UTAR researchers win Best Paper Award at international science and technology conference

A team of researchers from UTAR received the Best Paper Award at the 5th International Conference on Science, Engineering, and Technology (ICSET 2025), held from 13 to 14 November 2025 at The Pacific Sutera Hotel, Kota Kinabalu. Organised as a global platform for advancing ideas in science and engineering, ICSET 2025 brought together leading scholars, industry experts, and innovators to discuss pressing technological and environmental challenges.

The award-winning research paper, titled Machine Learning-Based Enhancement of CMORPH Satellite Rainfall Estimates: A Case Study in Kuala Lumpur, Selangor and Putrajaya, was the result of a strategic collaboration between UTAR, Universiti Malaysia Sabah (UMS), and India’s SRM Institute of Science and Technology. The research was led by Ts Dr Chin Ren Jie from the Department of Civil Engineering, Lee Kong Chian Faculty of Engineering and Science (LKC FES), UTAR, alongside Assoc Prof Ir Dr Ling Lloyd and Ms Chai Kai Li, also of LKC FES. Chai, a former final year project student under Dr Chin’s supervision, graduated with a Bachelor of Civil Engineering with Honours in June 2024. Their co-researchers included Dr Eugene Soo Zhen Xiang from UMS, and Dr Naga Malleswari T Y J and Dr Ushasukhanya S from SRM Institute.

The award recognised the team’s innovation in addressing the longstanding issue of rainfall data accuracy in urban Malaysia. Noting the limitations of traditional CMORPH satellite rainfall products, particularly in detecting localised and high-intensity tropical storms, the researchers proposed a novel enhancement technique using machine learning (ML). The study integrated three robust ML models: Artificial Neural Network (ANN), Random Forest (RF), and Support Vector Machine (SVM), alongside essential meteorological variables. The approach yielded significantly improved rainfall estimates, which are expected to benefit flood forecasting, climate adaptation, and hydrological modelling efforts.

“This recognition strengthens the credibility and visibility of our research on satellite-based rainfall estimation, especially in the context of urban flood resilience and climate adaptation,” remarked Dr Chin. He also added, “It also highlights the importance of integrating machine learning with remote sensing, and reflects the strength of our partnership with SRM Institute and UMS.”