Accurate rainfall forecasting plays a crucial role in flood prediction, water resource management, and environmental planning, particularly in flood-prone regions. This study develops an Adaptive Neuro-Fuzzy Inference System (ANFIS) model for forecasting rainfall and predicting potential river discharge in Lokoja, Kogi State, Nigeria. Meteorological data comprising temperature, relative humidity, wind speed, and rainfall for the month of July were obtained from the Nigerian Meteorological Agency (NiMet) for the years 2023–2025. These parameters were used as input variables to the ANFIS model, while rainfall served as the output variable. The model was implemented using the MATLAB ANFIS toolbox with generalized bell membership functions and a hybrid learning algorithm for parameter optimization. Model performance was evaluated using statistical indicators such as Mean Absolute Percentage Error (MAPE), Mean Square Error (MSE), Root Mean Square Error (RMSE), and correlation coefficient (R). The developed model achieved a MAPE of approximately 3% and prediction efficiency of about 97%, demonstrating strong predictive capability. The results indicate that rainfall intensity is likely to increase significantly toward the end of July 2026, with peak rainfall expected on the 28th and 29th, suggesting a high possibility of river discharge around the River Niger in Lokoja. The study confirms that ANFIS is a reliable tool for rainfall forecasting and flood risk assessment
Stephen et al. (Tue,) studied this question.