ISTNUBA), Denpasar, Bali 80119, Indonesia *chonnaniyah[at]unud.ac.id 2) Center for Research and Application of Satellite Remote Sensing (YUCARS), Yamaguchi University, Ube, Yamaguchi 755-8611, Japan 3) Marine Science Department, Faculty of Marine and Fisheries, Udayana University, Bukit Jimbaran Campus, Bali 80361, Indonesia Abstract Internal solitary waves (ISWs) are nonlinear internal waves that exert significant influence on subsurface ocean mixing, sediment resuspension, and coastal current dynamics. Their occurrence and variability have critical implications for navigation safety, offshore infrastructure, and climate-related energy redistribution in the upper ocean. Traditional studies of ISWs using synthetic aperture radar (SAR) imagery have primarily relied on manual interpretation to estimate parameters such as soliton count, wavelength, and propagation direction. While effective in specific case studies, manual approaches are labor-intensive, subjective, and challenging to scale for large, multi-year satellite archives. This study introduces an artificial intelligence framework for automated detection and parameter estimation of ISWs using Sentinel-1 SAR imagery. The approach integrates convolutional neural networks (CNNs) for spatial feature extraction, long short-term memory (LSTM) modules for sequence learning, and a self-attention mechanism to emphasize wave-relevant features. Sentinel-1 SAR imagery was preprocessed through radiometric calibration, speckle filtering, terrain correction, and patch-based extraction. A dataset of 128 x 128 patches containing visible internal wave signatures was compiled, with annotations including wavefront masks, soliton count, wavelength, and orientation. Results demonstrate that the hybrid CNN-LSTM-attention model can delineate ISW wavefronts, estimate soliton count with a mean absolute error below one soliton, and achieve wavelength predictions within 10 pixels of ground truth. Ablation experiments indicate progressive performance improvements when sequential and attention mechanisms are included. The study highlights the feasibility of applying AI for large-scale, automated monitoring of ISWs, offering pathways toward more systematic investigation of internal wave dynamics in the Indonesian seas and globally. Keywords: Deep learning, internal solitary waves, oceanography, remote sensing, Sentinel-1 Share Link | Plain Format | Corresponding Author (Chonnaniyah Chonnaniyah)

173	Topic B: Applications of Remote Sensing	ABS-127
Potential of SWOT Mission in Monitoring Taiwan Surface Water Dynamics Chia-Hao Wang1*, Kuo-Hsin Tseng1,2 1Department of Civil Engineering, National Central University, Taiwan 2Center for Space and Remote Sensing Research, National Central University, Taiwan * kevinwang081[at]gmail.com Abstract The Surface Water and Ocean Topography (SWOT) mission, equipped with a Ka-band interferometric altimeter, has provided high-precision, wide-swath measurements of terrestrial water bodies and oceans since its launch on December 16, 2022. However, the accuracy of SWOT water surface elevation (WSE) data over small waterbodies still requires further evaluation. This study utilizes SWOT Level 2 LakeSP and Pixel Cloud (PIXC) products to conduct a time-series comparison with in-situ data collected from 14 reservoirs and 15 ponds across Taiwan. Through this comparison, LakeSP is found to capture temporal variations in water levels, with average root-mean-square errors (RMSEs) of 1.55 m for reservoirs and 1.21 m for ponds, and standard deviations (STDs) of 0.97 m and 1.02 m, respectively. With the application of a predefined water mask and a tailored processing workflow to extract valid PIXC data points, the accuracy was significantly improved, reducing RMSEs to 0.53 m and 0.15 m, and STDs to 0.30 m and 0.10 m for reservoirs and ponds. Additionally, detectability was enhanced, with the PIXC product successfully identifying water bodies as small as 11,992 square meters (approximately 110* 110 m) -substantially smaller than the original mission requirement of 250* 250 m. These findings highlight SWOT strong capability in tracking seasonal water level dynamics and evidence its value for managing water resources in small and ungauged water bodies. Keywords: SWOT, Inland water bodies, Elevation change Share Link | Plain Format | Corresponding Author (Chia-Hao WANG)

