Dony Kushardono

Scopus Publications

Remote Sensing-Based Urban Environmental Quality Indicators: A Review
Nurwita Mustika Sari, Dwi Nowo Martono, Raldi Hendrotoro Seputro Koestoer, and Dony Kushardono
Pandawa Institute
Most of the global population lives in urban areas, which also serve as hubs of economy, industry, and government activities. Various factors that affect the quality of cities have been studied in different locations. This article reviews various papers that examine environmental quality indicators in urban areas that can be extracted from remote sensing data. The first aspect is vegetation cover, which is known from the vegetation index normalized difference vegetation index (NVDI), and the second aspect is surface temperature, which is known from land surface temperature (LST). In this work, urban environmental conditions in various countries are compared with urban conditions in Indonesia based on these indicators. It is found that NDVI and LST are indicators from remote sensing that are widely used to analyze urban environmental conditions. The vegetation index has a negative correlation with surface temperature. High surface temperature creates discomfort in urban quality of life and brings mental stress to residents living in those areas. Based on bibliometric analysis and network map, it is known that there are 30 most relevant words or terms to the keywords “urban remote sensing” and “remote sensing environment indicator” with the highest frequency of occurrence and relevance. This study can serve as input for the government as policymakers and urban planners to formulate spatial planning policies oriented towards sustainability and to research current topics related and relevant to remote sensing-based urban environmental quality indicators.

Sentinel-2A multispectral image analysis for seagrass mapping in Bintan's shallow water ecosystem: A case study of Teluk Bakau, Malang Rapat, and Berakit villages
Pragunanti Turissa, Bisman Nababan, Vincentius P. Siregar, Dony Kushardono, Hawis H. Madduppa, Muhammad R. Nandika, and Septiyan Firmansyah
Elsevier BV

Rice fields classification through spectral-temporal data fusion during the rainy and dry seasons using Sentinel-2 optical images in Subang Regency, West Java, Indonesia
Kustiyo Kustiyo, Rokhmatuloh Rokhmatuloh, Adhi Harmoko Saputro, and Dony Kushardono
Springer Science and Business Media LLC

Paddy Fields Classification Using A 2-Dimensional Scatterplot of Growth Phenological Features from Sentinel-1 Data
Kustiyo Kustiyo, Rokhmatuloh Rokhmatuloh, Adhi Harmoko Saputro, Dony Kushardono, Ratih Dewanti Dimyati, and Lilik Budi Prasetyo
Institut Pertanian Bogor
Rice plays an essential role in ensuring the food security of Indonesia. Hence, rice (paddy) field monitoring using synthetic aperture radar (SAR) satellite data is critical, particularly in tropical regions. This study presents a new algorithm to detect paddy fields in Subang, West Java, using Sentinel-1 SAR with a 12-day revisit acquisition. Three temporal phenological features of paddy growth were used, namely, the minimum and maximum backscatter, as well as their differences. Paddy fields were discriminated from other land covers using a simple thresholding algorithm based on their specific pattern of low minimum, high maximum, and high difference of vertical transmithorizontal receive polarization (VH) backscatter on a 2-dimensional (2D) scatter plot. The results showed that the proposed algorithm had an accuracy of 94.02%, comparable to that of the random forest algorithm and other studies using 3-dimensional (3D) parameters. The proposed algorithm reduces the dimensionality from 3D to 2D and is practical for mapping and monitoring paddy fields. In this context, the application of the algorithm to the surrounding regions of Karawang, Indramayu, and Bekasi achieved high accuracy rates of 93.37%, 92.87%, and 88.13%, respectively.

