A NOVEL METHOD FOR WEATHER NOWCASTING BASED ON SPATIAL COMPLEX FUZZY INFERENCE WITH MULTIPLE BAND INPUT DATA

The prediction of weather changes, such as rainfall, clouds, floods, and storms, is critical in forecasting. There are several sources input data for this purpose, including radar observational data, but satellite remote sensing images the most commonly used due to their ease collection. In paper, we present a novel method nowcasting based on Mamdani complex fuzzy inference with multiple band data. proposed approach splits process into two parts: first part converts real imaginary parts facilitate rule process, second uses Spatial CFIS+ algorithm generate predicted state, taking account factors cloud, wind, temperature. use MapReduce helps speed up algorithm's performance. Our experimental results show that new outperforms other relevant methods demonstrates improved accuracy.