Doctor of Philosophy, Computer Science, Faculty of Computer Science, Universitas Indonesia
Master of Technology, Remote Sensing & GIS, Indian Institute of Remote Sensing
Bachelor of Engineering, Geodetic Engineering, Institute of Technology Bandung
RESEARCH INTERESTS
GIS, Remote Sensing, Geodesy, Interpolation, Geostatistics, DEM, SAR
36
Scopus Publications
Scopus Publications
Synthetic Aperture Radar Technology for Policies Contributing to Natural Disaster Mitigation and Food Security Issues in Indonesia Nugraheni Setyaningrum, Andie Setiyoko, Galih Prasetya Dinanta, Dandy Aditya Novresiandi, Arief Darmawan, Edy Trihatmoko, Joko Widodo, Budhi Gustiandi Geomatics and Environmental Engineering, 2025 Natural disasters and food security challenges frequently impact many countries, including Indonesia. Over the past decade, the development of remote-sensing technology (particularly, synthetic aperture radar [SAR]) has garnered the attention of policymakers. Its ability to penetrate clouds and rain and data-acquisition techniques unaffected by time (day or night) provide advantages for describing the equatorial region. The application of SAR technology in Indonesia has progressed significantly. However, an important question has arisen: to what extent is the impact of using SAR data? Most SAR data in Indonesia is still limited to academic circles. To address this question comprehensively, this research examines the extent to which studies utilize SAR data – particularly, in global publications. The scope of this research was limited to articles published between 2013 and early 2025 that utilized SAR as the primary or secondary methods. The gap between the numerous studies on SAR technology and its significant impact on various government policies was quantitatively analyzed. In conclusion, this research underscored the need for a more nuanced approach toward integrating SAR technology into policymaking in Indonesia. This study serves as a critical reflection on the current state of SAR research in Indonesia, calling for a more concerted effort to bridge the gap between technical studies and actionable policy formulation.
Haze Correlation Analysis in Determining Haze Factor for Haze Removal in SPOT 6 and SPOT 7 Images D. Heri Y. Sulyantara, Dianovita, Kurnia Ulfa, Musyarofah, Novie Indriasari, Mulia Inda Rahayu, Andie Setiyoko, Orbita Roswintiarti, Sastra Kusuma Wijaya, Abdul Haris 2025 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology Icares 2025 Conference Proceedings, 2025 Multispectral images acquired by optical remote sensing satellite in tropical areas, like Indonesia, are frequently affected by some distortions as a result of the presence of clouds and thin clouds or haziness. These distortions cause a decrease in image quality and the accuracy of image interpretation. Researchers have developed various methodologies to detect and remove hazed images achieved by optical remote sensing satellite. Nevertheless, the method development of haze elimination remains a challenge in improving the good aspect of multispectral optical remote sensing images, especially in providing cloud-free mosaic images. In this research, a haze removal technique on SPOT 6 and SPOT 7 images using a haze index algorithm was introduced. The algorithm is based on the reflectance values of the blue and red channels on SPOT 6 and SPOT 7 images. This paper tests the correlation of hazy images with a clean reference image to look for the most optimal haze factor coefficient value to remove haze in SPOT 6 and SPOT 7 images. In this haze removal process, a haze index algorithm and predetermined haze limit values were applied. Based on empirical discovery in the research, it is concluded that this correlation test obtains a haze factor coefficient that can provide optimal results in the haze removal process using the haze index algorithm for SPOT 6 and SPOT 7 images.
Dynamic Geo-Visualization of Urban Land Subsidence and Land Cover Data Using PS-InSAR and Google Earth Engine (GEE) for Spatial Planning Assessment Joko Widodo, Edy Trihatmoko, Muhammad Rokhis Khomarudin, Mohammad Ardha, Udhi Catur Nugroho, Nugraheni Setyaningrum, Galih Prasetya Dinanta, Rahmat Arief, Andie Setiyoko, Dandy Aditya Novresiandi, Rendi Handika, Muhammad Priyatna, Shinichi Sobue, Dwi Sarah, Wawan Hermawan Urban Science, 2024 The North Java coastal area, known as the Pantura region, is experiencing significant land subsidence, with certain areas sinking up to 10 cm per year. Pekalongan is among the most affected, with subsidence rates between 10 and 19 cm annually, mainly due to groundwater extraction, sediment compaction, and coastal erosion. Other coastal cities, like Semarang and Demak, show rates averaging 4 to 10 cm per year. This rapid subsidence is due to favorable geological conditions and ongoing urban development. This study investigates land subsidence in Pekalongan using the PS-InSAR method and dynamic visualization of time-series land cover data. PS-InSAR was applied to 45 scenes from ALOS-2 PALSAR-2 to monitor subsidence from 2014 to 2022. The results were validated with in situ subsidence benchmarks. Urban development dynamics were analyzed through land cover and land use change (LULC) and population density over the same period, using the GLC_FCS30D dataset in the GEE to detect non-natural LULC. The PS-InSAR results indicated that over 60.9% of investigation points experienced subsidence, up to 100 cm between 2014 and 2022. Ground validation showed an 83% agreement with PS-InSAR results. A statistical analysis of LULC from 2014 to 2022 did not show significant built-up area development, but the extension of salt marshes and water bodies indicated subsidence expansion. The population density reached 6873 people per square km by 2022, causing extensive groundwater use for domestic and industrial purposes, further aggravating the subsidence.