Spatial distribution models for the four commercial tuna in the sea of maritime continent using multi-sensor remote sensing and maximum entropy
Emi Yati, Lilis Sadiyah, Fayakun Satria, Irene D. Alabia, Sayidah Sulma, Teguh Prayogo, Sartono Marpaung, Hastuadi Harsa, Dony Kushardono, Jonson Lumban-Gaol,et al.
Elsevier BV

Assessing land subsidence and analyzing tidal flooding in Tangerang, Banten
Risti Endriani Arhatin, Jonson Lumban Gaol, I Wayan Nurjaya, Setyo Budi Susilo, Dony Kushardono, Udhi Catur Nugroho, Muhammad Ishak Jumarang, Maya Eria Sinurat, and Nabil Balbeid
EDP Sciences
The increase in ocean temperature causes the expansion of seawater volume, resulting in an increase in sea level rise. The phenomenon of land subsidence also exacerbates the occurrence of tidal floods in coastal areas of Indonesia. This has prompted the need for a study of land subsidence and the distribution of tidal floods in Tangerang as a basis for taking anticipatory steps to reduce the negative impacts. The methods used for estimating land subsidence involved the SAR Sentinel-1A. The research utilized a total of 170 data points, spanning from 2017 until 2022. Data processing was carried out using the Parallel Small Baseline Subset method. The supporting data used in this study included SRTM data, tidal range, rainfall data, wind speed and direction. The results of this study reveal that the city of Tangerang has a maximum deformation value of -10.8 cm per year in the Periuk Sub District. Meanwhile, Tangerang Regency experienced land subsidence at a rate of -8.6 cm per year in Kosambi Sub District. Significant subsidence deformations occurred on the northeast side of Tangerang District and the southeast side of Tangerang City. Based on data analysis, it is evident that the total area inundated by tidal floods in Tangerang covers 33.267 hectares, with the largest affected area being in Pakuhaji District, spanning 9,262 hectares.

Semantic Deep Learning for Open-Pit Mining Detection Using High Resolution SAR Data
Udhi C Nugroho, Tri Muji Susantoro, Dony Kushardono, Gatot Nugroho, Herru L. Setiawan, Suliantara, and Nurul Ichsan
IEEE
Indonesia is rich in mineral resources primarily extracted through open-pit mining. However, these mining activities significantly impact the Earth's surface, necessitating effective monitoring to mitigate environmental consequences through advanced digital technologies. Remote sensing technology has proven effective for monitoring open-pit mining operations. This study utilises high-resolution Synthetic Aperture Radar (SAR) data from the TerraSAR-X, integrated with deep learning, to identify and monitor open-pit mining activities in the South Bangka Regency. This region, known for its extensive tin mining operations, faces substantial ecological challenges due to the disruptive effects of open-pit mining on ecosystems and landscapes. Employing the U-Net model with a ResNet-34 backbone, we processed TerraSAR-X imagery to classify land cover types into open-pit mining areas, vegetation, water bodies, and settlements. The model achieved a classification accuracy of 71%, successfully identifying 2,346.9 hectares as mining areas. However, some classification challenges were encountered, particularly in areas with complex terrain and low backscatter shadow effects. Misclassifications, particularly between mining areas and water bodies due to similar backscatter values classification results showing “box” errors, highlight the necessity for further model refinement. Future research should focus on integrating multispectral data and additional deep learning features to improve classification accuracy. The findings underscore the potential of SAR and artificial intelligence (AI) to enhance sustainable mining practices and support environmental management strategies, reinforcing the need for ongoing advancements in remote sensing technologies for more effective monitoring and regulation of mining activities.

BURNED AREA DETECTION USING CONVOLUTIONAL NEURAL NETWORK BASED ON SPATIAL INFORMATION OF SYNTHETIC APERTURE RADAR DATA IN INDONESIA
Anugrah I. Lestari, Dony Kushardono, and Athar A. Bayanuddin
Russian Geographical Society
Forest and land fires are disasters that often occur in Indonesia which affects neighbouring countries. The burned area can be observed using remote sensing. Synthetic aperture radar (SAR) sensor data is advantageous since it can penetrate clouds and smoke. However, image analysis of SAR data differs from optical data, which is based on properties such as intensity, texture, and polarimetric feature. This research aims to propose a method to detect burned areas from the extracted feature of Sentinel-1 data. The features were classified using the Convolutional Neural Network (CNN) classifier. To find the best input features, several classification schemes were tested, including intensity and polarimetric features by applying the Boxcar speckle filter and the Gray Level Co-occurrence Matrix (GLCM) texture feature without using the Boxcar speckle filter. Additionally, this research investigates the significance of a window size parameter for each scheme. The results show the highest overall accuracy achieved 84% using CNN classification utilizing the GLCM texture features and without conducting the Boxcar speckle filter on the window size of 17×17 pixels when tested on the part region of Pulang Pisau Regency and Kapuas Regency, Central Kalimantan in 2019. The total burned area was 76,098.6 ha. The use of GLCM texture features without conducting the Boxcar speckle filter as input classification performs better than using intensity and polarimetric features that undergo the Boxcar speckle filter. Combining intensity and polarimetric features with performing the Boxcar speckle filter improves better classification performance over utilizing them separately. Furthermore, the selection of window size also contributes to improve the model performance.

