Transdisciplinary coordination is essential for advancing agricultural modeling with machine learning
Abstract
Crop models play a key role in the study of climate change impacts on food production as well as improving food systems resilience and analyzing the effect of potential adaptation interventions. Here, we illustrate opportunities that machine learning offers for tackling key challenges of agricultural modeling. However, to unlock the full potential of machine learning, and thereby accelerate progress toward a more secure and sustainable global food system, serious pitfalls must first be addressed. We argue that transdisciplinary coordination is needed to identify impactful research gaps, curate and maintain benchmark datasets, and establish domain-specific best practices.
Download full text in pdf format
Published as:
L.-B. Sweet,
I. N. Athanasiadis,
R. van Bree,
A. Castellano,
P. Martre,
D. Paudel,
A. C. Ruane,
J. Zscheischler,
Transdisciplinary coordination is essential for advancing agricultural modeling with machine learning,
One Earth, 8:101233,
2025, Elsevier BV, doi:10.1016/j.oneear.2025.101233.
You might also enjoy (View all publications)
- The first geospatial dataset of irrigated fields (2020–2024) in Vojvodina (Serbia)
- Transdisciplinary coordination is essential for advancing agricultural modeling with machine learning
- Knowledge-guided machine learning with multivariate sparse data for crop growth modelling