Application of Advanced Optimized Soft Computing Models for Atmospheric Variable Forecasting

Precise Air temperature modeling is crucial for a sustainable environment. In this study, novel binary optimized machine learning model, the random vector functional link (RVFL) with integration of Moth Flame Optimization Algorithm (MFO) and Water Cycle (WCA) examined to estimate monthly daily time series Rajshahi Climatic station in Bangladesh. Various combinations precipitation were used predict series. The prediction ability model (RVFL-WCAMFO) compared single models (RVFL-WCA RVFL-MFO) standalone (RVFL). Root mean square errors (RMSE), absolute error (MAE), Nash–Sutcliffe efficiency (NSE), determination coefficient (R2) statistical indexes utilized access selected models. proposed outperformed other air on both scales, i.e., scale. Cross-validation technique was applied determine best testing dataset it found that M3 provided more accurate results scale, whereas M1 two datasets On periodicity input also added see effect accuracy. It improved accuracy precipitation-based inputs did not very comparison temperature-based inputs. outcomes study recommend use RVFL-WCAMFO modeling.