# Efficient data-driven gap filling of satellite image time series using deep neural networks with partial convolutions

arXiv: https://arxiv.org/abs/2208.08781 · HTML: https://mlsanity.com/paper/2208.08781/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 31 references that are in the map.
- First posted on arXiv 18 Aug 2022.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [Forecasting Global Weather with Graph Neural Networks](https://mlsanity.com/paper/2202.07575/) (2022)
- [Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge](https://mlsanity.com/paper/1711.07970/) (2017)
- [Predicting into unknown space? Estimating the area of applicability of spatial prediction models](https://mlsanity.com/paper/2005.07939/) (2020)
- [Deep Integro-Difference Equation Models for Spatio-Temporal Forecasting](https://mlsanity.com/paper/1910.13524/) (2019)
- [Spatiotemporal Multi-Resolution Approximations for Analyzing Global Environmental Data](https://mlsanity.com/paper/2006.16606/) (2020)

## Built on by (most cited first, 4 of 4)

- [The Moon's Many Faces: A Single Unified Transformer for Multimodal Lunar Reconstruction](https://mlsanity.com/paper/2505.05644/) (2025)
- [Data-Driven Uncertainty-Aware Forecasting of Sea Ice Conditions in the Gulf of Ob Based on Satellite Radar Imagery](https://mlsanity.com/paper/2410.19782/) (2024)
- [Remote sensing data imputation using deep learning for multispectral imagery](https://mlsanity.com/paper/2605.24003/) (2026)
- [From Surface Forecasting to Observability Forecasting: A Latent World Model for Cloud-Aware EO Monitoring](https://mlsanity.com/paper/2607.13651/) (2026)

## Abstract (arXiv)

The abundance of gaps in satellite image time series often complicates the application of deep learning models such as convolutional neural networks for spatiotemporal modeling. Based on previous work in computer vision on image inpainting, this paper shows how three-dimensional spatiotemporal partial convolutions can be used as layers in neural networks to fill gaps in satellite image time series. To evaluate the approach, we apply a U-Net-like model on incomplete image time series of quasi-global carbon monoxide observations from the Sentinel-5P satellite. Prediction errors were comparable to two considered statistical approaches while computation times for predictions were up to three orders of magnitude faster, making the approach applicable to process large amounts of satellite data. Partial convolutions can be added as layers to other types of neural networks, making it relatively easy to integrate with existing deep learning models. However, the approach does not quantify prediction errors and further research is needed to understand and improve model transferability. The implementation of spatiotemporal partial convolutions and the U-Net-like model is available as open-source software.