174	Topic B: Applications of Remote Sensing	ABS-383
MORPHOLOGICAL ANATOMY OF MOUNT UNGARAN: REMOTE SENSING AND PETROLOGICAL APPROACH USING HIGH RESOLUTION DRONE TO REVEAL VOLCANIC STRATIGTRAPHY AND GEOLOGICAL STRUCTURE Brany kurnianto1,2, Emi Sukiyah3*, Agus Didit Haryanto3, Budi Muljana3, Shaparas Daliman4 1Doctor Program of Geological Engineering, Universitas Padjadjaran- 2 Geological Engineering Study Program, Institut Teknologi Nasional Yogyakarta, Indonesia- 3 Department of Geoscience, Universitas Padjadjaran, Indonesia- 4Faculty of Earth Science, Universiti Malaysia Kelantan, 17600 Jeli, Kelantan, Malaysia. Abstract Abstract Mount Ungaran, a stratovolcano in Central Java, Indonesia, exhibits complex morphological and structural characteristics that remain relatively underexplored. Understanding its volcanostratigraphy and internal structure is crucial for reconstructing its eruptive history and assessing potential geological hazards. This study employs a high-resolution drone-based remote sensing approach integrated with petrological analysis to investigate the volcano^s morphological anatomy, structural framework, and volcanostratigraphic evolution. High-resolution aerial imagery drone were generated to analyze topographic variations, volcanic landforms, and structural features such as faults, fractures, and lava flow distributions. The remote sensing data were complemented by field observations and petrographic analysis of rock samples to characterize lithological variations and identify key eruptive phases. Structural analysis focused on fault patterns and deformation features to understand the volcano^s tectonic influences and potential instability zones. Preliminary results reveal distinct stratigraphic sequences that indicate multiple eruptive stages, with significant variations in lava composition and depositional environments. Fault structures and fractures suggest interplay between regional tectonics and volcanic activity, contributing to the formation of the current morphology. The integration of remote sensing and petrology provides a more comprehensive understanding of Mount Ungaran^s geological evolution, allowing for improved hazard assessment and risk mitigation strategies. Keywords: Mount Ungaran, volcanic stratigraphy, remote sensing, high resolution drone, structural geology Share Link | Plain Format | Corresponding Author (brany kurnianto)

175	Topic B: Applications of Remote Sensing	ABS-128
Indicative Mapping of Rice Cropping Systems in Timor-Leste Using PlanetScope NDVI Time Series and DTW Clustering Pedro Junior Fernandes (a*), Masahiko Nagai (b) Yamaguchi University Abstract Monitoring rice cropping systems and their seasonal dynamics is crucial for assessing production and planning, particularly in regions with limited field observations. We introduce a hexagonal grid-based time-series framework that segments rice-growing patterns and phenology in Timor-Leste using monthly 3 m PlanetScope imagery. The Normalized Difference Vegetation Index (NDVI) was extracted for approximately 6,000 hexagonal grid cells (50 m) from December 2018 to September 2022 and clustered using Dynamic Time Warping (DTW) to group similar growth trajectories. The optimal number of phenological regimes was determined by a majority decision across internal validity indices: Silhouette, Davies-Bouldin, and Calinski-Harabasz. These indices consistently favored two clusters, although the Elbow curve indicated a bend near three. For agronomic interpretation, we summarized each cluster^s NDVI profile into phenology metrics, including mean, max, min, amplitude, counts of low-cover months below 0.45, sustained greenness above 0.55, and peaks at or above 0.60, and assigned functional labels. The analysis identified two temporally stable regimes aligned with the national cropping calendar: (1) a single-crop system with one main-season green-up from December to May and predominantly low off-season NDVI below 0.45, and (2) an irrigated double-crop system maintaining elevated off-season greenness, with NDVI frequently at or above 0.60 for multiple months from June to November, indicating a second cycle. The results indicate that DTW clustering of satellite NDVI can effectively delineate dominant phenology and distinguish between single and double rice cropping in data-scarce settings. While the workflow is scalable and transferable, findings are indicative rather than definitive due to limited ground truth. Future work should incorporate plot-level observations, such as sowing and harvest dates, irrigation records, and GPS photo points, to calibrate labels and quantify accuracy Keywords: ndvi, dtw clustering, time series analysis, rice crop system, Timor-Leste Share Link | Plain Format | Corresponding Author (PEDRO JUNIOR FERNANDES)

