A Quantitative Analysis on the Use of Supervised Machine Learning in Earth Science

Recent review papers have discussed the opportunities and challenges of applying machine learning (ML) techniques to Earth science data. A common challenge cited in these papers is the lack of labeled training data. A literature review of Earth science papers over the last 10 years demonstrates that while there is rapid adoption of ML, particularly in biogeoscience and land surface research, the training datasets typically contain only hundreds of samples. This lack of training data limits the use of deep learning algorithms, which require larger volumes of labeled data. In situ training data are most frequently used in almost all domains, followed by model output and satellite data. The atmosphere and solid Earth domains use the largest training datasets, an order of magnitude larger than in biogeoscience papers. Random forest is the most commonly applied ML algorithm in all domains except atmospheric science and biogeoscience, which more frequently use fully connected neural networks.

1. Introduction

Interest in machine learning (ML) techniques is growing within the Earth science community. Recent review papers [1], [2] have discussed both the opportunities and the challenges in applying ML techniques to Earth science problems. A common challenge cited in these papers is the lack of training (or labeled) data, along with other challenges ranging from interpretability of the results to computational demand and data issues.