Jurnal Penginderaan Jauh dan Pengolahan Data Citra Digital

Flood Prone Area Analysis using Landsat 9 and MCDA Method in Bekasi Regency

2025-07-31T13:52:11+07:00

Mapping reveals Bekasi (total 126,266.77 ha) has four flood vulnerability classes. Most land (68.5% or 86,454.87 ha) is Medium risk, primarily in transitional zones prone to inundation from extreme rain or land-use changes. High-risk areas cover 21,831.52 ha, while Low-risk zones span 17,980.39 ha. This distribution shows the regency is predominantly moderate-to-highly vulnerable, driven by lowland topography and proximity to rivers. As West Java's most flood-damaged region in the past decade, a study integrated Landsat 9 imagery and MCDA to map flood risk using five parameters (land cover, elevation, rainfall, soil, river buffers). Validated with BNPB historical data, the model confirmed northern areas (Tambun, Muara Gembong, Babelan) as highest risk due to low elevation (<10 m), alluvial soil, and frequent flooding.

The Use of Active Remote Sensing Data and Adaptive Threshold Method for Analysing Oil Spill in West Side of Java Sea

2025-07-31T14:02:04+07:00

Oil spill phenomena, particularly in the West Side of Java Sea, occur due to the dense oil industry and maritime activities causing potential vulnerability to oil pollution. Rapid detection of oil spill distribution needs to be conducted to minimize the resulting impacts. By developing an early detection method for oil spills in the Western Java Sea using Synthetic Aperture Radar (SAR) technology from Sentinel-1A Satellite using SNAP software with an Adaptive Threshold approach. The detection method is based on the principle that oil causes the sea surface to become calm, resulting in a drastic reduction in radar wave reflection values. Research results show oil spill detection in June 2023 with an area reaching 73,823 km² and an accuracy level of 93,75% based on confusion matrix validation. This research also integrates windfield analysis to support radar image interpretation, with wind speed estimation results of 1-12 m/s and dominant direction toward northwest to north. Windfield data was validated using BMKG reanalysis data and Copernicus Marine My Ocean Pro. The developed method is superior to optical imagery in terms of detection visualization and object classification capability within the spill area. The findings of this research provide important contributions to the development of effective monitoring and response systems to protect marine ecosystems, and can serve as a basis for planning environmental impact mitigation from oil spills in the region.

High-Resolution Rooftop Solar PV Potential Assessment Using an Open-Source Remote Sensing Data and Cloud Computing: A Case Study in Padang Utara Subdistrict

2025-11-05T18:11:48+07:00

High-resolution assessment of rooftop solar photovoltaic (PV) potential in urban areas is often constrained by the high cost of commercial data like LiDAR and the computational intensity of analyzing complex geometries. This study develops and applies a novel, fully open-source remote sensing workflow that leverages cloud computing to overcome these limitations. The methodology integrates open-source building and canopy height data to generate a Digital Surface Model (DSM) and introduces a novel Urban Geometric Correction Factor (UGCF). The UGCF combines a multi-temporal Shading Factor, calculated efficiently in Google Earth Engine (GEE), with a Sky View Factor (SVF) to realistically model solar irradiance on individual rooftops. Applied to the complex urban morphology of Padang Utara, Indonesia, the workflow identified significant potential, with 47.17% of viable rooftops classified as 'Optimal' or 'Very Optimal', with a radiation value range of 758.8–848.63 kWh/m²/year. Spatially, the highest potential is concentrated in lower-profile residential areas, not necessarily on the tallest buildings, Critically revealed that internal roof shading is a dominant limiting factor for large buildings. This research presents a cost-effective and replicable methodology, contributing a significant tool for detailed urban solar potential assessment and supporting data-driven sustainable energy planning.

Landslide Potential Detection Model Using rdNDVI and the GEE Platform in Leuwiliang District, Bogor

2025-11-03T12:22:25+07:00

Landslide is among the most frequent natural disasters in Indonesia, especially in regions characterized by steep slopes and high rainfall. This study analyzes the potential for landslides in Leuwiliang District, Bogor Regency, using the Relative Difference Normalized Difference Vegetation Index (rdNDVI) and the Google Earth Engine (GEE) platform. Sentinel-2A imagery with a 10-meter spatial resolution was used to calculate rdNDVI values from pre- and post-event periods (2020–2023). Slope data derived from Digital Elevation Models (DEM) were integrated to identify areas exceeding a 10% slope threshold, categorized as high-risk zones. The rdNDVI analysis revealed that Karehkel Village had the largest landslide-prone area (40.06 ha), while Leuwiliang Village had the smallest (20.88 ha). Validation using field survey data in 2025 showed an accuracy of 78% for a slope threshold of 10%. The resulting WebGIS system provides interactive visualization for disaster risk mapping and supports decision-making for local mitigation planning. The combination of rdNDVI and GEE demonstrates the potential of cloud-based remote sensing for rapid and scalable landslide detection. Future work should include additional parameters such as rainfall intensity and soil moisture to enhance prediction accuracy.

Air Temperature-based Spatial Modeling of Remote Sensing Data Using Machine Learning Approaches: a Systematic Literature Review

2025-09-11T06:07:03+07:00

This study presents a systematic review of spatial air temperature modeling based on remote sensing data using machine learning approaches during the period 2016–2025. Using the PRISMA framework, we conducted literature searches in Google Scholar (998 articles) and Scopus (489 articles).. After merging the datasets, removing duplicates, and applying inclusion–exclusion criteria, 12 articles were retained for in-depth analysis. The findings indicate a marked increase in publications since 2021, reflecting growing global interest in integrating remote sensing and machine learning for air temperature estimation. Ensemble algorithms such as Random Forest and XGBoost dominate due to their balance of accuracy and computational efficiency, while temporal deep learning approaches such as LSTM and TCN are emerging as powerful tools for capturing complex atmospheric dynamics. Among remote sensing predictors, Land Surface Temperature (LST) is the most frequently used, often complemented by NDVI, albedo, and elevation to improve spatial accuracy. Geographical context strongly influences methodological performance. XGBoost proves effective in heterogeneous urban areas, Random Forest performs well in mountainous regions, and artificial neural networks demonstrate higher adaptability in extreme environments such as the Greenland ice sheet. Nonetheless, limited ground-based observations and sparse station networks remain key challenges, particularly across tropical and archipelagic regions. This review identifies three major directions for future research: (1) expanding studies to underrepresented tropical regions, (2) leveraging temporal deep learning methods for detecting extreme events, and (3) integrating multisensor data with innovative validation strategies to enhance the robustness and reliability of air temperature modeling.