176	Topic B: Applications of Remote Sensing	ABS-131
Right of Way Acquisition Using Geospatial Technologies Florence Galeon University of the Philippines Abstract The acquisition of right-of-way (ROW) is essential to the implementation of government projects such as transportation infrastructure, utilities, and coastal protection. Traditional ROW processes often involve time-consuming surveys, bureaucratic delays, and disputes with property owners. This study demonstrates how geospatial technologies, specifically Geographic Information Systems (GIS), Global Navigation Satellite Systems (GNSS) and Unmanned Aerial Vehicles (UAVs), streamline ROW acquisition for government infrastructure. A seawall project in the coastal municipalities of Minalabac, Pasacao, and San Fernando in the province of Camarines Sur was used as a case example. Through spatial analysis, the project identified 45 priority segments totaling 21 km for seawall construction, significantly reducing coverage from the original 45 km, resulting in cost savings. The ROW Acquisition Plan (RAP) is divided into parcellary survey and property valuation. Real-Time Kinematic (RTK) GPS was used for accurate parcel delineation, while drone imagery and satellite data supported field inspections for asset valuation. Both land and physical improvements, such as houses and trees, were assessed to determine compensation. The total ROW area was calculated at 573,213 square meters with a land value of Php 488.4 million, equivalent to USD 8.6 million. Including other assets, the total estimated acquisition cost reached Php 881.9 million, equivalent to USD 15.5 million. These findings provide the Department of Public Works and Highways (DPWH) with a precise basis for resource allocation. Overall, the study underscores the critical role of geospatial technologies in modernizing ROW acquisition. By improving efficiency, accuracy, and transparency, these tools support faster project delivery and minimize adverse effects on affected communities. Keywords: geospatial technologies, parcellary survey, right-of-way, seawall Share Link | Plain Format | Corresponding Author (Florence Galeon)

177	Topic B: Applications of Remote Sensing	ABS-134
Enhancing Interpretability in Landslide Detection: A U-Net Based Framework with Uncertainty-Aware Classification Hina Tachikawa1*, Yuki Mizuno1, Naoyoshi Hirade1, Kenlo Nishida Nasahara2 and Taro Uchida3 1 Graduate student, Graduate School of Science and Technology, University of Tsukuba, Japan 2 Associate Professor, Institute of Life and Environmental Sciences, University of Tsukuba, Japan 3 Professor, Institute of Life and Environmental Sciences, University of Tsukuba, Japan htl21.tachikawa[at]gmail.com Abstract Automatic landslide mapping plays a critical role in disaster response and risk assessment. However, deep learning models are often prone to misclassifications, such as overlooked landslides and non landslide areas wrongly identified as landslides, which can hinder accurate interpretation and decision making. Conventional approaches typically provide only landslide or non landslide classes without indicating the chance of misclassification. Consequently, smaller landslide areas are more likely to be overlooked in comparison to large ones, and false readings are more likely to occur at the edges of landslide. To address this limitation, we propose a four category classification scheme that improves interpretability by distinguishing between reliable results and areas with high misclassification possibilities. We applied Monte Carlo dropout to a U-Net based model trained on three landslide events in Japan when testing on a separate area. Using 20 stochastic forward passes, we computed the mean and standard deviation of landslide probabilities. A low standard deviation indicates a reliable result, while a high standard deviation suggests a high chances of misclassification. Based on these values, each pixel was classified into one of four categories, Landslide, Non landslide, Potential false negative, and Potential false positive. The proposed method successfully visualized small landslide and landslide edges as regions with high probability of misclassification. This enhanced the interpretability of the output and demonstrated the potential in improving the trustworthiness in landslide detection. The proposed four class classification scheme offers a novel way to assess and communicate model confidence, addressing a key limitation of conventional binary classification approaches. For instance, considering potential false negative class let us examine the safety aspect. Alternatively, focusing exclusively on reliable classes let us consider minimum required response. Keywords: landslide detection, deep learning, U-Net, Monte Carlo dropout, satellite remote sensing Share Link | Plain Format | Corresponding Author (Hina Tachikawa)

178	Topic B: Applications of Remote Sensing	ABS-135
GIS-Based Land Suitability Analysis for Potential Solar Farms in Baqubah City Nada Kadhim Department of Civil Engineering, Faculty of Engineering, University of Diyala, Iraq Abstract Solar energy is leading the charge in the shift to renewable energy sources because of its sustainability and abundance. With the use of remote sensing data and Geographic Information System (GIS) technology for land suitability research, this study evaluates the viability of developing solar farms in Baqubah City, Diyala, Iraq. Iraq is well-positioned for the spread of solar power due to its growing energy demand and dedication to diversifying its energy mix. Key elements included in the analysis were slope, land cover, solar irradiation, proximity to transmission lines, and environmental restrictions. A comprehensive suitability map classifying land into high, moderate, and low potential zones for solar farms was created by integrating spatial data using a GIS. According to the findings, about 25% of Baqubah is very ideal for the establishment of solar farms, mostly in flat, bare areas with strong solar radiation and easy access to the transmission infrastructure that is already in place. About 40% of land is covered by moderate suitability zones, which are frequently constrained by partial land cover limitations or higher slopes. The remaining 35% are low suitability zones, which include locations that are environmentally protected, agricultural, or densely populated. The study aids Baqubah local government in achieving its sustainable development and renewable energy targets by identifying investment-friendly locations that balance technical viability and environmental stewardship, thereby guiding strategic planning for solar energy projects. Keywords: Please Just Try to Submit This Sample Abstract Share Link | Plain Format | Corresponding Author (Nada Kadhim)

