Missing Data as Augmentation in the Earth Observation Domain: A Multi-View Learning Approach

TL;DR

This paper introduces novel multi-view learning methods for Earth Observation data that effectively handle missing views by simulating all missing data combinations and using dynamic merge functions, improving robustness and performance.

Contribution

The paper presents new MVL techniques tailored for EO data that simulate missing views and employ dynamic merging, enhancing model robustness and generalization.

Findings

Improved robustness under moderate missing data conditions.

Enhanced predictive performance with complete views.

Effective handling of heterogeneous and missing data in EO.

Abstract

Multi-view learning (MVL) leverages multiple sources or views of data to enhance machine learning model performance and robustness. This approach has been successfully used in the Earth Observation (EO) domain, where views have a heterogeneous nature and can be affected by missing data. Despite the negative effect that missing data has on model predictions, the ML literature has used it as an augmentation technique to improve model generalization, like masking the input data. Inspired by this, we introduce novel methods for EO applications tailored to MVL with missing views. Our methods integrate the combination of a set to simulate all combinations of missing views as different training samples. Instead of replacing missing data with a numerical value, we use dynamic merge functions, like average, and more complex ones like Transformer. This allows the MVL model to entirely ignore the missing views, enhancing its predictive robustness. We experiment on four EO datasets with temporal and static views, including state-of-the-art methods from the EO domain. The results indicate that our methods improve model robustness under conditions of moderate missingness, and improve the predictive performance when all views are present. The proposed methods offer a single adaptive solution to operate effectively with any combination of available views.