cover
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kota adm. jakarta timur,
Dki jakarta
INDONESIA
International Journal of Remote Sensing and Earth Sciences (IJReSES)
ISSN : 02166739     EISSN : 2549516X     DOI : -
Core Subject : Science,
International Journal of Remote Sensing and Earth Sciences (IJReSES) is expected to enrich the serial publications on earth sciences, in general, and remote sensing in particular, not only in Indonesia and Asian countries, but also worldwide. This journal is intended, among others, to complement information on Remote Sensing and Earth Sciences, and also encourage young scientists in Indonesia and Asian countries to contribute their research results. This journal published by LAPAN.
Arjuna Subject : -
Articles 11 Documents
Search results for , issue "Vol 19, No.1 (2022)" : 11 Documents clear
COMPARISON OF MACHINE LEARNING MODELS FOR LAND COVER CLASSIFICATION Bambang Trisasongko; Dyah Panuju; Nur Etika Karyati; Rizqi I'anatus Sholihah
International Journal of Remote Sensing and Earth Sciences (IJReSES) Vol 19, No.1 (2022)
Publisher : Ikatan Geografi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30536/j.ijreses.2022.v19.a3786

Abstract

Land cover data remain one of crucial information for public use.  With rapid human-associated land alteration, this information needs to be frequently updated. Remotely-sensed data provide the best option to construct land cover maps with numerous methods available in the literature. While disagreement exists to select the robust one, further exploration should be made to extend the understanding on the behavior of machine learners, in particular, for classification problems. This article discusses performance of pixel-based machine learning algorithms, frequently used in research or implementation. Five popular algorithms were evaluated to distinguish five rural land cover classes, i.e. built-ups, crops, mixed garden, oil palm plantations and rubber estates, from Sentinel-2 data. This research found that the benchmark, classification and regression tree, was unable to differentiate woody vegetation, although the overall accuracy was sufficiently moderate. This suggested that overall accuracy cannot be seen as the only measure for assessing the quality of the thematic output. Meanwhile, support vector machines and random forest competed to yield the highest accuracy and class detection capability, although the latter was in favor with 98% accuracy level. A newly developed model, like extreme gradient boosting, achieved a similar level of accuracy. This research implies that modern machine learning approaches would be invaluable for land cover classification; hence, access to these modeling toolkits is substantial.
ANALYSIS OF CLASSIFICATION METHODS FOR MAPPING SHALLOW WATER HABITATS USING SPOT-7 SATELLITE IMAGERY IN NUSA LEMBONGAN ISLAND, BALI Kuncoro Teguh Setiawan; Gathot Winarso; Andi Ibrahim; Anang Dwi Purwanto; I Made Parsa
International Journal of Remote Sensing and Earth Sciences (IJReSES) Vol 19, No.1 (2022)
Publisher : Ikatan Geografi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30536/j.ijreses.2022.v19.a3748

Abstract

Shallow water habitat maps are crucial for the sustainable management purposes of marine resources. The use of a better digital classification method can provide shallow water habitat maps with the best accuracy rate that is able to indicate actual conditions. Experts use the object-based classification method as an alternative to the pixel-based method. However, the pixel-based classification method continues to be relied upon by experts in obtaining benthic habitat conditions in shallow water. This study aims to analyze the classification results and examine the accuracy rate of shallow-water habitats distribution using SPOT-7 satellite imagery in Nusa Lembongan Island, Bali. Water column correction by Lyzenga 2006 was opted, while object-based and pixel-based classification was used in this study. The benthic habitat classification scheme uses four classes: substrate, seagrass, macroalgae, and coral. The results show different accuracy is obtained between pixel-based classification with maximum likelihood models and object-based classification with decision tree models. Mapping benthic habitats in Nusa Lembongan, Bali, with object-based classification and decision tree models, has higher accuracy than the other with 68%.
ESTIMATION OF OIL PALM PLANT PRODUCTIVITY USING SENTINEL-2A IMAGERY AT CIKASUNGKA PLANATION PTPN VIII, BOGOR, WEST JAVA Afifah Nur Rahmasari; Supriatna .; Andry Rustanto
International Journal of Remote Sensing and Earth Sciences (IJReSES) Vol 19, No.1 (2022)
Publisher : Ikatan Geografi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30536/j.ijreses.2022.v19.a3775

