ESTIMATION OF ABOVEGROUND CARBON STOCK USING SAR SENTINEL-1 IMAGERY IN SAMARINDA CITY

Estimation of aboveground carbon stock on stands vegetation, especially in green open space, has become an urgent issue in the effort to calculate, monitor, manage, and evaluate carbon stocks, especially in a massive urban area such as Samarinda City, Kalimantan Timur Province, Indonesia. The use of Sentinel-1 imagery was maximised to accommodate the weaknesses in its optical imagery, and combined with its ability to produce cloud-free imagery and minimal atmospheric influence. The study aims to test the accuracy of the estimated model of above-ground carbon stocks, to ascertain the total carbon stock, and to map the spatial distribution of carbon stocks on stands vegetation in Samarinda City. The methods used included empirical modelling of carbon stocks and statistical analysis comparing backscatter values and actual carbon stocks in the field using VV and VH polarisation. Model accuracy tests were performed using the standard error of estimate in independent accuracy test samples. The results show that Samarinda Utara subdistrict had the highest carbon stock of 3,765,255.9 tons in the VH exponential model. Total carbon stocks in the exponential VH models were 6,489,478.1 tons, with the highest maximum accuracy of 87.6 %, and an estimated error of 0.57 tons/pixel.

Backpages Vol.18 No.1 (2021)

Backpages Vol.18 No.1 (2021)

Front Pages IJReSES Vol. 18, No. 1 (2021)

Front Pages IJReSES Vol. 18, No. 1 (2021)

MACHINE LEARNING APPLIED TO SENTINEL-2 AND LANDSAT-8 MULTISPECTRAL AND MEDIUM-RESOLUTION SATELLITE IMAGERY FOR THE DETECTION OF RICE PRODUCTION AREAS IN NGANJUK, EAST JAVA, INDONESIA

Statistics Indonesia (BPS) has been introducing the use of Area Sampling Frame (ASF) surveys from 2018 to estimate rice production areas, although the process continues to suffer from the high costs of human and other resources. To support this type of conventional field survey, a more scalable and inexpensive approach using publicly-available remote sensing data, for example from the Sentinel-2 and Landsat-8 satellites, has been explored. In this research, we compare the performance gain from Sentinel-2 and Landsat-8 images using a multiple composite-index enriched machine learning classifier to detect rice production areas located in Nganjuk, East Java, Indonesia as a case study area. We build a detection model from a set of machine learning classifiers, Decision Tree (CART), Support Vector Machine, Logistic Regression, Ensemble Bagging Methods (Random Forest and Extra Trees), and Ensemble Boosting Methods (AdaBoost and XGBoost). The composite indices consist of the NDVI and EVI for agricultural and forest areas, NDWI for water and cloud, and NDBI, NDTI, and BSI for built-up areas, fallows, and asphalt-based roads. Validated by k-fold cross-validation, Sentinel-2 and Landsat-8 achieved F1-scores of 0.930 and 0.919 respectively at the scale of 30 meters per pixel. Using a 10 meter resolution per pixel for the Sentinel-2 imagery showed an increased F1-score of up to 0.971. Our evaluation shows that the higher spatial resolution imagery of Sentinel-2 achieves a better prediction, not only performance-wise, but also as a better representation of actual conditions.

RADAR-BASED STOCHASTIC PRECIPITATION NOWCASTING USING THE SHORT-TERM ENSEMBLE PREDICTION SYSTEM (STEPS) (CASE STUDY: PANGKALAN BUN WEATHER RADAR)

Nowcasting, or the short-term forecasting of precipitation, is urgently needed to support the mitigation circle in hydrometeorological disasters. Pangkalan Bun weather radar is single-polarization radar with a 200 km maximum range and which runs 10 elevation angles in 10 minutes with a 250 meters spatial resolution. There is no terrain blocking around the covered area. The Short-Term Ensemble Prediction System (STEPS) is one of many algorithms that is used to generate precipitation nowcasting, and is already in operational use. STEPS has the advantage of producing ensemble nowcasts, by which nowcast uncertainties can be statistically quantified. This research aims to apply STEPS to generate stochastic nowcasting in Pangkalan Bun weather radar and to analyze its advantages and weaknesses. Accuracy is measured by counting the possibility of detection and false alarms under the 5 dBZ threshold and plotting them in a relative operating characteristic (ROC) curve. The observed frequency and forecast probability is represented by a reliability diagram to evaluate nowcast reliability and sharpness. Qualitative analysis of the results showed that the STEPS ensemble produces smoothed reflectivity fields that cannot capture extreme values in an observed quasi-linear convective system (QLCS), but that the algorithm achieves good accuracy under the threshold used, up to 40 minutes lead time. The ROC shows a curved upper left-hand corner, and the reliability diagram is an almost perfect nowcast diagonal line.

OIL PALM PLANTATION DETECTION IN INDONESIA USING SENTINEL-2 AND LANDSAT-8 OPTICAL SATELLITE IMAGERY (CASE STUDY: ROKAN HULU REGENCY, RIAU PROVINCE)

The objective of this work is to assess the capability of multispectral optical Landsat and Sentinel images to detect oil palm plantations in Rokan Hulu, Riau, one of the largest palm oil producers in Indonesia, by combining multispectral bands and composite indices. In addition to comparing two different sets of satellite images, we also ascertain which gives the best performance among the supervised machine learning classifiers CART Decision Tree, Random Forest, Support Vector Machine, and Naive Bayes. With the use of multispectral bands and derived composite indices, the best classifier achieved an overall accuracy of up to 92%. The findings and contributions of the study include: (1) insight into a set of feature combinations that provides the highest model accuracy, and (2) an extensive evaluation of machine learning-based classifiers on two different optical satellite imageries. Our study could further be beneficial for the government in providing more scalable plantation statistics.

