Quantification and machine learning based N<sub>2</sub>O–N and CO<sub>2</sub>–C emissions predictions from a decomposing rye cover crop
Deepak R. Joshi, David E. Clay, Sharon A. Clay, Janet Moriles‐Miller, Aaron Lee M. Daigh, Graig Reicks, Shaina Westhoff
Abstract
Abstract Cover crops improve soil health and reduce the risk of soil erosion. However, their impact on the carbon dioxide equivalence (CO 2e ) is unknown. Therefore, the objective of this 2‐yr study was to quantify the effect of cover crop‐induced differences in soil moisture, temperature, organic C, and microorganisms on CO 2e , and to develop machine learning algorithms that predict daily N 2 O–N and CO 2 –C emissions. The prediction models tested were multiple linear regression, partial least square regression, support vector machine, random forest (RF), and artificial neural network. Models’ performance was accessed using R 2 , RMSE and mean of absolute value of error. Rye ( Secale cereale L.) was dormant seeded in mid‐October, and in the following spring it was terminated at corn's ( Zea mays L.) V4 growth stage. Soil temperature, moisture, and N 2 O–N and CO 2 –C emissions were measured near continuously from soil thaw to harvest in 2019 and 2020. Prior to termination, the cover crop decreased N 2 O–N emissions by 34% ( p = .05), and over the entire season, N 2 O–N emissions from cover crop and no cover crop treatments were similar ( p = .71). Based on N 2 O–N and CO 2 –C emissions over the entire season and the estimated fixed cover crop‐C remaining in the soil, the partial CO 2e were −1,061 and 496 kg CO 2e ha –1 in the cover crop and no cover crop treatments, respectively. The RF algorithm explained more of the daily N 2 O–N (73%) and CO 2 –C (85%) emissions variability during validation than the other models. Across models, the most important variables were temperature and the amount of cover crop‐C added to the soil.