SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery
The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Abstract
Geographic information is essential for modeling tasks in fields ranging from ecology to epidemiology. However, extracting relevant location characteristics for a given task can be challenging, often requiring expensive data fusion or distillation from massive global imagery datasets. To address this challenge, we introduce Satellite Contrastive Location-Image Pretraining (SatCLIP). This global, general-purpose geographic location encoder learns an implicit representation of locations by matching CNN and ViT inferred visual patterns of openly available satellite imagery with their geographic coordinates. The resulting SatCLIP location encoder efficiently summarizes the characteristics of any given location for convenient use in downstream tasks. In our experiments, we use SatCLIP embeddings to improve performance on nine diverse geospatial prediction tasks including temperature prediction, animal recognition, and population density estimation. Across tasks, SatCLIP consistently outperforms alternative location encoders and shows promise for improving geographic domain adaptation. These results demonstrate the potential of vision-location models to learn meaningful representations of our planet from the vast, varied, and largely untapped modalities of geospatial data.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“While these approaches represent progress in the application of ML to EO data, none satisfy all of the following key properties: (1) multi-source or multi-modality, (2) inclusion of time into the modeling framework, or (3) spatial resolution at a precision useful for serving operational mapping use cases.”
From AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data (2025) · cites this paper as Klemmer et al., 2025
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“A new generation of geospatial foundation model approaches can be roughly characterized as derivatives of SatMAE (Cong et al., 2022) or implicit models such as SatCLIP (Klemmer et al., 2025).”
From AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data (2025) · cites this paper as Klemmer et al., 2025
In the citing paper
“SatCLIP is a deep learning-based approach that takes inspiration from CLIP approach (Radford et al., 2021), training location and image encoders via contrastive learning and matching images to their corresponding locations (Klemmer et al., 2025).”
From AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data (2025) · cites this paper as Klemmer et al., 2025
In the citing paper
“We evaluate only the SatCLIP Vit16-L40 model, which outperforms other versions according to the SatCLIP paper (Klemmer et al., 2025).”
From AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data (2025) · cites this paper as Klemmer et al., 2025
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
An ecoregion-based approach to protecting half the terrestrial realm
Dinerstein, E., Olson, D., Joshi, A., Vynne, C., Burgess, N. D., Wikramanayake, E., Hahn, N., Palminteri, S., Hedao, P., Noss, R., et al. (2017) · BioScience · doi:10.1093/biosci/bix014 · Cited by 2,460
Research works printed but not linked: 28
- Beery, S.; Wu, G.; Edwards, T.; Pavetic, F.; Majewski, B.; Mukher- jee, S.; Chan, S.; Morgan, J.; Rathod, V.; and Huang, J. 2022. The Auto Arborist Dataset: A Large-Scale Benchmark for Multiview Urban Forest Monitoring Under Domain Shift. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 21294-21307.
- Cepeda, V. V.; Nayak, G. K.; and Shah, M. 2023. GeoCLIP: Clip- Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization. arXiv preprint arXiv:2309.16020. · arXiv
- Chen, C.; Li, K.; Teo, S. G.; Zou, X.; Wang, K.; Wang, J.; and Zeng, Z. 2019. Gated residual recurrent graph neural networks for traffic prediction. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, 485-492. AAAI Press. ISBN 9781577358091.
- Christie, G.; Fendley, N.; Wilson, J.; and Mukherjee, R. 2018. Functional Map of the World. In Proceedings of the IEEE Com- puter Society Conference on Computer Vision and Pattern Recog- nition (CVPR), 6172-6180.
- Cole, E.; Horn, G. V.; Lange, C.; Shepard, A.; Leary, P.; Perona, P.; Loarie, S.; and Mac Aodha, O. 2023. Spatial Implicit Neu- ral Representations for Global-Scale Species Mapping. In Krause, A.; Brunskill, E.; Cho, K.; Engelhardt, B.; Sabato, S.; and Scarlett, J., eds., Proceedings of the 40th International Conference on Ma- chine Learning, volume 202 of Proceedings of Machine Learning Research, 6320-6342.
- PMLR.
- Dosovitskiy, A.; Beyer, L.; Kolesnikov, A.; Weissenborn, D.; Zhai, X.; Unterthiner, T.; Dehghani, M.; Minderer, M.; Heigold, G.; Gelly, S.; et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929. · arXiv
- He, K.; Fan, H.; Wu, Y.; Xie, S.; and Girshick, R. 2020. Momen- tum contrast for unsupervised visual representation learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 9729-9738.
- Horn, G. V.; Aodha, O. M.; Song, Y.; Cui, Y.; Sun, C.; Shepard, A.; Adam, H.; Perona, P.; Belongie, S.; Google, C. .; and Tech, C. 2018. The iNaturalist Species Classification and Detection Dataset. In Proceedings of the IEEE Computer Society Conference on Com- puter Vision and Pattern Recognition (CVPR), 8769-8778. ISBN 5,986561,767.
- Jia, J.; and Benson, A. R. 2020. Residual Correlation in Graph Neural Network Regression. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Min- ing, 588-598. Association for Computing Machinery. ISBN 9781450379984.
- Klemmer, K.; and Neill, D. B. 2021. Auxiliary-task learning for geographic data with autoregressive embeddings. In SIGSPATIAL: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems.
- Klemmer, K.; Rolf, E.; Robinson, C.; Mackey, L.; and Rußwurm, M. 2023. Satclip: Global, general-purpose location embeddings with satellite imagery. arXiv preprint arXiv:2311.17179. · arXiv
- Klemmer, K.; Xu, T.; Acciaio, B.; and Neill, D. B. 2022. SPATE-GAN: Improved Generative Modeling of Dynamic Spatio- Temporal Patterns with an Autoregressive Embedding Loss. Pro- ceedings of the AAAI Conference on Artificial Intelligence, 36: 4523-4531.