Abstract

Palm oil is one of the commodities that is growing well in Indonesia with a high commercial value which makes the demand for processed palm oil products increase, it is necessary to have data and technology to estimate the productivity of oil palm plantations more efficiently. Remote sensing technology is one of the technologies that can be used to decision problems spatially and accurately, efficiently, and dynamically. One of them is remote sensing using Sentinel-2A imagery. This study aims to analyze the distribution and the accuracy of the NDVI and ARVI algorithms for the estimation of oil palm productivity at the Cikasungka Plantation PTPN VIII. The estimated productivity of oil palm plantations at Cikasungka Plantation varies in each block with an estimated productivity of oil palm plantations of 35,061 Kg/Ha/Month using the algorithm NDVI and ARVI algorithm is 35,431 Kg/Ha/Month. Oil palm productivity was regressed by vegetation index and plant age to generate a model. Based on modeling with these two algorithms, the accuracy of the ARVI algorithm model has a lower RMSE value than NDVI, so it can be said that it is better in estimation of oil palm plant productivity  at the Cikasungka Plantation.
LAND USE/COVER CHANGE ON POTENTIAL LOSS OF SUMATRAN TIGERS IN KERINCI SEBLAT NATIONAL PARK BASED ON REMOTE SENSING DATA Mohammad Ardha; Muhammad Rokhis Khomarudin; Gatot Nugroho
International Journal of Remote Sensing and Earth Sciences (IJReSES) Vol 19, No.1 (2022)
Publisher : Ikatan Geografi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30536/j.ijreses.2022.v19.a3782

Abstract

The Sumatran tiger is an animal whose life is threatened due to land use changes and human activities. This study described the correlations between land cover/use change and the potential loss of Sumatran tigers in Kerinci Seblat National Park (KSNP) based on remote sensing data. Remote sensing technology was used due to the good historical data, and it can be used for land cover change analysis. The results of the land change analysis can be used to the analysis of the changes in the suitability level of the Sumatran tiger habitat. The analysis of land change in 2000 and 2020 with the random forest classification method and changes in the level of suitability of the Sumatran Tiger habitat has been carried out. The results of the analysis of land cover/use changes showed a very significant reduction in the area of primary forest, namely 282.58 km2, while the increase in the area of plantations and secondary forests was 186.52 km2 and 101.68 km2. This change affects the suitability level of the Sumatran tiger habitat from a very suitable level decreased from 164.42 km2 to suitable and not suitable. The declining suitability level class indicated the potential loss of Sumatran tigers in the Kerinci Seblat National Park. The increasing of plantation and settlement areas will increase the activity of humans. The conflict of human activity with Sumatran tigers’ life will impact the loss of Sumatran Tigers in KSNP
COMPARISON OF DATA ASSIMILATION USING SURFACE OBSERVATION, UPPER AIR, AND SATELLITE RADIATION DATA ON RAINFALL PREDICTION IN THE JAMBI REGION (CASE STUDY OF HEAVY RAIN OCTOBER 20TH, 2020) Saveira Fairuz Ismah; Nidya Pradita; Danurahni Aryashta; Gandhi Mahendra
International Journal of Remote Sensing and Earth Sciences (IJReSES) Vol 19, No.1 (2022)
Publisher : Ikatan Geografi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30536/j.ijreses.2022.v19.a3758