Monitoring Land Cover Change and Its Estimated Carbon Loss in the Nusantara Capital City Indonesia on High-Resolution Planet Satellite Imagery
Galdita A. Chulafak, Gatot Nugroho, Parwati Sofan, Anjar I. Pambudi, and Dony Kushardono
SPIE

A Bibliometric Analysis of Urban Environment Quality Studies Based on Satellite Remote Sensing Data
Nurwita Mustika Sari, Dony Kushardono, Masita Dwi Mandini Manessa, Kustiyo, Mukhoriyah, Andy Indradjad, Samsul Arifin, and Ahmad Maryanto
AIP Publishing

Rapid Detection of Devegetation Using Multitemporal Sentinel-1 C-Band SAR Data
Anugrah Indah Lestari, Dony Kushardono, Yenni Vetrita, Imam Santoso, Tatik Kartika, and Indah Prasasti
AIP Publishing

Analysis of land use and spatial planning in the Upstream Citarum watershed of West Java based on remote sensing data
Mukhoriyah Mukhoriyah, Samsul Arifin, Dony Kushardono, Mohammad Ardha, and Fajar Yulianto
Faculty of Agriculture, Brawijaya University
<p>The Upstream Citarum watershed has a critical essential role in maintaining the quality and quantity of its water resources, which are a source of drinking water, agriculture, fisheries, irrigation, and electricity generation. The upstream watershed acts as a water catchment area that contributes as a place to accommodate the availability of water, especially during the dry season, and also as a protector of the entire area, both downstream and middle, so that the carrying capacity of the ecological balance can be protected. The increasing total population was inversely related to the condition of land use which is decreasing in quality, so to fulfill these needs, there was a land conversion that caused changes in land use. The Landsat-8 satellite imagery, SPOT 7, and spatial planning maps were used to analyze the suitability and incompatibility of land use with spatial pattern plans, evaluation, and directions for controlling the use of space. The result of the most extensive existing land use in the Upstream Citarum watershed in 2021 used for fields is 30% of the total area of 66,831.66 ha. Meanwhile, the spatial pattern plan was classified into protected and cultivated areas. The built-up area has the largest area, 35% or 75,223.96 ha. The results of the suitability of land use classes obtained that the level of suitability between the existing land use and the spatial pattern plan from the Maps of Regional Spatial Planning with the appropriate class was 52.50% or 96,205.43 ha, and the unsuitable class was 47.50% or 87,028.75 ha.</p>

Fishing Ground and Primary Production Analysis Based on DNB SNPP-VIIRS and Aqua-MODIS Imagery in Mentawai Island and Nias Waters
Teguh Prayogo, Hastuadi Harsa, Sayidah Sulma, Emi Yati, Sartono Marpaung, and Dony Kushardono
IOP Publishing
Abstract The study of fishing grounds in coastal areas is part of fisheries management activities, especially capture fisheries by coastal fishermen. The absence of GPS, AIS and VMS systems on traditional fishing boats causes difficulties in monitoring the fishing grounds (FG) of coastal fishermen in the waters of Nias Island and Mentawai Islands. The objectives of this study to assess the fishing ground area and analyse its seasonal variability based on fishing light boats (FLB) from the DNB SNPP-VIIRS satellite imagery and the primary productivity condition in FG area from Aqua-MODIS imagery in the Nias Island and Mentawai Islands waters. FG is determined based on the clustering point density method, and statistical correlation analysis. Based on the FLB imagery (2015-2020), peak season fishing operation occurred twice a year in January/February and June/July, while the lowest fishing season occurs in April and October. In general, there are four main locations of fishing grounds in the study area, i.e Sibolga waters, Batu Islands, Mentawai Island and West Sumatra coastal. The FLB can describe the location of FG spatial and temporally, and it was correlated with the bathymetry and chlorophyll-a concentration rather than primary production in the waters of Nias Island and Mentawai Islands. Spatial and temporally distribution the fishing grounds and its density change by seasonal and inter-annual variations. The lowest conditions occurred in 2016 and the highest in 2019 which were each influenced by the nIOD and pIOD phenomena.

