The accuracy of seismic attribute prediction directly affects the interpretation of underground structures and the identification of oil and gas reservoirs. In view of the difficulty of traditional methods in modeling non-Euclidean spatial dependencies and physical dynamics, this paper proposes a joint prediction met...
Guo-Qing Chen, Tian-Wen Zhao, Cong Pang et al.· Scientific Reports· 0 citations
Green finance is widely regarded as a key policy instrument for China’s carbon neutrality goals, yet identifying its effect on low-carbon transition requires addressing green finance’s high correlation with regional development, and its nonlinear features remain insufficiently tested at a fine geographic scale. Using a...
Yan-Qin Xu, Monchaya Chiangpradit, P. Busababodhin· Sustainability· 0 citations
This paper addresses the challenges of nonlinearity, spatiotemporal dependence, and coupling with external factors in global trade network forecasting. A hybrid model (ST-GBDT) integrating spatiotemporal graph neural networks and gradient boosting decision trees is proposed. This model constructs a multi-channel spat...