- Kondmann, L.; Toker, A.; Rußwurm, M.; Camero, A.; Peressuti, D.; Milcinski, G.; Mathieu, P.-P.; Longépé, N.; Davis, T.; Marchi- sio, G.; et al. 2021. DENETHOR: The DynamicEarthNET dataset for Harmonized, inter-Operable, analysis-Ready, daily crop moni- toring from space. In Thirty-fifth Conference on Neural Informa- tion Processing Systems Datasets and Benchmarks Track (Round 2).
- Larson, M.; Soleymani, M.; Gravier, G.; Ionescu, B.; and Jones, G. J. 2017. The Benchmarking Initiative for Multimedia Evalua- tion: MediaEval 2016. IEEE Multimedia, 24: 93-96.
- Mac Aodha, O.; Cole, E.; and Perona, P. 2019. Presence-Only Ge- ographical Priors for Fine-Grained Image Classification. In ICCV.
- Mai, G.; Lao, N.; He, Y.; Song, J.; and Ermon, S. 2023. CSP: Self- Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations. arXiv preprint arXiv:2305.01118. · arXiv
- Pace, R. K.; and Barry, R. 2003. Sparse spatial autoregressions. Statistics & Probability Letters, 33: 291-297.
- Radford, A.; Kim, J. W.; Hallacy, C.; Ramesh, A.; Goh, G.; Agar- wal, S.; Sastry, G.; Askell, A.; Mishkin, P.; Clark, J.; Krueger, G.; and Sutskever, I. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings in the International Conference on Machine Learning (ICML), 8748-8763. PMLR.
- Reiersen, G.; Dao, D.; Lütjens, B.; Klemmer, K.; Amara, K.; Steinegger, A.; Zhang, C.; and Zhu, X. 2022. ReforesTree: A Dataset for Estimating Tropical Forest Carbon Stock with Deep Learning and Aerial Imagery. Proceedings of the AAAI Conference on Artificial Intelligence, 36: 12119-12125.
- Rolf, E.; Klemmer, K.; Robinson, C.; and Kerner, H. 2024. Po- sition: Mission Critical -Satellite Data is a Distinct Modality in Machine Learning. In Forty-first International Conference on Ma- chine Learning.
- Rußwurm, M.; Klemmer, K.; Rolf, E.; Zbinden, R.; and Tuia, D. 2024. Geographic Location Encoding with Spherical Harmonics and Sinusoidal Representation Networks. Proceedings in the In- ternational Conference on Learning Representations (ICLR).
- Rußwurm, M.; Wang, S.; Korner, M.; and Lobell, D. 2020. Meta- learning for few-shot land cover classification. In Proceedings of the ieee/cvf conference on computer vision and pattern recognition workshops, 200-201.
- Sitzmann, V.; Martel, J. N. P.; Bergman, A. W.; Lindell, D. B.; and Wetzstein, G. 2020. Implicit Neural Representations with Periodic Activation Functions. Advances in Neural Information Processing Systems, 33: 7462-7473.
- Thomee, B.; Elizalde, B.; Shamma, D. A.; Ni, K.; Friedland, G.; Poland, D.; Borth, D.; and Li, L. J. 2016. YFCC100M. Communi- cations of the ACM, 59: 64-73.
- Tseng, G.; Kerner, H.; and Rolnick, D. 2022. TIML: Task-informed meta-learning for agriculture. arXiv preprint arXiv:2202.02124. · arXiv
- Yin, Y.; Liu, Z.; Zhang, Y.; Wang, S.; Shah, R. R.; and Zimmer- mann, R. 2019. GPS2Vec: Towards generating worldwide GPS embeddings. In SIGSPATIAL: Proceedings of the ACM Interna- tional Symposium on Advances in Geographic Information Sys- tems, 416-419. Association for Computing Machinery. ISBN 9781450369091.
- Zhai, X.; Mustafa, B.; Kolesnikov, A.; Beyer, L.; and Deepmind, G. 2023. Sigmoid Loss for Language Image Pre-Training. In ICCV.
Cited by
Artificial intelligence for geoscience: Progress, challenges, and perspectives
Zhao, T., Wang, S., Ouyang, C., Chen, M., Liu, C., Zhang, J., Yu, L., Wang, F., Xie, Y., Li, J., et al. (2024) · The Innovation · doi:10.1016/j.xinn.2024.100691 · Cited by 360
Brown, C. F., Kazmierski, M. R., Pasquarella, V. J., Rucklidge, W. J., Samsikova, M., Zhang, C., Shelhamer, E., Lahera, E., Wiles, O., Ilyushchenko, S., et al. (2025) · arXiv · doi:10.48550/arxiv.2507.22291 · Cited by 172
Metadata
- Authors
- Klemmer, K., Rolf, E., Robinson, C., Mackey, L., & Rußwurm, M.
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2025-04-11
- Volume
- 39
- Issue
- 4
- Pages
- 4347-4355
- ISSN
- 2374-3468
- 2159-5399
- Cited by
- 86
- References
- 1
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery. https://app.cochat.ai/papers/10.1609/aaai.v39i4.32457
- The paper
- Klemmer, K., Rolf, E., Robinson, C., Mackey, L., & Rußwurm, M. (2025). SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery. Proceedings of the AAAI Conference on Artificial Intelligence. https://doi.org/10.1609/aaai.v39i4.32457
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.