Fuzzy Ranking Algorithm with Seagull Optimization-Based Decision Tree for Short-Term/Long-Term Rainfall Prediction

Abstract

An exact rainfall prediction is a major challenge for agriculture subordinate nations for evaluating the productivity of crop, utilization of water resources and preplanning of water assets. Besides, because of different climate nature, rainfall prediction system cannot execute well for short-term and long-term rainfall prediction. Thus, to enhance the accuracy of short-term and long-term rainfall prediction, hybrid machine learning techniques are used in this approach. At first, we present fuzzy ranking algorithm to select the optimal subset of features. Using the selected features, short-term and long-term rainfalls are predicted by presenting optimized Decision Tree (DT). The decision node or upper level of the DT is chosen optimally using seagull optimization algorithm (SOA). Results of the article prove that the proposed rainfall prediction model obtains better accuracy than the existing prediction models.