Forecasting Monthly Rainfall in the Pirmam area, Kurdistan Region, Iraq: A Machine Learning Approach.

Agriculture, emergency preparedness, and water resource management all depend on accurate rainfall forecasts. This study investigates how well machine learning models predict monthly rainfall in the Kurdistan Region of Iraq, specifically in the Pirmam area. Historical weather data was analyzed using a variety of models, such as Artificial Neural Networks (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS), Multiple Linear Regression (MLR), Least Absolute Shrinkage and Selection Operator (LASSO), Elastic Net (ELNET), and Ridge Regression. Statistical measures including Nash-Sutcliffe Efficiency (NSE), Mean Bias Error (MBE), Normalized Root Mean Squared Error (nRMSE), Coefficient of Determination (R2), and Root Mean Squared Error (RMSE) were used to assess the performance of these models. According to the findings, ANN was the best model for predicting monthly rainfall in the Pirmam region, demonstrating exceptional accuracy in identifying intricate patterns and non-linear correlations. ANFIS had trouble with validation but did well with calibration. The top three linear models were LASSO, Ridge, MLR, and EN. This study demonstrates how machine learning approaches can improve the accuracy of rainfall forecasts, which can help with regional decision-making on water resource management and climate adaptation plans.