Page 4 (data 91 to 120 of 351) | Displayed ini 30 data/page
<< PREV 1 2 3 4 5 6 7 8 9 10 11 12 NEXT >>

91	Topic B: Applications of Remote Sensing	ABS-293
Mapping Seagrass Cover Percentage and Estimation of Aboveground Carbon Stock using PlanetScope SuperDove Imagery and Random Forest Algorithm in Bontang, East Kalimantan Diki Akhyar Amanatulloh (a*)- Pramaditya Wicaksono (b)- Wirastuti Widyatmanti (b) a) Master of Science in Remote Sensing, Faculty of Geography, Universitas Gadjah Mada, Sleman, Daerah Istimewa Yogyakarta 55281, Indonesia b) Department of Geographic Information Science, Faculty of Geography, Universitas Gadjah Mada, Sleman, 55281, Indonesia Abstract Seagrass meadows are a vital component of blue carbon ecosystems, playing a significant role in carbon sequestration and storage, and contributing effectively to climate change mitigation. However, the sustainability of seagrass ecosystems is increasingly threatened by climate-induced degradation and anthropogenic disturbances. Therefore, spatial inventory of seagrass meadows including aboveground carbon stock (AGCseagrass) estimation is essential for conservation and climate action. High-resolution remote sensing imagery from PlanetScope SuperDove, integrated with field survey data, offers an optimal approach for mapping benthic habitats, seagrass percent cover (PC), and AGCseagrass. This method is particularly effective and efficient for covering extensive areas with diverse terrain conditions. The aim of this research is to map benthic habitats, seagrass percent cover, and aboveground carbon stock using PlanetScope SuperDove imagery with a spatial resolution of 3 meters. The Random Forest algorithm was employed for both classification and regression, integrating remote sensing data with field observations. The results indicate the presence of five benthic habitat classification classes, with an overall accuracy (OA) of 96.44% and a kappa accuracy of 95.16%. For seagrass percent cover modeling, the Random Forest algorithm yielded an R2 of 0.66 (RMSE = 21.09), and an average seagrass percent cover of 67.06%. The estimated total aboveground carbon stock (AGCseagrass) in Bontang reached 984,915 tons C, with an average value of 274.05 g C/m2, calculated across a spatial extent of 32.35 km2. The AGC modeling also resulted in an R2 of 0.66 (RMSE = 9.25). Keywords: seagrass, percent cover, aboveground carbon stock, planetscope superdove Share Link | Plain Format | Corresponding Author (Diki Akhyar Amanatulloh)

92	Topic B: Applications of Remote Sensing	ABS-38
Semantic Segmentation of Building Components from UAV LiDAR Point Clouds for Structural Analysis Shiori Kubo (a*), Daigo Meguro (b), Hidenori Yoshida(b) a) Institute of Education, Research and Regional Cooperation for Crisis Management Shikoku, Kagawa University, 1-1 Saiwaicho, Takamatsu 760-8521, Japan b) Faculty of Engineering And Design, Kagawa University, 2217-20 Hayashicho Takamatsu Kagawa, Japan Abstract Delays in issuing Disaster Victim Certificates after major earthquakes in Japan hinder the prompt provision of public support and victim recovery. These delays are caused by the current damage assessment process, which relies on on-site visual inspections that are time-consuming, labor-intensive, subjective, and hazardous for personnel. To address these issues, this study proposes a foundational method for the automated extraction of structural building components from high-precision LiDAR point clouds acquired by drones. We employ the PointNet++ deep learning model, a network designed for unstructured 3D data, to perform semantic segmentation. The model classifies points into four categories, Roof, Wall, Ground, and Others, providing the necessary geometric data for subsequent inclination analysis. The method was validated on a real-world dataset from areas affected by the 2024 Noto Peninsula Earthquake, achieving a mean Intersection over Union of 77.3% and an Overall Accuracy of 88.6%. The Roof and Ground classes yielded excellent results with an IoU of approximately 85%. While the classification of the Wall class, with an IoU of 59.4%, remains a challenge due to class imbalance and geometric constraints, the model successfully recognized the complex 3D structure of both intact and tilted houses, a key capability for damage assessment. This demonstrates the potential of 3D point clouds to overcome the limitations of 2D imagery for structural assessment. The proposed method establishes a robust foundation for the future automated calculation of house inclination, which is expected to contribute to a more rapid, objective, and safe damage assessment process, accelerating the issuance of Disaster Victim Certificates for affected communities. Keywords: Deep learning- Disaster management- Lidar- Semantic Segmentation- UAV Share Link | Plain Format | Corresponding Author (Shiori Kubo)

93	Topic B: Applications of Remote Sensing	ABS-39
Adoption of Remote Sensing Technologies for Site Supervision in Construction Projects in Hong Kong Anthony C.T. So and Tony Y.K. Ho Development Bureau, The Government of the Hong Kong Special Administrative Region, Hong Kong, China Abstract The Government of the Hong Kong Special Administrative Region (HKSARG) has been advocating for change in the construction industry by implementing ^Construction 2.0^ to enhance construction productivity, quality and safety through wider adoption of innovation and technology. The ^Construction 2.0^ initiative is steered by the Development Bureau of the HKSARG which has been promoting application of digitalisation and advanced technologies in public works contracts such as remote sensing, Internet of Things (IoT), Artificial Intelligence (AI), robotics, etc. No doubt, going digitalisation would be the trend in enhancing the efficiency, effectiveness and safety of operations in construction sites in Hong Kong and elsewhere. Among various advanced technologies, remote sensing techniques, particularly Light Detection and Ranging (LiDAR) and photogrammetry are broadly applied in different construction projects, covering a wide range of applicability including progress monitoring, quality control of works, site measurements, tracking and structure monitoring. Interferometric Synthetic Aperture Radar (InSAR) which may be used to monitor ground displacements is also being studied to provide a tailor-made solution for the unique construction site conditions in Hong Kong. For contracts where the sites are scattered or located in remote areas, close site supervision could be challenging. The use of remote sensing techniques could significantly improve the quality and efficiency of site supervision work. This paper presents the findings of a comprehensive review of different remote sensing techniques being applied in construction sites and evaluates the potential of wider adoption for site supervision. Keywords: Photogrammetry, LiDAR, remote sensing, site supervision, technologies Share Link | Plain Format | Corresponding Author (Anthony Chak Tong So)

94	Topic B: Applications of Remote Sensing	ABS-295
Mapping Crop Types across Mixed Single- and Double-Cropping Systems in Brazil Using Satellite Time-Series Data and Machine Learning Shoki Shimada, and Kei Oyoshi Japan Aerospace Exploration Agency (JAXA) Abstract Brazil, a major global agricultural exporter, plays a key role in the food supply chain, making accurate monitoring of its crop production essential for food security. Due to its vast area, satellite remote sensing is crucial for timely and cost-effective crop mapping, particularly given Brazil^s mix of double and single cropping systems, such as soybean-corn or soybean-cotton rotations and long-cycle crops like sugarcane. This study maps five key crops, soybean, corn, cotton, sugarcane, and grains (sorghum and millet), using Geen Cholophill Vgetation Index (GCVI) time series data from Landsat and Sentinel-2 between September 2023 and August 2024. The data were smoothed using the Harmonic ANalysis of Time Series (HANTS) algorithm in Google Earth Engine, and crop cycles were segmented through peak detection. Skewed normal distributions were fitted to each season^s phenology, and their parameters were used as input features for a Random Forest model to classify crop types in central Brazil. The model achieved an overall accuracy of 0.826, and municipality-level estimates for soybean, corn, cotton, and sugarcane showed strong agreement with official statistics, with R-squared values of 0.95, 0.95, 0.98, and 0.81 respectively. These results demonstrate the method^s effectiveness for accurate and timely crop mapping in regions with complex agricultural practices. Keywords: Phenology, Random Forest, Food Security, Remote Sensing Share Link | Plain Format | Corresponding Author (Shoki Shimada)