AN OPTIMIZED ARTIFICIAL NEURAL NETWORK FOR THE CLASSIFICATION OF URBAN ENVIRONMENT COMFORT USING LANDSAT-8 REMOTE SENSING DATA IN GREATER JAKARTA AREA, INDONESIA
Nurwita Mustika Sari, Dony Kushardono, Mukhoriyah Mukhoriyah, Kustiyo Kustiyo, and Masita Dwi Mandini Manessa
Yayasan Riset dan Pengembangan Intelektual
The development of computer vision technology as a type of artificial intelligence is increasing rapidly in various fields. This method uses deep learning methods based on artificial neural networks, a well-performed algorithm in multi-parameter analysis. One of the development of computer vision models and algorithms is for a thematic digital image classification, such as environmental analysis. Remote sensing based digital image classification is one of the reliable tools for environmental quality analysis. This study aims to perform neural network optimization for the analysis of the urban environment comfort based on satellite data. The input data used are 4 types of geobiophysical indexes as urban environmental comfort parameters derived from cloud-free annual mosaics Landsat-8 remote sensing satellite data. The results obtained in this study indicate that the 1 hidden layer neural network architecture with 16 neurons for the classification of urban environmental comfort and 10 other land cover classes is quite good. The result of the classification using this optimized artificial neural network shows that the distribution of classes is very uncomfortable which dominates the Greater Jakarta area and its surroundings. For other classes in the study area, some are uncomfortable and rather comfortable. By using this method, we obtained a fast classification training time of 18 seconds for 145 iterations to achieve an RMS Error of 0.01, and has a fairly high classification accuracy overall 89% with a Kappa coefficient of 0.88, while the 2 hidden layer neural network architecture does not succeed in achieving convergence

Identification method of vegetation cover changes derived from mosaic Landsat-8 Data: Case Study Sumatera, Kalimantan, and Java Island
T Kartika, D Kushardono, Y Setiawan, A Ibrahim, Kustiyo, A Sutanto, H Noviar, M R Khomarudin, I Carolita, A Tosiani,et al.
IOP Publishing
Abstract Vegetation cover changes information is essential in forest and plantation management. Low-resolution remote sensing in mosaic data format has been widely used for vegetation cover change mapping on a global scale by implementing the threshold method. However, the problem with this method in Landsat-8 - which has a higher resolution - is that it is challenging to obtain the appropriate value due to the diversity of Indonesia’s land ecosystems. This research aimed to determine the threshold value for detecting devegetation and revegetation to identify vegetation cover changes rapidly. This research used Oldeman Climate Classification with zone A and B as the references. The threshold values to classify vegetation cover changes were derived from the delta Normalized Burn Ratio (dNBR) of Analysis Ready Data (ARD) Landsat-8 - taken in Sumatera as the pilot area. Moreover, the proposed method was also applied to Kalimantan and Java Islands, with have identical climates. The results indicated that dNBR threshold for devegetation was more than 0.376, while revegetation was less than -0.269. These results were evaluated using high-resolution satellite imagery and ground-truth information. It concluded that Kalimantan Island obtained good results in mapping vegetation cover change with the threshold; however, Java Island required further adjustment for the threshold.

