EcoMapper: Generative Modeling for Climate-Aware Satellite Imagery

Muhammed Goktepe, Amir Hossein Shamseddin, Erencan Uysal, Javier Muinelo Monteagudo, Lukas Drees, Aysim Toker, Senthold Asseng, Malte Von Bloh
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19734-19754, 2025.

Abstract

Satellite imagery is essential for Earth observation, enabling applications like crop yield prediction, environmental monitoring, and climate change assessment. However, integrating satellite imagery with climate data remains a challenge, limiting its utility for forecasting and scenario analysis. We introduce a novel dataset of 2.9 million Sentinel-2 images spanning 15 land cover types with corresponding climate records, forming the foundation for two satellite image generation approaches using fine-tuned Stable Diffusion 3 models. The first is a text-to-image generation model that uses textual prompts with climate and land cover details to produce realistic synthetic imagery for specific regions. The second leverages ControlNet for multi-conditional image generation, preserving spatial structures while mapping climate data or generating time-series to simulate landscape evolution. By combining synthetic image generation with climate and land cover data, our work advances generative modeling in remote sensing, offering realistic inputs for environmental forecasting and new possibilities for climate adaptation and geospatial analysis.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-goktepe25a, title = {{E}co{M}apper: Generative Modeling for Climate-Aware Satellite Imagery}, author = {Goktepe, Muhammed and Shamseddin, Amir Hossein and Uysal, Erencan and Monteagudo, Javier Muinelo and Drees, Lukas and Toker, Aysim and Asseng, Senthold and Bloh, Malte Von}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {19734--19754}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/goktepe25a/goktepe25a.pdf}, url = {https://proceedings.mlr.press/v267/goktepe25a.html}, abstract = {Satellite imagery is essential for Earth observation, enabling applications like crop yield prediction, environmental monitoring, and climate change assessment. However, integrating satellite imagery with climate data remains a challenge, limiting its utility for forecasting and scenario analysis. We introduce a novel dataset of 2.9 million Sentinel-2 images spanning 15 land cover types with corresponding climate records, forming the foundation for two satellite image generation approaches using fine-tuned Stable Diffusion 3 models. The first is a text-to-image generation model that uses textual prompts with climate and land cover details to produce realistic synthetic imagery for specific regions. The second leverages ControlNet for multi-conditional image generation, preserving spatial structures while mapping climate data or generating time-series to simulate landscape evolution. By combining synthetic image generation with climate and land cover data, our work advances generative modeling in remote sensing, offering realistic inputs for environmental forecasting and new possibilities for climate adaptation and geospatial analysis.} }
Endnote
%0 Conference Paper %T EcoMapper: Generative Modeling for Climate-Aware Satellite Imagery %A Muhammed Goktepe %A Amir Hossein Shamseddin %A Erencan Uysal %A Javier Muinelo Monteagudo %A Lukas Drees %A Aysim Toker %A Senthold Asseng %A Malte Von Bloh %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-goktepe25a %I PMLR %P 19734--19754 %U https://proceedings.mlr.press/v267/goktepe25a.html %V 267 %X Satellite imagery is essential for Earth observation, enabling applications like crop yield prediction, environmental monitoring, and climate change assessment. However, integrating satellite imagery with climate data remains a challenge, limiting its utility for forecasting and scenario analysis. We introduce a novel dataset of 2.9 million Sentinel-2 images spanning 15 land cover types with corresponding climate records, forming the foundation for two satellite image generation approaches using fine-tuned Stable Diffusion 3 models. The first is a text-to-image generation model that uses textual prompts with climate and land cover details to produce realistic synthetic imagery for specific regions. The second leverages ControlNet for multi-conditional image generation, preserving spatial structures while mapping climate data or generating time-series to simulate landscape evolution. By combining synthetic image generation with climate and land cover data, our work advances generative modeling in remote sensing, offering realistic inputs for environmental forecasting and new possibilities for climate adaptation and geospatial analysis.
APA
Goktepe, M., Shamseddin, A.H., Uysal, E., Monteagudo, J.M., Drees, L., Toker, A., Asseng, S. & Bloh, M.V.. (2025). EcoMapper: Generative Modeling for Climate-Aware Satellite Imagery. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:19734-19754 Available from https://proceedings.mlr.press/v267/goktepe25a.html.

Related Material