95	Topic B: Applications of Remote Sensing	ABS-296
Assessment of Urban Heat Island Intensity and Key Drivers in Three Major Indonesian Cities Using Machine Learning Wulan Salle Karurung 1*, Lee Ki Rim 2, Lee Won Hee 3 1 Graduate Student, Department of Convergence and Fusion System Engineering, Kyungpook National University, Republic of Korea. *wulansalle[at]gmail.com 2 Research Visiting Professor, Research Institute of Artificial Intelligent Diagnosis Technology for Multi-Scale Organic and Inorganic Structure, Kyungpook National University, Republic of Korea 3 Professor, Department of Location-Based Information System, Kyungpook National University, Republic of Korea Abstract Urban heat island (UHI) effects in tropical cities are increasingly severe due to urban expansion, reduced green cover, and high population density. Environmental and anthropological factors interact to increase surface temperatures, necessitating studies that examine these factors in detail areas to anticipate further long-term impacts. This study aims to quantify and compare UHI characteristics and driving factors in three metropolitan cities in Indonesia, such as Jakarta, Surabaya, and Makassar. This study integrates the multivariate spatiotemporal data monthly in 2019-2020, covering the natural and anthropogenic factors. The datasets were collected from satellite derived datasets, including urban heat index intensity (UHII), land surface temperature (LST), vegetation indices (NDVI), built-up indices (NDBI), PM2.5, NO2, precipitation, population density, and land use/land cover sourced from MODIS, Landsat 8, Sentinel 5P, and other open-access platforms. All the datasets were standardized into a 100 m spatial resolution. Three machine learning models, Random Forest (RF), XGBoost, and LightGBM (LGBM), were compared to evaluate the prediction accuracy. Based on the final accuracy results, RF outperformed other models with R2 values of 0.92 for Jakarta, 0.86 for Surabaya, and 0.82 for Makassar. SHAP and partial dependence plots (PDP) were used to interpret the importance of features and their effects on interaction, using the results of RF models. The results show Jakarta had the highest UHI intensity, and the top influencing factors were population density, PM2.5, and LST. In contrast, Surabaya and Makassar were more influenced by population and precipitation. This study demonstrates the importance of integrating multi-feature geospatial data with machine learning to improve our understanding of data interactions in prediction models. The results can support regional climate resilience actions by identifying vulnerable areas and key factors for sustainable urban planning. Keywords: Urban Heat Island (UHI), Machine Learning, Spatiotemporal Analysis, Remote Sensing Share Link | Plain Format | Corresponding Author (Wulan Salle Karurung)

96	Topic B: Applications of Remote Sensing	ABS-297
AI Enhanced Urban Microclimate Mapping Using Deep Learning Algorithms Dr. Heltin Genitha C(a*), Aashika Perpetual G(b), Mohanapriya K(c) a*- Professor, Department of Information Technology, St Joseph^s College of Engineering. b, c- Student, Department of Information Technology, St Joseph^s College of Engineering. Abstract Urban microclimates-localized variations in temperature, humidity, and air quality-are strongly influenced by factors such as building density, traffic, vegetation, and land use. Traditional climate monitoring methods lack the spatial granularity needed to capture these variations, limiting their usefulness for urban planning and environmental management. This paper presents an AI-driven framework for dynamic urban microclimate mapping using satellite-based remote sensing data. The system integrates multi-temporal imagery from the Sentinel and Landsat datasets with advanced machine learning models to analyze both spatial and temporal environmental patterns. A ResNet-based Convolutional Neural Network (CNN) is employed for spatial feature extraction from satellite imagery, while a Long Short-Term Memory (LSTM) network models temporal trends across different urban zones. The framework was implemented and evaluated on satellite data from a Chennai metropolitan area, India demonstrating enhanced spatial resolution and predictive accuracy in detecting heat islands and pollution zones. The resulting heatmaps and environmental visualizations provide valuable insights for urban planners and policymakers, supporting data-driven decisions for climate-resilient infrastructure and sustainable development. Keywords: Urban Microclimate, Remote Sensing, Sentinel, Landsat, Deep Learning, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Heat Island Detection. Share Link | Plain Format | Corresponding Author (Heltin Genitha C)

97	Topic B: Applications of Remote Sensing	ABS-42
Remote Sensing-Based Analysis of Potential Epithermal Gold Mineralization in the Sunda Arc Region of Bogor Regency Silmi Afina Aliyan*1, Nikolas Anggi Putra Panjaitan2, Shafira Himayah1 1) Sains Informasi Geografi, Fakultas Pendidikan Ilmu Pengetahuan Sosial, Universitas Pendidikan Indonesia 2) Survey Pemetaan dan Informasi Geografis, Fakultas Pendidikan Ilmu Pengetahuan Sosial, Universitas Pendidikan Indonesia Abstract The Sunda magmatic arc that passes through the island of Java has played a role in the formation of gold deposits, particularly in the formation of low-sulfidation epithermal deposits in the Pongkor region, Bogor Regency. Currently, PT Antam Tbk. through its Gold Mining Business Unit (UPBE) manages an underground gold mine that produces pure gold and silver as its main products. Since 2016, UPBE Pongkor has experienced a decline in gold ore production, and various efforts have been made to explore and produce gold ore. Remote sensing technology, with the utilization of multispectral imagery, was used in this study to detect suspected zones of potential epithermal gold mineralization. This study used several geological indicators related to epithermal gold formation, such as the presence of propylitic and agrilic alteration minerals, lineament, and lithological characteristics. The processing techniques used in this study were Sabin^s Ratio algorithm and Crosta^s Directed Principal Component Analysis (DPCA). Both techniques were used to obtain information on the presence of surface minerals resulting from hydrothermal alteration, such as chlorite and smectite-illite minerals. This study integrates the indicators using the weight of evidence (WOE) method. The results of the study indicate that the presence of chlorite minerals is positively associated with the presence of gold deposits in the mining business permit (IUP) area of UBPE PT. Antam Pongkor has a value of 0.1492. The presence of lineaments is positively associated with gold deposits, with a value of 0.4726 at the lineament buffer class value of 0-100 meters. While the lithology of volcanic rocks is positively associated with gold deposits at values of 0.4760 and 0.3486. The results of the analysis show that epithermal gold deposits in Bogor Regency are associated with propylitic alteration types, with a distance buffer from the lineament of 0-100 meters, and are found in volcanic rocks in the form of basalt, andesite, and tuff. This association shows the distribution of suspected zones of potential epithermal gold mineralization in 5 areas around Bogor Regency, namely Parung Panjang, Cigudeg, and Jasinga sub-districts. Keywords: Remote Sensing, Epithermal Gold Deposit, Sabin^s Ratio, Crosta^s Directed PCA, Weight of Evidence Share Link | Plain Format | Corresponding Author (Silmi Afina Aliyan)

98	Topic B: Applications of Remote Sensing	ABS-298
Application of Remote Sensing Analysis for Shoreline Change as a Basis for Coastal Abrasion and Erosion Disaster Mitigation on the Selayar Limestone Formation, South Sulawesi Province Indonesia Hendra Pachri, and Zarwa Zashika Department of Geological Engineering, Faculty of Engineering, Hasanuddin University, Indonesia Abstract The coastal area of Bulukumba area, in South Sulawesi Province is composed of carbonate sedimentary rocks, particularly limestone. In this region, limestone tends to be relatively fragile and easily eroded, making the area highly vulnerable to coastal abrasion and erosion. This study aims to analyze shoreline changes over the past 10-15 years using remote sensing methods, including the use of satellite imagery such as Landsat and Sentinel-2, the Normalized Difference Water Index (NDWI), the Normalized Difference Moisture Index (NDMI), and shoreline change analysis through the Digital Shoreline Analysis System (DSAS). Additionally, geological interpretation of the coastal area, particularly the limestone lithology, was conducted to examine its correlation with the pattern of shoreline change. This research is expected to produce shoreline change maps, abrasion and erosion zonation maps, and coastal geological vulnerability maps. The information obtained can serve as a reference for formulating disaster mitigation strategies related to coastal abrasion and erosion in the study area. Keywords: shoreline change, remote sensing, abrasion, erosion, mitigation Share Link | Plain Format | Corresponding Author (Hendra Pachri)

