International Journal of Remote Sensing and Earth Sciences (IJReSES)
Not a member yet
334 research outputs found
Sort by
SPATIAL MACHINE LEARNING FOR MONITORING TEA LEAVES AND CROP YIELD ESTIMATION USING SENTINEL-2 IMAGERY, (A Case of Gunung Mas Plantation, Bogor)
Full text linkIndonesia's tea production and export volume have fluctuated with a downward trend in the last five years, partly due to the increasingly competitive world tea quality. Crop yield estimation is part of the management of tea plucking, affecting tea quality and quantity. The constraint in estimating crop yields requires technology that can make the process more effective and efficient. Remote sensing technology and machine learning have been widely used in precision agriculture. Recently, big data processing, especially remote sensing data, machine learning, and deep learning have been carried out using a cloud computing platform. Therefore, we propose using GeoAI, a combination of Sentinel-2A imagery, machine learning, and Google Collaboratory, to predict ready for plucking tea leaves at optimal plucking time at Gunung Mas Plantation Bogor. We used selected bands of Sentinel-2A and extracted more features (i.e., NDVI) as a training set. Then we utilized the tea blocks boundary and tea plucking data to generate labels using Random Forest (RF) and Support Vector Machine (SVM). The classification results were further used to estimate the production of crop tea yield. The RF classifier is able to achieve overall accuracy at 51% and SVM at 54%. Meanwhile, accuracy at optimally aged tea blocks is able to achieve at 75.62% for RF and 52.88% for SVM. Thus, the SVM classifier is better in terms of overall accuracy. Meanwhile, the RF classifier is superior in predicting ready for plucking tea at optimally aged tea blocks
RESIDENTIAL CLASSIFICATION USING GEOBIA IN PART OF JAKARTA SUBURBAN AREA
Full text linkThe increasing of urban population followed by socioeconomic problems leads to emerging various number of researchs in urban area, especially in Jakarta Metropolitan Area. One of them are escalated tension-conflict due to rise of newly Gated Communities residential that sprawl across local residents (Kampung Kota). There is urgency to map all 3 types of residential (Kampung Kota, Perumnas, Cluster) through satellite imagery on a wide-scale. This study uses WorldView-2 imagery data recorded for 2020. The method used is an object-based method, namely GEOBIA using the eCognition Developer 64 software. The GEOBIA process is carried out through three stages, firstly the segmentation to separate residential blocks from surrounding land cover objects (bodies of water, vegetation, open land, non-residential built-up land) as well as exploring the variable values of each object, then sample-based classification using the SVM algorithm on Google Earth Engine application, and accuracy test to evaluate semantic and geometric accuracy levels. The results of the mapping are 3 classes of residential types followed by 4 classes of land cover. The overall accuracy of the three types of residential is 80% which means that the GEOBIA approach is able to show good performance
DIFFERENCES OF COASTALLINE CHANGES IN THE AREA AFFECTED BY LAND COVER CHANGES AND COASTAL GEOMORPHOLOGICAL SOUTH BALI 1995 - 2021
Full text linkThe South Bali coast is prone to abrasion due to its geographical position facing the Indian Ocean. High sea waves and currents in the south of Bali will erode beaches whose lithology and morphology are prone to abrasion. Land cover conditions that do not support coastal protection will also affect the high abrasion of the southern coast of Bali. This study aims to analyze the shoreline changes in South Bali from 1995-2021. The analytical method used is the Digital shoreline analysis system (DSAS), with data from Landsat 5 TM, Landsat 7 ETM+, Landsat 8 OLI/TIRS, and Sentinel 2A. The analysis results show that the area directly facing the waves is relatively high, with volcanic rock formations, and there is no mangrove as coastal protection. The lack of good coastal management shows the area with the highest abrasion. It was found in the western part of Tabanan Regency, eastern Gianyar, and southern Badung. Meanwhile, the average coastal accretion was relatively high in the neck of South Bali, in areas where the land cover was mangrove and adjacent to river mouths, which experienced much sedimentation
