| Abstract |
Precipitation in any structure like a rainstorm, snow, and hail, can influence everyday open-air exercises. Precipitation expectation is one of the difficult errands in the weather condition evaluating process. Because of outrageous environment varieties, an exact precipitation expectation is presently more troublesome than previously. AI strategies can anticipate the precipitation by separating the concealed examples from authentic climate information. The choice of a proper grouping method for expectation is troublesome work. This study proposes an original continuous precipitation expectation framework utilizing machine learning (ML) methods, including Multiple Linear Regression, Integrated technique (Singular Spectrum Analysis (SSA)—Least-Squares Support Vector Regression (LSSVR), SSA—Least Square Random Forest (LSRF)), Artificial Neural Networks (ANN), Deep ESN technique (Echo state Network), Random Forest (RF), and Support Vector Machines (SVM). Pre-handling undertakings, for example, cleaning and standardization are completed based on a dataset that was previously discussed. In this research, the proposed model may show better performance as compared to all mentioned techniques. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. |
