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

TL;DR

This paper proposes two novel methods, ISensD and ESensI, to improve the robustness of multi-sensor Earth Observation models against missing sensor data, demonstrating effectiveness across multiple datasets.

Contribution

Introduction of Input Sensor Dropout and Ensemble Sensor Invariant methods specifically designed for multi-sensor scenarios to handle missing data.

Findings

Ensemble multi-sensor models are most robust to missing sensors.

Sensor dropout in ISensD improves robustness.

Methods tested on three multi-sensor EO datasets.

Abstract

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.