Page 3 (data 61 to 90 of 351) | Displayed ini 30 data/page
<< PREV 1 2 3 4 5 6 7 8 9 10 11 12 NEXT >>

61	Topic B: Applications of Remote Sensing	ABS-10
From Horizontal to Vertical Urban Growth: A Decade of LULC Change in Penang Island, Malaysia Nur Faziera Yaakub (a*), Mohd Hasmadi Ismail (b) & Azita Ahmad Zawawi (c) a) Department of Forestry Science and Biodiversity, Faculty of Forestry and Environment Universiti Putra Malaysia, 43400 UPM, Serdang, Selangor, Malaysia. *sdgisfaziera[at]gmail.com b) Department of Forestry Science and Biodiversity, Faculty of Forestry and Environment Universiti Putra Malaysia, 43400 UPM, Serdang, Selangor, Malaysia. c) Department of Recreation and Ecotourism, Faculty of Forestry and Environment Universiti Putra Malaysia, 43400 UPM, Serdang, Selangor, Malaysia. Abstract Urban growth is conventionally defined by spatial expansion and the increase in built-up areas. This study, however, reveals a counterintuitive trend in Penang Island, Malaysia, between 2014 and 2023. Utilising 1.5 m pansharpened SPOT 6 and 7 satellite imagery classified with a Support Vector Machine (SVM), we analysed spatiotemporal changes in land use and land cover (LULC). Our findings indicate a decline in built-up areas, a stark contrast to the official Department of Statistics Malaysia (DoSM) figures, which show a significant increase in population. This paradox challenges traditional urbanisation patterns, necessitating a more in-depth examination of the underlying spatial, spectral, and socio-economic dynamics. We explore several plausible explanations: vertical urban densification through high-rise development, urban redevelopment cycles involving temporary demolition, and policy-driven land-use conversions towards green infrastructure for enhanced liveability and climate resilience. Furthermore, technical limitations in remote sensing, such as spectral occlusion from dense vegetation or shadows, were identified as potential contributors to classification errors, validated through fieldwork and ground truthing. These findings highlight the critical need for a multidimensional understanding of urbanisation, moving beyond mere horizontal expansion to encompass vertical growth, redevelopment lag, spatial constraints, and policy-driven transformations. This analysis is situated within the context of Sustainable Development Goal 11, the New Urban Agenda, and Malaysia^s National Physical Plan Thrust 2, which advocates for a more holistic approach to sustainable urban development. Keywords: LULC change, remote sensing, vertical urban growth, densification, sustainable development Share Link | Plain Format | Corresponding Author (Nur Faziera Yaakub)

62	Topic B: Applications of Remote Sensing	ABS-11
Spatial Insights into Mangrove Ecosystem Services in Perak, Malaysia: A Preliminary Assessment Using Satellite Imagery Muhammad Akmal Roslani 1*, Mohd Hasmadi Ismail 2 and Norizah Kamaruddin 3 1,2,3 Department of Forestry Science and Biodiversity, Faculty of Forestry and Environment, Universiti Putra Malaysia, 43400, UPM Serdang, Selangor, Malaysia. 1 Faculty of Applied Sciences, Universiti Teknologi MARA, Perlis Branch, Arau Campus, 02600 Arau, Perlis, Malaysia. 3 Institute of Tropical Forestry and Forest Products, Universiti Putra Malaysia, 43400, UPM Serdang, Selangor, Malaysia. Abstract Mangrove ecosystems are critical to coastal resilience, biodiversity conservation, and human livelihoods. They provide a range of ecosystem services (ES), such as flood protection, carbon storage, nutrient cycling, and support for fisheries. However, assessing and mapping these services on a broad landscape scale remains challenging, particularly in regions with limited data availability. This study presents a preliminary assessment of the potential supply of mangrove ecosystem services in Tanjung Burung and Matang, Perak, Malaysia. Using SPOT satellite imagery and a Land Use Land Cover (LULC) matrix approach, we classified mangrove areas and analysed their spatial contribution to key ES categories. Expert surveys were conducted to gather both qualitative insights and quantitative estimations of ES supply, covering regulating, supporting, cultural, and provisioning services. The preliminary analysis revealed that regulating and maintenance (supporting) services were the most dominant, followed by moderate levels of provisioning services and average levels of cultural services. A spatial visualisation of these services was generated, offering a clearer understanding of their distribution and intensity across the landscape. The result highlights the value of remote sensing as a scalable tool for ES assessment, especially in data-scarce contexts. Keywords: Mangrove Ecosystem Services, Ecosystem Service Mapping, SPOT Imagery, Land Use Land Cover Matrix, Sustainable Mangrove Management. Share Link | Plain Format | Corresponding Author (MUHAMMAD AKMAL ROSLANI)

63	Topic B: Applications of Remote Sensing	ABS-12
Ecosystem Stress of Rare Earth Mining in Northen Myanmar Myint M.M Mapping and Natural Resources Informatics (MNRI), Switzerland Abstract ABSTRACT Rare Earth Elements (REE) are essential for production of future technologies that will generally improve quality of life of people. However, the ways REE are extracted largely damages communities, contaminates surrounding environment, and destroys the forested vegetations. The REE originated from Northern Myanmar are being produced using REE leaching ponds. This research study explored the ecosystem stress at REE leaching ponds and surrounding areas at the sub-watersheds of Chipwi township, where REE leaching ponds are unmanageably abundant. Enhanced Vegetation Index (EVI) is calculated using time series MODIS, Landsat, and Sentinel 2 MSI data for the reference period when REE leaching ponds were not introduced- and for the recent periods when REE leaching ponds are operational. Based on the reference and recent periods, accumulated EVI anomalies are calculated and presented as maps and charts on how ecosystem accumulates or degrades using Python codes and Google Earth Engine (GEE). This research paper contributes the methodology on EVI anomalies of MODIS, Landsat, and Sentinel 2A for ecosystem stress mapping and charting. Moreover, this paper provides detail mapping of the REE leaching ponds and general local hydrology of toxic flow and leaching to May-Kha River which is the one of the water sources of Irrawaddy River. The information contributed by this paper will be beneficial for the scientific community and sustainable landscape management. Keywords: REE, EVI, Ecosystem Share Link | Plain Format | Corresponding Author (Maung Moe Myint)

64	Topic B: Applications of Remote Sensing	ABS-14
GeoAI Techniques for Detecting and Classifying Roofs-Included Solar Panels on Remote Sensing Imagery in Thai Urban Historical Heritage: The old moat of Nakhonratchasima City Municipality, Thailand Yaowaret Jantakat, Pongpun Juntakut, Chomphak Jantakat 1. Rajamangala University of Technology Isan, Nakhon Ratchasima, Thailand 2. Royal Thai Armed Forces Headquarters, Bangkok, Thailand 3. Vongchavalitkul University, Nakhon Ratchasima, Thailand Abstract Presently, the utilization of solar panels on rooftop received a lot of attention because it helps save electricity and protect the environment. Therefore, this study have attention to promote using solar panels on rooftop especially city areas because there are a lot of buildings and impervious surfaces (where are mainly artificial structures). The aim of this study was to survey and support collecting data about the quantity of solar panels on building^ rooftops from using satellite imagery of Google Earth. Deep learning is one type of GeoAI (Geospatial Artificial Intelligence) techniques that was used for the roofs with the solar panels on classification of satellite imagery of Google Earth in this study. The old moat of Nakhonratchasima City Municipality (NCM) is selected as the case study or area-specific characteristics because it is ancient city mixed presently modern structure with a full of impervious building materials brick and concrete block. Deep learning-based Deepness panel in QGIS, was employed to analyze buildings and their solar panels on rooftops. This was a collection of pre-trained deep learning models in the ONNX format that was needed for this plugin in QGIS. This study used the Solar PV segmentation. As the results, this study found that deep learning technique can detect solar panels on rooftops of 12,888 of 53,559 buildings (22.83%) in the old moat of NCM. The output was investigation on true ground with accuracy assessment 82.08% so deep learning technique is suitable for detecting solar panels on building^ rooftops in the old moat of NCM. Keywords: Deep learning, solar panel, Renewable energy source, Spatial tool, GeoAI Share Link | Plain Format | Corresponding Author (Yaowaret Jantakat)