99	Topic B: Applications of Remote Sensing	ABS-299
Assessing the Impact of Land Use Change and Hydrological Interventions on Tidal Flooding in Eretan, Indramayu Priyatna. M.*, Khomarudin M.R., Nugroho G., Nugroho J.T., Riyanto B., and Prasetio W. The National Research and Innovation Agency/BRIN Abstract Tidal flooding in Eretan, Indramayu Regency, has become a significant environmental concern since 2020. This study investigates the underlying causes of the observed inundation using high-resolution Planet satellite imagery, Digital Elevation Models (DEM), coastline change data, and land use classification. Interviews with local residents identified two primary contributing factors: (1) the reclamation of coastal areas for aquaculture (fishpond) development and (2) the construction of a dam on the Kali Prawan River, which became operational in 2020. A modeling approach was employed to simulate the impacts of these two factors on tidal flooding dynamics in the region. To enhance the analysis, this study also develops and applies a 3D simulation framework for modeling tidal inundation scenarios. The approach integrates raster and vector geospatial datasets-including DEMs, high-resolution satellite imagery, shapefiles (SHP), and MSLX land subsidence records-within a Geographic Information System (GIS) environment. The workflow involves data preprocessing, spatial clipping, and 3D analysis to generate predictive inundation models. Model outputs were verified and validated using historical flood extent data, local GPS-based land subsidence measurements, and field surveys conducted between 2023 till 2025. Simulation results show that both coastal reclamation and dam construction have contributed to the worsening of flood events, with aquaculture-related land reclamation having a more pronounced impact than the dam. The findings indicate that the expansion of fishpond areas has significantly increased the vulnerability of Eretan^s coastal zone to tidal inundation, while the influence of the dam remains relatively limited. This study highlights the complex interplay between anthropogenic land use change and hydrological infrastructure in shaping coastal flood risks and provides critical insights for future land management and flood mitigation strategies in vulnerable coastal regions of Indonesia. Keywords: Tidal flooding, coastal reclamation, Eretan, Indramayu, Planet satellite imagery, Digital Elevation Model (DEM), coastline change, land use, Kali Prawan dam, flood modeling, hydrological impacts, aquaculture. Share Link | Plain Format | Corresponding Author (Muhammad Priyatna)

100	Topic B: Applications of Remote Sensing	ABS-300
Integrating Urban Mobility Analysis and Flood Risk Mapping: A Case Study in Ho Chi Minh City Syazwi Quthbi Al Azizi (1,2), Nurjannah Nurdin (2) School of Architecture, Planning and Policy Development, Bandung Institute of Technology (ITB), Bandung, Indonesia (1), Research and Development Center for Marine, Coast and Small Islands, Hasanuddin University, Makassar, 90245, Indonesia (2) Abstract Ho Chi Minh City, with 45% of its area lying less than one meter above sea level, faces dual challenges of rapid urbanization and frequent flooding, which severely impact urban mobility and resilience. On rainy days, its intricate road network intensifies traffic congestion, particularly for car commuters. This study examines the relationship between urban mobility patterns and flood risk in Districts 1, 4, 5, 6, and 11-areas characterized by high mobility density and significant flood exposure. Using historical traffic data and Sentinel-1 SAR imagery from 2020 to 2022, spatial and temporal analyses were conducted to assess the impacts of flooding on mobility and population exposure. The mobility analysis reveals that average vehicle speeds often drop below 25 km/h during peak hours, while flood extent mapping using VH polarization-based change detection identifies annual flood coverage ranging from 1,538 to 2,359 hectares. Affected population estimates range from 157 to 77,404 individuals, underscoring the dual vulnerabilities of congestion and inundation. To address these challenges, the study proposes the integration of sustainable transport systems to alleviate congestion, the implementation of nature-based flood mitigation strategies in central districts, and the adoption of resilient urban planning to reduce exposure and enhance adaptive capacity. These measures aim to minimize disruption and promote a more sustainable and resilient urban environment in Ho Chi Minh City. Keywords: Urban Mobility, Flood Risk Mapping, Ho Chi Minh City, Sentinel-1 SAR, Spatial Analysis. Share Link | Plain Format | Corresponding Author (Syazwi Qutbhi Al Azizi)

101	Topic B: Applications of Remote Sensing	ABS-46
Image Quality Assessment for UAV-based Infrastructure Inspection: An AI Pre-selection Strategy Ya-Li Lin(a*), Guan-Chin Su(a), Lai-Han Zou(a), Chao-Hung Lin(b), Jiann-Yeou Rau(b), Wei-Shen Lai(c), Chih-Chao Hu(c) (a) Student, Department of Geomatics, National Cheng-Kung University, Taiwan * alecfree2[at]gmail.com (b) Professor, Department of Geomatics, National Cheng-Kung University, Taiwan (c) Researcher, Transportation Engineering Division, Institute of Transportation, Taiwan Abstract Image quality assessment is a fundamental step for image-based technologies such as deep learning detection, 3D reconstruction, and deformation monitoring. In UAV-based infrastructure inspection, image quality often declines because of the platform vibration, unstable lighting, and motion blur, which affects the accuracy and consistency of downstream analysis. Current image selection rely on manual and visual inspection, which is generally labor-intensive and qualtiy inconsistent. Although no-reference image quality assessment (IQA) has gained increasing attention in recent years, existing methods rely on subjectively labeled datasets which lack the objectivity and interpretability required in real-world applications. This study proposes a reference-free IQA framework designed for UAV imagery, and introduces a structural similarity index enhanced with a CLIP encoder (CSSIM) to address pixel misalignment caused by image cropping. A standardized and objective data construction pipeline is developed to support the generation of image quality maps (IQMs) using a Swin-Unet model. The Swin-Unet network architecture enables fast, full-image inference, providing consistent and efficient assessment of high-resolution UAV images and making IQA feasible for field deployment. Furthermore, the generated IQMs are used in an AI image selection strategy for UAV-based infrastructure inspection, allowing automatic removal of low-quality images prior to tasks such as bridge geometry reconstruction and structural recognition. The proposed method has been successfully applied in real UAV bridge inspection scenarios, significantly improving model prediction accuracy and showcasing its value in scalable, quality-aware infrastructure monitoring. Keywords: UAV, image quality accessment, deep learning, infrastructure monitoring Share Link | Plain Format | Corresponding Author (Ya Li Lin)

