Cloud Affected Solar UV Prediction With Three-Phase Wavelet Hybrid Convolutional Long Short-Term Memory Network Multi-Step Forecast System

Harmful exposure to erythemally-effective ultraviolet radiation (UVR) poses high health risks such as malignant keratinocyte cancers and eye-related diseases. Delivering short-term forecasts of the solar index (UVI) is an effective way advise UVR information public at risk. This research reports on a novel framework built forecast UVI, integrating antecedent lagged memory cloud statistical properties zenith angle (SZA). To produce multi-step horizon we design 3-phase hybrid convolutional long network (W-O-convLSTM) model, validated with Queensland-based datasets in near real-time ( i.e ., 10-minute, 20-minute, 30-minute 1 hour horizon). Our approach optimizing performance also entails robust selective filtering method using BorutaShap algorithm, data decomposition stationary wavelet transformation hyperparameter optimization Optuna algorithm. We assess proposed W-O-convLSTM model alongside baseline benchmark models. The captured results, through metrics visual infographics, elucidate superior objective UVI forecasting. For instance, 10-minute horizon, our yields relatively correlation coefficient ~0.961 autumn, 0.909 summer, 0.926 spring 0.936 winter season. Overall, O-convLSTM outperforms its competing counterpart models for all horizons lowest absolute error. robustness newly avers practical utility delivering sun-protection behavior recommendations that can mitigate UV-exposure-related recommend future integration aerosol ozone effects cover enhance forecasting wider applications energy or skin monitoring systems.