Jonathan Martin

Interpretable models for extrapolation in scientific machine learning

arXiv (Cornell University) · 2022-12-16 · 3 citations

Data-driven models are central to scientific discovery. In efforts to achieve state-of-the-art model accuracy, researchers are employing increasingly complex machine learning algorithms that often outperform simple regressions in interpolative settings (e.g. random k-fold cross-validation) but suffer from poor extrapolation performance, portability, and human interpretability, which limits their potential for facilitating novel scientific insight. Here we examine the trade-off between model perf…

Chemostratigraphy and mineralogy as correlation tools for the Triassic Skagerrak Formation in quadrants 22 and 30 of the Central Graben in the Central North Sea

Zeitschrift der Deutschen Gesellschaft für Geowissenschaften · 2024-11-14