102	Topic B: Applications of Remote Sensing	ABS-302
Assessing GSMaP Satellite-Based Precipitation for Runoff Modeling in a Data-Scarce Mountainous Basin: A Case Study of the Abra River Basin, Philippines Ma. Gloann Leizel P. Longboy(1), Nathaniel R. Alibuyog(2), Christopher Zamuco(3), and Rodel T. Utrera(4) (1)Research Directorate, Mariano Marcos State University, mplongboy[at]mmsu.edu.ph (2)Coastal Engineering Research and Management Center, Mariano Marcos State University, nralibuyog[at]mmsu.edu.ph (3)Research Directorate, Mariano Marcos State University, ctzamuco[at]mmsu.edu.ph (3)Research Directorate, Mariano Marcos State University, rtutrera[at]mmsu.edu.ph Abstract Accurate runoff estimation is vital for flood risk modeling and disaster preparedness, particularly in river basins with limited ground-based hydrometeorological observations. This study evaluates the applicability of GSMaP (Global Satellite Mapping of Precipitation) satellite-based rainfall data for hydrologic simulation in the Abra River Basin, a mountainous and data-scarce watershed in Northern Luzon, Philippines. A hydrologic model was developed using the HEC-HMS (Hydrologic Engineering Center - Hydrologic Modeling System) software, incorporating topographic inputs from a 5-meter IFSAR Digital Elevation Model (DEM). Land cover and soil data were processed in a GIS environment to generate a spatially distributed Curve Number (CN) map for estimating runoff potential. The model was calibrated using observed discharge and GSMaP rainfall data from Typhoon Ompong (Mangkhut, 2018), achieving a Nash-Sutcliffe Efficiency (NSE) of 0.763 and a percent bias of only 0.06%. Model validation using Typhoon Marce (Sinlaku, 2008) resulted in an NSE of 0.614, indicating reasonable model performance. These results demonstrate that GSMaP data can be effectively used to support hydrologic modeling and runoff estimation in ungauged or poorly instrumented basins. This study highlights the practical use of satellite-derived precipitation in flood modeling and early warning applications, contributing to disaster risk reduction and climate resilience. The integration of remote sensing and GIS in hydrologic modeling offers valuable insights for water resource planning and supports the broader application of remote sensing technologies in disaster-prone regions. Keywords: Satellite-based precipitation, Remote sensing for flood modeling, GIS-integrated hydrologic modeling, Disaster risk reduction, Abra River Basin Share Link | Plain Format | Corresponding Author (Rodel Tolosa Utrera)

103	Topic B: Applications of Remote Sensing	ABS-47
Verification of the effect of UAV shooting altitude on detection accuracy in asphalt crack detection using deep learning Eita Uotani(a), Mitsuharu Tokunaga(b) a)Graduate Student, Department of Civil and Environmental Engineering, Kanazawa Institute of Technology, Japan b)Professor, Department of Civil and Environmental Engineering, Kanazawa Institute of Technology, Japan Abstract Accurate identification of early deterioration in asphalt pavement and the implementation of appropriate preventive maintenance are critical issues in reducing life cycle costs (LCC). However, at present, regular inspections are conducted in only about 80% of prefectures and approximately 20% of municipalities, and standardized methods for data collection and management remain underdeveloped. This study aims to improve the efficiency and quality of pavement inspections by combining unmanned aerial vehicles (UAVs) with artificial intelligence(AI).A machine learning model was developed to automatically detect cracks from UAV-captured images of asphalt pavement. The study evaluated how detection accuracy is affected by imaging conditions such as flight altitude, camera angle, and lighting, as well as by model architecture and training methods. Analysis under multiple conditions revealed a tendency for detection accuracy to decline as flight altitude increases. However, the introduction of model optimization techniques and data augmentation was found to effectively suppress this decline.As a result, high-accuracy crack detection was demonstrated to be feasible even from relatively high altitudes, enabling more extensive and efficient pavement inspection. This approach is expected to contribute to the advancement of road management practices. Keywords: Deep Learning, YOLO, Asphalt Crack, UAV altitude Share Link | Plain Format | Corresponding Author (eita uotani)

104	Topic B: Applications of Remote Sensing	ABS-303
Analysis of SO2 and NO2 Air Quality Parameters Based on Satellite Imagery in Cement Industrial Area Nurul Masyiah Rani Harusi 1,2*, Hengky Palalangan1, Sumarni Hamid Aly 1,2, Ibrahim Djamaluddin 1,2, A.Azizah Nurul Dinanti 1,2 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 3 Department of Environmental Engineering, Faculty of Engineering, Muslim University of Indonesia, Jl. Urip Sumoharjo km.05 Makassar City, 90231, Indonesia Abstract The decline in air quality due to industrial activities, particularly in the cement industry, has become a serious environmental and public health concern. Emissions of hazardous gases such as sulfur dioxide (SO2) and Nitrogen Dioxide (NO2) from coal combustion and cement production processes significantly contribute to atmospheric pollution. Limitations in air quality monitoring are often caused by the lack of Air Quality Monitoring Stations (AQMS), resulting in uneven pollutant distribution data. Satellite-based remote sensing, particularly using Landsat 8 OLI/TIRS, offers an alternative for efficient spatial and temporal air quality monitoring. This study employs a Land Surface Temperature (LST) approach processed through Google Earth Engine (GEE) to estimate SO2 and NO2 concentration and analyze air quality based on the Air Pollution Standard Index (ISPU). LST values were extracted from Landsat 8 SR Collection 2 Level 2 data and then used to estimate SO2 and NO2 concentrations using empirical algorithms from Mahardianti et al. (2024). Field validation was conducted using measurements from the October 2023 Monitoring Report. Accuracy was assessed using the Root Mean Square Error (RMSE) method. Based on ISPU classification, NO2 values were within the Good category and SO2 Moderate category. Keywords: Landsat 8, Google Earth Enginer, NO2, Cement Industry, Remote Sensing, Air Pollution Index Share Link | Plain Format | Corresponding Author (Nurul Masyiah Rani Harusi)

105	Topic B: Applications of Remote Sensing	ABS-48
Spatiotemporal Variability of Chlorophyll-a in the Malacca Strait for Algal Bloom Monitoring Using Multispectral Satellite Observations Wiliam (1*), Po-Chun Hsu (1) 1) Center for Space and Remote Sensing Research, National Central University, Taoyuan City, Taiwan Abstract The Malacca Strait, a narrow and ecologically sensitive maritime corridor, exhibits seasonal variation in primary productivity influenced by both monsoonal forcing and anthropogenic inputs. This study examines the spatiotemporal variability of chlorophyll-a (CHL) concentrations, a proxy for phytoplankton biomass and potential algal blooms, utilizing Sentinel-3 OLCI multispectral satellite data at 4 km resolution (1998-2024) and 300 m resolution (2017-2024). Monthly and seasonal CHL climatologies reveal a pronounced increase during the Northeast Monsoon (December-February), coinciding with positive wind stress curl patterns that indicate upwelling-favorable conditions in the central and southern parts of the strait. This suggests that monsoonal wind forcing contributes to nutrient enrichment and enhanced phytoplankton growth during this period. These findings highlight the physical-biological coupling that shapes bloom dynamics in semi-enclosed tropical seas. While multispectral data effectively capture surface CHL variability, the integration of hyperspectral remote sensing is recommended for future studies to improve species-level discrimination and enable early detection of harmful algal blooms. This research highlights the importance of satellite-based monitoring for assessing water quality and conserving biodiversity in the Malacca Strait. Keywords: Chlorophyll-a, Northeast Monsoon, Sentinel-3 OLCI, Malacca Strait Share Link | Plain Format | Corresponding Author (WILIAM )

106	Topic B: Applications of Remote Sensing	ABS-304
Seagrass Meadow Mapping in the Bay of Bengal Using Machine Learning and Remote Sensing Lingeswaran A(1), Melvin Fredrick J.S(1), Vimalathitthan Shanmugam(1*) and Lathaselvi G(1) (1) Department of Information Technology, St. Josephs College of Engineering, Chennai, India *email:vimalathitthan[at]stjosephs.ac.in Abstract Seagrasses are vital for the health of coastal ecosystems, maintaining biodiversity and acting as buffers against climate change through carbon storage. Seagrasses remain threatened by coastal development, pollution, and climate change, especially in sensitive areas such as the Bay of Bengal. Reliable and timely seagrass distribution mapping is crucial in ensuring successful conservation and management. This research is interested in the automated mapping of Bay of Bengal seagrass beds based on sophisticated machine learning algorithms and satellite remote sensing. In this research, we use machine learning algorithms to process satellite remote sensing data to map seagrass meadows throughout the Bay of Bengal. Multispectral images acquired from Sentinel-2 and Landsat 8 satellites are processed with supervised classification techniques, such as Random Forest and Support Vector Machines, to differentiate seagrass from other benthic substrates (Maxwell et al., 2017- Lyons et al., 2012). Spectral indices like Normalized Difference Vegetation Index (NDVI) and Bathymetric Index are utilized as input features to enhance model performance. Existing ecological surveys^ ground truth data and marine biodiversity repositories (e.g., UNEP-WCMC, 2020) are utilized for training and validation. The initial results indicate excellent classification accuracy and large-scale, automated monitoring capability. The resulting machine learning-driven seagrass distribution maps provide valuable information to marine resource managers, policy-makers, and conservationists operating in the Bay of Bengal. Keywords: Seagrass, Multispectral, NDVI,ML, Remote Sensing Share Link | Plain Format | Corresponding Author (Vimalathitthan Shanmugam)

