Ecology informed machine learning

Jun 27, 2021

As biodiversity declines and anthropogenic pressure increases, there is a crucial need for accurate ecosystem models that can capture the dynamics of real ecosystems in order to predict and mitigate collapses. Yet it remains a daunting task to obtain an agreement between current ecosystem models and real world ecosystems. In this project we aim at bridging machine learning techniques and mechanistic models in order to extrapolate beyond data. By embedding prior scientific knowledge in the structure of mechanistic models, this approach should generalise better, be more interpretable and require less data than current techniques.

Scientific Machine Learning Ecology and evolution
Victor Boussange
Victor Boussange
Postdoctoral researcher

Researcher in ecology and evolution, scientific machine learning enthusiastic.

Publications

Mini-batching ecological data to improve ecosystem models with machine learning
Ecosystems are involved in global biogeochemical cycles that regulate climate and provide essential services to human societies. Mechanistic models are required to describe ecosystem dynamics and anticipate their response to anthropogenic pressure, but their adoption has been limited in practice because of issues with parameter identification and because of model inaccuracies. We propose a machine learning (ML) framework relying on a mini-batch method combined with automatic differentiation and state-of-the-art optimizers. The proposed ML framework can efficiently learn from data and elucidate mechanistic pathways to improve our understanding and predictions of ecosystem dynamics.
Victor Boussange, Pau Vilimelis Aceituno, Loïc Pellissier
PDF Cite Code Project DOI
Mini-batching ecological data to improve ecosystem models with machine learning