ABSTRACT
A sequence of radar echo maps can visually show the motion and variation trends of the echo area, making it a common tool for precipitation forecasting. The spatiotemporal context reveals the correlations of variation trends among different parts within the echo area. This paper proposes a novel precipitation forecasting model, ISTC-SA-MIM (Interactive Spatiotemporal Context Learning with Self-Attention and Memory in Memory), based on the MIM. Leveraging the spatiotemporal interactions and self-attention mechanism of the ISTC-SA structure, the proposed model effectively captures both long-term and short-term spatiotemporal contexts. By memorizing the spatiotemporal context and non-stationary information, ISTC-SA-MIM can accurately predict the motion and variation trends of the echo area. Radar echo data from the Qingdao station are collected as the dataset to evaluate the commonly used spatiotemporal models and ISTC-SA-MIM. The experiments demonstrate that ISTC-SA-MIM can predict the variation trends of the echo area more accurately by learning the spatiotemporal context.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Additional information
Funding
Notes on contributors
Lianen Qu
Lianen Qu received his B.S. degree in Computer Science from Qingdao University of Science and Technology, Qingdao, China, in 2005, and his M.S. degree in Computer Software and Theory from Ocean University China in 2010. He obtained his Ph.D. degree in Computer Science from the Asian Institute of Technology. His research interests include computer vision, machine learning, and weather prediction based on deep learning.
Zhongwei Qu
Zhongwei Qu received his B.S. degree in Computer Science from Qilu Normal University, Jinan, China, in 2020, and his M.S. degree in Computer Science from Qingdao University of Technology, Qingdao, China, in 2023. His research interests include deep learning. He is currently working on utilizing deep learning techniques to process radar data for weather prediction.
Qiang Hu
Qiang Hu received his Ph.D. degree from Shandong University of Science and Technology, Qingdao, China, in 2014. He is currently an associate professor in the College of Information Science and Technology at Qingdao University of Science and Technology, Qingdao, China. His research interests include formal methods, service computing, and text mining.
Minghua Liu
Minghua Liu, Doctor of Engineering, associate professor, and master tutor, is mainly engaged in research in robotics, unmanned aerial systems, computer vision, and pattern recognition. His technical expertise encompasses machine learning, deep learning-based target detection and tracking, UAV target detection and tracking, attitude estimation and action recognition, image understanding, and segmentation.
Zhikao Ren
Zhikao Ren is an associate professor in the College of Information Science and Technology at Qingdao University of Science and Technology. His primary research focuses on computer system development technology and deep learning. He has previously worked as a computer system development technology engineer on various projects. His research interests include encompass computer system development technology, machine learning and the application of deep learning in the field of computer system development engineering.