Threshold soil moisture levels influence soil CO2 emissions: A machine learning approach to predict short-term soil CO2 emissions from climate-smart fields

Authors: VEETTIL, ANOOP - Prairie View A & M University; RAHMAN, ATIKUR - Prairie View A & M University; AWAL, RIPENDRA - Prairie View A & M University; FARES, ALI - Prairie View A & M University; Green, Timothy; THAPPA, BINITA - Prairie View A & M University; ELHASSAN, ALMOUTAZ - Prairie View A & M University

Submitted to: Sustainability
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 7/1/2025
Publication Date: 7/3/2025
Citation: Veettil, A.V., Rahman, A., Awal, R., Fares, A., Green, T.R., Thappa, B., Elhassan, A. 2025. Threshold soil moisture levels influence soil CO2 emissions: A machine learning approach to predict short-term soil CO2 emissions from climate-smart fields. Sustainability. 17(13). Article e6101. https://doi.org/10.3390/su17136101.
DOI: https://doi.org/10.3390/su17136101

Interpretive Summary: Agricultural practices, including intensive tillage, animal confinement operations, and manure application comprise more than 10% of global greenhouse gases (GHG) emissions. In many environments, soil amendments are viable Climate-Smart Agriculture strategies to reduce GHG emissions while maintaining adequate crop yields. This study used machine learning and statistical regression methods to investigate thresholds of soil moisture that affect CO2 emissions from organically amended field plots. The different organic amendments considered in this study are biochar, chicken manure, and dairy manure under a sweet corn crop grown in southern Texas. We identified a direct linkage between soil moisture level and the magnitude of CO2 emissions. The highest rate of biochar (double the recommended rate) reduced soil CO2 emissions by 15% compared to the control plots without any amendments. The greatest reductions occurred where chicken and biochar were applied. We conclude that quantifying soil moisture thresholds will provide valuable soil CO2 emission mitigation information.

Technical Abstract: Machine learning (ML) models are widely used to analyze the spatiotemporal impacts of agricultural practices on environmental sustainability, including the contribution to global greenhouse gas (GHG) emissions. Management practices, such as organic amendment applications, are critical pillars of Climate-smart agriculture (CSA) strategies that mitigate GHG emissions while maintaining adequate crop yields. This study investigated the critical threshold of soil moisture level associated with soil CO2 emissions from organically amended plots using the classification and regression tree (CART) algorithm. Also, the study predicted the short-term soil CO2 emissions from organically amended systems using soil moisture and weather variables (i.e., air temperature, relative humidity, and solar radiation) using multilinear regression (MLR) and generalized additive models (GAMs). The different organic amendments considered in this study are biochar (2268 and 4536 kg ha-1) and chicken and dairy manure (0, 224, and 448 kg N/ha) under a sweet corn crop in the greater Houston area, Texas. The results of the CART analysis indicated a direct link between soil moisture level and the magnitude of CO2 flux emission from the amended plots. A threshold of 0.103 m3m-3 was calculated for treatment amended by biochar level I (2268 kg ha-1) and chicken manure at the N recommended rate (CXBX), indicating that if the soil moisture is less than the 0.103 m3m-3 threshold, then the median soil CO2 emission is 142 kg ha-1 d-1. Furthermore, applying biochar at a rate of 4536 kg ha-1 reduced the soil CO2 emissions by 14.5% compared to the control plots. Additionally, the results demonstrate that GAMs outperformed MLR, exhibiting the highest performance under the combined effect of chicken and biochar. We conclude that quantifying soil moisture thresholds will provide valuable information for the sustainable mitigation of soil CO2 emissions.