Article Per Year (5 Year)
p-Index From 2021 - 2026
0.751
P-Index
This Author published in this journals
All Journal Jurnal Pijar MIPA Jurnal Penginderaan Jauh Indonesia Jurnal Penginderaan Jauh dan Pengolahan Data Citra Digital
Sampelan, David
Unknown Affiliation
Aerospace Engineering Agriculture, Biological Sciences & Forestry Astronomy Biochemistry, Genetics & Molecular Biology Chemistry Computer Science & IT Control & Systems Engineering Earth & Planetary Sciences Electrical & Electronics Engineering Engineering Mathematics Physics

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Air Temperature-based Spatial Modeling of Remote Sensing Data Using Machine Learning Approaches: a Systematic Literature Review Sampelan, David; Pratiwi, Anggitya; Baihaqi, Anas; Agustiarini, Suci
Jurnal Penginderaan Jauh dan Pengolahan Data Citra Digital Vol. 19 No. 2 (2025)
Publisher : Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/inderaja.v19i2.8450

Abstract

This study presents a systematic review of spatial air temperature modeling based on remote sensing data using machine learning approaches during the period 2016–2025. Using the PRISMA framework, we conducted literature searches in Google Scholar (998 articles) and Scopus (489 articles).. After merging the datasets, removing duplicates, and applying inclusion–exclusion criteria, 12 articles were retained for in-depth analysis. The findings indicate a marked increase in publications since 2021, reflecting growing global interest in integrating remote sensing and machine learning for air temperature estimation. Ensemble algorithms such as Random Forest and XGBoost dominate due to their balance of accuracy and computational efficiency, while temporal deep learning approaches such as LSTM and TCN are emerging as powerful tools for capturing complex atmospheric dynamics. Among remote sensing predictors, Land Surface Temperature (LST) is the most frequently used, often complemented by NDVI, albedo, and elevation to improve spatial accuracy. Geographical context strongly influences methodological performance. XGBoost proves effective in heterogeneous urban areas, Random Forest performs well in mountainous regions, and artificial neural networks demonstrate higher adaptability in extreme environments such as the Greenland ice sheet. Nonetheless, limited ground-based observations and sparse station networks remain key challenges, particularly across tropical and archipelagic regions. This review identifies three major directions for future research: (1) expanding studies to underrepresented tropical regions, (2) leveraging temporal deep learning methods for detecting extreme events, and (3) integrating multisensor data with innovative validation strategies to enhance the robustness and reliability of air temperature modeling.
Study of Developing Models of Crop Failure Risk Information Agustiarini, Suci; Sampelan, David; Maurits, Yuhanna; Baihaqi, Anas; Patria Megantara, Restu; Ulfah, Afriyas; Permana, Angga; Kirana, Nindya; Sulistio Adi Wibowo, Dewo; Purwaningsih, Ni Made Adi; Pamungkas, Cakra Mahasurya Atmojo; Putrantijo, Nuga; Fajariana, Yuaning
Jurnal Pijar Mipa Vol. 19 No. 1 (2024): January 2024
Publisher : Department of Mathematics and Science Education, Faculty of Teacher Training and Education, University of Mataram. Jurnal Pijar MIPA colaborates with Perkumpulan Pendidik IPA Indonesia Wilayah Nusa Tenggara Barat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jpm.v19i1.5981

Abstract

Climate is one factor that can influence plant growth. The risk of crop failure due to climate variability can be in the form of reduced water sources, which impact water needs in the land and the emergence of pests and diseases in plants. The risk of planting failure can impact product quality, which has the potential to decrease, higher plant handling costs, and various things that cause losses to farming businesses. The availability of climate forecast information, such as rainfall and other parameters, encourages writers to apply it to information that is easier for users to understand. One of the machine learning algorithms, Decision Tree, is used as a model in determining the risk of planting failure based on each attribute/parameter, including monthly rain, ENSO and IOD phenomena, drought, groundwater availability, and Oldeman climate type. This study aims to make a model prediction of crop failure risk potential, and the calculation is based on climate prediction data. The results of this study show differences in climatic conditions for each commodity when there is an increased potential risk of planting failure. Monthly rainfall is the most dominant factor influencing rice, maize, and soybean planting failure. Validation of the decision tree model shows that this model is quite good in determining the potential risk of crop failure in all commodities studied, with the proportion of correct proportion of more than 65%. However, the Heidke Skill Score (HSS) shows that this model is good for Paddy and Soybean; Maize shows an HSS of less than zero.
Comparative Analysis of SAVI and NDVI Correlations with Land Surface Temperature in Mandalika Special Economic Zone Using Landsat 8 Imagery Sampelan, David; Pratiwi, Anggitya; Baihaqi, Anas
Jurnal Penginderaan Jauh dan Pengolahan Data Citra Digital Vol. 19 No. 1 (2025)
Publisher : Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/inderaja.v19i1.4442

