KDD 2026 | (7月轮)时空数据(Spatial-temporal)论文总结（时空预测，轨迹数据，人群移动，天气预报，多-港品优选

KDD 2026将在2026年8月9日至13日于韩国济州（Jeju, Korea ）举行。

本文总结了KDD 2026（July Cycle）上有关时空数据（Spatial-Temporal）的相关论文。

时空数据Topic：时空（交通）预测，轨迹数据挖掘（表示，生成）人群移动，天气预报以及（多模态）大模型和Agent在时空数据的应用等。

Research Track
1. Incident-Guided Spatiotemporal Traffic Forecasting.
2. Leveraging the Spatial Hierarchy: Coarse-to-fine Trajectory Generation via Cascaded Hybrid Diffusion.
3. DSPIGCN: Dual-stream Physics-informed Graph Convolutional Network for Reliable Pedestrian Trajectory Prediction.
4. CFLight: Enhancing Safety with Traffic Signal Control through Counterfactual Learning.
5. Multi-View Urban Region Embedding via Commonality-Specificity Disentanglement.
6. Traj-MLLM: Can Multimodal Large Language Models Reform Trajectory Data Mining?
7. UniLLM: A Unified Large Language Model for Multi-Modal Urban Dynamics Prediction.
8. RIPCN: A Road Impedance Principal Component Network for Probabilistic Traffic Flow Forecasting.
9. UniExtreme: A Universal Foundation Model for Extreme Weather Forecasting.
10. AnchorGK: Anchor-based Incremental and Stratified Graph Learning Framework for Inductive Spatio-Temporal Kriging.
11. Beyond Routines: Adaptive Mobility Prediction via Sequential-Relational Fusion.
12. Towards Resilient Transportation: A Conditional Transformer for Accident-Informed Traffic Forecasting.
13. CSSG: A Continuous Spatio-temporal Graph Learning Framework with Scalable Spatial Granularity.
14. MoST: A Foundation Model for Multi-modality Spatio-temporal Traffic Prediction.
15. FaST: Efficient and Effective Long-Horizon Forecasting for Large-Scale Spatial-Temporal Graphs via Mixture-of-Experts.
16. Think2Go: Generative Next POI Recommendation with LLM Reasoning.
17. KFTD: Koopman-Fourier Time-Differentiable Network for Continuous Ocean Spatiotemporal Forecasting.
18. Spatiotemporal Graph Learning with Direct Volumetric Information Passing and Feature Enhancement.
ADS Track
19. StormMind: Disentangled Layerwise Modeling for Convective Weather Systems.
20. ASTAFN: Bridging the Gap Between Weather Foundation Models and Accurate Station-Level Forecasting.
Data & Benchmark Track
21. Generating Realistic Human Mobility Data with Hybrid Large Language Model Agent.
22. Learning Multimodal Embeddings for Traffic Accident Prediction and Causal Estimation.
23. FireSentry: A Multi-Modal Spatio-temporal Benchmark Dataset for Fine-Grained Wildfire Spread Forecasting.

Research Track

1 Incident-Guided Spatiotemporal Traffic Forecasting.

链接：https://dl.acm.org/doi/10.1145/3770854.3780215

代码：https://github.com/fanlixiang/IGSTGNN

作者：Lixiang Fan, Bohao Li, Tao Zou, Junchen Ye, Bowen Du

关键词：交通预测，事件驱动

2 Leveraging the Spatial Hierarchy: Coarse-to-fine Trajectory Generation via Cascaded Hybrid Diffusion.

链接：https://dl.acm.org/doi/10.1145/3770854.3780191

代码：https://github.com/urban-mobility-generation/Cardiff

作者：Baoshen Guo, Zhiqing Hong, Junyi Li, Shenhao Wang, Jinhua Zhao

关键词：轨迹生成，扩散模型，多层级多尺度

3 DSPIGCN: Dual-stream Physics-informed Graph Convolutional Network for Reliable Pedestrian Trajectory Prediction.

链接：https://dl.acm.org/doi/10.1145/3770854.3780329

作者：Runkang Guo, Bin Chen, Zhengqiu Zhu, Chen Gao, Yong Zhao, Quanjun Yin

关键词：轨迹预测，物理驱动，对偶时空图，物理运动学，锚点采样?

