Timezone: »

 
Causal Modeling of Soil Processes for Improved Generalization
Somya Sharma · Swati Sharma · Emre Kiciman · Andy Neal · Ranveer Chandra · John Crawford · Sara Malvar · Eduardo Rodrigues

@
in Tackling Climate Change with Machine Learning »
Event URL: https://www.climatechange.ai/papers/neurips2022/53 »

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.

[ Topia] 

Author Information

Somya Sharma (University of Minnesota)
Swati Sharma (Microsoft Research)
Emre Kiciman (Microsoft Research)
Andy Neal (Rothamstead)
Ranveer Chandra (Microsoft)
John Crawford (University of Glasgow)
Sara Malvar (Microsoft)
Eduardo Rodrigues (Microsoft Research)

More from the Same Authors