# Generating Physically-Consistent Satellite Imagery for Climate Visualizations

arXiv: https://arxiv.org/abs/2104.04785 · HTML: https://mlsanity.com/paper/2104.04785/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 100 references that are in the map.
- First posted on arXiv 10 Apr 2021.

## Builds on (most cited first, 30 of 42)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Image Transformer](https://mlsanity.com/paper/1802.05751/) (2018)
- [Hamiltonian Neural Networks](https://mlsanity.com/paper/1906.01563/) (2019)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [Deep learning for universal linear embeddings of nonlinear dynamics](https://mlsanity.com/paper/1712.09707/) (2017)
- [Toward Multimodal Image-to-Image Translation](https://mlsanity.com/paper/1711.11586/) (2017)
- [Understanding the Role of Individual Units in a Deep Neural Network](https://mlsanity.com/paper/2009.05041/) (2020)
- [Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations](https://mlsanity.com/paper/1801.06637/) (2018)
- [Pros and Cons of GAN Evaluation Measures](https://mlsanity.com/paper/1802.03446/) (2018)
- [Generating Images with Perceptual Similarity Metrics based on Deep Networks](https://mlsanity.com/paper/1602.02644/) (2016)
- [PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network](https://mlsanity.com/paper/1812.04426/) (2018)
- [SRFlow: Learning the Super-Resolution Space with Normalizing Flow](https://mlsanity.com/paper/2006.14200/) (2020)
- [Deep learning to represent sub-grid processes in climate models](https://mlsanity.com/paper/1806.04731/) (2018)
- [Pyramid Attention Network for Semantic Segmentation](https://mlsanity.com/paper/1805.10180/) (2018)
- [Physics-guided Neural Networks (PGNN): An Application in Lake Temperature Modeling](https://mlsanity.com/paper/1710.11431/) (2017)
- [You Only Need Adversarial Supervision for Semantic Image Synthesis](https://mlsanity.com/paper/2012.04781/) (2020)
- [Mode Regularized Generative Adversarial Networks](https://mlsanity.com/paper/1612.02136/) (2016)

## Built on by (most cited first, 13 of 13)

- [GEO-Bench: Toward Foundation Models for Earth Monitoring](https://mlsanity.com/paper/2306.03831/) (2023)
- [Language in the Flow of Time: Time-Series-Paired Texts Weaved into a Unified Temporal Narrative](https://mlsanity.com/paper/2502.08942/) (2025)
- [Foundation Models for Weather and Climate Data Understanding: A Comprehensive Survey](https://mlsanity.com/paper/2312.03014/) (2023)
- [Toward Foundation Models for Earth Monitoring: Proposal for a Climate Change Benchmark](https://mlsanity.com/paper/2112.00570/) (2021)
- [Entity Aware Modelling: A Survey](https://mlsanity.com/paper/2302.08406/) (2023)
- [Physics-Informed Deep Learning: A Promising Technique for System Reliability Assessment](https://mlsanity.com/paper/2108.10828/) (2021)
- [AI for Extreme Event Modeling and Understanding: Methodologies and Challenges](https://mlsanity.com/paper/2406.20080/) (2024)
- [FlowEO: Generative Unsupervised Domain Adaptation for Earth Observation](https://mlsanity.com/paper/2512.05140/) (2025)
- [RiverMamba: A State Space Model for Global River Discharge and Flood Forecasting](https://mlsanity.com/paper/2505.22535/) (2025)
- [ChangeBridge: Spatiotemporal Image Generation with Multimodal Controls for Remote Sensing](https://mlsanity.com/paper/2507.04678/) (2025)
- [Capabilities, Limitations and Challenges of Style Transfer with CycleGANs: A Study on Automatic Ring Design Generation](https://mlsanity.com/paper/2207.08989/) (2022)
- [MeltwaterBench: Deep learning for spatiotemporal downscaling of surface meltwater](https://mlsanity.com/paper/2512.12142/) (2025)
- [FlowForm: Synergizing Fluid Physics with Topological Consistency for Satellite Flood Synthesis](https://mlsanity.com/paper/2608.03822/) (2026)

## Abstract (arXiv)

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 urlhttps://github.com/blutjens/eie-earth-public.