Abstract:Abstract: Gross Regional Domestic Product (GRDP) is one of the most important socio-economic indicators. In order to gain a more comprehensive understanding of the current economic situation and regional differences, estimating…
imating GRDP using integration of satellite imagery and official statistics data can provide valuable information. This research estimates the GRDP value in 2022 by using data in 2019 to 2021 related to two aspects, agriculture and non-agriculture. Soil adjusted vegetation index (SAVI), enhanced vegetation index (EVI), and land cover (LC) used as agriculture aspect, while nighttime light (NTL), human settlement index (HSI), land area, and population per regency/city used as non-agriculture aspect. GRDP estimation are produced with machine learning approach using support vector machine (SVM) and random forest (RF) method. Correlation test on each variable shows only land area that does not have a significant correlation with GRDP. RF model then chosen as the best model with RMSE, MSE, MAE, and R2 value of 0.2549; 0.5049; 0.7727; and 0.2543, respectively. The estimated values acquired in several regencies/cities have rather near, some even very close to the official statistics values.
Keywords: GRDP; satellite imagery; machine learning; random forest; support vector machine
Abstrak: Produk Domestik Regional Bruto (PDRB) merupakan salah satu indikator sosio-ekonomi yang penting. Penghitungan nilai PDRB dengan pendekatan yang melibatkan kombinasi data citra satelit dan statistik resmi dapat memberikan informasi serta pemahaman yang lebih komprehensif. Penelitian ini melakukan estimasi nilai PDRB pada tahun 2022 menggunakan data tahun 2019 hingga 2021 dengan melibatkan dua aspek, agrikultur dan non-agrikultur. Data soil adjusted vegetation index (SAVI), enhanced vegetation index (EVI), dan tutupan lahan (land cover/LC) digunakan sebagai aspek agrikultur, sementara data citra cahaya malam (NTL), human settlement indeks (HSI), luas wilayah kabupaten/kota, dan jumlah populasi per kabupaten/kota digunakan sebagai aspek non-agrikultur. Estimasi PDRB dihasilkan dengan menggunakan pendekatan machine learning berupa support vector machine (SVM) dan random forest (RF). Pengecekan korelasi antarvariabel menunjukkan bahwa hanya variabel luas wilayah tidak berpengaruh signifikan terhadap nilai PDRB. Model random forest kemudian dipilih sebagai model terbaik dengan nilai evaluasi RMSE, MSE, MAE, dan berturut-turut sebesar 0.2549, 0.5049, 0.7727, dan 0.2543. Nilai estimasi yang diperoleh di beberapa kabupaten/kota cukup mendekati, bahkan ada yang sangat dekat dengan nilai statistik resmi.
Kata kunci: PDRB; citra satelit; machine learning; random forest; support vector machine
Abstract:Tiakur City, the capital of Southwest Maluku Regency, has undergone significant physical development between 2015 and 2025, driven by population growth and economic activities. This study employs a quantitative approach…
using remote sensing technology with PlanetScope satellite imagery to analyze land cover changes. The analysis reveals an increase in built-up land area from 171.29 hectares (7.31%) in 2015 to 395.66 hectares (16.89%) in 2025, while non-built-up land experienced a decline. These findings indicate a rapid development rate and highlight the importance of sustainable spatial planning. In conclusion, understanding the patterns and intensity of land cover changes in Tiakur City is crucial for evaluating spatial planning policies and improving infrastructure development planning for the future.
Abstract:This study examines the suitability of land for the development of residential areas in Ambon City, based on the slope factor. The methods used include spatial analysis by utilizing Digital Elevation Model (DEM) data and…
the Ambon City Regional Spatial Plan (RTRW), as well as satellite image interpretation to identify suitable and unsuitable areas for residential development. The results show that more than 56% of the total planned land area is in the highly suitable category, while areas with steep slopes have a high potential for landslide risk. The discussion emphasizes the importance of settlement development focusing on safe and suitable areas, and the need for strict regulations to protect communities from disaster risks. The findings provide a strong basis for policy makers to formulate spatial planning strategies that are sustainable and responsive to the geographical conditions of Ambon City.
Abstract:This study aims to analyze land surface temperature changes in Sorong City, Indonesia using Landsat 8 satellite image data and Google Earth Engine cloud computing platform. With rapid urbanization, understanding the dynamics…
mics of surface temperature is important. Through satellite imagery and cloud computing technology, this analysis provides accurate monitoring of temperature change, supports climate change mitigation strategies, and designs more sustainable cities.
Abstract:The Paguyaman watershed in Gorontalo is crucial for life, but it faces land degradation and erosion. This study evaluates land conditions using satellite imagery and spatial data. Results indicate that 58.73% of the area…
is in moderate condition, while 27.4% is in poor or very poor condition. Recommendations include reforestation with local species and integrated farming systems to improve soil fertility. Regular monitoring using remote sensing technology is proposed for the early detection of vegetation changes. Collaboration between the government, community, and researchers is essential to achieving sustainable watershed management.