物理启发的图神经网络大气污染预报模型|周二直播 · 地球系统科学读书会

导语

分享背景
分享背景

分享简介
分享简介
分享大纲
分享大纲
-
大气污染研究背景、图神经网络简介
-
PCDCNet: 融入物理约束的大气污染代理模型
-
大气污染污染模拟、遥感数据同化
-
AI 大数据时代地球系统科学面临的机遇与挑战
核心概念
核心概念
• 图神经网络 (Graph Neural Network, GNN)
• 时空预测 (Spatio-temporal Prediction)
• 时序预测 (Time Series Prediction)
• 社区多尺度空气质量 (Community Multiscale Air Quality, CMAQ)
• 大气污染模拟 (Atmospheric Pollution Simulation)
主讲人简介
主讲人简介

报名参与
报名参与
直播信息
2025年3月11日19:00-21:00
报名加入社群(可开发票)

斑图链接:https://pattern.swarma.org/study_group_issue/867
推荐阅读
推荐阅读
-
Shuo Wang, et al.. 2025. PCDCNet: A Surrogate Model for Air Quality Forecasting with Physical-Chemical Dynamics and Constraints. In Submission.
-
Shuo Wang, et al.. 2020. PM2.5-GNN: A domain knowledge enhanced graph neural network for pm2.5 forecasting. ACM SIGSPATIAL.
-
George Em Karniadakis, et al.. 2021. Physics-informed machine learning. Nature Reviews Physics.
-
Thomas Kipf, et al.. 2017. Semi-supervised classification with graph convolutional networks. ICLR.
-
Zhaoqi Gao, et al.. 2024. A review of the CAMx, CMAQ, WRF-Chem and NAQPMS models: Application, evaluation and uncertainty factors. Environmental Pollution.
-
Jinghai Li, et al.. 2019. Paradigm shift in science with tackling global challenges. National Science Review.
-
Markus reichstein, et al.. 2019. Deep learning and process understanding for data-driven Earth system science. Nature
-
Jindong Tian, et al.. 2025. Air Quality Prediction with Physics-Informed Dual Neural ODEs in Open Systems. ICLR.
地球系统科学读书会





