Application of adaptive neuro-fuzzy inference system to model CO۲ emissions of chickpea production in Kangavar county, Iran

The main objectives of this study were determination of carbon dioxide (CO۲) emissions and finding relation between CO۲ emissions and harvested crop usingadaptive neuro-fuzzy inference system (ANFIS) in the production process of chickpea under dry farming system in the Kangavar county of Kermanshah province that is located in the west of Iran. ۲۵ farmers were considered to collect data. Results indicated that total CO۲ emissions in chickpea farms was about۲۲۵ kg CO۲ eq. ha-۱. Diesel fuel was determined as the main CO۲ emitter input with ۱۷۳.۴۹ kg CO۲ eq. that was more than ۷۷% of total emissions. Modeling results revealed that ANFIS architecture with two-level was computed as the best model with cceptable statistical indices. According to ANFIS (۳) results, R۲ was calculated as ۰.۹۵۴ and RMSE and MAE were determined as ۲.۸۲ kg CO۲ eq. and ۰.۵۱, respectively. Finally, it can be concluded that artificial intelligence methods especially ANFIS can be useful for modeling with high accuracy in the agricultural activity.

کلیدواژه ها:

Adaptive neuro-fuzzy inference system ، Agriculture ، Chickpea ، CO۲ ، Prediction