Klasifikasi Curah Hujan Menggunakan Neuro-Fuzzy System Melalui Citra Radar Cuaca

Abstract

Rainfall intensity can be measured one of them through the reading of the reflectivity of raindrops on the weather radar. Reflectivity values are represented through colors in the visualization of two-dimensional radar images. Based on several approaches to the classification of weather conditions through radar data that has been successfully carried out, a system is designed to classify rainfall according to weather conditions in an area by utilizing weather radar imagery.The system implementation is carried out in several stages, namely pre-processing, feature extraction and labeling, and classification. Pre-processing is done to visualize radar data from Yogyakarta Climatology Station into a two-dimensional image. After capturing features using the RGB and HSV methods and labeling the rain class, classification is performed using the Neuro-fuzzy algorithm with the Adaptive Neuro-fuzzy Inference System (ANFIS) architecture. The results showed that the Neuro-fuzzy System algorithm was able to classify rainfall better on the RGB feature with an accuracy of 85.02% and a precision of 86.19%, while for the HSV feature the accuracy was 82.68%, 86.67% precision.