The influence of increasing sea surface temperature on particulate organic carbon in Indonesian waters based on MODIS Aqua satellite
E Yati, D Kushardono, J L Gaol, T Prayogo, S Sulma, S Marpaung, M R Nandika, L Sadiyah, F Satria, H A Shidiqy,et al.
IOP Publishing
Abstract Both Sea Surface Temperature (SST) and Particulate Organic Carbon (POC) have important roles in the marine ecosystem and carbon cycle. Therefore, we analyze the influence of SST on POC in Indonesian water. We used SST and POC products from the moderate-resolution imaging spectroradiometer (MODIS) Aqua satellite from 2003 to 2021 (nineteen years). Regression and a temporal anomaly correlation approach were applied to assess the effect of SST on POC in Indonesian waters. Our results show that the southeast Indonesian waters, south of Java Island and around the Riau Islands, mostly have a high SST variation. On the other hand, the high variation of POC mostly appeared in Indonesian coastal. During the last nineteen years, the increasing SST anomalies (SSTA) in Indonesian waters have been followed by decreasing POC anomalies (POCA). These results indicate that rising SST reduces the ocean’s ability to absorb carbon in Indonesian waters. A strong negative relation between SSTA on POCA was found from April to August and October to January in a seasonal timescale. In the interannual timescale, our result reveals that the strong negative relationship between SSTA and POCA is likely linked to the El Niño Southern Oscillation, the Indian Ocean Dipole, and global warming.

Urban Vegetation Quality Assessment Using Vegetation Index and Leaf Area Index from Spot 7 Data with Fuzzy Logic Algorithm
Nurwita Mustika Sari, Tito Latif Indra, and Dony Kushardono
Insight Society

Evaluation of the Threshold for an Improved Surface Water Extraction Index Using Optical Remote Sensing Data
Fajar Yulianto, Dony Kushardono, Syarif Budhiman, Gatot Nugroho, Galdita Aruba Chulafak, Esthi Kurnia Dewi, and Anjar Ilham Pambudi
Hindawi Limited
In this study, we proposed an automatic water extraction index (AWEI) threshold improvement model that can be used to detect lake surface water based on optical remote sensing data. An annual Landsat 8 mosaic was created using the Google Earth Engine (GEE) platform to obtain cloud-free satellite image data. The challenge of this study was to determine the threshold value, which is essential to show the boundary between water and nonwater. The AWEI was selected for the study to address this challenge. The AWEI approach was developed by adding a threshold water value based on the split-based approach (SBA) calculation analysis for Landsat 8 satellite images. The SBA was used to determine local threshold variations in data scenes that were used to classify water and nonwater. The class threshold between water and nonwater in each selected subscene image can be determined based on the calculation of class intervals generated by geostatistical analysis, initially referred to as smart quantiles. It was used to determine the class separation between water and nonwater in the resulting subscene images. The objectives of this study were (a) to increase the accuracy of automatic lake surface water detection by improvising the determination of threshold values based on analysis and calculations using the SBA and (b) to conduct a test case study of AWEI threshold improvement on several lakes’ surface water, which has a variety of different or heterogeneous characteristics. The results show that the threshold value obtained based on the smart quantile calculation from the natural break approach (AWEI ≥ −0.23) gave an overall accuracy of close to 100%. Those results were better than the normal threshold (AWEI ≥ 0.00), with an overall accuracy of 98%. It shows that there has been an increase of 2% in the accuracy based on the confusion matrix calculation. In addition to that, the results obtained when classifying water and nonwater classes for the different national priority lakes in Indonesia vary in overall accuracy from 94% to 100%.

Speckle noise reduction of Sentinel-1 SAR data using fast fourier transform temporal filtering to monitor paddy field area
Kustiyo, Rokhmatuloh, A H Saputro, and D Kushardono
IOP Publishing

Utilization of Multi-Temporal Sentinel-1 Satellite Imagery for Detecting Aquatic Vegetation Change in Lake Rawapening, Central Java, Indonesia
Galdita Aruba Chulafak, Dony Kushardono, and Fajar Yulianto
Informa UK Limited
Abstract Lake Rawapening has high ecological, historical, and economic value, such as in terms of agricultural irrigation, fisheries, hydropower generation, and tourism. However, a major problem faced by the lake is the uncontrolled growth of aquatic vegetation. Monitoring of the dynamics of the condition of the vegetation cover on the waters needs to be conducted periodically as one of the lake management efforts. We propose an Automatic Aquatic Vegetation Extraction method to monitor the dynamics of the condition of the lake's vegetation using multitemporal C-band radar satellite imagery. The method utilizes data from the SAR satellite imagery to ascertain the maximum water boundary, which can be used to distinguish between aquatic and terrestrial vegetation. The Otsu algorithm approach was used to determine the boundary between land and water areas. The method was applied on several dates, employing VV and VH polarizations. The results show that the proposed method could rapidly monitor lakes and their aquatic vegetation from year to year. The overall accuracy of the study varied from 79.48 to 88.46 percent, with an average of 84.4 percent.