HYDRO-METEOROLOGICAL ASPECTS OF THE 2021 SOUTH KALIMANTAN FLOOD: TOPOGRAPHY, TIDES, AND PRECIPITATION

The 2021 South Kalimantan flood was recorded as the most serious ever to have taken place in the province. It occurred due to high-intensity rain during the period 10-19 January, accompanied by a spring tide. This study provides an overview of the disaster, with reference to the hydro-meteorological conditions (topography, tides, and precipitation). The method used was the analysis of the precipitation and its monthly rainfall pattern anomalies using remote sensing data. A Digital Elevation Model (DEM) was also analyzed to indicate the most noticeably flood-affected area. In certain areas, total precipitation during the ten days reached 672.8 mm, with daily precipitation peaking at 255 mm on January 14, greater than the 25-year return period value. The flood coincided with a spring tide, which peaked at 1.21 m on the evening of January 15. Using 20- year GPM data, it was found that ENSO and IOD coexisted with both the highest and lowest anomalies. With a La Niña event at the end of 2020, a positive precipitation anomaly in 2021 was expected. The extreme precipitation is suspected to be the main driver of the 2021 South Kalimantan flood, whose impact was worsened by the spring tides. This study conducts further research on the correlation between land-use change, rainfall, spring tide and flooding in South Kalimantan. In addition, it is recommended that the government plan flood risk management by prioritizing areas based on vulnerability to climate hazards.

APPLICATION OF LAPAN A3 SATELLITE DATA FOR THE IDENTIFICATION OF PADDY FIELDS USING OBJECT BASED IMAGE ANALYSIS (OBIA)

The role of agriculture is directly related to SDG No.2, which is running a programme until 2030 to reduce national poverty, eradicate hunger by increasing food security and improving nutrition and support sustainable agriculture. Problems faced include the reduction in agricultural land, which results in lower rice production, and the limited information on the monitoring of paddy fields using spatial data. The purpose of this study is to identify paddy fields using LAPAN A3 satellite imagery based on OBIA classification. The data used were from LAPAN A3 multispectral imagery dated 19 June 2017, Landsat 8 imagery dated 17 June 2017, DEM SRTM (BIG), and the Administrative Boundary Map (BIG). The analysis method was segmentation by grouping image pixels, and supervised classification by taking several sample areas based on Random Stratified Sampling. The results will be carried using a confusion matrix. The classification results produced four classes; watery paddy fields, vegetation paddy fields, fallow paddy fields, and non-paddy fields, using of the green, red, and NIR bands for the LAPAN A3 data. From the results of the segmentation process, there remain some oversegmented features in the appearance of the same object. Oversegmentation is due to an inaccurate value assignment to each algorithm parameter when the segmentation process is performed. For example, watery paddy fields appear almost the same as open land (fallow paddy fields), the water object is darker purple. The visual classification results (Landsat 8 data) are considered as the reference for the digital classification results (LAPAN A3). Forty-eight samples were taken and divided into four classes, with each class consisting of 12 samples. The results of the accuracy test show that the total accuracy of the object-based digital classification for visual classification is 62.5% with a Kappa accuracy value of 0.5. The conclusion is that LAPAN A3 data can be used to identify paddy fields based on spectral resolution and to complement Landsat 8 data. To improve the accuracy of the classification results, more samples and the correct RGB composition are needed.

COASTLINE CHANGE ANALYSIS ON BALI ISLAND USING SENTINEL-1 SATELLITE IMAGERY

Bali is well-known as a popular tourism location for both local and foreign tourists. There are nine areas designated for tourism, eight of which are coastal. However, due to coastal erosion, the coastline of Bali is changing every year. The purpose of this study is to determine the changes that took place between 2015 and 2020 using Sentinel-1 satellite imagery. The study was conducted along the coastline of Bali Island at coordinates 08° 53' 35.5648" S, 114° 24' 41.8359" E and 08° 00' 46.7865" S, 115° 44' 17.5928" E. The coastlines were identified using the Otsu image thresholding method and linear tidal correction was performed. The coastline change analysis was made using the transect method. Ground truths were conducted in representative areas where major changes had occurred, either as a result of abrasion or accretion. According to the Sentinel-1 analysis, the coastline changes in Bali during the period 2015 – 2020 were mainly caused by abrasion, apart from at Buleleng, which were generally caused by accretion. Abrasion in Bali is dominantly affected by strong currents and high waves meanwhile accretion which having weak currents and low waves was more affected by human factor such as the construction in this study area.

SPATIO-TEMPORAL ANOMALIES IN SURFACE BRIGHTNESS TEMPERATURE PRECEDING VOLCANO ERUPTIONS DETECTED BY THE LANDSAT-8 THERMAL INFRARED SENSOR (CASE STUDY: KARANGETANG VOLCANO)

Indonesia's geological as part of the “ring of fire” includes the consequence that community life could be affected by volcanic activity. The catastrophic incidence of volcanic eruptions in the last ten years has had a disastrous impact on human life. To overcome this problem, it is necessary to conduct research on the strengthening of the early warning system for volcanic eruptions utilising remote sensing technology. This study analyses spatial and temporal anomalies of surface brightness temperature in the peak area of Karangetang volcano during the 2018-2019 eruption. Karangetang volcano is an active volcano located in North Sulawesi, with a magmatic eruption type that releases lava flow. We analyse the anomalies in the brightness temperature from channel-10 of the Landsat-8 TIRS (Thermal Infrared Scanner) time series during the period in question. The results of the research demonstrate that in the case of Karangetang Volcano the eruptions of 2018-2019 indicate increases in the surface brightness temperature of the crater region. As this volcano has many craters, the method is also very useful to establish in which crater the center of the eruption occurred.