4 CFLight: Enhancing Safety with Traffic Signal Control through Counterfactual Learning.

链接：https://dl.acm.org/doi/10.1145/3770854.3780308

代码：https://github.com/MJLee00/CFLight

作者：Mingyuan Li, Chunyu Liu, Zhuojun Li, Xiao Liu, Guangsheng Yu, Bo Du, Jun Shen, Qiang Wu

关键词：信号灯控制，反事实学习

5 Multi-View Urban Region Embedding via Commonality-Specificity Disentanglement.

链接：https://dl.acm.org/doi/10.1145/3770854.3780234

代码：https://github.com/AIMUrban/ComSRE

作者：Zechen Li, Hongwei Jia, Kai Zhao, Weiming Huang, Meng Chen

关键词：城市区域嵌入，多视图表示学习，城市画像

6 Traj-MLLM: Can Multimodal Large Language Models Reform Trajectory Data Mining?

链接：https://dl.acm.org/doi/10.1145/3770854.3780225

作者：Shuo Liu, Di Yao, Yan Lin, Gao Cong, Jingping Bi

关键词：轨迹表示学习，多模态大模型

7 UniLLM: A Unified Large Language Model for Multi-Modal Urban Dynamics Prediction.

链接：https://dl.acm.org/doi/10.1145/3770854.3780232

代码：https://github.com/Yliu1111/UniLLM

作者：Yuhang Liu, Yingxue Zhang, Xin Zhang, Yanhua Li, Jun Luo

关键词：城市需求预测，多模态，大模型，统一模型

8 RIPCN: A Road Impedance Principal Component Network for Probabilistic Traffic Flow Forecasting.

链接：https://dl.acm.org/doi/10.1145/3770854.3780183

代码：https://github.com/LvHaochenBANG/RIPCN

作者：Haochen Lv, Yan Lin, Shengnan Guo, Xiaowei Mao, Hong Nie, Letian Gong, Youfang Lin, Huaiyu Wan

关键词：交通预测，不确定性估计，主成分分析

9 UniExtreme: A Universal Foundation Model for Extreme Weather Forecasting.

链接：https://dl.acm.org/doi/10.1145/3770854.3780172

代码：https://github.com/usail-hkust/UniExtreme

作者：Hang Ni, Weijia Zhang, Hao Liu

关键词：（极端）天气预测，基础模型，频域

10 AnchorGK: Anchor-based Incremental and Stratified Graph Learning Framework for Inductive Spatio-Temporal Kriging.

链接：https://dl.acm.org/doi/10.1145/3770854.3780189

代码：https://github.com/xren451/Spatial-interpolation

作者：Xiaobin Ren, Kaiqi Zhao, Katerina Taskova, Patricia Riddle

关键词：时空克里格，增量训练，不完美特征，空间相关性，GNN

11 Beyond Routines: Adaptive Mobility Prediction via Sequential-Relational Fusion.

链接：https://dl.acm.org/doi/10.1145/3770854.3780268

代码：https://github.com/AIMUrban/ROAM

作者：Tianao Sun, Ruizhe Liu, Wenzhen Jia, Kai Zhao, Weiming Huang, Meng Chen

关键词：下一位置预测，非常规行为，人类移动建模

12 Towards Resilient Transportation: A Conditional Transformer for Accident-Informed Traffic Forecasting.

链接：https://dl.acm.org/doi/10.1145/3770854.3780312

代码：https://github.com/Dreamzz5/ConFormer

作者：Hongjun Wang, Jiawei Yong, Jiawei Wang, Shintaro Fukushima, Renhe Jiang

关键词：时空预测，交通事故

13 CSSG: A Continuous Spatio-temporal Graph Learning Framework with Scalable Spatial Granularity.

链接：https://dl.acm.org/doi/10.1145/3770854.3780161

代码：https://github.com/kaiwxai/CSSG

作者：Kaiwen Xia, Li Lin, Qi Zhang, Xinrui Zhang, Shuai Wang, Xuming Hu, Philip S. Yu

关键词：时空预测，动态图，可扩展的空间粒度

14 MoST: A Foundation Model for Multi-modality Spatio-temporal Traffic Prediction.

链接：https://dl.acm.org/doi/10.1145/3770854.3780162

作者：Ronghui Xu, Jihao Chen, Jindong Tian, Chenjuan Guo, Bin Yang

关键词：时空预测，多模态学习，基础模型

15 FaST: Efficient and Effective Long-Horizon Forecasting for Large-Scale Spatial-Temporal Graphs via Mixture-of-Experts.

