Machine Learning Approach to Simulate Soil CO2 Fluxes under Cropping Systems

With the growing number of datasets to describe greenhouse gas (GHG) emissions, there is an opportunity to develop novel predictive models that require neither the expense nor time required to make direct field measurements. This study evaluates the potential for machine learning (ML) approaches to predict soil GHG emissions without the biogeochemical expertise that is required to use many current models for simulating soil GHGs. There are ample data from field measurements now publicly available to test new modeling approaches. The objective of this paper was to develop and evaluate machine learning (ML) models using field data (soil temperature, soil moisture, soil classification, crop type, fertilization type, and air temperature) available in the Greenhouse gas Reduction through Agricultural Carbon Enhancement network (GRACEnet) database to simulate soil CO2 fluxes with different fertilization methods. Four machine learning algorithms—K nearest neighbor regression (KNN), support vector regression (SVR), random forest (RF) regression, and gradient boosted (GB) regression—were used to develop the models. The GB regression model outperformed all the other models on the training dataset with R2 = 0.88, MAE = 2177.89 g C ha−1 day−1, and RMSE 4405.43 g C ha−1 day−1. However, the RF and GB regression models both performed optimally on the unseen test dataset with R2 = 0.82. Machine learning tools were useful for developing predictors based on soil classification, soil temperature and air temperature when a large database like GRACEnet is available, but these were not highly predictive variables in correlation analysis. This study demonstrates the suitability of using tree-based ML algorithms for predictive modeling of CO2 fluxes, but no biogeochemical processes can be described with such models.

Response of vegetation and soil biological properties to deformation in logging trails in drained boreal peatland forests

In the boreal region, peatland forests are a significant resource of timber. Under pressure from a growing bioeconomy and climate change, timber harvesting is increasingly occurring over unfrozen soils. This is likely to cause disturbance in the soil biogeochemistry. We studied the impact of machinery-induced soil disturbance on the vegetation, microbes, and soil biogeochemistry of drained boreal peatland forests caused by machinery traffic during thinning operations. To assess potential recovery, we sampled six sites that ranged in time since thinning from a few months to 15 years. Soil disturbance directly decreased moss biomass and led to an increase in sedge cover and a decrease in root production. Moreover, soil CO2 production potential, and soil CO2 and CH4 concentrations were greater in recently disturbed areas than in the control areas. In contrast, CO2 and CH4 emissions, microbial biomass and structure, and the decomposition rate of cellulose appeared to be uncoupled and did not show signs of impact. While the impacted properties varied in their rate of recovery, they all fully recovered within 15 years covered by our chronosequence study. Conclusively, drained boreal peatlands appeared to have high biological resilience to soil disturbance caused by forest machinery during thinning operations.