Abstract

Weather Research and Forecasting (WRF) is a mesoscale numerical weather prediction model that can provide good rainfall prediction information. The accuracy of the initial conditions and the accuracy of the parameterization scheme used in the WRF model affect the quality of the resulting rainfall prediction. Therefore it is necessary to assimilate to optimize the accuracy of the initial conditions in the model using the Three Dimensional Variational (3DVAR) assimilation technique. The purpose of this study was to determine the effect of applying the 3DVAR assimilation technique with the surface, upper air, and satellite radiation observations in predicting the occurrence of heavy rain on October 20th, 2020, in the Jambi region by first conducting a parameterization test of the cumulus and microphysical schemes. In this study, four experimental schemes were used, namely no assimilation (NON), observation data assimilation (OBS), satellite radiation data assimilation (SAT), and satellite radiation and observation data assimilation (BOTH). Each experimental model result was then verified statistically and spatially to determine the effect of the applied data assimilation. The results of this study indicate that the combination of Grell-3D and Thompson scheme shows the best performance in predicting rainfall. Then based on the spatial analysis of the SAT experiment, it is known that it can improve the model's initial conditions on the temperature and pressure parameters. Meanwhile, based on statistical verification, the SAT experiment improved the accuracy of rainfall predictions with a better forecast skill score than other experiments tested.
CARBON MONOXIDE SPATIAL PATTERN BASED ON VEHICLE VOLUME DISTRIBUTION IN TANGERANG CITY Arfani Priyambodo; Adi Wibowo; M. Dadang Basuki
International Journal of Remote Sensing and Earth Sciences (IJReSES) Vol 19, No.1 (2022)
Publisher : Ikatan Geografi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30536/j.ijreses.2022.v19.a3789

Abstract

Air pollution conditions in urban areas continue to increase due to the volume of vehicles every year. This volume increases sources of pollution such as motor vehicles which account for 60-70% of pollution. This study aims to analyze the distribution of vehicle volume and spatial pattern of CO in Tangerang City and see the relationship. The analysis used is descriptive and statistical spatial analysis. The results showed the distribution of vehicle volume in the morning ranged from <800-1600 vehicles on primary collector roads, while in the afternoon, there were 800 to >2000 vehicles on primary arterial roads. The spatial pattern of CO that formed on primary and collector arterial roads with residential land uses, industrial areas, and warehouses, then the CO concentration tends to be high. Meanwhile, other primary collector roads have low to moderate CO concentrations. The Spearman test and linear regression results showed a significant effect between vehicle volume on the Tangerang City CO pattern, with a strength value of 0.689 and an R Square of 0.476.
BIOMASS ESTIMATION MODEL AND CARBON DIOXIDE SEQUESTRATION FOR MANGROVE FOREST USING SENTINEL-2 IN BENOA BAY, BALI A. A. Md. Ananda Putra Suardana; Nanin Anggraini; Kholifatul Aziz; Muhammad Rizki Nandika; Azura Ulfa; Agung Dwi Wijaya; Abd. Rahman As-syakur; Gathot Winarso; Wiji Prasetio; Ratih Dewanti
International Journal of Remote Sensing and Earth Sciences (IJReSES) Vol 19, No.1 (2022)
Publisher : Ikatan Geografi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30536/j.ijreses.2022.v19.a3797

Abstract

Remote sensing technology can be used to find out the potential of mangrove forests information. One of the potentials is to be able to absorb three times more CO2 than other forests. CO2 absorbed during the photosynthesis process, produces organic compounds that are stored in the mangrove forest biomass. Utilization of remote sensing technology is able to detect mangrove forest biomass using the density level of the vegetation index. This study focuses on determining the best AGB model based on the vegetation index and the ability of mangrove forests to absorb CO2. This research was conducted in Benoa Bay, Bali Province, Indonesia. The satellite image used is Sentinel-2. Classification of mangroves and non-mangroves using a multivariate random forest algorithm. Furthermore, the mangrove forest biomass model using a semi-empirical approach, while the estimation of CO2 sequestration using allometric equations. Mean Absolute Error (MAE) is used to evaluate the validation of the model results. The classification results showed that the detected area of Benoa Bay mangrove forest reached 1134 ha (OA: 0.98, kappa: 0.95). The best AGB estimation result is the DVI-based AGB model (MAE: 23,525) with a value range of 0 to 468.38 Mg/ha. DVI-based AGB derivatives are BGB with a value range of 0 to 79.425 Mg/ha, TAB with a value range of 0 to 547.8 Mg/ha, TCS with a value range of 0 to 257.47 Mg/ha, and ACS with a value range of 0 to 944.912 Mg/ha.
LOCAL CLIMATE ZONE (LCZ) IN BANDAR LAMPUNG CITY Farhan Anfasa Putra; Adi Wibowo; Iqbal Putut Ash Sidiq
International Journal of Remote Sensing and Earth Sciences (IJReSES) Vol 19, No.1 (2022)
Publisher : Ikatan Geografi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30536/j.ijreses.2022.v19.a3790