Enhancing Remote Sensing Image Quality through Data Fusion and Synthetic Aperture Radar (SAR): A Comparative Analysis of CNN, Lightweight ConvNet, and VGG16 Models Desynike Puspa Anggreyni, Indriatmoko, Aniati Murni Arymurthy, Andie Setiyoko Jurnal Online Informatika, 2024 Remote sensing technology benefits many parties, especially for carrying out land surveillance with comprehensive coverage without needing to move the equipment close to photograph the area. However, this technology needs to improve: the image quality depends on natural conditions, so objects such as fog, clouds, and smoke can interfere with the image results. This study uses data fusion techniques to enhance the quality of remote-sensing images affected by natural conditions. The method involves using Synthetic Aperture Radar (SAR) to combine adjacent satellite images from different viewpoints, thereby improving image coverage. Three image classification models were evaluated to process the fused data: Convolutional Neural Network (CNN), Lightweight ConvNet, and Visual Geometry Group 16 (VGG16). The results indicate that all three models achieve similar accuracy and execution speed, namely 0.925, with VGG16 demonstrating a slight superiority over the others, namely 0.90.
UNet-Based Land Cover Segmentation With Ensembled Encoder for Fine Details Enhancement Steven Christ Pinantyo, Muhammad Yusuf Kardawi, Aniati Murni Arymurthy, Andie Setiyoko, Muhammad Ridha Adhari 2024 Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems Scis and Isis 2024, 2024 Satellite technology has made it possible to capture Earth's surface with very high accuracy in the centimeter range. This is crucial for remote sensing tasks, particularly land use mapping, which is frequently used for urban planning and tracking land-use changes. However, processing remote sensing data is quite challenging, where several objects have similarities in color, shape, or texture, which can impact how the model separates objects into corresponding labels. In addition, due to extensive spatial remote sensing coverage, class imbalance becomes a significant issue, which impacts model decisions when classifying the objects. To overcome this issue, we proposed a modified U-Net model using pre-trained as the backbone for the encoder to reduce overfitting and help the model extract better information from pre-trained weights. In addition, the model will be trained using the joint loss consisting of dice loss adapted for multiclass problems to balance recall and precision in classification and focal loss, an improved cross-entropy specifically for class imbalance tasks. Then, we select three models as weak learners in an ensemble architecture that uses a majority voting strategy. Our experiments show the best results with Dice and mIoU of 86.71% and 77.25%, respectively, for the GID-5 dataset and 76.14% and 63.68% for the WHDLD dataset.
Systematic Geometric Correction Method of Stereo Image Data Proposes for the Next Indonesian Satellite Musyarofah, Rise Hapshary Surayuda, Dinari Nikken Sulastrie Sirin, Ahmad Maryanto, Andie Setiyoko, Zylshal, Sartika, Athar Abdurrahman Bayanuddin 2023 IEEE Asia Pacific Conference on Geoscience Electronics and Remote Sensing Technology Global Challenges in Geoscience Electronics and Remote Sensing Future Directions in City Land and Ocean Sustainable Development Agers 2023, 2023
Palm Trees Counting Using MobileNet Convolutional Neural Network in Very High-Resolution Satellite Images Yudhi Prabowo, Kuncoro Adi Pradono, Qonita Amriyah, Fadillah Halim Rasyidy, Ita Carolita, Andie Setiyoko, Danang Surya Candra, Musyarofah, Kurnia Ulfa, Yohanes Fridolin Hestrio 2022 IEEE Asia Pacific Conference on Geoscience Electronics and Remote Sensing Technology Understanding the Interaction of Land Ocean and Atmosphere Smart City and Disaster Mitigation for Regional Resilience Agers 2022 Proceeding, 2022