Machine Learning Approach to Simulate Soil CO2 Fluxes under Cropping Systems

Adjuik, Toby A.; Davis, Sarah C.

doi:10.3390/agronomy12010197

Cited by 23 publications

(7 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most authors argue that soil temperature is associated with CO 2 and NO 2 emissions: as the soil temperature increases, so does the release of these gases into the atmosphere. Thus, this effect becomes a positive feedback loop in the climate system [ 55 ]. Our results confirm that meteorological conditions are important (Tables 4 and 5); precipitation decreased during the vegetation period and active temperatures were also lower compared to the long-term averages.…”

Section: Resultsmentioning

confidence: 99%

Soil Water Capacity, Pore Size Distribution, and CO2 Emission in Different Soil Tillage Systems and Straw Retention

Steponavičienė

Bogužas

Sinkevičienė

et al. 2022

Plants

View full text Add to dashboard Cite

The long-term implementation of crop rotation and tillage has an impact on the soil environment through inputs and soil disturbance, which in turn has an impact on soil quality. Tillage has a long-term impact on the agroecosystems. Since 1999, a long-term field experiment has been carried out at the Experimental Station of Vytautas Magnus University. The aim of this experiment is to investigate the effects of long-term various-intensity tillage and straw retention systems on soil physical properties. The results were obtained in 2013 and 2019 (spring rape was growing). According to the latest edition of the International Soil Classification System, the soil in the experimental field was classified as Endocalcaric Stagnosol (Aric, Drainic, Ruptic, and Amphisiltic). The treatments were arranged using a split-plot design. In a two-factor field experiment, the straw was removed from one part of the experimental field, and the entire straw yield was chopped and spread at harvest in the other part of the field (Factor A). There were three different tillage systems as a subplot (conventional deep ploughing, cover cropping with following shallow termination, and no-tillage) (Factor B). There were four replications. The long-term application of reduced tillage significantly increased soil water retention and improved the pore structure and CO2 emissions. Irrespective of the incorporation of straw, it was found that as the amount of water available to plants increases, CO2 emissions from the soil increase to some extent and then start to decrease. Simplified tillage and no-tillage in uncultivated soil reduce CO2 emissions by increasing the amount of water available to plants from 0.151 to 0.233 m3·m−3.

show abstract

Section: Resultsmentioning

confidence: 99%

Soil Water Capacity, Pore Size Distribution, and CO2 Emission in Different Soil Tillage Systems and Straw Retention

Steponavičienė

Bogužas

Sinkevičienė

et al. 2022

Plants

View full text Add to dashboard Cite

show abstract

“…Carbon sequestration rates found in previous studies range from 0.1 to 3.0 Mg ha −1 year −1 (Table 5), but the mean sequestration rate reported in prior works was 1.1 Mg ha −1 year −1 , similar to the mean resolved in this study (Table 5). The diverse site conditions, geographical locations, soil types, management strategies, and prior land use histories may provide an explanation for the range in C accumulation (Adjuik & Davis, 2022; Anderson‐Teixeira et al., 2009; Davis et al., 2013; Zimmermann et al., 2013).…”

Section: Discussionmentioning

confidence: 99%

Decadal change in soil carbon and nitrogen with a Miscanthus × giganteus crop on abandoned agricultural land in southeast Ohio

