Machine Learning Models of Exergoenvironmental Damages and Emissions Social Cost for Mushroom Production

Applying conventional methods for prediction of environmental impacts in agricultural production is not actually applicable because they usually ignore other aspects such as useful energy and economic consequence. As such, this article evaluates intelligent models exergoenvironmental damage emissions social cost (ESC) mushroom Isfahan province, Iran, by three machine learning (ML) methods, namely adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN), support vector regression (SVR). Accordingly, life cycle damages, cumulative exergy demand, ESC are examined the ReCiPe2016 method 100 tons after data collection interview. Exergoenvironmental results reveal that, human health ecosystems, direct emissions, resources categories, diesel fuel compost main hotspots. Economic analysis also shows that total about 1035$. Results ML indicate ANN with a 6-8-3 structure optimum topology forecasting outputs. Moreover, two-level ANFIS has weak comparison ANN. However, (SVR) an absolute average relative error (AARE) (%) between 0.85 1.03 (based on specific unit), coefficient determination (R2) 0.989 0.993 root mean square (RMSE) 0.003 0.011 unit) selected best model. It concluded can furnish comprehensive exergoenvironmental-economical assessment products.