Causal Machine Learning for Sustainable Agroecosystems

Vasileios Sitokonstantinou

Keywords: machine learning, causal inference, sustainable agriculture, food security, evidence-based decision making

TL;DR: This paper presents a framework that integrates causal inference with machine learning to support sustainable decision-making in agriculture by quantifying the effects of interventions in agroecosystems.

Abstract:

Sustainable agriculture is essential for food security and environmental health in a changing climate. However, it is challenging to understand the complex interactions among its biophysical, social, and economic components. Predictive machine learning (ML), with its capacity to learn from data, is leveraged in sustainable agriculture for applications like yield prediction and weather forecasting. Nevertheless, it cannot explain causal mechanisms and remains descriptive rather than prescriptive. To address this gap, we propose the use of causal ML, which merges ML's capacity for data processing with causality's ability to reason about change. This facilitates quantifying intervention impacts for evidence-based decision-making and enhances predictive model robustness. We showcase the potential of causal ML through eight diverse applications that benefit stakeholders across the agri-food chain, including farmers, policymakers, and researchers.

arXiv preprint: https://arxiv.org/pdf/2408.13155

Submission Number: 58