Abstract

The rapid growth of the population in Bandar Lampung has led to a change in the land's usage from vegetation to built-up land. In the end, less vegetation will be present, which also results in higher temperatures in urban. This study intends to identify the state of the city's building density, vegetation density, land surface temperature, and Local Climate Zone (LCZ) in Bandar Lampung. Local Climate Zone (LCZ) maps can provide information on the physical structure of urban planning based on building density, and vegetation density, and are useful in the mitigation and public monitoring of increasing urban temperatures. The data was collected using images from Landsat 8 OLI/TIRS and high-resolution satellite imagery from Maxar Technologies downloaded using Google Earth Pro. Additionally, a field survey was used to measure the air temperature. The LCZ Generator WUDAPT is used to process LCZ data. The findings revealed that Bandar Lampung was dominated by medium-density buildings in the city's canter and medium-density vegetation in its western. The highest LST in residential areas is 35°C, while forest areas have the lowest LST at 15,68°C. There are 14 LCZ classifications, covering seven building types and seven land cover types. The dense tree zone has the highest vegetation density, the open low-rise zone has the highest land surface temperature, and the compact low-rise zone has the highest building density.
SPATIAL DISTRIBUTION OF GREEN OPEN SPACES AND RELATION TO LAND SURFACE TEMPERATURE IN BANDAR LAMPUNG CITY Rizky Cahaya Meikatama; Adi Wibowo; Iqbal Putut Ash Sidiq
International Journal of Remote Sensing and Earth Sciences (IJReSES) Vol 19, No.1 (2022)
Publisher : Ikatan Geografi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30536/j.ijreses.2022.v19.a3795

Abstract

Bandar Lampung City, the capital city of Lampung Province in Indonesia, became the number three city on the island of Sumatra, with enormous population growth from 2000 to 2015. Population growth resulted in increasing built-up land affecting several aspects, one of which was the increase in surface temperature in urban areas. This study aims to determine changes in green open space, land surface temperature (LST), and the spatial pattern of changes in Bandar Lampung City. Data processing uses Landsat 8 imagery for green space and Google Earth Engine for LST. The results of this study indicate that the distribution of changes in green open space the east to west experienced a change in green open space to non-green open space which resulted in an increase in temperature in the east, southeast, and west, from 25-30oC the temperature increased to >30oC. The change in green open space in the west and some areas found that a change from non-RTH to a public or private green open space resulted in a decrease in temperature starting from 25-30oC decreased to 20-25oC. The spatial pattern of changes in green open space in Bandar Lampung City has a clustered pattern in the west and east of the area following the topography (100-500 masl). At the same time, the land surface temperature pattern (LST) in Bandar Lampung City has a clustered pattern at temperatures <20oC, 20-25oC (found at an altitude of 100-500 masl), and >30oC (following an altitude of 25-100 masl) while for temperatures 25-30oC has a scattered pattern (following an altitude of 25-100 masl) in Bandar Lampung City.
Front Pages IJReSES Vol. 19, No. 1 (2022) Journal Manager
International Journal of Remote Sensing and Earth Sciences (IJReSES) Vol 19, No.1 (2022)
Publisher : Ikatan Geografi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30536/j.ijreses.2022.v19.a3859

Abstract

Front Pages IJReSES Vol. 19, No. 1 (2022)

Page 1 of 2 | Total Record : 11