This study aimed to develop Multiple Linear Regression (MLR) and Artificial Neural Network (ANN) models to predict Soil Organic Carbon (SOC) using Remote Sensing (RS) data. Therefore, 60 surface soil samples were collected from 0-20 cm depth across the watershed of Qeshlaq Dam in western Iran, and soil properties were analyzed. A total of 11 auxiliary variables were obtained from three Landsat 9 satellite image databases, topographic indices and soil properties. Finally, the predicted data from the aforementioned approaches were used to prepare a spatial distribution map of SOC. The measured SOC values showed good correlation with EC, Color Index, Brightness Temperature Index 10 and 11 indices. The comparative evaluation of the results from the two models showed that the ANN with a higher correlation coefficient (R=0.821) and lower error (RMSE=0.108, MAE=0.002) provided better accuracy than the MLR method. The spatial distribution maps obtained from the two models showed that the ANN produced a more uniform and reliable spatial pattern and more stable spots. In contrast, the map obtained from the MLR had more extreme values and obvious point dispersion, which is a result of the limitation of linear models in representing spatial complexity. Therefore, ANN can be used in other regions and similar studies as a useful and rapid tool and can be effectively used in reducing soil sampling costs with spatial information-based management. The results of the present study highlight the integration of RS datasets and advanced machine learning models for accurate SOC estimation.
Fatehi, D. , Souri, B. and Saedpanah, M. (2026). Evaluation of Soil Organic Carbon Using Integration of Remote Sensing and Artificial Neural Network. Sustainable Earth Trends, (), -. doi: 10.48308/set.2026.243186.1178
MLA
Fatehi, D. , , Souri, B. , and Saedpanah, M. . "Evaluation of Soil Organic Carbon Using Integration of Remote Sensing and Artificial Neural Network", Sustainable Earth Trends, , , 2026, -. doi: 10.48308/set.2026.243186.1178
HARVARD
Fatehi, D., Souri, B., Saedpanah, M. (2026). 'Evaluation of Soil Organic Carbon Using Integration of Remote Sensing and Artificial Neural Network', Sustainable Earth Trends, (), pp. -. doi: 10.48308/set.2026.243186.1178
CHICAGO
D. Fatehi , B. Souri and M. Saedpanah, "Evaluation of Soil Organic Carbon Using Integration of Remote Sensing and Artificial Neural Network," Sustainable Earth Trends, (2026): -, doi: 10.48308/set.2026.243186.1178
VANCOUVER
Fatehi, D., Souri, B., Saedpanah, M. Evaluation of Soil Organic Carbon Using Integration of Remote Sensing and Artificial Neural Network. Sustainable Earth Trends, 2026; (): -. doi: 10.48308/set.2026.243186.1178
)