Better, Not Just More: Data-Centric Machine Learning for Earth Observation

TL;DR

This paper advocates shifting from a model-centric to a data-centric approach in geospatial machine learning to improve accuracy, generalization, and real-world applicability, emphasizing the entire ML cycle.

Contribution

It provides a clear definition, categorization, and overview of automated data-centric learning methods specifically for geospatial data, highlighting their role alongside traditional model-centric approaches.

Findings

Data-centric approaches enhance model robustness in geospatial tasks.

Experiments demonstrate practical implementation steps for data-centric ML.

Review categorizes existing geospatial ML methods into distinct groups.

Abstract

Recent developments and research in modern machine learning have led to substantial improvements in the geospatial field. Although numerous deep learning architectures and models have been proposed, the majority of them have been solely developed on benchmark datasets that lack strong real-world relevance. Furthermore, the performance of many methods has already saturated on these datasets. We argue that a shift from a model-centric view to a complementary data-centric perspective is necessary for further improvements in accuracy, generalization ability, and real impact on end-user applications. Furthermore, considering the entire machine learning cycle-from problem definition to model deployment with feedback-is crucial for enhancing machine learning models that can be reliable in unforeseen situations. This work presents a definition as well as a precise categorization and overview of automated data-centric learning approaches for geospatial data. It highlights the complementary role of data-centric learning with respect to model-centric in the larger machine learning deployment cycle. We review papers across the entire geospatial field and categorize them into different groups. A set of representative experiments shows concrete implementation examples. These examples provide concrete steps to act on geospatial data with data-centric machine learning approaches.