65	Topic B: Applications of Remote Sensing	ABS-270
J-GMS Sentinel-1 Based Ground Deformation Monitoring Across Japan for Infrastructure Risk Assessment Khin Myat Kyaw, Wataru Takeuchi Institute of Industrial Science, The University of Tokyo Abstract This paper outlines the Japan Ground Motions Service (J-GMS), designed to analyze ground deformation across Japan comprehensively. Leveraging Sentinel-1 satellite data, the service delivers time-series of ground deformations in the satellite^s line-of-sight direction, with a final spatial resolution of ~30x30 m. The dataset covers January 2016 to May 2025, featuring descending passes at 12-day intervals and occasional ascending data, subject to availability. Ground deformation data is regionally classified using polygon IDs based on Copernicus DEM. The framework employs advanced Interferometric Synthetic Aperture Radar (InSAR) techniques, specifically the Small Baseline Subset (SBAS) approach, to produce interferograms for effective monitoring of surface deformation over natural terrains. Ground movements are relative observations within each frame, and residual tropospheric noise is mitigated using ERA5 atmospheric data from ECMWF. The regional ground deformation results from J-GMS are crucial for evaluating infrastructure safety, tracking natural hazards such as landslides, and examining environmental effects like groundwater extraction. GNSS data was utilized for validation in selected areas, with plans to enhance outputs through GNSS-calibrated results in the future. The service^s frequent revisit schedule and weather-independent data make it a valuable asset for geophysical and environmental studies. Keywords: InSAR, subsidence, infrastructure, planning, hazard management Share Link | Plain Format | Corresponding Author (Khin Myat Kyaw)

66	Topic B: Applications of Remote Sensing	ABS-15
THE ACCURACY OF OBIA METHOD TO DETERMINE LANDSLIDE CANDIDATES IN SIRIMAU AND NUSANIWE DISTRICT, AMBON CITY Ferad Puturuhu (a*) a) Pattimura University. *feradputuruhu[at]gmail.com Abstract The purpose of this study is to test the accuracy of the OBIA (Object Based Image Analysis) method in identifying landslide candidates in Sirimau and Nusanive Districts, Ambon City. This study was conducted using the OBIA digital interpretation method, which was carried out on Landsat 8 images with a 653 composite, using Idrisi Selva software. With two major stages in this process, namely: segmentation and classification. In the segmentation process there are several stages, namely: a) segmentation by determining how large the segmentation vector is used, b) segmentation training to create land cover training areas, c) classification is carried out using the maximum likelihood algorithm, and d) land cover segmentation classification is carried out. From this segmentation classification, a land cover classification is produced, with open land as a candidate for landslides. The results obtained from this study were that the results of digital interpretation with OBIA found 7 candidate landslides with a Similarity Tolerance of 50, while 9 existing landslides were found with an accuracy of 43.8%. Keywords: Accuracy, OBIA, Landslide Share Link | Plain Format | Corresponding Author (Ferad Puturuhu)

67	Topic B: Applications of Remote Sensing	ABS-16
LiDAR Applications in Structural Health Monitoring of Cable-Stayed Bridges: A Systematic Review Nain Dhaniarti Raharjo (a*), Lalu Muhamad Jaelani (b) a) Department of Geomatics Engineering, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia b) Department of Geomatics Engineering, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia Abstract Structural Health Monitoring (SHM) is increasingly being recognized as an important area for monitoring the structural health and safety of large structures such as cable-stayed bridges under the influence of different loading scenarios and structural vibrations. This in-depth review of literature aims to investigate the use of Light Detection and Ranging (LiDAR) technology focusing on structural health monitoring (SHM) of cable-stayed bridges. The aim of this review is to analyze the LiDAR for geometric mapping, deformation monitoring, and the role of LiDAR in numerical models and machine learning. The study is a PRISMA compliant compilation of a variety of studies. There are still challenges remain including data validation, ambient noise, and integration of a real-time system into an operational system. It is important that these issues be considered as part of the initial health review for new, LiDAR-based bridge applications in order to enhance maintenance strategies. has become increasingly important in managing the structural integrity and safety of large structures, such as cable-stayed bridges, under a variety of loading conditions and structural actions. This SLR targets Light Detection and Ranging (LiDAR) applied for structural health monitoring (SHM) of cable-stayed bridges. In accordance with the PRISMA guidelines, the review integrates the results obtained in several works, performing a compilation in order to contribute to evaluate that LiDAR for geometric mapping, deformation detection and its connection with numerical models and machine learning. However, there are still challenges such as data validation, environmental noise and real-time integration into a working system. Early health monitoring of new LiDAR applications to bridges needs to solve these problems and to help the better maintenance. Keywords: LiDAR, Structural-Health-Monitoring, Cable-Stayed, Monitoring-Systems, Systematic-Literature-Review Share Link | Plain Format | Corresponding Author (Nain Dhaniarti Raharjo)

68	Topic B: Applications of Remote Sensing	ABS-273
Object-Based Temporal Analysis of Ice Mass Change in the Antarctic Region Using Machine Learning Algorithms Saziye Ozge Atik, Mehmet Arkali, Muhammed Enes Atik Istanbul Technical University Abstract Climate change is causing changes in many areas of the world, and changes in some natural classes also constitute a significant part of this. Analyzing the impact of climate change on glaciers in the southern hemisphere is crucial. Satellite imagery, which is openly shared and can be acquired periodically, is a suitable data source for these analyses. Machine learning methods are among the most promising cutting-edge algorithms in this field. Using Sentinel-2A imagery, we analyzed the ice mass change in a selected region of Horseshoe Island, Antarctica, over 15 years, with five-year intervals. Using low-cloud images taken every five years, both in summer and winter, segments were generated using object-based image analysis (OBIA) in the study area and classified into three different classes. The support vector machine algorithm produced results with higher accuracy than the k-nearest neighbor algorithm. These analyses analyzed the time-dependent rate of ice mass decline over the last 15 years, providing researchers with insights into future predictions. Such studies can be used to provide ideas for measures that can be taken for the future. Keywords: Machine Learning , Object-Based , Antarctica, SVM, k-NN Share Link | Plain Format | Corresponding Author (Saziye Ozge Atik)

