Using Machine Learning Algorithms to Estimate Soil Organic Carbon Variability with Environmental Variables and Soil Nutrient Indicators in an Alluvial Soil

John, Kingsley; Isong, Isong Abraham; Kebonye, Ndiye Michael; Ayito, Esther O.; Agyeman, Prince Chapman; Afu, Sunday Marcus

doi:10.3390/land9120487

Cited by 105 publications

(62 citation statements)

References 59 publications

(89 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, there are no models available for modelling the soil properties after digestate application. Furthermore, using the multiple linear regression (MLR) there is possible to see the relationship between the SOC stock and other soil´s properties [45][46][47]. Many of the MLR studies are focused on SOC stock modelling on large scale (e.g., large areas of individual states or continents, etc.)…”

Section: Introductionmentioning

confidence: 99%

The Soil Organic Matter in Connection with Soil Properties and Soil Inputs

et al. 2021

View full text Add to dashboard Cite

The content of organic matter in the soil, its labile (hot water extractable carbon–HWEC) and stable (soil organic carbon–SOC) form is a fundamental factor affecting soil productivity and health. The current research in soil organic matter (SOM) is focused on individual fragmented approaches and comprehensive evaluation of HWEC and SOC changes. The present state of the soil together with soil’s management practices are usually monitoring today but there has not been any common model for both that has been published. Our approach should help to assess the changes in HWEC and SOC content depending on the physico-chemical properties and soil´s management practices (e.g., digestate application, livestock and mineral fertilisers, post-harvest residues, etc.). The one- and multidimensional linear regressions were used. Data were obtained from the various soil´s climatic conditions (68 localities) of the Czech Republic. The Czech farms in operating conditions were observed during the period 2008–2018. The obtained results of ll monitored experimental sites showed increasing in the SOC content, while the HWEC content has decreased. Furthermore, a decline in pH and soil´s saturation was documented by regression modelling. Mainly digestate application was responsible for this negative consequence across all soils in studied climatic regions. The multivariate linear regression models (MLR) also showed that HWEC content is significantly affected by natural soil fertility (soil type), phosphorus content (−30%), digestate application (+29%), saturation of the soil sorption complex (SEBCT, 21%) and the dose of total nitrogen (N) applied into the soil (−20%). Here we report that the labile forms (HWEC) are affected by the application of digestate (15%), the soil saturation (37%), the application of mineral potassium (−7%), soil pH (−14%) and the overall condition of the soil (−27%). The stable components (SOM) are affected by the content of HWEC (17%), soil texture 0.01–0.001mm (10%), and input of organic matter and nutrients from animal production (10%). Results also showed that the mineral fertilization has a negative effect (−14%), together with the soil depth (−11%), and the soil texture 0.25–2 mm (−21%) on SOM. Using modern statistical procedures (MRLs) it was confirmed that SOM plays an important role in maintaining resp. improving soil physical, biochemical and biological properties, which is particularly important to ensure the productivity of agroecosystems (soil quality and health) and to future food security.

show abstract

Section: Introductionmentioning

confidence: 99%

The Soil Organic Matter in Connection with Soil Properties and Soil Inputs

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The analysis presented here is not exhaustive but considers almost 50 relevant publications from scientific journals, mainly dealing with soil spectra measurement in the UltraViolet-Visible Near-Infrared (UV-VIS-NIR) range [ 11 , 14 , 35 , 36 , 37 , 38 , 39 ].…”

Section: Analysis Of Machine Learning Methodsmentioning

confidence: 99%

Machine Learning Strategy for Soil Nutrients Prediction Using Spectroscopic Method

ml.¹,

Chambers²

2021

Sensors

View full text Add to dashboard Cite

The research presented in this paper is based on the hypothesis that the machine learning approach improves the accuracy of soil properties prediction. The correlations obtained in this research are important for understanding the overall strategy for soil properties prediction using optical spectroscopy sensors. Several research results have been stated and investigated. A comparison is made between six commonly used techniques: Random Forest, Decision Tree, Naïve Bayes, Support Vector Machine, Least-Square Support Vector Machine and Artificial Neural Network, showing that the best prediction accuracy cannot always be achieved by the most common and complicated method. The influence of the chosen category for nutrient characterization was investigated, indicating better prediction when a multi-component strategy was used. In contrast, the prediction of single-component soil properties was less accurate. In addition, the influence of category levels was not as significant as expected when choosing between 3-level, 5-level or 13-level nutrient characterization for some nutrients, which can be used for a more precise nutrient characterization strategy. A comparative analysis was performed between soil from a local farm with similar texture and soils collected from different locations in Slovenia, which gave a better prediction for a local farm. Finally, the influence of principal component analysis was validated using 5, 10, 20 and 50 first principal components, indicating the better performance of machine learning when using the 50 principal components.

show abstract

“…Cherkassky and Mulier, 41 pioneered SVMR as a regression based on kernel, and its computation was performed using a linear regression model with a multinational space function. John et al, 42…”

Section: Support Vector Machine Regressionmentioning

confidence: 99%

Prediction of Nickel Concentrations in Urban and Peri-Urban Soils: Application of a Hybridized Empirical Bayesian Kriging and Support Vector Machine Regression Approach

Kebonye

John

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Soil pollution is a big issue caused by anthropogenic activities. The spatial distribution of potentially toxic elements (PTEs) varies in most urban and peri-urban areas. As a result, spatially predicting the PTEs content in such soil is difficult. A total number of 115 samples were obtained from Frydek Mistek in the Czech Republic. Calcium(Ca), magnesium(Mg), potassium(K), and nickel (Ni) concentrations were determined using Inductively Coupled Plasma Optical Emission Spectroscopy. The correlation matrix between the response variable and the predictors revealed a satisfactory correlation between the elements. The prediction results indicated that support vector machine regression (SVMR) performed well although its estimated root mean square error (RMSE) (235.974) and mean absolute error (MAE) (166.946) were higher when compared with the other methods applied. Conversely, the hybridized model of empirical bayesian kriging -multiple linear regression (EBK-MLR) performed poorly as indicated by the measured coefficient of determination value below 0.1. The empirical bayesian kriging-support vector machine regression (EBK-SVMR) model was the best model, with low RMSE (95.479) and MAE (77.368) values and a high coefficient of determination (R2 = 0.637). EBK-SVMR modeling technique was visualized using self-organizing map. The clustered neurons of the hybridized model CakMg -EBK-SVMR component plane showed a diverse color pattern predicting the concentration of Ni in the urban and peri urban soil. The results proved that combining EBK and SVMR is an effective technique for predicting Ni concentrations in urban and peri-urban soil.

show abstract

Using Machine Learning Algorithms to Estimate Soil Organic Carbon Variability with Environmental Variables and Soil Nutrient Indicators in an Alluvial Soil

Cited by 105 publications

References 59 publications

The Soil Organic Matter in Connection with Soil Properties and Soil Inputs

The Soil Organic Matter in Connection with Soil Properties and Soil Inputs

Machine Learning Strategy for Soil Nutrients Prediction Using Spectroscopic Method

Prediction of Nickel Concentrations in Urban and Peri-Urban Soils: Application of a Hybridized Empirical Bayesian Kriging and Support Vector Machine Regression Approach

Contact Info

Product

Resources

About