Accuracy assessment of several classification algorithms with and without hue saturation intensity input features on object analyses on benthic habitat mapping in the Pajenekang Island Waters, South Sulawesi
T Pragunanti, B Nababan, H Madduppa, and D Kushardono
IOP Publishing

RGB cloud free image of Sentinel-2 imageries using temporal transformation algorithm to identify paddy fields in Subang, West Java

Developing the temporal composite of Sentinel-1 SAR data to identify paddy field area in Subang, West Java
Kustiyo Kustiyo, . Rochmatulloh, Adhi Harmoko Saputro, and Donny Kushardono
SPIE
Accurate information of actual paddy field area is very importance for food security to support decision making. Remote sensing data is a use-full tools to detect and to create the paddy field area information, because of spatial and temporal characteristics. It is challenging in using the time series single polarization Synthetic Aperture Radar (SAR) data to detect such information. This research used the Sentinel-1 VH polarization and GRD level in Subang district of West Java in 2018 with 12-days temporal interval, around 30 temporal data were used. The remote sensing image pre-processing steps were applied in every single data such as geometric correction, backscattered calculation, topographic flattening, and lee filtering. The ready data was in 30x30 meter pixel resolution then be filtered by temporal filter using median moving window. Then, it was transformed using phenological approach by temporal transformation. The are several RGB composite products were compared and analyzed by using paddy field map from Ministry of Agriculture as reference data. The results show that the best RGB composite for detecting paddy field area is the RGB temporal combination of minimum backscatter Jan-June as Red layer, minimum backscatter July-December as Green layer, and maximum backscatter Jan-December as Blue layer. The blue color indicates the paddy field, it means that during Jan-June and July-Dec the area was inundated, and during a year there was vegetation covering the area.

Assessing the Potential of LAPAN-A3 Data for Landuse/landcover Mapping
Zylshal Zylshal, Rachmad Wirawan, and Dony Kushardono
Universitas Gadjah Mada
LAPAN-A3 / LAPAN-IPB is the third generation of micro-satellite developed by Indonesian National Institute of Aeronautics and Space (LAPAN). The satellite carries a multispectral push-broom sensor that can record the earth's surface at the visible and near-infrared spectrum. Being launched in June 2016, there has no been many publications related to the use of LAPAN-A3 multispectral data for landuse/landcover (LULC) mapping. This paper aims to provide information regarding the use of LAPAN-A3 data for the LULC extraction maximum likelihood algorithm as well as neural network and then evaluate the results. The LAPAN-A3 image was geometrically corrected by using Landsat-8 OLI image as reference data. Three test areas with a size of 1200x945 pixels are then selected for pixel-based classification with the two aforementioned algorithms. For comparison, both LAPAN-A3 and Landsat-8 data were classified for 3 test areas. Accuracy assessment was performed on both datasets using manually interpreted SPOT-6 Pansharpened image as reference data. Preliminary results showed that LAPAN-A3 were able to extract 10 different LULC classes, comprises of built-up area, forest, rivers, fishponds, shrubs, wetland forests, rice fields, sea, agricultural land, and bare soil. The overall accuracy of LAPAN-A3 data is generally lower than Landsat-8, which ranges from 49.76% to 71.74%. These results illustrate the potential of LAPAN-A3 data to derive LULC information. The lack of necessary parameters to perform radiometric correction and blurring effect are several issues that need to be solved to improve the accuracy LULC.

Study of 3D bathymetry modelling using LAPAN Surveillance Unmanned Aerial Vehicle 02 (LSU-02) photo data with stereo photogrammetry technique, Wawaran Beach, Pacitan, East Java, Indonesia
N M Sari, J T Nugroho, G A Chulafak, and D Kushardono
IOP Publishing

Dony Kushardono

EDUCATION

RESEARCH INTERESTS

Scopus Publications

RECENT SCHOLAR PUBLICATIONS