Artificial intelligence models for prediction of monthly rainfall without climatic data for meteorological stations in Ethiopia

Abstract Global climate change is affecting water resources and other aspects of life in many countries. Rainfall the most significant element livelihood well-being majority Ethiopians. variability has a great impact on agricultural production, supply, transportation, environment, urban planning. Because all activities subsequent national crop production hinge amount distribution rainfall, accurate monthly seasonal predictions this rainfall are vital for prediction also useful governmental, non-governmental, private agencies making long-term decisions planning numerous areas such as farming, early warning potential hazards, drought mitigation, disaster prevention, insurance policy. Artificial Intelligence (AI) been widely used almost every area, one them. In study, we attempt to investigate use AI-based models predict at 92 Ethiopian meteorological stations. The applicability Neural Networks (ANNs) Adaptive Neuro-Fuzzy Inference System (ANFIS) predicting precipitation was investigated using geographical periodicity component (longitude, latitude, altitude) data collected from 2011 2021. experimental results reveal that ANFIS model outperforms ANN assessment criteria across testing Nash–Sutcliffe efficiency coefficients were 0.995 0.935 over