69	Topic B: Applications of Remote Sensing	ABS-274
Mapping Tree Crown Dynamics and Biomass Accumulation Using LiDAR-Derived Canopy Metrics Atikah Razaki(a), Nurul Ain Mohd Zaki(b)(e)*,Zulkiflee Abd Latif(c)(e), Mohd Zainee Zainal(b), Hamdan Omar(f) and Mohd Nazip Suratman(d)(e) (a)Students, Faculty of Built Environment, Universiti Teknologi MARA, Perlis Branch, Arau Campus, 02600, Arau, Perlis, Malaysia (b)Senior Lecturer, Faculty of Built Environment, Universiti Teknologi MARA, Perlis Branch, Arau Campus, 02600, Arau, Perlis, Malaysia (c)Senior Lecturer, Faculty of Built Environment, Universiti Teknologi MARA, Shah Alam, 40450, Shah Alam, Malaysia (d)Senior Lecturer, Faculty of Applied Sciences, Universiti Teknologi MARA, Shah Alam, 40450, Shah Alam, Malaysia (e)Associate Fellow, Institute for Biodiversity and Sustainable Development, Universiti Teknologi MARA, Shah Alam, 40450, Malaysia (f)Forest Research Institute Malaysia (FRIM), 68100 Kuala Lumpur, Federal Territory of Kuala Lumpur Abstract Tropical forests are critical carbon reservoirs that contribute significantly to climate regulation. Accurate monitoring of above-ground biomass (AGB) and carbon stock changes is essential for understanding forest dynamics and supporting climate change mitigation policies. This study evaluates the temporal changes in AGB and carbon stock at the Forest Research Institute Malaysia (FRIM), Kepong, by utilizing high-resolution airborne Light Detection and Ranging (LiDAR) datasets acquired in 2009 and 2014. The methodology involved three main phases: LiDAR data pre-processing, generation of Canopy Height Models (CHMs), and individual tree crown (ITC) delineation using a watershed segmentation algorithm. Local maxima detection was applied to the CHM raster to identify tree tops, which served as seeds for watershed transformation. The delineated crowns enabled the extraction of tree height and crown projection area (CPA) for individual trees. Statistical analysis, including a paired sample t-test, revealed a significant increase in both tree height and CPA between 2009 and 2014. Mapping outputs visualized spatial distribution and changes in carbon stock, highlighting areas with the most significant growth. The integration of multitemporal LiDAR and remote sensing techniques proved effective for non-destructive, large-scale forest monitoring. This research underscores the value of LiDAR technology in enhancing the accuracy of forest biomass assessments and contributes to the development of robust methodologies for carbon accounting in tropical forest ecosystems. Keywords: LiDAR, Above-ground Biomass, Carbon Stock, Tropical Forest Share Link | Plain Format | Corresponding Author (NURUL AIN MOHD ZAKI)

70	Topic B: Applications of Remote Sensing	ABS-19
Analiysis of Environmental Criticallity Index (ECI) in Bandung Basin Using Remote Sensing Lili Somantri (a*) Haikal Muhammad Ihsan (b) (a, b) Departement of Geography Education, Universitas Pendidikan Indonesia, Bandung, Indonesia *lilisomantri[at]upi.edu Abstract Bandung City and this surrounding areas are experiencing intensive land cover change and surface temperature dynamics due to significant population growthand massive infrastructure development. This study aims to analyze the Environmental Criticality Index (ECI) to identify spatial patterns of environmental vulnerability using remote sensing and GIS techniques. The ECI serves as a synthetic index to measure environmental stress resulting from urbanization, particularly in areas with intensive built-up growth and vegetation loss. Landsat 8 and 9 OLI/TIRS imagery from the years 2019 and 2024 are utilized to extract relevant parameters, including Land Surface Temperature (LST), Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-Up Index (NDBI), and Modified Normalized Difference Water Index (MNDWI). These parameters are processed and integrated into the ECI model, focusing on the combination of built-up density and thermal characteristics to determine critical zones. The spatial analysis results reveal increasing environmental criticality in urban fringes and previously green areas, driven by land conversion and infrastructure development. By mapping and visualizing the distribution of environmental pressure, this study provides a comprehensive overview of ecological vulnerability across the Bandung Basin. The findings emphasize the need for environmentally sensitive spatial planning policies that consider thermal regulation, vegetation preservation, and sustainable land use. The ECI-based approach demonstrated in this study can serve as a valuable tool for monitoring urban impacts on the environment and for supporting local governments in making informed planning decisions aimed at enhancing ecological resilience and urban sustainability. Keywords: bandung basin- environmental criticality index- land surface tempertaure- remote sensing- spatial planning Share Link | Plain Format | Corresponding Author (Lili Somantri)

71	Topic B: Applications of Remote Sensing	ABS-276
Land Use and Land Cover Change Analysis Following the 2025 Myanmar Earthquake Shindai Kanai (a*), Rin Owa (a), Ye Htet (b), Osamu Kozan (b) a) Graduate School of Asian and African Area Studies, Kyoto University, Japan b) Center for Southeast Asian Studies, Kyoto University, Japan Abstract On March 28, 2025, a magnitude 7.7 earthquake struck central Myanmar followed by another magnitude 6.4 one. Amid an ongoing civil war between the military regime and pro-democracy forces since the 2021 coup in this Southeast Asian country, the disaster further deepened the crisis for already vulnerable communities. Over 3,400 fatalities and the destruction or damage of more than 40,000 buildings have been reported, but the full extent of the damage remains unclear. This study aims to provide a comprehensive damage assessment of the affected areas through remote sensing-based land use and land cover (LULC) mapping. While satellite-based damage assessments are gaining attention in post-disaster contexts, most existing efforts focused on accessible regions or were conducted under government direction. In contrast, there are few cases of LULC mapping in armed-conflict zones like Myanmar, where reliable information is scarce. This study seeks to visualize on-the-ground realities from a civilian-centered perspective by leveraging open-access satellite data. We used high-resolution satellite imagery from Google Earth and geotagged social media posts related to the earthquake to generate training data for supervised classification. By employing both optical and synthetic aperture radar imagery from Sentinel-1 and Sentinel-2 satellites, two LULC maps were produced: one covering the period from March to July 2024 (pre-earthquake) and another from March to July 2025 (post-earthquake). Classification was conducted using the Random Forest algorithm, targeting major land cover categories including built-up areas, forests, croplands, and water bodies. By visualizing LULC changes triggered by the earthquake, this research aims to contribute to understanding the large coverage area of the impact and highlight the utility of remote sensing as a reactive tool in data scarce and politically sensitive contexts. Keywords: LULC, Earthquake Damage Assessment, Southeast Asian Area Studies Share Link | Plain Format | Corresponding Author (Shindai Kanai)

72	Topic B: Applications of Remote Sensing	ABS-21
Cloud-Native Deployment of a Sinkhole Susceptibility Mapping Platform Using Google Earth Engine and Colab in Urbanised Karst Terrain Tan Yan Eng and Siti Nur Aliaa Roslan Faculty of Engineering, Universiti Putra Malaysia, Malaysia Abstract Sinkholes are a critical geohazard in rapidly urbanising karst landscapes, where natural subsurface dissolution is intensified by human activities such as construction and groundwater extraction. Despite their increasing frequency, public access to sinkhole risk information remains limited, particularly in developing urban settings like Kuala Lumpur, Malaysia. This study presents a cloud-native platform for sinkhole susceptibility mapping, integrating multi-source geospatial data with machine learning to achieve both technical scalability and public usability. The proposed workflow leverages Google Earth Engine (GEE) for geospatial data processing and Google Colab for model training, enabling a seamless end-to-end pipeline without reliance on desktop GIS tools. A lightweight one-dimensional Convolutional Neural Network (1D CNN) is implemented to classify sinkhole susceptibility based on 14 spatial control factors representing geological, topographic, hydrological, and anthropogenic influences. The model produces a continuous susceptibility surface, allowing for nuanced risk interpretation. Performance evaluation achieved a high AUC-ROC of 0.97, demonstrating strong discriminatory power despite a limited training dataset. The final susceptibility map is deployed via a public-accessible GEE web application that includes toggleable data layers and interactive query functions designed for planners, engineers, and the general public. The platform supports scalable updates and future integration with real-time data sources. Overall, this study demonstrates the feasibility of cloud-based geospatial modelling for hazard communication in data-scarce urban environments and provides a reproducible, user-friendly template for karst risk assessment in other rapidly developing cities. Keywords: Google Earth Engine, karst, sinkhole susceptibility, Convolutional Neural Network Share Link | Plain Format | Corresponding Author (Yan Eng Tan)

