# Increasing the Robustness of Model Predictions to Missing Sensors in Earth Observation

arXiv: https://arxiv.org/abs/2407.15512 · HTML: https://mlsanity.com/paper/2407.15512/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 26 references that are in the map.
- First posted on arXiv 22 Jul 2024.

## Builds on (most cited first, 14 of 14)

- [SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery](https://mlsanity.com/paper/2312.10115/) (2023)
- [Are Multimodal Transformers Robust to Missing Modality?](https://mlsanity.com/paper/2204.05454/) (2022)
- [More Diverse Means Better: Multimodal Deep Learning Meets Remote Sensing Imagery Classification](https://mlsanity.com/paper/2008.05457/) (2020)
- [Lightweight, Pre-trained Transformers for Remote Sensing Timeseries](https://mlsanity.com/paper/2304.14065/) (2023)
- [OmniSat: Self-Supervised Modality Fusion for Earth Observation](https://mlsanity.com/paper/2404.08351/) (2024)
- [Multi-Modal Temporal Attention Models for Crop Mapping from Satellite Time Series](https://mlsanity.com/paper/2112.07558/) (2021)
- [Self-supervised Vision Transformers for Joint SAR-optical Representation Learning](https://mlsanity.com/paper/2204.05381/) (2022)
- [Understanding urban landuse from the above and ground perspectives: a deep learning, multimodal solution](https://mlsanity.com/paper/1905.01752/) (2019)
- [Exploring Masked Autoencoders for Sensor-Agnostic Image Retrieval in Remote Sensing](https://mlsanity.com/paper/2401.07782/) (2024)
- [Targeted Adversarial Attacks on Wind Power Forecasts](https://mlsanity.com/paper/2303.16633/) (2023)
- [Predicting Crop Yield With Machine Learning: An Extensive Analysis Of Input Modalities And Models On a Field and sub-field Level](https://mlsanity.com/paper/2308.08948/) (2023)
- [Impact Assessment of Missing Data in Model Predictions for Earth Observation Applications](https://mlsanity.com/paper/2403.14297/) (2024)
- [In the Search for Optimal Multi-view Learning Models for Crop Classification with Global Remote Sensing Data](https://mlsanity.com/paper/2403.16582/) (2024)
- [Multi-Modal Vision Transformers for Crop Mapping from Satellite Image Time Series](https://mlsanity.com/paper/2406.16513/) (2024)

## Built on by (most cited first, 5 of 5)

- [Missing Data as Augmentation in the Earth Observation Domain: A Multi-View Learning Approach](https://mlsanity.com/paper/2501.01132/) (2025)
- [An Analysis of Temporal Dropout in Earth Observation Time Series for Regression Tasks](https://mlsanity.com/paper/2504.06915/) (2025)
- [Multi-modal Co-learning for Earth Observation: Enhancing single-modality models via modality collaboration](https://mlsanity.com/paper/2510.19579/) (2025)
- [On What Depends the Robustness of Multi-source Models to Missing Data in Earth Observation?](https://mlsanity.com/paper/2503.19719/) (2025)
- [Reliable Virtual Sensing: A Multi-Domain Benchmark for Robustness Under Sensor Failures](https://mlsanity.com/paper/2609.18396/) (2026)

## Abstract (arXiv)

Multi-sensor ML models for EO aim to enhance prediction accuracy by integrating data from various sources. However, the presence of missing data poses a significant challenge, particularly in non-persistent sensors that can be affected by external factors. Existing literature has explored strategies like temporal dropout and sensor-invariant models to address the generalization to missing data issues. Inspired by these works, we study two novel methods tailored for multi-sensor scenarios, namely Input Sensor Dropout (ISensD) and Ensemble Sensor Invariant (ESensI). Through experimentation on three multi-sensor temporal EO datasets, we demonstrate that these methods effectively increase the robustness of model predictions to missing sensors. Particularly, we focus on how the predictive performance of models drops when sensors are missing at different levels. We observe that ensemble multi-sensor models are the most robust to the lack of sensors. In addition, the sensor dropout component in ISensD shows promising robustness results.