107	Topic B: Applications of Remote Sensing	ABS-50
Temporal Assessment of Mangrove Restoration Success Using NDVI from Remote Sensing Data (2021-2023) Luisa Febrina Amalo (a*), Novia Ramadhani (b), Tarisa Fadilah (a), and Luluk Dwi Wulan Handayani (a) a) Center for Environmental Research, IPB University, Indonesia b) Conservation of Forest Resources and Ecotourism Study Program, Faculty of Forestry and Environment, IPB University, Indonesia *luisafebrina[at]gmail.com Abstract Remote sensing technologies enable successful mangrove restoration monitoring because they allow the tracking of vegetation changes across large areas at affordable costs with reliable results. The Normalized Difference Vegetation Index (NDVI) serves as a reliable remote sensing index that monitors vegetation health and density, as well as ecosystem recovery. The study aims to examine the changes in NDVI values at a mangrove restoration area over three years, from 2021 to 2023, as the plants developed from seedlings into saplings. The study results demonstrated that NDVI values increased throughout the research duration, indicating successful vegetation growth and restoration. The early growth phase of 2021 showed NDVI readings between 0.077 and 0.258, which indicated that sparse vegetation was beginning to develop its canopy. The 2022 sapling stage began with NDVI values ranging from 0.134 to 0.567, indicating the onset of plant structure development and increasing vegetation density. The NDVI values in 2023 for the advanced sapling stage increased substantially from 0.261 to 0.868, indicating the formation of dense and fully developed mangrove vegetation. The research demonstrates that NDVI serves as a quantitative tool, enabling scientists to measure the progress of mangrove restoration efforts and track their growth patterns. Remote sensing technology becomes vital for maintaining long-term mangrove ecosystem monitoring systems because NDVI values increase from year to year, indicating successful ecological growth. Keywords: Mangrove restoration- NDVI- Remote sensing- Vegetation index- Share Link | Plain Format | Corresponding Author (Luisa Febrina Amalo)

108	Topic B: Applications of Remote Sensing	ABS-51
Assessment of Slope Instability in Post-Wildfire Areas Using UAV-derived DTM and QGIS Park J. W.1, Koo S1., Jung Y. H.2 and Kim S. S.3* 1 Researcher, National Disaster Management Research Institute, Republic of Korea 2 Senior Researcher, National Disaster Management Research Institute, Republic of Korea 3 Senior Research Officer, National Disaster Management Research Institute, Republic of Korea *sskim73[at]korea.kr (*Corresponding author^s email only) Abstract Wildfires significantly increase slope instability by inducing vegetation loss, topsoil erosion, and the formation of hydrophobic layers. When combined with rainfall, these changes can lead to large-scale mass movement phenomena such as landslides and debris flows within a short period. However, conventional slope instability assessments based on satellite imagery or field observations often lack the spatial resolution and accuracy required for detailed analysis. In contrast, UAV-based photogrammetry enables the acquisition of high-spatial-resolution imagery and point cloud data at centimeter-level precision, allowing for fine-scale analysis of ground cover under the burned canopy. In this study, UAV photogrammetry was acquired using a state-of-the-art DJI Matrice 350 RTK drone equipped with a Zenmuse P1 optical camera. A Digital Elevation Model (DEM) was generated through DJI Terra software, and terrain analysis was conducted using QGIS. The analysis included slope mapping and distance evaluation between slopes and residential structures. Considering the lack of vegetation in the post-fire environment, the results demonstrate that UAV-based photogrammetry can serve as an effective tool for high-spatial-resolution slope instability assessment. This approach presents a practical and scalable methodology that can contribute valuable data for post-wildfire disaster response and recovery planning. Keywords: Wildfire , UAV, Photogrammetry, Slope instability, GIS Share Link | Plain Format | Corresponding Author (JungWook Park)

109	Topic B: Applications of Remote Sensing	ABS-308
Deriving Nighttime Light Metrics for Disaster Assessment Towards Area Prioritisation and Tracking Lois Anne B. Leal (a*), Juan Antonio Mari F. Carpio (b), Niel Mawen B. Getigan (b), Anne Moselle C. Rubio (b), Leonard Bryan B. Paet (a), Reinabelle C. Reyes (a) a) Philippine Space Agency, Metro Manila, Philippines *lois.leal[at]philsa.gov.ph b) Department of Physics, Ateneo de Manila University, Metro Manila, Philippines Abstract Disasters generate widespread damage and displacement, requiring scalable methods to track impact and recovery over time. This study introduces a unified nighttime lights (NTL) framework that integrates percent-based and difference-based metrics with a temporal point of interest approach for continuous disaster assessment and area prioritisation. Using 12 years of NASA VIIRS VNP46A3 data, we analyse 281 barangays in Eastern Visayas, Philippines, affected by Super Typhoon Yolanda (Haiyan) in 2013, capturing the full arc from impact to recovery. Results show severe losses (up to -148.3 nW/cm2/sr, -85.11%) and recovery trajectories extending over 11.5 years, with 57 barangays still below pre-disaster levels as of May 2025. The framework reveals long-term dynamics including displacement, resettlement, and infrastructure-driven gains, aligning with high-resolution imagery and reports. Beyond Haiyan, this approach provides a generalisable, data-driven system for disaster tracking, supporting evidence-based recovery planning and scalable prioritisation across Asia and beyond. Keywords: Nighttime Lights, Disaster Assessment, Disaster Metrics, Area Prioritisation, Tracking Share Link | Plain Format | Corresponding Author (Lois Anne Leal)

110	Topic B: Applications of Remote Sensing	ABS-54
Utilizaing Drone Mapping Technology for Hazard Assessment of Steep Slopes Jung Y.H.(a), Lim E.T.(b), Koo S.(c), Park J.W.(c), Suk J.W.(d), and Kim S.S.(e*) a) Senior Researcher, Disaster Scientific Investigation Div., National Disaster Management Research Institute, Rep. of Korea b) Senior Researcher, Disaster Resilience Research Center., National Disaster Management Research Institute, Rep. of Korea c) Researcher, Disaster Scientific Investigation Div., National Disaster Management Research Institute, Rep. of Korea d) Research Officer, Safety Research Div., National Disaster Management Research Institute, Rep. of Korea e) Senior Research Officer, Disaster Scientific Investigation Div., National Disaster Management Research Institute, Rep. of Korea * sskim73[at]korea.kr Abstract During the thawing season, when frozen ground begins to melt, the risk of slope-related disasters such as rockfalls, landslides, and road subsidence increases significantly. Coastal steep slopes, particularly cliff-type terrains adjacent to seaside roads, are prone to frequent rockfalls due to continuous wave-induced erosion and weathering. In the Republic of Korea, annual inspections are conducted under the ^Act on the Prevention of Disasters on Steep Slopes,^ led by expert teams that assess slope stability. However, conventional ground-based surveys often face limitations in visibility and accessibility due to vegetation and slope height. To overcome these challenges, this study explores the use of drone mapping technology as a complementary method for hazard assessment. The study focuses on Hyeonpo-ri District in Ulleung-gun, where a massive rockfall event involving approximately 100 tons of debris occurred in March 2025. Drones were deployed to capture high-resolution imagery of inaccessible upper slopes. High-resolution images were captured from multiple angles, and processed into orthomosaics, 3D models, and point clouds. These products enabled detailed identification of rockfall zones, slope geometry, and collapse features, surpassing the capabilities of traditional visual inspections. The estimated collapsed area was also quantified using point cloud analysis. As a result, the site was assigned a hazard risk score of 69 (Grade D). This study demonstrates the applicability of drone mapping technology for evaluating slope hazard potential in the Hyeonpo-ri area, where a significant rockfall had occurred. By overcoming the accessibility constraints of conventional ground-based surveys, drone-based methods provide high-resolution spatial data that enable more accurate and quantitative risk assessments. The approach holds promise for future disaster prevention and hazard analysis in similar topographic settings. Keywords: UAV, Disaster risk assessment, Point cloud, 3D modeling, Geospatial analysis Share Link | Plain Format | Corresponding Author (Yonghan Jung)