73	Topic B: Applications of Remote Sensing	ABS-277
Camera Position Estimation with a Limited Number of Known Landmarks Kim C.W.(1), Yi S.U.(2), Yoon W.S.(3), and Rhee S.A.(4*) (1) Image Eng. Research Centre: Associate Research Engineer, 3DLabs Co. Ltd, Republic of Korea (2) Image Eng. Research Centre: Assistant Research Engineer, 3DLabs Co. Ltd, Republic of Korea (3) Image Eng. Research Centre: Research Engineer, 3DLabs Co. Ltd, Republic of Korea (4*) Image Eng. Research Centre: Director of the Research Centre, 3DLabs Co. Ltd, Republic of Korea *ahmkun[at]3dlabs.co.kr Abstract In crowded and complex indoor environments such as shopping malls and subway stations, individuals often find it difficult to navigate or determine their current location. The problem becomes more serious in environments surrounded by tall buildings or located deep underground, where Global Positioning System (GPS) signals are weak or completely unavailable. With the recent advancement of the geospatial information industry, interest in indoor spatial data development and indoor positioning technologies has been steadily increasing. This study proposes a method for estimating camera position using known points (landmarks) within images captured by a smartphone camera. In particular, we experimentally evaluate the feasibility of indoor positioning when only a limited number of known points is available. The proposed method begins by capturing indoor images with a smartphone camera. Simultaneously, external orientation parameters (roll, pitch, azimuth) are acquired through a custom Android-based application developed for this study. Ground truth data, including camera and landmark positions, are also collected. Next, we define a pinhole-based camera model for the smartphone. Given the limited number of known points, we assume that the camera and the landmarks lie on the same plane and accordingly fix certain parameters to simplify the model. Based on this camera model, observation equations are formulated and the parameters are estimated using the Least Squares Estimation (LSE) method. Although the proposed method does not reach the accuracy of approaches like SolvePnP, which use many landmarks to estimate both camera orientation and position, it still produces position estimates close to the ground truth in our experiments. The experimental results confirm that indoor position estimation is feasible with limited known landmarks. Future research will invesigate automation techniques such as AI-based object detection and automated landmark extraction, to further enhance the robustness and usability of the method. Keywords: Indoor Positioning, Camera Pose Estimation, Landmark-based Localization Share Link | Plain Format | Corresponding Author (CHEOLWOOK KIM)

74	Topic B: Applications of Remote Sensing	ABS-278
Monitoring Forest Structure Using UAS Photogrammetry in Tropical Forest Restoration Project Wong W.V.C.1*, Ioki K.2 and Phua M.H.1 1Faculty of Tropical Forestry, University Malaysia Sabah, Malaysia 2Faculty of Engineering, Musashino University, Japan Abstract Monitoring forest structure in tropical forest restoration projects is essential for assessing restoration success, tracking progress and guiding adaptive management strategies. Unmanned aerial systems (UAS) are valuable tools for monitoring forest structure, offering a cost-effective and efficient way to assess and track changes over time. In this paper, forest structure dynamics was studied at an interval of a year using the UAS photogrammetry for a tropical forest restoration project located in Northern Borneo. We incorporated the use of field plot (40 m x 40 m) and LiDAR data for prediction method and digital terrain model (DTM), respectively. The results demonstrated that UAS photogrammetry is capable of providing forest structure information to enhance global efforts towards effective and sustainable forest restoration monitoring. Keywords: UAS, aerial photogrammetry, forest structure, forest restoration Share Link | Plain Format | Corresponding Author (Wilson V. C. WONG)

75	Topic B: Applications of Remote Sensing	ABS-24
Remote Sensing-Based Interpretation and Analysis of Hydrothermal Alteration Zones in Mount Patuha and Surrounding, Bandung Regency, West Java Adang Saputra 1*, Denny Lumban Raja1, and Murni Sulastri 1 Geological Technology Study Program, Politeknik Energi Pertambangan Bandung, Indonesia Abstract The research was located in the Mount Patuha area, which is part of the Bandung Regency. Gemorphologically, this area consists of undulating hills with a slope gradient of around 10% to above 45%. Vegetation in the area consists of forests, mixed plantations and rice fields which are generally planted with trees. Interpretation and analysis of this hydrothermal alteration were conducted using remote sensing. Remote sensing is a method for collecting data or information without touching the object being studied. In this study, the author used Landsat 8 OLI/TIRS Satellite Imagery. Remote sensing is widely used for geothermal exploration because it has the advantage of not requiring large costs and can also access remote areas. The research aimed to map hydrothermal alteration areas regionally in Rancabali District and its surroundings, Bandung Regency, West Java. The research was conducted by processing several bands with pixel ranges that can represent hydrothermal alteration minerals in the study area. The method used in the study was Density Slicing. Alteration minerals detected in the research area are yellow to orange using composite images 4/2, 6/7, 5 and 10. From the research results, it was obtained that hydrothermally altered rocks reached an area of 20,409,300 m2 or 2,040.93 hectares (Ha). Keywords: Remote sensing, Mount Patuha, Hydrothemal, Alteration minerals, Share Link | Plain Format | Corresponding Author (Adang Saputra Adang)

76	Topic B: Applications of Remote Sensing	ABS-281
Optimizing PlanetScope-Based Satellite-Derived Bathymetry: A Single-Band Approach with 3D Spatial and Statistical Filtering Rizka Maharani (a), Fahreza Okta Setyawan (a), Sarono (b*) a) Faculty of Fisheries and Marine Sciences, Brawijaya University, Malang, Indonesia b) Faculty of Geography, Gadjah Mada University, Yogyakarta, Indonesia *sarono90[at]mail.ugm.ac.id Abstract Satellite-Derived Bathymetry (SDB) is an efficient method for mapping shallow water depths, particularly in large tropical areas that are difficult to survey using conventional techniques. This study optimises the single-band approach on PlanetScope imagery by integrating statistical filtering with 3D geospatial interpolation to improve accuracy and reduce prediction errors. Of the three spectral channels used (red, green, blue), the green band provided the best initial performance (R^2 = 0.211- RMSE = 2.080 m) and was selected for the basis predictive model advanced. Bathymetry reference data from Single Beam Echosounder System (SBES) surveys, reduced to Mean Sea Level (MSL), were used as reference data for model calibration and validation, with 30 points as controls. Optimisation involved applying Cloth Simulation Filtering (CSF) to the estimated depth point cloud, followed by spatial interpolation using Kriging, Inverse Distance Weighting (IDW), Spline, and Natural Neighbour methods. The results show that the combination of CSF and IDW provides the best performance with an increase in the correlation value of 0.462 (from R = 0.211 to R = 0.673), an increase in determination R^2 to 0.452, and a decrease in RMSE to 1.619 m. Additionally, using a smaller cloth resolution resulted in a more accurate model, indicating the high sensitivity of the CSF parameter to the quality of the final results. This study demonstrates that the integration of statistical filtering and geospatial interpolation can significantly improve the performance of single-band SDB method, offering an accurate and cost-effective solution for large-scale bathymetry mapping with improved accuracy. Keywords: Satellite-Derived Bathymetry (SDB), PlanetScope, Statistical Filtering, 3D Geospatial Filtering, Bathymetry Accuracy Share Link | Plain Format | Corresponding Author (Rizka Maharani)

