Application of artificial intelligence for forecasting surface quality index of irrigation systems in the Red River Delta, Vietnam

Abstract Water sources for irrigation systems in the Red River Delta are crucial to socioeconomic growth of region's communities. Human activities (discharge) have polluted water source recent years, and from upstream is limited. Currently, surface quality index (WQI), which calculated numerous parameters (physical, chemical, microbiological, heavy metals, etc.) frequently used evaluate systems. However, calculation WQI monitoring remains constrained due need a large number relative complexity calculation. To better serve assessment study area, it essential conduct research identify an efficient accurate method calculating WQI. This machine learning deep algorithms calculate with minimal input data (water parameters) reduce cost quality. The Bayes (BMA) select important (BOD 5 , NH 4 + PO 3− turbidity, TSS, coliform, DO). results indicate that model more effective than model, gradient boosting having most prediction because has highest coefficient determination R 2 (0.96). solid scientific basis result application area. also demonstrated potential artificial intelligence improve forecasting compared traditional methods time.