Feature Importance in Machine Learning with Explainable Artificial Intelligence (XAI) for Rainfall Prediction

• Published in: ITM web of conferences Vol. 65; p. 3007
• Main Authors: Patel, Mehul, Shah, Ankit
• Format: Journal Article Conference Proceeding
• Language: English
• Published: Les Ulis EDP Sciences 2024
• Subjects: Explainable artificial intelligence; Machine learning; machine learning and ai; Rainfall; remote sensing; Weather; Weather forecasting; xai
• ISSN: 2271-2097; 2431-7578; 2271-2097
• DOI: 10.1051/itmconf/20246503007

Precipitation expectation is a pivotal subject for the administration of water assets and counteraction of hydrological calamities. To make a precipitation forecast and find the essential elements influencing precipitation, this study presents a logical profound learning approach in two sections. The initial segment with a consideration system which could foresee precipitation, while second part the clarification figures attribution values for the information weather conditions elements to evaluate their significance. A contextual investigation is led on hourly precipitation information for India’s population wise top eight urban cities. The outcomes predominantly demonstrate that the main elements for precipitation whose component esteem is adversely/decidedly corresponded with its attribution esteem. The review’s importance lies in upgrading the giving interpretability through recognizable proof of persuasive variables, which works with long haul arranging of water assets and more profound comprehension of mind-boggling climate frameworks.