77	Topic B: Applications of Remote Sensing	ABS-282
A Novel Swin Transformer Based Deep Learning Model for Building Extraction from Very High Resolution Images Kavzoglu, T. and Yilmaz, E.O Gebze Technical University Abstract The extraction of building footprints from very high-resolution remote sensing imagery plays a vital role in a wide range of geospatial applications, including spatial planning, crisis management, and the development of data-driven smart cities. While deep learning-based approaches have significantly enhanced the accuracy and automation of this task in recent years, several challenges persist. These challenges are especially prominent in densely built environments, where complex urban morphology and spectrally similar surface materials hinder precise segmentation. The issue of delineating building boundaries is frequently impeded by these factors, thus necessitating the development of more robust and context-aware segmentation strategies. In this study, a novel Swin Transformer-based model was proposed for building extraction, and its performance was tested on a well-known benchmark dataset, namely the Massachusetts Building Dataset. The model aims to accurately identify building boundaries by effectively capturing local textural details and global contextual information through a multi-scale, window-based attention mechanism. The performance of the model is benchmarked against SOTA deep learning architectures, including DeepLabV3+, SegFormer, UPerNet, and PAN, which underwent training and testing under the same dataset and parameter settings. The results revealed that the proposed model exhibited superior performance in terms of evaluation metrics. To be more specific, the proposed model demonstrated a precision of 87.98%, a recall of 86.03%, an IoU of 77.94% and an overall accuracy of 92.54%. On the other hand, SegFormer, UPerNet, DeepLabV3+, and PAN achieved IoU scores of 75.41%, 75.66%, 73.36%, and 69.78%, respectively. The findings indicate that the proposed model is capable of delineating more precise building boundaries, particularly in areas characterized by high-density construction, and demonstrates a strong capacity for generalization. Moreover, results show that transformer-based architectures offer a powerful alternative for remote sensing and geospatial artificial intelligence applications, providing more lightweight, accurate, and scalable solutions for building extraction. Keywords: Building footprint extraction, semantic segmentation, swin transformer, VHR imagery, remote sensing. Share Link | Plain Format | Corresponding Author (TASKIN KAVZOGLU)

78	Topic B: Applications of Remote Sensing	ABS-283
Evaluation of Sentinel-2 and PlanetScope Image Fusion for Tree Species Identification in Wanagama Tropical Forest, Indonesia Sarono (a*), Muhammad Kamal (a), Sigit Heru Murti BS (a), Emma Soraya (b) a) Faculty of Geography, Gadjah Mada University, Yogyakarta,Indonesia *sarono90[at]mail.ugm.ac.id b) Faculty of Forestry, Gadjah Mada University, Yogyakarta, Indonesia Abstract Remote sensing-based tree species classification requires a combination of high spatial resolution and rich spectral information. Sentinel-2 offers advantages in spectral diversity and spectral consistency, but is limited by its spatial resolution of 10-20 meters. In contrast, PlanetScope provides finer spatial resolution (3.3 meters) and high revisit frequency, yet is often criticized for spectral inconsistency across satellites and potential radiometric noise. This study aims to evaluate the fusion of both sensors to improve species classification accuracy in the Wanagama Educational Forest, Gunung Kidul, Yogyakarta, by leveraging the spectral strength of Sentinel-2 and the spatial resolution of PlanetScope. Image fusion was carried out using the Gram-Schmidt method with two main schemes: (1) spectral band matching from Sentinel-2 pansharpened with single-band PlanetScope data, and (2) PCA extraction from PlanetScope RGBNIR bands followed by pansharpening with Sentinel-2. Spectral validation was conducted using 700 random samples. The highest correlation was observed in the PCA-Gram-Schmidt approach (R = 0.37) against Sentinel-2, while the single-band Gram-Schmidt scheme showed strong correlation with PlanetScope (R = 0.99), indicating that the generated fused data relates to both sources. Further classification was performed using 404 samples model and 151 ground truth with three parametric algorithms: Maximum Likelihood, Minimum Distance to Mean, and Mahalanobis Distance. The highest accuracy was achieved using the PCA-Gram-Schmidt (GSPCA) method under the Maximum Likelihood classifier, with an overall accuracy of 26.96%, outperforming Sentinel-2 (24.35%) and PlanetScope (23.48%). Although the accuracy remains moderate, this approach demonstrates the potential of multisensor fusion for tree species classification in tropical forests. Keywords: Spectral Fusion, Sentinel-2, PlanetScope, Tree Species Classification, Gram-Schmidt PCA Share Link | Plain Format | Corresponding Author (Sarono Sarono)

79	Topic B: Applications of Remote Sensing	ABS-28
From Data to Information: Evaluating Attribute-Enriched Point Clouds for Accurate Urban Corner and Edge Measurement Yung-Ching Yang(a*), Yu-Yun Chen(b), Jen-Jer Jaw(a) a) Department of Civil Engineering, National Taiwan University No. 1, Sec. 4, Roosevelt Rd., Taipei 106319, Taiwan *ivy.ycyang[at]gmail.com b) Chinese Society of Photogrammetry & Remote Sensing, CSPRS 3F., No. 111, Sec. 5, Roosevelt Rd., Taipei 11681 , Taiwan Abstract Accurate measurement of building corners and edges from point clouds is essential for advancing automation in urban mapping. Traditional point clouds-composed purely of 3D geometric coordinates-often lack the contextual cues to identify structural features in dense urban scenes. This study investigates transforming point cloud data into information by integrating attribute information during the point cloud generation and fusion process. Emphasizing the preservation and propagation of attribute information, starting from the multi-view image domain, through the point cloud generation process, and ultimately into the final 3D representation. We extract attribute information directly from the source imagery, such as corner-like features and semantic labels. These features are retained and embedded as attributes throughout the multi-view fusion process, resulting in attribute-enriched point clouds that combine spatial geometry with descriptive metadata. This study compares two point cloud generation modes: (1) geometry-only point clouds, and (2) enriched point clouds containing feature traces and scene understanding. The enriched data allows for spatial measurement and provides higher-level interpretability, improving the clarity and confidence of corner and edge identification. Instead of relying on purely geometric saliency at the end stage, we analyze how information preserved from the image domain can influence feature selection within the 3D data. Furthermore, we demonstrate that these enriched point clouds can be organized into structured attribute tables, facilitating the automation of feature selection and information retrieval in future workflows. Experimental results show that attribute-integrated point clouds exhibit greater reliability in identifying urban structural features. These findings underline the shift from passive 3D capture toward active, information-driven point cloud modeling that bridges the gap between perception and measurement. Keywords: Attribute-Enriched Point Cloud- Multi-View Image Fusion- Corner and Edge Measurement- Semantic-Guided Reconstruction- 3D Spatial Information Modeling Share Link | Plain Format | Corresponding Author (Yung-Ching Yang)