111	Topic B: Applications of Remote Sensing	ABS-310
Integration of Participatory GIS and Local Knowledge to Identify Best Route for Sustainable Tourism in Machhapuchchhre Model Trek, Kaski, Nepal Krishna Prasad Bhandari PleaseThe Participatory Geographic Information System (PGIS), integrated with local knowledge, is a potential decision-supporting tool for sustainable tourism planning, performance evaluation, and site selection. The purpose of this study is to determine the optimal planning of resources for developing ecotourism through the integration of PGIS and local knowledge. The study investigates a case study in the Machhapuchchhre model trek and prepared sustainable ecotourism planning for this region located in the Machhapuchchhre Rural Municipality of Kaski, Nepal. The Machhapuchchhre model treks consist of natural resources, and the associated tourism industry has a significant impact on both the local community and, rural municipality of Machhapuchchhre, and the national economy of Nepal. This research enumerates about lack of planning and management of cultural, natural, and adventure trekking, sustainable tourism development. Ecotourism development and planning is considered using PGIS and local knowledge as a decision support tool for land use and land cover maps, educational tourism, cultural tourism, and adventure tourism using GIS tools. Six different factors maps were finally prepared, among them, the best route regarding the different factors was prepared. Abstract The Participatory Geographic Information System (PGIS), integrated with local knowledge, is a potential decision-supporting tool for sustainable tourism planning, performance evaluation, and site selection. The purpose of this study is to determine the optimal planning of resources for developing ecotourism through the integration of PGIS and local knowledge. The study investigates a case study in the Machhapuchchhre model trek and prepared sustainable ecotourism planning for this region located in the Machhapuchchhre Rural Municipality of Kaski, Nepal. The Machhapuchchhre model treks consist of natural resources, and the associated tourism industry has a significant impact on both the local community and, rural municipality of Machhapuchchhre, and the national economy of Nepal. This research enumerates about lack of planning and management of cultural, natural, and adventure trekking, sustainable tourism development. Ecotourism development and planning is considered using PGIS and local knowledge as a decision support tool for land use and land cover maps, educational tourism, cultural tourism, and adventure tourism using GIS tools. Six different factors maps were finally prepared, among them, the best route regarding the different factors was prepared. Keywords: PGIS, Participatory, Model Trek, Thematic Mapping, Ecotourism Share Link | Plain Format | Corresponding Author (Krishna Prasad BHANDARI)

112	Topic B: Applications of Remote Sensing	ABS-311
Spatio-Temporal Modeling of Macroalgae Biomass and Alginate Content Using High-Resolution Satellite Imagery: A Case Study of Pannikiang Island, South Sulawesi Aswar Anas (a*), M. Akbar AS (a,d), Agus Aris (a,b,d), Nurjannah Nurdin (a,b,c) a) Research and Development Center for Marine, Coastal and Small Island, Hasanuddin University, Jl. Perintis Kemerdekaan Km.10, Makassar, 90245, Indonesia *aswarmarineunhas[at]gmail.com b) Department of Remote Sensing and Geographic Information System, Vocational Faculty, Hasanuddin University, Jl. Perintis Kemerdekaan Km. 10, Makassar, 90245, Indonesia c) Marine Science Departement, Marine Science and Fisheries Faculty, Hasanuddin University, Makassar, 90245, Indonesia d) The Environmental Science Study Program, Doctoral Program, Graduate School, Hasanuddin University, Makassar, 90245. Indonesia Abstract Accurate mapping of macroalgae habitats is essential for assessing their ecological functions and bioeconomic potential, particularly for high-value compounds, such as sodium alginate. With the advancement of high-resolution satellite imagery and classification algorithms, remote sensing now offers an efficient and non-destructive approach for the spatiotemporal monitoring of macroalgae. This study aimed to model the spatiotemporal dynamics of dominant macroalgae species (Sargassum and Turbinaria) and estimate their biomass and alginate content on Pannikiang Island, South Sulawesi, using time-series data from PlanetScope imagery within the Google Earth Engine (GEE) platform. The methodology included image preprocessing, extraction of vegetation indices based on green and red-edge bands, classification using the Random Forest algorithm, and regression modeling (both linear and nonlinear) between spectral indices and in situ measurements of biomass and alginate content. The results revealed that seasonal growth patterns of macroalgae can be consistently detected through variations in vegetation indices, with biomass peaks occurring during transitional monsoon periods. The predictive models demonstrated strong correlations between the vegetation indices and estimates of biomass. These findings highlight the potential of high-resolution time-series satellite imagery integrated into GEE for the sustainable monitoring of coastal ecosystems and bioeconomic assessment of macroalgae. Keywords: Macroalgae- Spatio-Temporal- Biomass- Alginate- High-Resolution Share Link | Plain Format | Corresponding Author (Aswar Anas)

113	Topic B: Applications of Remote Sensing	ABS-312
Retrieval of Water Quality Parameters in Tasik Kenyir, Malaysia Using Sentinel-2 MSI Satellite Idris M.S. 1*, Khalil I.1 and Mat Amin R.1 1Faculty of Science and Marine Environment, Universiti Malaysia Terengganu, 21030 Kuala Nerus, Terengganu, Malaysia Abstract Tasik Kenyir, the largest man-made lake in Malaysia, is a vital freshwater ecosystem that supports biodiversity, fisheries and ecotourism. However, its water quality (WQ) is increasingly threatened by human activities, underscoring the need for long-term monitoring. This study aimed to evaluate the S2-MSI capability to derive key WQ parameters- chlorophyll-a (Chl-a), colored dissolved organic matter (CDOM), suspended particulate matter (SPM) and Secchi disk depth (SDD) in Tasik Kenyir. Using an in-situ dataset of WQ parameters and optical measurements collected during multiple field campaigns, we developed WQ algorithms for the S2-MSI sensor. To ensure reliable evaluation, several atmospheric correction (AC) models were assessed for their accuracy in retrieving water reflectance (Rrs) from S2-MSI data. Among the AC models tested, C2RCC yielded the most accurate Rrs, demonstrating strong agreement with field measurements. Validation results revealed that Chl-a can be accurately estimated using the NIR-blue band ratio, while the blue-green band ratio was more responsive to changes in CDOM and SDD. The results also showed that a single-band Rrs based on the red wavelength was the most reliable predictor of SPM in the study area. The best-performing algorithms for each parameter were then applied to cloud-free S2-MSI images acquired over a 5-year period to assess seasonal variations in WQ. The analysis revealed significant seasonality in all parameters, with maximum values during the northeast monsoon and minimum values during the spring inter-monsoon. Despite these seasonal fluctuations, the spatial distribution of WQ parameters within each season remained relatively uniform, with similar patterns of water characteristics, indicating minimal spatial variation across the lake. This study demonstrates the applicability of S2-MSI for retrieving WQ parameters, offering valuable support for long-term monitoring programs, which are currently insufficient in Tasik Kenyir. Keywords: water quality, Tasik Kenyir, algorithms, Sentinel-2 Share Link | Plain Format | Corresponding Author (MD SUFFIAN IDRIS)

