.png){kind=icon}
.png){kind=icon}
Return
Generating Physically-Consistent Satellite Imagery for Climate Visualizations
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2024.3493763.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Deep generative vision models are now able to synthesize realistic-looking satellite imagery. However, the possibility of hallucinations prevents their adoption of risk-sensitive applications, such as generating materials for communicating climate change. To demonstrate this issue, we train a generative adversarial network (GAN, 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 hallucinate floods at locations that are 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 128 x 128 pixels-for segmentation guided image-to-image (im2im) translation in Earth observation. Code and data are available at github.com/blutjens/eie-earth-public.
Keywords:
Climate change
Artificial intelligence
Machine learning
Generative adversarial networks
Image processing
Reforestation
Visualization
Satellite images
Remote sensing
deep generative vision models
flooding
generative adversarial networks (GANs)
generative AI
image-to-image (im2im) translation
physics-informed machine learning (ML)
reforestation
remote sensing
synthetic satellite imagery
visualization
Journal
IF:
8.6
Papers:
2.1W
Citations:
10.7W
View more organizations