80	Topic B: Applications of Remote Sensing	ABS-284
Dynamics of Seagrass Expansion During Dry and Rainy Seasons Using Planetscope Imagery and Machine Learning Agus Aris (a,b*), Nurjannah Nurdin (c,d), Supriadi Mashoreng (c), Eymal Bahsar Demmalino (e), Chair Rani (c), S H Aly (f) a) The Environmental Science Study Program Doctoral Program, Hasanuddin University Graduate School b) Department of Remote Sensing and Geographic Information Systems, Vocational Faculty, Hasanuddin University, Jl. Perintis Kemerdekaan km.10, Makassar 90245, Indonesia *agus.aris[at]unhas.ac.id c) Departement of Marine Science Faculty of Marine Science & Fisheries, Hasanuddin University, Makassar, 90245. Indonesia d) Research and Development Center for Marine, Coast and Small Islands, Hasanuddin University, Makassar 90245. Indonesia e) Environmental Science study program, Hasanuddin University Graduate School f) Department of Environmental Engineering, Engineering Faculty, Hasanuddin University, Makassar, Indonesia Abstract This preliminary study aims to estimate the carbon produced by seagrass meadows and develop a model to assess the relationship between organic carbon and bulk density in seagrass meadows and sediments, along with various environmental parameters (temperature, salinity, total suspended solids (TSS), NO2, CO, rainfall, and wind). The research focuses on seagrass meadows as critical carbon-sequestering ecosystems. The objective is to map the dynamics of seagrass meadows across different seasons using SuperDove imagery from PlanetScope, which offers a spatial resolution of 3 meters. The data utilized in this study encompass seagrass conditions and SuperDove imagery from 2020 to 2025. The methods employed in this research involve a machine learning approach, incorporating processes such as sun glint correction, segmentation, seagrass masking, and pixel-based classification using the random forest method. The results indicate significant spatial and temporal variations in seagrass coverage, particularly in the northern, western, and southern parts of the island, with accuracy levels between 70% and 75%. The high temporal resolution of SuperDove imagery demonstrates its effectiveness in tracking seagrass dynamics. Following laboratory analysis, this data will be utilized to estimate carbon based on varying seagrass density levels. Keywords: Seagrass- Dry and Rainy Seasons- SuperDove- Machine Learning- Blue Carbon Share Link | Plain Format | Corresponding Author (Agus Aris)

81	Topic B: Applications of Remote Sensing	ABS-29
Development of a Low-Cost LiDAR-Based Vehicle-Mounted MMS for Road Snow Monitoring in Winter Conditions Kazuyoshi Takahashi(a*),Takeshi Nakamura(a) a)Nagaoka University of Technology,1603-1,Kamitomioka,Nagaoka,Niigata,Japan Abstract Vehicle-mounted mobile mapping systems (MMSs) offer an efficient means of acquiring geospatial information over wide areas. In particular, they are increasingly used in road management for three-dimensional mapping of pavement surfaces and roadside features. While commercial high-performance MMSs are effective for large-scale surveys and detailed infrastructure modeling, their precision and cost often exceed the requirements of many practical applications. For instance, in scenarios such as post-disaster damage location mapping, simple road surface inspection, or documenting the current status of roadside assets for local governments, it is often sufficient to capture approximate shapes and positions. In such cases, commercial MMSs tend to provide excessive capabilities, and instead, low cost and portability become more valuable. Lowering the cost of MMSs can create new opportunities for municipalities and small businesses to collect geospatial data on their own, thereby promoting spatial data utilization and contributing to local problem-solving and value creation. This study presents the development of a low-cost LiDAR-based vehicle-mounted MMS for monitoring road snow conditions in winter. The system is built using an affordable commercial LiDAR sensor (Livox Mid-360) and a GNSS/INS unit (Bynav X1-5H). We introduce a newly implemented boresight calibration method that eliminates the need for physical targets, enabling efficient setup even under harsh weather. Preliminary results from pilot runs on snow-covered roads demonstrate that the system can acquire usable point clouds through intermittent operation during winter fieldwork. Keywords: geospatial data acquisition, snow-cover, mapping,point cloud Share Link | Plain Format | Corresponding Author (Kazuyoshi Takahashi)

82	Topic B: Applications of Remote Sensing	ABS-30
Monitoring Snowbanks along Highways Using a Low-Cost Vehicle-Mounted Mobile Laser Scanning System Takeshi Nakamura(a*), Takeshi Furukawa(b), Ryo Arakawa(b), Yukinobu Sugihara(a),Seiji Kamimura(a),Kazuyoshi Takahashi(a) a)Nagaoka University of Technology b)NEXCO-Engineering Niigata Co.,Ltd. Abstract Snowbanks that form along highways during winter can pose serious safety hazards if they collapse unexpectedly. Monitoring the geometry of these snowbanks in a timely and cost-effective manner is therefore essential for road management and snow removal planning. While high-end Mobile Laser Scanning (MLS) systems offer precise measurements, their cost is often expensive for regular operation. This study investigates the feasibility of using a low-cost vehicle-mounted MLS system, originally developed for snow surveys on local roads, to monitor snowbanks along major expressways. Field experiments were conducted on the Kanetsu Expressway in Japan, where the point clouds were obtained the both of the custom-built MLS system and a commercial, simplified MLS system (N-Quick) . The resulting point clouds were compared in terms of density and cross-sectional snowbank profiles under different surface conditions?namely moist and wet pavements. Preliminary results suggest that the low-cost MLS system can capture snowbank geometry with a level of accuracy comparable to that of the commercial system, particularly under dry or moderately moist conditions. However, challenges remain under more adverse conditions, such as wet pavement, where the system fs measurement performance may degrade. Keywords: snowbank monitoring, mobile laser scanning, point cloud, highway, low-cost sensor Share Link | Plain Format | Corresponding Author (Takeshi Nakamura)

83	Topic B: Applications of Remote Sensing	ABS-286
Modeling Aboveground Biomass Using Non-Redundant Vegetation Indices from PlanetScope Imagery via Multiple Linear Regression in Planted Forests Sarono (a*), Erna Kurniati (a) a) Faculty of Geography, Gadjah Mada University, Yogyakarta,Indonesia *sarono90[at]mail.ugm.ac.id Abstract Aboveground biomass (AGB) estimation using single Vegetation Indices (VI) derived from satellite imagery has been widely implemented, yet often yields varying levels of accuracy due to limitations in representing vegetation heterogeneity. This study aims to develop an AGB estimation model based on a combination of non redundant vegetation indices derived from high resolution PlanetScope imagery in the Wanagama Forest area, Yogyakarta, Indonesia. A total of 19 VIs were calculated and analyzed using Pearson Correlation Matrix (PCM) on 404 correlation sample points. Index combinations were selected based on low inter-index correlation values (R) under 0.3, assuming that lower correlation represents more diverse spectral information while minimizing redundancy. The best combinations identified were EGCV (EVI,GNDVI,CIVE,VREI1) and EGGV (EVI,GNDVI,GLI,VREI1). Biomass estimation was performed through seven modeling scenarios: five single-index models and two combination models (EGCV and EGGV). A Multiple Linear Regression (MLR) model was applied for the combination schemes, while Simple Linear Regression (SLR) was used for the single-index models. The models were trained using 137 training samples and validated with 63 test samples derived from field-measured tree diameter and height. Results show that total biomass estimation across the seven scenarios ranged from 20.9 to 3,562 tons, with the highest correlation value 0.56 obtained from the EGGV model. The EGGV model outperformed both the EGCV combination and all single index models, which only achieved R values ranging from 0.17 to 0.55. RMSE, MAE, and R values were consistently aligned, confirming that the EGGV combination model provided the most accurate results. This study demonstrates that selecting VIs based on PCM analysis can improve AGB estimation accuracy and minimize spectral information redundancy in high resolution remote sensing applications. Keywords: Aboveground Biomass, PlanetScope , Vegetation Indices, Pearson Coeficient Matrix, PCM, Multivariate Regression, Correlation Analysis Share Link | Plain Format | Corresponding Author (Sarono Sarono)