Abstract

The rapid infrastructure development within the Mandalika Special Economic Zone (SEZ) has significantly altered land cover and potentially influenced land surface temperature (LST). This study aims to compare the correlation strength of two remote sensing-based vegetation indices, Normalized Difference Vegetation Index (NDVI) and Soil Adjusted Vegetation Index (SAVI) with LST to determine which index better represents surface temperature variability in areas undergoing rapid development. Landsat 8 imagery from 2014 to 2023 was used to derive NDVI, SAVI, and LST values. Spearman’s Rho correlation and simple linear regression were employed to evaluate the strength and consistency of the relationships between vegetation indices and LST. The Shapiro – Wilk test confirmed that all variables were not normally distributed, leading to the use of Spearman's rho correlation. Both indices showed significant negative correlations with LST, with NDVI slightly stronger (r = -0.555) than SAVI (r = -0.536). Simple linear regression revealed NDVI had a higher R² (0.392) and lower residual error than SAVI, indicating a more robust model fit. Although SAVI is more suitable in mixed land cover conditions due to its soil background correction, NDVI provides stronger statistical performance in modeling LST in Mandalika SEZ. These findings support the strategic use of NDVI as a primary indicator in environmental planning and sustainable development monitoring or for Urban Heat Island mitigation policy in developing regions.
Tinjauan Pustaka: Pemodelan Spasial Suhu Udara Berbasis Machine Learning dengan Integrasi LST, Albedo, dan Data Observasi Stasiun Cuaca Sampelan, David
Jurnal Penginderaan Jauh Indonesia Vol 4 No 2 (2025)
Publisher : Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/jpji.v4i2.8130

Abstract

Suhu udara (Ta) merupakan indikator iklim penting yang berperan dalam kajian lingkungan, kesehatan, dan perencanaan wilayah. Keterbatasan stasiun cuaca menjadikan variasi spasial Ta sulit dipetakan secara detail, terutama di wilayah dengan topografi kompleks. Kajian ini menyajikan systematic literature review mengenai pemodelan spasial Ta berbasis machine learning (ML) dengan integrasi data suhu permukaan darat (Land Surface Temperature/LST), Albedo, dan observasi stasiun cuaca. Pencarian pustaka dilakukan menggunakan perangkat Publish or Perish yang terhubung ke Google Scholar untuk periode 2016–2025. Dari 1.000 publikasi yang diperoleh, hanya 8 artikel yang memenuhi kriteria inklusi dan relevan dianalisis lebih lanjut. Hasil telaah menunjukkan bahwa LST merupakan variabel utama yang digunakan dalam seluruh studi, dengan dukungan variabel tambahan seperti Albedo, NDVI, DEM, radiasi matahari, dan faktor meteorologi. Metode ML yang paling dominan adalah Random Forest (RF), disusul Gradient Boosting, Support Vector Regression (SVR), Cubist Regression, serta Multiple Linear Regression (MLR) sebagai pembanding. RF dan Gradient Boosting banyak diterapkan karena akurasinya tinggi dalam menangani data heterogen, sementara SVR efektif untuk regresi nonlinier, dan Cubist Regression terbukti stabil di wilayah bertopografi ekstrem. Secara umum, integrasi data satelit dengan pengamatan darat menghasilkan model dengan performa tinggi (R2 > 0,9 dan RMSE sekitar 1–2 °C). Kajian ini menegaskan bahwa pendekatan ML berbasis penginderaan jauh memiliki potensi besar untuk meningkatkan pemahaman dan pemodelan Ta, sekaligus membuka peluang penelitian lanjutan di wilayah dengan dinamika lingkungan yang beragam.  
Co-Authors Agustiarini, Suci Angga Permana Baihaqi, Anas Fajariana, Yuaning Kirana, Nindya Maurits, Yuhanna Pamungkas, Cakra Mahasurya Atmojo Patria Megantara, Restu Pratiwi, Anggitya Purwaningsih, Ni Made Adi Putrantijo, Nuga Sulistio Adi Wibowo, Dewo Ulfah, Afriyas