Abstract

Soil organic carbon (SOC) is a very important component of soil that supports the sustainability and quality in all ecosystems, especially in semi-arid region. This study was conducted to evaluate the effects of 15 different climatic, soil, and geometric factors on the SOC contents in different land use patterns and to determine relative importance of these desired variables for SOC estimation in one of the semi arid watershed zones in the western part of Iran. Feed forward back propagation artificial neural networks (ANN), was used to model and predict SOC. The performance of the model was evaluated using R² and MBE values of tested data set. Results showed that 31-2-1 neural networks have highest predictive ability that explains %76 of SOC variability. Neural network models slightly overestimated SOC content, and had higher ability to detect management variables effects on SOC variability. In all ANN structure, management system dominantly controlled SOC variability in rainfed crop land of semi arid condition.

This work is licensed under a Creative Commons Attribution 4.0 License.