THE SPATIO-TEMPORAL DYNAMIC IN WATER NEAR PALABUHAN RATU COAL FIRE PLANT, SUKABUMI, WEST JAVA
Full text linkIndonesia Power PLTU Jabar 2 Palabuhanratu's activities have an impact on the quality of the surrounding river water and ocean. Monitoring the quality of the water thereafter became an important factor. Using remote sensing technologies, the spatial and temporal sea surface temperature and chlorophyll-a of water can be determined. This study aims to (1) ; (2) ; and (3) . River water and ocean quality, including physical parameters (total dissolved solids, electrical conductivity, and temperature) and chemical parameters (pH and salinity). (1) River water and saltwater quality in the Cimandiri Downstream River and Batu Bintang Beach are suitable with regard to physical parameters (total dissolved solids, electrical conductivity, and temperature) and chemical parameters (pH and salinity). (2) According to Health Ministerial Regulation No. 32/2017 and Government Regulation No.22/2021, the river and seawater quality in the Cimandiri Downstream River and Batu Bintang Beach for clean water is adequate in terms of physical characteristics (total dissolved solids, electrical conductivity, and temperature) and chemical parameters (pH and salinity). (3) The average Salinity from August through November of 2021 was 20.76 ppt, 16.25 ppt, 15.76 ppt, and 18.51 ppt. The average Salinity between April and July of 2022 was -2.74 ppt, 3.51 ppt, 0.51 ppt, and 4.25 ppt
ASSESSING THE POSSIBILITY OF LAND SUBSIDENCE DUE TO GEOTHERMAL PRODUCTION IN SARULLA GEOTHERMAL FIELD USING SENTINEL-1
No full textSarulla geothermal field is one of the largest geothermal fields in the world which has a 330 MW installed capacity. The field consists of three areas, namely Namora Langit (NIL)-1, NIL-2, and Silangkitang (SIL) which operated from 2017 and 2018. It is situated precisely at the Sarulla graben which is an active tectonic area composed of Quaternary Toba tuff and intermediate lava and extrusive felsic pyroclastic Toru. This study aims to see whether land subsidence may emerge in the Sarulla geothermal field and its environs in addition to determining whether the geothermal activity or anthropogenic is responsible for the deformation. We used the persistent scatterer (PS) interferometry synthetic aperture radar (InSAR) method to calculate the rate of subsidence in the area. 30 ascending images from Sentinel-1 were gathered from 5 January to 18 December 2020 with a separation of 12 days to run the analysis. The results demonstrate that Sarulla is undergoing subsidence occurring at NIL and SIL with a velocity of 0 to -32.9 mm/year. Although negative deformation occurs in the geothermal area, there is no solid evidence indicating geothermal fluid extraction is the cause of subsidence
COMPARISON OF THE MANGROVE FOREST MAPPING ALGORITHMS IN KELABAT BAY USING RANDOM FOREST AND SUPPORT VECTOR MACHINES
Full text linkOne of the tropical ecosystems is the mangrove forest, which thrives on protected coastlines such as bays, estuaries, lagoons, and rivers. These are usually found in the intertidal zone. Mangroves are a valuable natural resource because they stabilize coastlines, prevent erosion, retain sediment and nutrients, protect against storms, regulate floods and currents, sequester carbon, maintain water quality, serve as spawning grounds for fish and other marine life, and provide food For plankton. With over 59.8% of the total area of mangroves on the planet, Indonesia has some of the largest mangrove forests in the world. With the case study of Kelabat Bay in Bangka Regency and the Bangka Belitung Islands, this study compares the use of random forest (RF) techniques and support vector machines (SVM) for mapping mangrove forests. Landsat-9 imagery from 2022, taken via the Google Earth Engine (GEE), is the data source used in this study. This study utilizes computer programming and accuracy testing. As a result, RF detected mangrove forests covering an area of approximately 67 ha (OA: 0.932), while SVM detected mangrove forests covering an area of approximately 62 ha (OA: 0.912)
ENVIRONMENT QUALITY IDENTIFICATION USING LANDSAT-8 IN THE PERIOD OF COVID-19 LOCKDOWN IN JAKARTA
