Terra is a global multimodal spatiotemporal dataset jointly created by the Hong Kong University of Science and Technology (Guangzhou) and Sichuan University in 2024.Terra: A Multimodal Spatio-Temporal Dataset Spanning the EarthThis dataset provides 45 years of spatiotemporal data worldwide, covering 6.48 million high-resolution grid points, and is designed to promote future research in spatiotemporal data mining and advance the realization of broader spatiotemporal intelligence.

Citation

@inproceedings{chen2024terra, title={Terra: A Multimodal Spatio-Temporal Dataset Spanning the Earth}, author={Wei Chen, Xixuan Hao, Yuankai Wu, Yuxuan Liang} booktitle={Advances in Neural Information Processing Systems}, year={2024} }