链接：https://dl.acm.org/doi/10.1145/3770854.3780165

代码：https://github.com/yijizhao/FaST

作者：Yiji Zhao, Zihao Zhong, Ao Wang, Haomin Wen, Ming Jin, Yuxuan Liang, Huaiyu Wan, Hao Wu

关键词：长程预测，大规模时空图，混合专家系统（MoE)

16 Think2Go: Generative Next POI Recommendation with LLM Reasoning.

链接：https://dl.acm.org/doi/10.1145/3770854.3780334

作者：Zhuang Zhuang, Shanshan Feng, Hangwei Qian, Mingqi Yang, Heng Qi, Yanming Shen, Baocai Yin

关键词：POI推荐，生成模型，推理模型，LLM

17 KFTD: Koopman-Fourier Time-Differentiable Network for Continuous Ocean Spatiotemporal Forecasting.

链接：https://dl.acm.org/doi/10.1145/3770854.3780278

作者：Qinghui Chen, Zekai Zhang, Hailong Liu, Jinglin Zhang, Cong Bai

关键词：时空预报，海洋动力学，业务海洋预报，物理信息学习，库普曼神经网络算子

18 Spatiotemporal Graph Learning with Direct Volumetric Information Passing and Feature Enhancement.

链接：https://dl.acm.org/doi/10.1145/3770854.3780155

代码：https://github.com/intell-sci-comput/CeFeGNN

作者：Yuan Mi, Qi Wang, Xueqin Hu, Yike Guo, Ji-Rong Wen, Yang Liu, Hao Sun

关键词：图学习，时空预测，高阶动力学

ADS Track

19 StormMind: Disentangled Layerwise Modeling for Convective Weather Systems.

链接：https://dl.acm.org/doi/10.1145/3770854.3783926

作者：Jun Chen, Minghui Qiu, Lin Chen, Yan Fang, Shuxin Zhong, Binghong Chen, Kaishun Wu

关键词：天气系统、降水临近预报

20 ASTAFN: Bridging the Gap Between Weather Foundation Models and Accurate Station-Level Forecasting.

链接：https://dl.acm.org/doi/10.1145/3770854.3783935

代码：https://github.com/xubihe-bjtu/ASTAFN

作者：Bihe Xu, Zhicheng Yan, Qingyong Li, Zhiqing Guo, Dong Zheng, Wen Yao, Bo Wang, Zhao Wang, Yangliao Geng

关键词：天气基础模型，站点级天气预报

Data & Benchmark Track

21 Generating Realistic Human Mobility Data with Hybrid Large Language Model Agent.

链接：https://dl.acm.org/doi/10.1145/3770854.3785685

代码：https://github.com/tsinghua-fib-lab/CoPB

作者：Chenyang Shao, Bingbing Fan, Jingtao Ding, Yuan Yuan, Meng Wang, Fengli Xu

关键词：移动数据生成，扩散模型，LLM Agent

22 Learning Multimodal Embeddings for Traffic Accident Prediction and Causal Estimation.

链接：https://dl.acm.org/doi/10.1145/3770854.3785677

代码：https://github.com/VirtuosoResearch/MMTraCE

作者：Ziniu Zhang, Minxuan Duan, Haris N. Koutsopoulos, Hongyang R. Zhang

关键词：多模态学习，卫星图像，道路安全，因果分析

21 FireSentry: A Multi-Modal Spatio-temporal Benchmark Dataset for Fine-Grained Wildfire Spread Forecasting.

链接：https://dl.acm.org/doi/10.1145/3770854.3785696

代码：https://github.com/Munan222/FireSentry-Benchmark-Dataset

作者：Nan Zhou, Huandong Wang, Jiahao Li, Han Li, Yali Song, Qiuhua Wang, Yong Li, Xinlei Chen

