# Impact Assessment of Missing Data in Model Predictions for Earth Observation Applications

arXiv: https://arxiv.org/abs/2403.14297 · HTML: https://mlsanity.com/paper/2403.14297/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 11 references that are in the map.
- First posted on arXiv 21 Mar 2024.

## Builds on (most cited first, 6 of 6)

- [More Diverse Means Better: Multimodal Deep Learning Meets Remote Sensing Imagery Classification](https://mlsanity.com/paper/2008.05457/) (2020)
- [Multi-Modal Temporal Attention Models for Crop Mapping from Satellite Time Series](https://mlsanity.com/paper/2112.07558/) (2021)
- [Understanding urban landuse from the above and ground perspectives: a deep learning, multimodal solution](https://mlsanity.com/paper/1905.01752/) (2019)
- [Targeted Adversarial Attacks on Wind Power Forecasts](https://mlsanity.com/paper/2303.16633/) (2023)
- [Common Practices and Taxonomy in Deep Multi-view Fusion for Remote Sensing Applications](https://mlsanity.com/paper/2301.01200/) (2022)
- [A Comparative Assessment of Multi-view fusion learning for Crop Classification](https://mlsanity.com/paper/2308.05407/) (2023)

## Built on by (most cited first, 3 of 3)

- [Increasing the Robustness of Model Predictions to Missing Sensors in Earth Observation](https://mlsanity.com/paper/2407.15512/) (2024)
- [Missing Data as Augmentation in the Earth Observation Domain: A Multi-View Learning Approach](https://mlsanity.com/paper/2501.01132/) (2025)
- [On What Depends the Robustness of Multi-source Models to Missing Data in Earth Observation?](https://mlsanity.com/paper/2503.19719/) (2025)

## Abstract (arXiv)

Earth observation (EO) applications involving complex and heterogeneous data sources are commonly approached with machine learning models. However, there is a common assumption that data sources will be persistently available. Different situations could affect the availability of EO sources, like noise, clouds, or satellite mission failures. In this work, we assess the impact of missing temporal and static EO sources in trained models across four datasets with classification and regression tasks. We compare the predictive quality of different methods and find that some are naturally more robust to missing data. The Ensemble strategy, in particular, achieves a prediction robustness up to 100%. We evidence that missing scenarios are significantly more challenging in regression than classification tasks. Finally, we find that the optical view is the most critical view when it is missing individually.