Causal Modeling of Soil Processes for Improved Generalization

TL;DR

This paper demonstrates that explicitly modeling causal relationships among soil processes significantly enhances the generalization ability of soil organic carbon prediction models across diverse conditions.

Contribution

It introduces a causal modeling framework for soil organic carbon estimation, improving out-of-distribution performance compared to traditional methods.

Findings

81% improvement in test mean squared error

52% improvement in test mean absolute error

Causal discovery enhances model generalization

Abstract

Measuring and monitoring soil organic carbon is critical for agricultural productivity and for addressing critical environmental problems. Soil organic carbon not only enriches nutrition in soil, but also has a gamut of co-benefits such as improving water storage and limiting physical erosion. Despite a litany of work in soil organic carbon estimation, current approaches do not generalize well across soil conditions and management practices. We empirically show that explicit modeling of cause-and-effect relationships among the soil processes improves the out-of-distribution generalizability of prediction models. We provide a comparative analysis of soil organic carbon estimation models where the skeleton is estimated using causal discovery methods. Our framework provide an average improvement of 81% in test mean squared error and 52% in test mean absolute error.