84	Topic B: Applications of Remote Sensing	ABS-31
Monitoring Slow Slip Events in the Nankai Trough Region Using PSInSAR Ching-Lun Lin (1), Chung-Pai Chang (2) Center for Space and Remote Sensing Research, National Central University, Taiwan Abstract The Nankai Trough, an active subduction zone off southern Japan, poses a significant seismic hazard due to its potential for generating destructive megathrust earthquakes. Episodic slow slip events (SSEs), which occur aseismically along the plate interface, are key indicators of stress accumulation and interplate coupling. While Japan^s dense GNSS network has enabled reliable SSE detection, its cost and limited applicability in other tectonic regions underscore the need for alternative approaches. This study evaluates the capability of Persistent Scatterer Interferometric Synthetic Aperture Radar (PSInSAR) as a complementary technique, offering centimeter-scale displacement sensitivity, broad spatial coverage, and sufficient temporal resolution. Using Sentinel-1 SAR data (2017-2025), processed through ESA^s SNAP and StaMPS software, the analysis focuses on detecting subtle crustal deformation in the Nankai Trough region. PSInSAR-derived signals are cross-validated against GNSS and seismicity data to assess their spatial extent and temporal evolution. The results highlight the potential of PSInSAR for monitoring slow tectonic transients in subduction zones, thereby contributing to a more comprehensive understanding of the seismic cycle and long-term hazard assessment in the Nankai Trough. Keywords: Slow earthquake, PSInSAR, Nankai Trough, Slow slip events, StaMPS Share Link | Plain Format | Corresponding Author (Ching Lun Lin)

85	Topic B: Applications of Remote Sensing	ABS-287
Identifying Priority Areas for Nature-based Solutions to Mitigate Urban Flood Risk Using Blue-Green Infrastructure in Parepare City, Indonesia Syazwi Quthbi Al Azizi School of Architecture, Planning and Policy Development, Bandung Institute of Technology (ITB), Bandung, Indonesia Abstract Rapid urbanization and climate change have amplified urban flood risks, especially in medium-sized coastal cities of developing countries. Parepare City, Indonesia, exemplifies this challenge due to its high flood hazard levels, multidimensional vulnerability-including physical, social, and economic aspects-and limited adaptive capacity. This study aims to identify priority areas for implementing nature-based solutions (NbS) by integrating flood risk mapping with spatial analysis of existing urban space. Flood risk was assessed through a spatial multi-criteria analysis (SMCA) that combined indicators of hazard, vulnerability, and capacity. The results show that high-risk zones are mainly concentrated along river corridors and low-lying areas prone to high flood discharge and significant socio-economic vulnerability. Furthermore, the study analyzes the distribution and accessibility of blue-green spaces relative to built-up areas and population density to guide NbS planning. Priority areas are classified into three groups based on flood risk levels and the availability of blue-green infrastructure. Proposed interventions include rainwater harvesting, permeable pavements, urban forest enhancement, and retention ponds. The findings highlight the necessity of integrating detailed flood risk assessments with spatial analysis of blue-green infrastructure to enhance flood resilience in medium-sized coastal cities. Keywords: urban flood risk- nature-based solutions- blue-green infrastructure- spatial multi-criteria analysis- Parepare- Indonesia Share Link | Plain Format | Corresponding Author (Syazwi Qutbhi Al Azizi)

86	Topic B: Applications of Remote Sensing	ABS-32
Residual landslide susceptibility analysis based on integrated machine learning framework Shou Hao,Chiang, Tung Cheng,Lu First Author^s Affiliation: Professor, Center for Space and Remote Sensing Research, National Central University, Taiwan Second Author^s Affiliation: Research Assistant, Center for Space and Remote Sensing Research, National Central University, Taiwan Abstract In this study, residual landslides refer to slopes characterized by substantial accumulations of landslide-derived failure materials, forming unstable colluvium that may serve as primary source zones for debris flows, especially under conditions of intense rainfall, thereby posing significant hazards to downstream areas. In Taiwan, such residual landslides present a critical challenge for watershed management and sediment-related disaster mitigation. The inaccessibility of mountainous terrain, combined with the increasing frequency and intensity of extreme precipitation events driven by climate change, has exacerbated the risks and unpredictability associated with landslides and debris flows. To address these challenges, this study proposes an advanced machine learning framework for assessing residual landslide hazards. The approach involves the development of a predictive model to evaluate the potential activity of residual landslides through the integration of temporal remote sensing data, including time-series satellite observations from Sentinel-1 and Sentinel-2. This methodology enables systematic inventory mapping and activity assessment across mountainous regions, thereby enhancing early warning capabilities and informing more effective sediment disaster prevention and management strategies. Keywords: Residual landslide, Sentinel-1, Sentinel-2, machine learning, Taiwan Share Link | Plain Format | Corresponding Author (Tung Cheng Lu)

87	Topic B: Applications of Remote Sensing	ABS-288
AI-driven high-resolution flash flood susceptibility mapping and early warning in Son La, Vietnam Quang Binh Bui Institute of human geography and sustainable development, VASS, Hanoi, Vietnam Abstract Flash floods pose severe risks to rural communities in Northwest Vietnam, particularly in Son La province, due to its rugged terrain and intense monsoon rainfall. This study introduces an innovative framework for high-resolution flash flood susceptibility mapping and early warning, leveraging artificial intelligence (AI) and machine learning (ML) integrated with Geographic Information Systems (GIS). By combining multi-source remote sensing data (Landsat-8, Sentinel-1, ALOS-2 PALSAR) with topographic and meteorological inputs, we developed a 10-m resolution spatial model using Random Forest (RF), Artificial Neural Networks (ANN), Decision Trees (J48), and Logistic Regression (LR). The RF model achieved superior performance, with an Area Under the Curve (AUC) of 0.95, identifying 25% of the study area as highly flood-prone. An AI-supported WebGIS platform and mobile application were deployed, delivering real-time warnings with an 86% detection rate during 2020 monsoon trials. This research enhances disaster resilience and supports sustainable rural development, offering a scalable solution for flood-prone mountainous regions. Keywords: Flash flood susceptibility, Artificial Intelligence, Machine Learning, Random Forest, Early warning system Share Link | Plain Format | Corresponding Author (Quang Binh Bui)

