Generating Physically-Consistent Satellite Imagery for Climate Visualizations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2021
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914979170484224 |
|---|---|
| author | Lütjens, Björn Leshchinskiy, Brandon Boulais, Océane Chishtie, Farrukh Díaz-Rodríguez, Natalia Masson-Forsythe, Margaux Mata-Payerro, Ana Requena-Mesa, Christian Sankaranarayanan, Aruna Piña, Aaron Gal, Yarin Raïssi, Chedy Lavin, Alexander Newman, Dava |
| author_facet | Lütjens, Björn Leshchinskiy, Brandon Boulais, Océane Chishtie, Farrukh Díaz-Rodríguez, Natalia Masson-Forsythe, Margaux Mata-Payerro, Ana Requena-Mesa, Christian Sankaranarayanan, Aruna Piña, Aaron Gal, Yarin Raïssi, Chedy Lavin, Alexander Newman, Dava |
| contents | Deep generative vision models are now able to synthesize realistic-looking satellite imagery. But, the possibility of hallucinations prevents their adoption for risk-sensitive applications, such as generating materials for communicating climate change. To demonstrate this issue, we train a generative adversarial network (pix2pixHD) to create synthetic satellite imagery of future flooding and reforestation events. We find that a pure deep learning-based model can generate photorealistic flood visualizations but hallucinates floods at locations that were not susceptible to flooding. To address this issue, we propose to condition and evaluate generative vision models on segmentation maps of physics-based flood models. We show that our physics-conditioned model outperforms the pure deep learning-based model and a handcrafted baseline. We evaluate the generalization capability of our method to different remote sensing data and different climate-related events (reforestation). We publish our code and dataset which includes the data for a third case study of melting Arctic sea ice and $>$30,000 labeled HD image triplets -- or the equivalent of 5.5 million images at 128x128 pixels -- for segmentation guided image-to-image translation in Earth observation. Code and data is available at \url{https://github.com/blutjens/eie-earth-public}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2104_04785 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Generating Physically-Consistent Satellite Imagery for Climate Visualizations Lütjens, Björn Leshchinskiy, Brandon Boulais, Océane Chishtie, Farrukh Díaz-Rodríguez, Natalia Masson-Forsythe, Margaux Mata-Payerro, Ana Requena-Mesa, Christian Sankaranarayanan, Aruna Piña, Aaron Gal, Yarin Raïssi, Chedy Lavin, Alexander Newman, Dava Computer Vision and Pattern Recognition Machine Learning Image and Video Processing Deep generative vision models are now able to synthesize realistic-looking satellite imagery. But, the possibility of hallucinations prevents their adoption for risk-sensitive applications, such as generating materials for communicating climate change. To demonstrate this issue, we train a generative adversarial network (pix2pixHD) to create synthetic satellite imagery of future flooding and reforestation events. We find that a pure deep learning-based model can generate photorealistic flood visualizations but hallucinates floods at locations that were not susceptible to flooding. To address this issue, we propose to condition and evaluate generative vision models on segmentation maps of physics-based flood models. We show that our physics-conditioned model outperforms the pure deep learning-based model and a handcrafted baseline. We evaluate the generalization capability of our method to different remote sensing data and different climate-related events (reforestation). We publish our code and dataset which includes the data for a third case study of melting Arctic sea ice and $>$30,000 labeled HD image triplets -- or the equivalent of 5.5 million images at 128x128 pixels -- for segmentation guided image-to-image translation in Earth observation. Code and data is available at \url{https://github.com/blutjens/eie-earth-public}. |
| title | Generating Physically-Consistent Satellite Imagery for Climate Visualizations |
| topic | Computer Vision and Pattern Recognition Machine Learning Image and Video Processing |
| url | https://arxiv.org/abs/2104.04785 |