Adu Fosu,

Davis

2024

GCB Bioenergy

Self Cite

View full text Add to dashboard Cite

Miscanthus × giganteus (miscanthus) is considered a beneficial biomass energy crop because of its carbon (C) sequestration potential and low fertilizer requirements, but few studies in the United States have measured long‐term C sequestration of miscanthus on suboptimal agricultural lands over a decadal scale, and none have been conducted in southeast Ohio. The objective of this study was to measure the soil C sequestration on abandoned agricultural land with a miscanthus crop that is harvested annually, the long‐term changes in plant and soil nitrogen (N), and the photosynthetic capacity in the tenth year of growth. This study was conducted over a 10‐year period from 2013 through 2023. A significant amount of C was accumulated in the soil (p < 0.05) and the mean C sequestration rates were 0.83 and 1.37 Mg C ha−1 year−1 at two different sites. The amount of C accumulated in the miscanthus plots by the tenth year was also greater than soil C in unmanaged grassland soils, but the difference was not statistically significant (p > 0.05). There was no statistically significant change in the amount of N found in soil and plants over 10 years (p > 0.05), but the variability in plant N was greater in some years relative to others. Even though miscanthus was grown without N fertilizers in this study, soil N at 0–30 cm depth was not depleted over 10 years of crop management. The photosynthetic capacity of miscanthus measured in this study indicated that the plants were thriving after 10 years, and C assimilation for growth was consistent with the findings of prior work that evaluated the maximum photosynthetic rates of this species. The combination of significant soil C sequestration, sustained soil N, and high photosynthetic rates has important implications for the sustainability of miscanthus as a biomass crop.

show abstract

“…The model presented by Zhang et al [20] used multiple sets of machine learning methods to identify the carbon content in the soil in a specific region. Similarly, various other work was conducted to assess various problems that directly relate to assessment of soil quality; the studies included averaging method for soil properties [21], forecasting carbon in soil using multiple sets of machine learning [22], yield prediction [23], assessing effectiveness of machine learning [24], growth prediction using deep learning [25], assessing CO2 fluxes [26], prediction of texture [27], reliability forecasting model [28], and carbon variability assessment [29]. A fuzzy-logic-based approach for assessing soil quality has also been investigated by Ogunleye et al [30], Nooriman et al [31], Hoseini [32], Chen et al [33], and Atijosan et al [34].…”

Section: Review Of Literaturementioning

confidence: 99%

Prediction of Soil Quality in Rwanda for Ideal Cultivation of Potato (Solanum tuberosum) Using Fuzzy Logic and Machine Learning

Musanase,

Vodacek,

Hanyurwimfura

et al. 2023

IJFIS

View full text Add to dashboard Cite

The ability to estimate soil quality has great value for agriculture, especially for low-income regions with minimal agricultural and financial resources. This prediction provides users with information that is useful in determining whether the soil is suitable for a specific crop, such as potato (Solanum tuberosum). Farmers in Rwanda lack information on soil quality. There are not enough soil laboratories to perform the requisite measurements of NPK, pH, and organic carbon, nor are there enough experts to analyze the data and provide farmers with timely results. The prime objective of the proposed study is to develop a predictive framework that can estimate soil quality for the ideal cultivation of potato (Solanum tuberosum) considering a case study of Rwanda. In this study, bootstrapping is used to augment the small soil dataset, and fuzzy logic is used to label soil data into four classes of soil suitability, with verification of the labeling by soil experts. Several machine learning methods are then tested on the labeled data, resulting in the classification of suitability for the augmented dataset and an assessment of their performance as a way to support experts in predicting soil quality. All machine learning methods applied were viable, with the best performance achieved using an artificial neural network. The quantified outcome showed that the adoption of a neural-network-based scheme has an average accuracy of 32% in contrast to other learning schemes. However, 70%-80% accuracy was achieved upon the adoption of fuzzy logic.

show abstract

Machine Learning Approach to Simulate Soil CO2 Fluxes under Cropping Systems

Cited by 23 publications

References 66 publications

Soil Water Capacity, Pore Size Distribution, and CO2 Emission in Different Soil Tillage Systems and Straw Retention

Soil Water Capacity, Pore Size Distribution, and CO2 Emission in Different Soil Tillage Systems and Straw Retention

Decadal change in soil carbon and nitrogen with a Miscanthus × giganteus crop on abandoned agricultural land in southeast Ohio

Prediction of Soil Quality in Rwanda for Ideal Cultivation of Potato (Solanum tuberosum) Using Fuzzy Logic and Machine Learning

Contact Info

Product

Resources

About