# Resolution Revolution: A Physics-Guided Deep Learning Framework for Spatiotemporal Temperature Reconstruction

arXiv: https://arxiv.org/abs/2507.09872 · HTML: https://mlsanity.com/paper/2507.09872/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 41 references that are in the map.
- First posted on arXiv 14 Jul 2025.

## Builds on (most cited first, 9 of 9)

- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Deep learning to represent sub-grid processes in climate models](https://mlsanity.com/paper/1806.04731/) (2018)
- [PANGAEA: A Global and Inclusive Benchmark for Geospatial Foundation Models](https://mlsanity.com/paper/2412.04204/) (2024)
- [ClimateNeRF: Extreme Weather Synthesis in Neural Radiance Field](https://mlsanity.com/paper/2211.13226/) (2022)
- [On the Foundations of Earth and Climate Foundation Models](https://mlsanity.com/paper/2405.04285/) (2024)
- [Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel Synthesis](https://mlsanity.com/paper/2106.11485/) (2021)
- [Reconstructing Historical Climate Fields With Deep Learning](https://mlsanity.com/paper/2311.18348/) (2023)
- [Daily Land Surface Temperature Reconstruction in Landsat Cross-Track Areas Using Deep Ensemble Learning With Uncertainty Quantification](https://mlsanity.com/paper/2502.14433/) (2025)
- [Deep Feature Gaussian Processes for Single-Scene Aerosol Optical Depth Reconstruction](https://mlsanity.com/paper/2405.17262/) (2024)

## Built on by (most cited first, 1 of 1)

- [Uncertainty-Aware Hourly Air Temperature Mapping at 2 km Resolution via Physics-Guided Deep Learning](https://mlsanity.com/paper/2509.12329/) (2025)

## Abstract (arXiv)

Central to Earth observation is the trade-off between spatial and temporal resolution. For temperature, this is especially critical because real-world applications require high spatiotemporal resolution data. Current technology allows for hourly temperature observations at 2 km, but only every 16 days at 100 m, a gap further exacerbated by cloud cover. Earth system models offer continuous hourly temperature data, but at a much coarser spatial resolution (9-31 km). Here, we present a physics-guided deep learning framework for temperature data reconstruction that integrates these two data sources. The proposed framework uses a convolutional neural network that incorporates the annual temperature cycle and includes a linear term to amplify the coarse Earth system model output into fine-scale temperature values observed from satellites. We evaluated this framework using data from two satellites, GOES-16 (2 km, hourly) and Landsat (100 m, every 16 days), and demonstrated effective temperature reconstruction with hold-out and in situ data across four datasets. This physics-guided deep learning framework opens new possibilities for generating high-resolution temperature data across spatial and temporal scales, under all weather conditions and globally.