This repository contains a reading list of papers on Time Series Forecasting/Prediction (TSF) and Spatio-Temporal Forecasting/Prediction (STF). These papers are mainly categorized according to the type of model.

[TPAMI 2024] Awesome Resources of GNNs for Time Series Analysis (GNN4TS)

The official implementation for ICLR23 spotlight paper "DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion"

A comprehesive survey about foundation models for weather and cliamte data understanding.

Occ4cast: LiDAR-based 4D Occupancy Completion and Forecasting

[TKDE 2022] The official PyTorch implementation of the paper "Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs".

TianChi AIEarth Contest Solution

A diffusion-based framework for spatio-temporal point processes

Source code for 'Dual Attention Based FL for Wireless Traffic Prediction'

[AAAI 2019] DeepSTN+: Context-aware Spatial-Temporal Neural Network for Crowd Flow Prediction in Metropolis

[SIGKDD'2025] Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective

[CIKM 2022] Source codes of CIKM2022 Full Paper "Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities"

Semi-Supervised Hierarchical Recurrent Graph Neural Network for City-Wide Parking Availability Prediction

An implementation of LaneGCN (Learning Lane Graph Representations for Motion Forecasting)

[COLM 2024] LITE: Modeling Environmental Ecosystems with Multimodal Large Language Models

This repository contains the code for the paper "ST-MoE-BERT: A Spatial-Temporal Mixture-of-Experts Framework for Long-Term Cross-City Mobility Prediction".

The code of paper "Spatial-Temporal Attention Network for Crime Prediction with Adaptive Graph Learning"

Using a hybrid spatial-temporal deep learning approach to forecast subseasonal weather across 514 Western USA geographical regions

a novel transformer-based architecture named CSTTN for traffic prediction

A web-based tool that predicts crimes based on heterogeneous spatial patterns