关键词：野火蔓延预测，精细化，多模态数据集，生成模型

企业官网建设流程全解析

Research Track

1 Incident-Guided Spatiotemporal Traffic Forecasting.

2 Leveraging the Spatial Hierarchy: Coarse-to-fine Trajectory Generation via Cascaded Hybrid Diffusion.

3 DSPIGCN: Dual-stream Physics-informed Graph Convolutional Network for Reliable Pedestrian Trajectory Prediction.

4 CFLight: Enhancing Safety with Traffic Signal Control through Counterfactual Learning.

5 Multi-View Urban Region Embedding via Commonality-Specificity Disentanglement.

6 Traj-MLLM: Can Multimodal Large Language Models Reform Trajectory Data Mining?

7 UniLLM: A Unified Large Language Model for Multi-Modal Urban Dynamics Prediction.

8 RIPCN: A Road Impedance Principal Component Network for Probabilistic Traffic Flow Forecasting.

9 UniExtreme: A Universal Foundation Model for Extreme Weather Forecasting.

10 AnchorGK: Anchor-based Incremental and Stratified Graph Learning Framework for Inductive Spatio-Temporal Kriging.

11 Beyond Routines: Adaptive Mobility Prediction via Sequential-Relational Fusion.

12 Towards Resilient Transportation: A Conditional Transformer for Accident-Informed Traffic Forecasting.

13 CSSG: A Continuous Spatio-temporal Graph Learning Framework with Scalable Spatial Granularity.

14 MoST: A Foundation Model for Multi-modality Spatio-temporal Traffic Prediction.

15 FaST: Efficient and Effective Long-Horizon Forecasting for Large-Scale Spatial-Temporal Graphs via Mixture-of-Experts.

16 Think2Go: Generative Next POI Recommendation with LLM Reasoning.

17 KFTD: Koopman-Fourier Time-Differentiable Network for Continuous Ocean Spatiotemporal Forecasting.

18 Spatiotemporal Graph Learning with Direct Volumetric Information Passing and Feature Enhancement.

ADS Track

19 StormMind: Disentangled Layerwise Modeling for Convective Weather Systems.

20 ASTAFN: Bridging the Gap Between Weather Foundation Models and Accurate Station-Level Forecasting.

Data & Benchmark Track

21 Generating Realistic Human Mobility Data with Hybrid Large Language Model Agent.

22 Learning Multimodal Embeddings for Traffic Accident Prediction and Causal Estimation.

21 FireSentry: A Multi-Modal Spatio-temporal Benchmark Dataset for Fine-Grained Wildfire Spread Forecasting.

热门文章

文章分类

标签云

需要专业的网站建设服务？

企业官网建设流程全解析

Research Track

1 Incident-Guided Spatiotemporal Traffic Forecasting.

2 Leveraging the Spatial Hierarchy: Coarse-to-fine Trajectory Generation via Cascaded Hybrid Diffusion.

3 DSPIGCN: Dual-stream Physics-informed Graph Convolutional Network for Reliable Pedestrian Trajectory Prediction.

4 CFLight: Enhancing Safety with Traffic Signal Control through Counterfactual Learning.

5 Multi-View Urban Region Embedding via Commonality-Specificity Disentanglement.

6 Traj-MLLM: Can Multimodal Large Language Models Reform Trajectory Data Mining?

7 UniLLM: A Unified Large Language Model for Multi-Modal Urban Dynamics Prediction.

8 RIPCN: A Road Impedance Principal Component Network for Probabilistic Traffic Flow Forecasting.

9 UniExtreme: A Universal Foundation Model for Extreme Weather Forecasting.

10 AnchorGK: Anchor-based Incremental and Stratified Graph Learning Framework for Inductive Spatio-Temporal Kriging.

11 Beyond Routines: Adaptive Mobility Prediction via Sequential-Relational Fusion.

12 Towards Resilient Transportation: A Conditional Transformer for Accident-Informed Traffic Forecasting.

13 CSSG: A Continuous Spatio-temporal Graph Learning Framework with Scalable Spatial Granularity.

14 MoST: A Foundation Model for Multi-modality Spatio-temporal Traffic Prediction.

15 FaST: Efficient and Effective Long-Horizon Forecasting for Large-Scale Spatial-Temporal Graphs via Mixture-of-Experts.

16 Think2Go: Generative Next POI Recommendation with LLM Reasoning.

17 KFTD: Koopman-Fourier Time-Differentiable Network for Continuous Ocean Spatiotemporal Forecasting.

18 Spatiotemporal Graph Learning with Direct Volumetric Information Passing and Feature Enhancement.

ADS Track

19 StormMind: Disentangled Layerwise Modeling for Convective Weather Systems.

20 ASTAFN: Bridging the Gap Between Weather Foundation Models and Accurate Station-Level Forecasting.

Data & Benchmark Track

21 Generating Realistic Human Mobility Data with Hybrid Large Language Model Agent.

22 Learning Multimodal Embeddings for Traffic Accident Prediction and Causal Estimation.

21 FireSentry: A Multi-Modal Spatio-temporal Benchmark Dataset for Fine-Grained Wildfire Spread Forecasting.

热门文章

文章分类

标签云

相关文章

AGV与快速门联动控制：工业自动化物流无人化关键方案

基于DeepSeek的AI字幕翻译实践：从SRT文件处理到批量自动化

Codex接入DeepSeek实战：解决中文不生效与稳定部署指南

需要专业的网站建设服务？