Article: Spatiotemporal evolution analysis of extreme weather based on adaptive graph convolutional networks Journal: International Journal of Information and Communication Technology (IJICT) 2025 Vol.26 No.46 pp.95 - 113 Abstract: Extreme weather is intensifying and demands forecasts that capture how hazards emerge and travel. To address non-stationary dependencies and rare tails, this paper introduces an adaptive spatiotemporal graph framework. In the scheme, first a fused relational graph blends physical priors with a learned adjacency to follow changing pathways; then a multi-scale temporal encoder links weak precursors to rapid surges; finally calibrated decision layers set cost-aware thresholds and deliver coherent maps with an audit trail. Experiments show gains at six-hour lead: area under the precision-recall curve rises by 8.5% over graph WaveNet and 22% over LSTM, fractions skill at ten kilometres improves from 0.44 to 0.52, the Brier score drops from 0.134 to 0.117, and false alarms fall by about ten percent, while seasonal scores remain between 0.41 and 0.53. Inderscience Publishers - linking academia, business and industry through research

Title: Spatiotemporal evolution analysis of extreme weather based on adaptive graph convolutional networks

Authors: Yadi Zhang; Lin Zhou; Wencheng Sun

Addresses: Southwest Branch, State Grid Corporation of China, Chengdu, 610040, China ' Southwest Branch, State Grid Corporation of China, Chengdu, 610040, China ' Southwest Branch, State Grid Corporation of China, Chengdu, 610040, China

Abstract: Extreme weather is intensifying and demands forecasts that capture how hazards emerge and travel. To address non-stationary dependencies and rare tails, this paper introduces an adaptive spatiotemporal graph framework. In the scheme, first a fused relational graph blends physical priors with a learned adjacency to follow changing pathways; then a multi-scale temporal encoder links weak precursors to rapid surges; finally calibrated decision layers set cost-aware thresholds and deliver coherent maps with an audit trail. Experiments show gains at six-hour lead: area under the precision-recall curve rises by 8.5% over graph WaveNet and 22% over LSTM, fractions skill at ten kilometres improves from 0.44 to 0.52, the Brier score drops from 0.134 to 0.117, and false alarms fall by about ten percent, while seasonal scores remain between 0.41 and 0.53.

Keywords: adaptive graph convolution; extreme weather; spatiotemporal dependence; teleconnections; early warning.

DOI: 10.1504/IJICT.2025.150601

International Journal of Information and Communication Technology, 2025 Vol.26 No.46, pp.95 - 113

Received: 01 Sep 2025
Accepted: 02 Oct 2025
Published online: 17 Dec 2025 *

Title: Spatiotemporal evolution analysis of extreme weather based on adaptive graph convolutional networks

Keep up-to-date