Improving Prediction Accuracy of Solar Radiation for Human Skin Protection using Linear Regression Algorithm Compared with Random Forest

Solar radiation is of vital importance to environmental health, particularly concerning human skin exposure and protection. Too much ultraviolet (UV) radiation from the sun may cause sunburn, premature aging, and skin cancer. In this research, an effective machine learning-based approach is suggested to precisely forecast solar radiation levels to facilitate proactive protection of the skin. Based on real-time meteorological data, the research compares the accuracy and robustness of Linear Regression and Random Forest algorithms in solar radiation intensity prediction. Accuracy and robustness are evaluated using metrics like Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>score. The results reveal that the Random Forest algorithm outperforms Linear Regression considerably in identifying the non-linear relationships in solar radiation data, resulting in better prediction accuracy. This study emphasizes the value of machine learning in environmental health applications and validates the creation of smart skin protective systems that have the ability to give real-time UV exposure notices to people.