88	Topic B: Applications of Remote Sensing	ABS-290
Integrating Remote Sensing and Satellite Tracking to Unveil Whale Shark Spatial Ecology in the Dynamic Indo-Pacific Oceans Mochamad Iqbal Herwata Putra (a*),(b), Anindya Wiasatriya (c),(d), Abraham Sianipar (e), Ismail Syakurachman (b), Abdi Hasan (b), Edy Setyawan (e), Mark V. Erdmann (f), Jatna Supriatna (g), Masita Dwi Mandini Manessa(a) (a) Department of Geography, Faculty of Mathematics and Natural Sciences, Universitas Indonesia, Depok, Indonesia (b) Focal Species Conservation Program, Ocean and Science Department, Konservasi Indonesia, Jakarta, Jakarta, Indonesia (c) Department of Oceanography, Faculty of Fisheries and Marine Science, Universitas Diponegoro, Semarang, Indonesia (d) Center for coastal Rehabilitation and Disaster Mitigation Studies, Universitas Diponegoro, Semarang, Indonesia (e) Elasmobranch Institute Indonesia, Denpasar, Bali, Indonesia (f) Re:wild, Austin, Texas, USA (g) Department of Biology, Faculty of Mathematics and Natural Sciences, Universitas Indonesia, Depok, Indonesia Abstract Understanding the spatial ecology of the endangered whale shark (Rhincodon typus) is essential for informing conservation strategies, particularly in the Indo-Pacific, where populations have declined by nearly 60%. This study investigates how remote sensing data on sea level anomalies (SLA) and eddy kinetic energy (EKE) can reveal the environmental drivers of whale shark movements. From 2015 to 2025, 70 individuals (65 males and 5 females, 91% of which were large juveniles) were equipped with SPLASH tags across four aggregation sites in Indonesia: Saleh Bay (n = 24), Cenderawasih Bay (n = 34), Kaimana (n = 8), and Tomini Bay (n = 3). Whale shark tracks were reconstructed using a continuous-time correlated random walk state-space model (crw-SSM), while behavioral states were classified with a move persistence model (MPM) based on gamma (g) thresholds distinguishing foraging (g < 0.5538) from migratory (g >0.5538) behaviors. The results indicate that SLA gradients and EKE hotspots strongly influence movement pathways, with sharks frequently associating with eddy peripheries where planktonic prey is concentrated. Juvenile males showed strong responses to seasonal EKE variations, whereas juvenile females were more closely linked to SLA anomalies and deep-sea geomorphological features such as canyons. Adult males, though rarely detected, tended to follow seamount and escarpment corridors, likely utilizing localized upwelling zones as foraging stepping stones. These findings highlight the critical role of dynamic oceanographic variables particularly SLA and mesoscale eddies in shaping whale shark spatial ecology and emphasize the need to integrate these factors into habitat modeling and spatial management to safeguard key habitats and migratory routes in Indonesian waters, which remain underrepresented in current marine protected area networks. Keywords: whale shark- altimetry- satellite telemetry- movement ecology- Indo-Pacific Oceans Share Link | Plain Format | Corresponding Author (Mochamad Iqbal Herwata Putra)

89	Topic B: Applications of Remote Sensing	ABS-291
Preliminary Biomass Estimation and UAV Image Exploration of In-situ Phyllanthus rufuschaneyi in Sabah Ultramafic Soils Alexius Korom 1 2*, Nur Ain Munirah Amaruddin 3, Evy Michelle Emison 3, Rimi Repin 4, John Sugau 5 and Imam Purwadi 6 1Faculty of Plantation and Agrotechnology, Universiti Teknologi MARA Sabah Branch, Kota Kinabalu, Malaysia 2TANiLAB, Universiti Teknologi MARA Sabah Branch, Kota Kinabalu, Malaysia 3Centre of Postgraduate Studies, Universiti Teknologi MARA Sabah Branch, Kota Kinabalu, Malaysia 4Sabah Parks, Kota Kinabalu, Malaysia 5Forest Research Centre, Sabah Forest Department, Sandakan, Malaysia 6Botanickel Sabah, Malaysia Abstract Phyllanthus rufuschaneyi is a recently identified nickel hyperaccumulator with promising potential for agromining in ultramafic regions of Sabah, Malaysia. This study reports preliminary findings from a field campaign aimed at: a) understanding the relationship between biomass and selected biophysical parameters, and b) exploring the potential detection of the spatial distribution of individual biomass using UAV images. The study site is located at the degraded ultramafic soil area in Garas Hill of Ranau district, Sabah. A total of 36 destructive treelet samples and one plot of 10x10 meters field measurements, consisting of 90 readings, were conducted to quantify fresh and dry biomass and record plant characteristics. Samples were selected based on height, ranging from 103 to 620 cm at approximately 1-meter intervals. The dataset consists of measurements such as plant height, canopy size, and various biomass weights of components: leaves, rachises, trunk and roots. Initial analysis shows the power function demonstrated the highest predictive capacity, with an R^2 value of 0.913-0.927 for height, followed by trunk diameter (R^2 of 0.823-0.892), canopy size (R^2 of 0.552-0.655) and root length (R^2 of 0.417-0.614), suggesting potential for predictive modelling. Concurrently, aerial data were captured at a flying altitude of 130 meters using a DJI Phantom 4 Pro UAV to assess the plot-level spatial patterns. Based on early manual observations, ideal dimensions for the detection of individuals or clumping trees are exhibiting a height of at least 300 cm, a crown diameter of 100 cm or greater, and an estimated biomass equal to or exceeding 3000 grams. Although complete biomass modelling is still underway, these early results demonstrate the feasibility of integrating ground measurements with aerial data for biomass estimation of Phyllanthus rufuschaneyi, laying the foundation for non-destructive monitoring and sustainable metal cropping systems. Keywords: Biomass estimation, hyperaccumulator plant, Phyllanthus rufuschaneyi, ultramafic soils, UAV remote sensing Share Link | Plain Format | Corresponding Author (Alexius Korom)

90	Topic B: Applications of Remote Sensing	ABS-292
Comparative Evaluation of NDWI, NDVI, MNDWI, AWEI and EWI for Sentinel-2 Shoreline Delineation in Klungkung, Indonesia: KDE-Valley vs Otsu Thresholding Sakina Hasan(a*), Abd Rahman As-syakur(b), Xuan Truong Trinh(c), and Masahiko Nagai(d) a*, b) Faculty of Marine and Fisheries, Udayana University, Indonesia *hasan.2213511062[at]student.unud.ac.id c) Faculty of Engineering, Yamaguchi University, Japan d) Center for Research and Application of Remote Sensing, Yamaguchi University, Japan Abstract Shoreline detection is essential for coastal monitoring amid accelerating climate change and intensified human activities. This study examines the coastal area of Klungkung, which experiences recurrent erosion and abrasion. We evaluated six spectral indices-NDVI, NDWI, Modified NDWI (MNDWI), Automated Water Extraction Index-shadow (AWEI-SH), AWEI-non-shadow (AWEI-NSH), and the Enhanced Water Index (EWI)-using Sentinel-2 imagery to delineate the shoreline. Thresholds were derived with Otsu method and a kernel density estimation (KDE) valley approach applied to manually selected samples. Shorelines from each index were validated against the Last Vegetation Line (LVL) surveyed with a Garmin GPS, and mean distances to the LVL were compared. Results (mean distance error, meters) show that NDWI (6.26 m) and NDVI (6.45 m) outperformed MNDWI (10.50 m) and EWI (9.70 m). For NDWI, KDE-based thresholding yielded higher accuracy than Otsu method (6.26 m vs. 10.23 m). The lower performance of MNDWI and EWI likely reflects the use of 20-m Sentinel-2 bands, which reduced delineation precision. NDVI performed on par with NDWI, plausibly because the validation shoreline is defined by the vegetation line. Overall, NDWI and NDVI-particularly when paired with appropriate thresholding-provide high-accuracy shoreline detection in this setting. Future work should test higher-resolution sensors and extend the approach to region-wide shoreline monitoring. Keywords: Coastal erosion- Last Vegetation Line (LVL)- Field validation (GPS)- Water indices- Shoreline Monitoring Share Link | Plain Format | Corresponding Author (Sakina Hasan)

Page 3 (data 61 to 90 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