Causal Modeling of Soil Processes for Improved Generalization

Conference paper

Neal, A. L., Sharma, S., Crawford, J. W., Kiciman, E., Malvar, S., Rodriguez, E. and Chandra, R. 2022. Causal Modeling of Soil Processes for Improved Generalization. NeurIPS 2022. New Orleans Conference Center 28 Nov 2022

AuthorsNeal, A. L., Sharma, S., Crawford, J. W., Kiciman, E., Malvar, S., Rodriguez, E. and Chandra, R.
TypeConference paper
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.

KeywordsGraph neural network; Soil; Organic carbon; Casual discovery
Year of Publication2022
Conference titleNeurIPS 2022
Conference locationNew Orleans, LA
Event date28 Nov 2022
Open accessPublished as green open access
Accepted author manuscript
Output statusPublished
Publication dates
Online10 Nov 2022
Other fileCausal%20Modeling%20of%20Soil%20Processes%20for%20Improved%20Generalization.pdf

Permalink - https://repository.rothamsted.ac.uk/item/989xv/causal-modeling-of-soil-processes-for-improved-generalization

80 total views
81 total downloads
1 views this month
2 downloads this month
Download files as zip