179	Topic B: Applications of Remote Sensing	ABS-136
Aplication Of GIS Based Morphometric And Land Cover Analysis to Evaluate Flood Potential in The Wai Batu Gantung Watershed, Ambon City, Indonesia. Nabila Kalsum Tuanany - Emi Sukiyah - Boy Yoseph CSSSA - Arini Syafri Faculty Of Geological Engineering, Padjadjaran University Abstract This study analyzes morphometric parameters and land cover conditions to assess their relationship with flood potential in the Wai Batu Gantung Watershed, Ambon City, Indonesia. Watershed delineation and sub-watershed division (BGt1 - BGt6) were carried out using SRTM DEM data through hydrological analysis in ArcGIS 10.8. The morphometric parameters analyzed include the bifurcation ratio (Rb), drainage density (Dd), and texture ratio (Rt), while land cover classification was obtained from the overlay of land use maps and high resolution satellite imagery. The results indicate that the Wai Batu Gantung watershed has bifurcation ratios (Rb) ranging from 1.3 to 2.0, drainage density (Dd) value from 3.1 to 4.4, and ratio texture (Rt) values between 0.38 and 2.07. these variations show that the drainage pattern is influenced by geological structures and lithological conditions. Land cover analysis reveals that shrub vegetation dominates most of the watershed (81-100%), whila settlement areas are limited to BGt2 (1%) and BGt4 (8%), located in the middle and lower zones. The integration of morphometric characteristics and land cover indicates that areas with higher drainage density and coarse texture, combined with increasing built-up areas, exhibit greater flood potential. Maintaining vegetation cover in the upper watershed and controlling land conversion in the middle and downstream zones are therefore essential for sustainable watershed management in Ambon City. Keywords: ambon city, drainage density, flood potential, land cover, morphometric analysis Share Link | Plain Format | Corresponding Author (Nabila Kalsum Tuanany)

180	Topic B: Applications of Remote Sensing	ABS-137
Utilization of Planetscope Imagery to Identify Distribution Green Open Space in Urban Area of Padang Muhammad Ismail, Wikan Jaya P., Elisa Maiyenti, Hendry Frananda, Rifai Mardin, Mutiara Amelia P., Juana Wangsa P., and Rehan Pramudiva Z. Remote Sensing and Geographic Information System Program, Vocational School, Universitas Negeri Padang, Indonesia Civil Engineering Program, Faculty of Engineering, Universitas Negeri Padang, Indonesia Geography Program, Faculty of Social Science, Universitas Negeri Padang, Indonesia Regional and Urban Planning Program, Faculty of Engineering, Tadulako University, Indonesia Abstract Green open space plays a crucial role in maintaining ecological balance and quality of the urban environment. However, urban development has resulted a decline in green open space. The dynamics of green open space distribution due to rapid urbanization are often difficult to monitor effectively. Based on this, utilization of remote sensing is considered to facilitate effective and efficient monitoring of green open space areas. This study aims to identify and analyze the dynamics of green open space distribution in the urban area of Padang using Planetscope imagery. The methods used in this study include Planetscope image processing with spectral transformation techniques and multispectral classification as well as GIS-based spatial analysis. The analysis was conducted with a multitemporal approach to detect changes in the area and distribution of green open spaces over several time periods. Validation of the data analysis results was carried out by comparing the classification results with field reference data. The expected results of this study are geospatial visualization of the distribution of green open spaces in the urban area of Padang and an analysis of changes that have occurred in recent years. Therefore, outlook with the results of the study can contribute to the monitoring and management of green open spaces in the urban area of Padang more accurately and sustainably. The results of this study can also provide a reference in spatial planning and urban environmental conservation efforts in order to realize the Sustainable Development Goals (SDGs), especially point 11 sustainable cities and communities. Keywords: planetscope, green open space, urban, image processing, SDGs Share Link | Plain Format | Corresponding Author (Muhammad Ismail)

Page 6 (data 151 to 180 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