Verified @upiyptk.ac.id
Civil Engineering
Geotechnical Engineering
Scopus Publications
Scholar Citations
Scholar h-index
Fathoni Usman, Nanda Nanda, and Josaphat Tetuko Sri Sumantyo
ARTS Publishing
Earthquakes can inflict significant damage to structures and infrastructures. This paper presents a machine learning model to predict ground surface deformation (GDS) induced by earthquake events. The data on historical GSD is extracted from radar product of Synthetic Aperture Radar (SAR) data of one-year over five magnitude earthquakes that occurred within 200 kilometers of the Kota Padang Regency, West Sumatra. Building topology data of its footprint area, distance from shoreline, elevation, and coordinate were incorporated as the main features in the dataset. The earthquake parameters were taken from the USGS earthquake data catalog. Four machine learning algorithms of Neural Network (NN), Random Forest (RF), k-Nearest Neighbors (kNN), and Gradient Boosting (GB) are applied. The GSD from the trained models is predicted and compared with the measured GSD from the SAR’s product. The performances of proposed algorithms are evaluated in terms of the statistical index. A new dataset from the earthquake event in March 2022 is used to predict the GSD and further test the performance of the trained models. Overall, the four machine learning algorithms have outstanding performance, with a coefficient determinant of more than 0.9. The kNN algorithm outperforms compared to others in delineating the GSD. The trained models gave deficient prediction performance on the new dataset with a correlation coefficient of 0.228 predicted by the RF algorithm. Additional earthquake datasets and more unique features will improve the performance of the machine learning algorithms.
Fathoni Usman, Nanda, Rita Nasmirayanti, and Josapath Tetuko Sri Sumantyo
EDP Sciences
This paper presents an effort to evaluate the generated digital elevation model (DEM) from an active sensor onboard satellite of Sentinel-1A and from aerial photos taken using an unmanned aerial vehicle (UAV). The objective is to compare the quality of generated DEM and review the processes for disaster mitigation and prevention plans application. The radar data acquisition used in this study is pair of SLC-type radar data. The interferogram is processed from the coherence and the phase of complex data of the pair radar imageries. Meanwhile, aerial photography was taken within the smaller urban area in Padang City. The photogrammetry process to generate the DEM was conducted using the structure from motion (SfM) technique. The quality and procedures are reviewed by comparing the DEM products with other publicly available DEM data from DEMNAS, SRTM, and AW3D. This study found that generating the DEM from Sentinel-1 interferometry SAR is a challenging process. The product is unmatched and has lower quality compared to available DEM data due to several identified factors. In contrast, high computational cost photogrammetry produced good quality DEM if sufficient ground control points (GCP) were set.
K Jayasinghe, V Anggraini, A Syamsir, and Nanda
IOP Publishing
Abstract The deep soil with a relatively poor compressive strength has been an issue for the researchers and constructors for years since the hardships faced by them when trying to construct heavy structures on top of them. It is found that weak soils like those can be strengthened by adding different additives. Cement is commonly used for the above purpose but, since it’s expensive to use alone, cement mixed with fly ash was tested with different soils to strengthen them. The aim of the research was to find out the increase/decrease of strength when two different cement and fly ash mixtures were mixed with three different types of soils common in Malaysia in different proportions and to find the optimum percentages of each mixture to be mixed with each soil to obtain a desired strength. The Modified Standard Proctor test and the Unconfined Compressive Strength (UCS) tests were carried to study the behaviour and strength of the soils when mixed with the above additives.
Fathoni Usman and Nanda
IEEE
This paper presents a study on the surface deformation of Padang City area induced by over Mw 5.0 earthquake measured by using remote sensing of active sensor radar data. Padang City is an area with over 909 thousand and population density per sq. km of 1,309 within 694 km2. With its location facing the Andaman Sea, where the subduction zone is stretched, Padang City is highly vulnerable to natural hazards induced by earthquakes. This study used pairs of radar data from Sentinel-1 satellites selected based on relatively close to the post-earthquake events. The distances of the epicenter of the earthquakes are within 200 km from the study area. The short baseline technique analyzed the radiometric information on phase and amplitude in the single look complex (SLC) type of radar data. A correlation study has been used to determine the vulnerable area prone to natural hazards induced by earthquakes. From this study map of the vulnerable area that is responsive to the earthquake, events are delineated. There are 49.5% of the building blocks is in the medium vulnerability. The lowest and the highest vulnerability are less than 2%.