114	Topic B: Applications of Remote Sensing	ABS-314
Radar Signatures and Ocean Color Response of Internal Wave-Wave Interactions Between the Lombok Strait and the Flores Sea I Wayan Gede Astawa Karang(1,2*), I Gede Hendrawan (1,2), I Made Dwita Krisnanda (1), I Gusti Bagus Sila Dharma (1), I Wayan Krisna Eka Putra (3), I Made Mahendra Wicaksana Karang (1), Jonson Lumban Gaol (4) 1) Faculty of Marine Science and Fisheries, Udayana University, Indonesia 2) Centre for Remote Sensing and Ocean Sciences (CReSOS), Udayana University, Indonesia 3) Universitas Pendidikan Ganesha, Indonesia 4) Department of Marine Science and Technology, Bogor Agricultural University, Indonesia Abstract Many internal solitary wave (IWs) patterns have been observed in satellite images, particularly in the Lombok Strait and Flores Sea. However, there are no studies that have been made on internal wave interaction patterns in this area. Internal wave interactions may result in exceptionally large amplitudes in the interaction zone, which in turn pose threats to underwater structures. In this paper, we analyze the surface manifestation of internal wave-wave interaction patterns observed in satellite images of the Flores Sea. The data used are a Sentinel-1 SAR image (October 28, 2018) and a GCOM-C optical image (October 29, 2018). The methods applied to both images consist of preprocessing, image enhancement, and pattern extraction. The analysis of both images indicated the presence of internal wave packets propagating in the Lombok Strait and Flores Sea with soliton wavelengths of 3.9-5.0 km and phase velocities of 2.5-26 m/s. Analysis of the wave interactions revealed a clear grid-like interaction pattern, formed by the meeting of two non-linear internal wave packets originating from different sources. The first packet, propagating northward, was identified as originating from the Lombok Strait, while the second packet was propagating from the northeast. This ^woven^ pattern is a manifestation of a series of X-type interactions, forming rhomboid-shaped cells on the sea surface, with each grid cell area ranging from 19.3 - 21.4 km2. From visual analysis of the imagery, the angle between the wave crests is estimated to be approximately \(115\circ \) , indicating an interaction angle between the wave propagation directions of approximately \(65\circ \). This study indicates that both radar and optical are capable of detecting the surface manifestation of complex interactions by two or more internal wave packets. Further studies will focus on quantitative analysis of wave parameters to understand the impact of these interactions on local marine productivity. Keywords: Internal Waves, Internal Wave-Wave Interaction, Sentinel-1, GCOM-C, grid-like interaction pattern, Flores Sea, Lombok Strait Share Link | Plain Format | Corresponding Author (I Wayan Gede Astawa Karang)

115	Topic B: Applications of Remote Sensing	ABS-59
Landslide Detection with U-net Based SAR2OPT Framework : A Case Study of 2024 Hualien Earthquake Wen-Hong Chen. 1, Shou-Hao Chiang. 2 1Department of Civil Engineering, National Central University , Taiwan 2Center for Space and Remote Sensing Research, National Central University , Taiwan Abstract The 2024 Hualien earthquake caused multiple landslide, highlighting the need for dependable and rapid disaster detection. Synthetic Aperture Radar (SAR) offers an all-weather means of observation, making it a staple in remote-sensing studies. Yet, because SAR data lack the rich color and fine texture of optical imagery, extracting landslide information from them alone remains difficult. In this study, we embedded the modified U-net framework that combined four bands Sentinel-1 imagery, including VV and VH polarization data from ascending and descending observations. Fusing both orbits mitigates geometric layover and shadowing in rugged terrain, thereby preserving surface backscatter integrity. A sliding-window scheme with overlapping patches is employed during the training phase to preserve spatial context and minimize edge discontinuities between patches- specifically, 128*128 patches with a 64-pixel overlap and 256*256 patches with a 128-pixel overlap were tested. After end-to-end training, the model can rapidly produce optical-like NDVI maps directly from dual-orbit Sentinel-1 SAR imagery, offering an alternative for post-earthquake surface monitoring when optical data are not timely available. This study adopts the April 2024 Hualien earthquake in northeastern Taiwan as its testbed. The goal is to verify whether the SAR-derived optical products maintain enough spatial detail and spectral fidelity to support landslide mapping, paving the way for their fusion with machine-learning models in fully automated landslide detection. Keywords: SAR2OPT , Landslide Detection , Synthetic Aperture Radar , U-net , Hualien Earthquake Share Link | Plain Format | Corresponding Author (Wen-Hong Chen)

116	Topic B: Applications of Remote Sensing	ABS-60
Integration of Topobathymetry Mapping Techniques for Siltation Monitoring in the Reservoir Hanafie A.(a), Zahra Z. A. (b), Huang W. Y. (c) and Chang K.T. (d*) a) Vice Leader, Strong Engineering Consulting Co., Shalu Township, Taichung County, 43342, amricohanafie17[at]gmail.com b) Master student, Dept. of Civil Eng. And Environmental Informatics, Minghsin Uni. Of Science and Technology, Taiwan. zalfaafifahzahra[at]gmail.com, +886-919845642 c) Section Chief, Cadastral section, Xinzhuang Land Office, New Taipei City, Taiwan. why6311[at]gmail.com, +886-975069295 d) Professor, Dept. of Civil Eng. and Environmental Informatics, Minghsin Uni. of Science and Technology, Taiwan, +886-921214694 *ktchang1216[at]gmail.com Abstract Topographic and bathymetric surveying technologies provide critical data support and decision making references for the reservoir management. This paper integrates various advanced topographic and bathymetric mapping technologies to survey terrain and sedimentation around reservoirs. As surveying technologies advance, equipment such as LiDAR and Multibeam Echo Sounders (MBES) have significantly improved mapping accuracy in both terrestrial and underwater environments. LiDAR achieves 3~5 mm accuracy for terrain measurements, while MBES provides wide 150 degree swath coverage with up to 6 mm resolution for bathymetric mapping. However, an efficient and feasible integration is needed in shallow water and surrounding dense forests area. Data fusion approaches combine multiple systems to compensate for individual limitations in this work. In shallow or hard to reach areas, Unmanned Surface Vehicles (USVs) equipped with Single Beam Echo Sounders (SBES) and a mobile SLAM LiDAR system is utilized to enhance mapping completeness. Case studies include the Mingde Reservoir siltation monitoring, and the Hushan Reservoir interbasin water diversion project. It is worth noting that SBES equipped USVs conducted three rounds of surveys, also yielding 0.05 m RMSE. These results indicate that the technologies used in this case achieve high precision, comparable to MBES grade performance, especially for shallow water and land water interface mapping, outperforming traditional methods or SBES alone. Comparisons showed siltation of 0.3 to 2.0 m in two months at the Mingde Reservoir due to upstream river scouring, while Hushan Reservoir experienced the transbasin diversion caused up to -5.8 m of erosion and 0.4 to 2.5 m of downstream siltation. Temporal terrain model comparisons revealed two month siltation rates of 0.03 to 0.208 m in reservoirs. These findings highlight the importance of integrating diverse technologies for effective topographic and bathymetric mapping. Keywords: Data Fusion, LiDAR, Echo Sounder, Topobathymetric, Siltation and Sedimentation Share Link | Plain Format | Corresponding Author (Kuan-Tsung Chang)

