The Case for Open-Access ML-Ready Geospatial Training Data

Advancements in Machine Learning (ML) techniques have revolutionized model development and hypothesis testing in many fields including Earth science. ML frameworks enable fast iterations on numerous model architectures and rely heavily on training data to learn patterns or relationships. Therefore, training data are a key building block of reproducible ML pipelines. These data need to be curated accurately, be representative of their domain, and be accessible openly to advance ML applications in Earth science. In this paper, we discuss the need for open-access and ML-ready training datasets in Earth Sciences.

1. Introduction

Open research practices result in further reuse of the scientific findings, and enable reproducibility of the initial results. Meanwhile, openness in itself is not enough [1]. Research data need to be accompanied by code and examples that help the user to replicate what the initial researchers had produced.