Application of ANFIS, ELM, and ANN models to assess water productivity indicators based on agronomic techniques in the Lake Urmia Basin

Abstract Water productivity (WP) is one of the most important critical indicators in essential planning water consumption agricultural sector. For this purpose, WP and economic (WPe) were estimated using agronomic technologies. The impact technologies on WPe was carried out two parts field monitoring modeling novel intelligent approaches. Extreme learning machine (ELM), adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN) methods used to model WPe. A dataset including 200 data collected from five treatment control sections Malekan region, located southeast Lake Urmia, Iran, for crop year 2020–2021. Six different input combinations introduced estimate models evaluated mean squared error (RMSE), relative (RRMSE), efficiency measures (NSE). Field results showed that fields, with application technologies, yield, WP, increased by 17.9%, 30.1%, 19.9%, respectively. explained irrigation farms W1, W2, W3, W4, W5 decreased 23.9%, 21.3%, 29.5%, 16.5%, 2.7%, indicated ANFIS values RMSE = 0.016, RRMSE 0.018, NSE 0.960 performed better estimating than ANN ELM models. confirmed variety, fertilizer, plot dimensions are influencing parameters improving