117	Topic B: Applications of Remote Sensing	ABS-316
Assessment of the 2023-2024 El Nino-Driven Drought Impacts in the Philippines Using a Satellite-Based Combined Drought Index (CDI) Michael Angelo Valete (a*), Christine Marie Oca (a), Dhann Collin Davies Vergara (a), James Cesar Refran (a), Gay Jane Perez (a,b) a.) Philippine Space Agency, Quezon City, Philippines b.) Institute of Environmental Science & Meteorology, University of the Philippines, Diliman, Quezon City, Philippines michael.valete[at]philsa.gov.ph Abstract El Nino episodes in the Philippines trigger severe droughts, characterized by elevated land surface temperature, reduced water availability, and crop losses. This study evaluates the agricultural impacts of the 2023-2024 El Nino event using a satellite-derived Combined Drought Index (CDI). CDI integrates the following short-term meteorological and vegetation stress indicators: (1) Standardized Precipitation Index (SPI-3), (2) Temperature Condition Index (TCI), and (3) Vegetation Condition Index (VCI). CDI follows a rule-based progression framework, from no drought to full recovery, to characterize drought onset, persistence, temporary vegetation recovery, and return to normal conditions. The study validated the CDI against reported provincial crop production losses during the El Nino period and observed that provinces with higher CDI values generally correspond with drought-related production losses. The results show an overall accuracy of 63%, precision of 71%, hit rate of 70%, and an F-score of 70%. Even though the false alarm rate is at 53%, CDI effectively captured the broad timing and progression of drought conditions during the El Nino event. It reflected the steady increase of drought-affected areas, starting at 27% in January 2024 to 64% by May 2024, coinciding with rainfall deficits, heat stress, and vegetation decline. This study highlights the potential of a satellite-based CDI, grounded in drought evolution logic, as a practical tool for near-real-time monitoring, early warning, and agricultural drought preparedness in the Philippines. Keywords: Agricultural Drought, Crop Production Loss, ENSO Share Link | Plain Format | Corresponding Author (Christine Marie Oca)

118	Topic B: Applications of Remote Sensing	ABS-61
Topographical and Geological Controls on Shallow Landslide Movement Types Identified by Satellite Imagery YAMAGUCHI, Akari 1*, SATO, Go1, Tran The Viet 2, Nguyen Van Thang 2 1 First Author^s Affiliation: Department of Environment, Tokyo City University, Japan 2 Second Author^s Affiliation: Department of Civil Engineering, Thuyloi University, Vietnam Abstract In recent years, the frequency and magnitude of sediment disasters have increased due to heavy rainfall associated with climate change. In the southwestern region of Da Nang City, central Vietnam, a significant number of shallow landslides (hereinafter referred to as landslides) were triggered by the heavy rainfall associated with Typhoon Molave in October 2020. This study aims to clarify the relationship between topographical and geological conditions and the movement types of shallow landslides. Landslides were classified into four types: Slide-flow (Unchanneled), Slide-flow (Channeled), Slide-flow (Flood), and Slide/fall (Un-flow) based on satellite image interpretation. To characterize the topography for each movement type of landslide, topographic analysis was conducted using elevation, slope angle, slope aspect, and Topographic Position Index (TPI). Additionally, these types of landslide movement were compared across three geological units: granite, gneiss, and schist. As a result, 7,967 landslides were manually classified by movement types within the 234 km2 study area. The number of slide-flow (un-channeled) was 4,076, representing a proportion of 51 % of total landslides identified in the study area. In addition, the results of the topographic analysis confirmed that slide-flow (un-channeled) frequently occurred on the upper slope and ridge at elevations of 600 to 1,000 m and on slopes with angles of 25 to 35 degrees. Although the number of slide-flow (Flood) was relatively small, it was confirmed that the landslide mass flowed downslope from ridges to valleys, resulting in a larger area per landslide compared to other movement types. The distribution of landslides by movement type and geology revealed that the granite area had a larger average landslide area than other geological units, except for slide-flow (Flood). This is considered to be caused by the presence of weathered materials covering the bedrock in the granite area. Keywords: Remote sensing, Topographic interpretation, Shallow landslide distribution map, Geological characteristics, Da Nang City Share Link | Plain Format | Corresponding Author (Akari Yamaguchi)

119	Topic B: Applications of Remote Sensing	ABS-62
Mapping the 2024-2025 Lewotobi Volcano Eruption Dynamics Using Sentinel-1 InSAR and Optical Data Wiguna Jaya A.A.P. (a*), Harintaka Harintaka (b) a) Department of Geodetic Engineering, Faculty of Engineering, Universitas Gadjah Mada Jalan Grafika No.2, Yogyakarta 55281, Indonesia *anak.agung0300[at]mail.ugm.ac.id b) Department of Geodetic Engineering, Faculty of Engineering, Universitas Gadjah Mada Jalan Grafika No.2, Yogyakarta 55281, Indonesia Abstract Lewotobi Volcano in East Flores, Indonesia, experienced major eruptions between late 2023 and early 2025, significantly altering the landscape and threatening nearby communities. Understanding surface deformation before, during, and after these eruptions is essential for interpreting magmatic activity and enhancing hazard monitoring. This study uses Sentinel-1 SAR data processed with InSAR techniques to map ground deformation related to the 2024-2025 Lewotobi Laki-Laki eruption cycles. Ascending and descending orbit data from January 2020 to April 2025 were processed using ASF HyP3 and MintPy to generate time-series deformation maps. Additionally, Sentinel-2 optical imagery was used to detect lava flows and pyroclastic deposits. The results show inflation before eruptions in December 2023, November 2024, and March 2025, indicating magma accumulation, and deflation afterward, suggesting magma withdrawal. Persistent subsidence of up to -5.6 cm/year was observed on the northeastern to southeastern slopes, while uplift occurred near the summit. Deformation time-series from 15 points confirm the cyclic nature of activity, aligned with reported eruption phases. Sentinel-2 imagery supports the InSAR findings, showing visible lava and pyroclastic deposits in affected areas. This study demonstrates the effectiveness of combining free SAR and optical satellite data to monitor volcanic activity. The integration of InSAR and optical analysis enhances understanding of eruption dynamics and the relationship between surface deformation and subsurface magmatic processes. These findings may improve early warning systems and strengthen volcano monitoring in Indonesia and other tectonically active regions. Keywords: Lewotobi Laki-Laki Volcano- Ground Deformation- InSAR- MintPy- Sentinel-1 Share Link | Plain Format | Corresponding Author (Anak Agung Adi Putra Wiguna Jaya)

120	Topic B: Applications of Remote Sensing	ABS-318
Data-Driven Mapping of Forest Cover Changes in Chhattisgarh, India (2000-2024) Using Google Earth Engine Abhimanyu Kumar Gond(1), Aarif Jamal(1), Tarun Verma(1), (1)Department of Mining Engineering, IIT (BHU), Varanasi-221005, India Corresponding Author: abhimanyukrgond.rs.min21[at]itbhu.ac.in Corresponding Author ORCID ID: 0009-0004-3102-1485 Abstract Forests are vital for biodiversity, carbon sequestration, and livelihoods, yet deforestation remains a significant threat in biodiverse regions like Chhattisgarh, India, making robust monitoring essential for sustainable management. This study quantifies and maps forest cover dynamics in Chhattisgarh (135,154.63 square km) from 2000 to 2024 to support data-driven conservation strategies through precise, high-resolution forest change analysis. Using Google Earth Engine (GEE), a cloud-based geospatial analysis platform, the Hansen Global Forest Change dataset was processed through raster and vector conversions to calculate forest cover in 2000 (tree canopy cover greater than 30 percent), forest cover in 2024, total loss (2000-2024), total gain (2000-2012), and annual loss trends, with results visualized via spatiotemporal maps and time-series charts. Forest cover declined from 25,965.28 square km in 2000 to 25,417.67 square km in 2012, reflecting a net loss of 547.61 square km. By 2024, total forest loss reached 810.47 square km, with a modest gain of 4.78 square km in the southern region (2000-2012). Annual loss peaked at 90 square km in 2011, dropped to 18 square km in 2003 and 2020, and rose again to 60 square km between 2023 and 2024. Spatial analysis revealed denser forests in the southern and northern regions compared to central areas. These findings underscore significant deforestation pressures and provide critical insights for targeted conservation policies and afforestation initiatives, enabling the identification of deforestation hotspots and temporal trends to support sustainable forest management, biodiversity conservation, and climate change mitigation strategies. Keywords: Forest cover, deforestation, sustainable management, Chhattisgarh, Google Earth Engine, Share Link | Plain Format | Corresponding Author (Abhimanyu Kumar Gond)

Page 4 (data 91 to 120 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