Full text linkThe quality of the urban environment during the Covid-19 lockdown became a concern because it was reported that it had improved but the spatial studies were still limited. Spatial information at regional scale can be extracted from Landsat-8 imagery. This study aims to spatially and temporally analyze environmental quality variables from Landsat-8 Imagery and compare environmental quality indices before, during and after the Covid-19 lockdown in Jakarta. Environmental quality variables extracted from Landsat-8 imagery are PM10, LST, NDVI, NDWI, NDMI. Radiometric correction and masking were applied to obtain Landsat-8 reflectance and radian values. PM10 concentrations were estimated using linear regression between station data and visible-near infrared (VNIR) reflectance band values. The variable land surface temperature (LST) is obtained from the brightness temperature band 10 extraction. NDVI, NDWI, and NDMI are extracted from the transformation of the reflectance band index. The environmental quality index is extracted from a weighted linear combination method where each variable has a weighted value of 50% PM10, 31% LST, 11% NDVI, 5% NDWI, and 3% NDMI. The results of the distribution of the environmental quality index before, during and after the Covid-19 lockdown show changes. Before the lockdown, some areas in Jakarta had a poor environmental quality index, while during the lockdown, only a few areas were still of poor quality, including the reclamation island and the Cilincing industrial area, North Jakarta. After the lockdown, the environmental quality index decreased again i.e. good, medium and bad categories but the distribution was not as wide as before the lockdown
UTILIZING REMOTE SENSING AND MACHINE LEARNING FOR ECOSYSTEM SERVICES MAPPING AT GUNUNG MAS TEA PLANTATION
Full text linkLand use and land cover changes are one of the main factors affecting ecosystems and the services they provide. Conversion from natural vegetation to agricultural and urban land can lead to the degradation of ecosystem services and loss of biodiversity. Puncak area, Bogor, which is a highland area, has become an area that is synonymous with tea plantations because it has an ecosystem that is suitable for being a tea plantation area. Gunung Mas tea plantation managed by PTPN VIII is one of the largest tea plantations and a contributor to foreign exchange in Indonesia. The tourism potential in the plantation and agricultural business sectors has a high selling value as a tourist object and attraction. The purpose of this study is to find out the distribution of ecosystem services for climate regulation, water flow and flood regulation, and ecotourism and cultural recreation services at Gunung Mas tea plantation which is displayed in the form of an Ecosystem Service Map. The land cover classification was extracted from the Sentinel 2A image, which was then scored based on expert judgment. The scoring results are then processed using the AHP Pairwise Comparison method. The results of the study show that the research area has very high climate regulation ecosystem services, very high water flow and flood regulation, and high cultural recreation and ecotourism ecosystem services. Keywords: AHP, Ecosystem Services, Land Use and Land Cover, Supervised classification, Tea Plantation
ENHANCING COASTAL DISASTER MITIGATION MEASURES: VEGETATION BASED FEASIBILITY STUDY FOR SOUTHERN JAVA, INDONESIA
Full text linkIndonesia is a country that is prone to disaster especially earthquake and volcanic eruption because its located in the ring of fire. The type of disasters can produce another type of disaster which is: tsunami. Â The nature of tsunamis that were hard to predict and arrive with little warning, Indonesians can minimize the effect of tsunami by creating coastal protection. In this study we look for the location to create the coastal forest as an enhancement of the mitigation effort. We conducted our study in the Pangandaran district as were a severe tsunami in the 2006 that caused more than 400 deaths. We conducted a suitability analysis to identify tsunami prone area based on the following criteria: should be had elevation <10m, slope gradient <2%, within proximity of 500m from coastline, and <100m from river and should be settlement or urban area. The creation of vulnerability map was using map algebra to calculate the weighted parameter from each class. Based our analysis using GIS analysis, the most vulnerable area in the Pangandaran district is the bay area, where we founded 1,419 acres of coastal area for which coastal forests could be planted to enhance protection against tsunamis.Â