Researchers at Srinakharinwirot University's Department of Computer Engineering have developed a rainfall forecasting model using an Adaptive Neuro-Fuzzy Inference System (ANFIS). The approach combines the learning capabilities of neural networks with the reasoning of fuzzy logic to predict precipitation patterns more accurately.
The system, presented in a recent video by the SWU SoftwareEngineer channel, demonstrates how ANFIS can handle the inherent uncertainty and non-linearity of weather data. By training on historical rainfall records, the model learns complex relationships between atmospheric variables and rainfall amounts.
This work is part of ongoing research at the Computational Intelligence Research Lab (CIRL), which focuses on applying AI techniques to real-world problems. The team aims to improve prediction reliability for agriculture, water resource management, and disaster preparedness.
The video also highlights related projects, including neuro-fuzzy systems for diabetes diagnosis, battery fuel usage in hybrid vehicles, corn leaf disease detection, and electric motor fault detection. These applications showcase the versatility of hybrid intelligent systems across domains.
While the video is in Thai, the technical content focuses on the ANFIS architecture and its advantages over traditional statistical models. The research underscores the growing role of computational intelligence in environmental monitoring.