Prediction of Soil Organic Carbon at Field Scale by Regression Kriging and Multivariate Adaptive Regression Splines Using Geophysical Covariates

Benedetto, Daniela De; Barca, Emanuele; Castellini, Mirko; Popolizio, Stefano; Lacolla, Giovanni

doi:10.3390/land11030381

Cited by 10 publications

(1 citation statement)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These two assumptions imply the logic that data attribute estimation can be done using information from neighboring locations and that values at neighboring points will have more in common than those at distant points. In the Co-kriging principle, the spatial correlation between the main variable and the supporting variables [8] is an extension of kriging (limited to the main variable) and is more appropriate if all variables are measured [9] and correlated at all sample locations [10].…”

Section: Introductionmentioning

confidence: 99%

Geometric anisotropic Semi-variogram analysis of ozone levels in Daerah Istimewa Yogyakarta, Indonesia

Siswanto,

Mirna,

Heryanto

et al. 2024

Phys. Scr.

View full text Add to dashboard Cite

Identification of areas with high O3 levels that pose a risk to public health is necessary. Ordinary co-kriging is a geostatistical method that determines the value of primary variables at specific locations using weighted values of secondary parameters. A Semi-variogram is required to demonstrate the spatial correlation between the observations measured using this method. This study aims to determine the best Semi-variogram model and produce a map of the predicted O3 level interpolation results using the ordinary co-kriging method with a geometric anisotropic Semi-variogram. Data from the first quarter of 2018’s air quality monitoring in Daerah Istimewa Yogyakarta (DIY) were used to interpolate O3 levels, with 72 points for CO levels and 53 points for O3 levels. The results showed that the Semi-variogram model with the lowest mean error (ME) value is a gaussian model that differs from the spherical model by only 0.003. The Gaussian model has the lowest root mean squared error (RMSE), but it is only 0.002 different from the spherical model. However, by comparing the mean squared deviation ratio (MSDR) values of the three models, the spherical model's MSDR value is the lowest. A comprehensive analysis showed that the spherical geometric anisotropic Semi-variogram model performed superior, resulting in the smallest minimum mean error (ME), root mean square error (RMSE) and minimum squared deviation ratio (MSDR) values. These findings highlight the potential of this approach to accurately map the spatial distribution of O3 and support evidence-based decision-making related to public health.

show abstract

Section: Introductionmentioning

confidence: 99%

Geometric anisotropic Semi-variogram analysis of ozone levels in Daerah Istimewa Yogyakarta, Indonesia

Siswanto,

Mirna,

Heryanto

et al. 2024

Phys. Scr.

View full text Add to dashboard Cite

show abstract

Predicting wetland soil properties using machine learning, geophysics, and soil measurement data

Driba,

Emmanuel,

Doro

2024

J Soils Sediments

View full text Add to dashboard Cite

Purpose Machine learning models can improve the prediction of spatial variation of wetland soil properties, such as soil moisture content (SMC) and soil organic matter (SOM). Their performance, however, relies on the quantity of data used to train the model, limiting their use with insufficient data. In this study, we assessed the use of synthetic data constrained by limited field data for training an eXtreme Gradient Boosting (XGBoost) algorithm used to predict the distribution of soil properties based on geophysical measurements constrained by soil samples. Materials and methods A spatial distribution of soil apparent electrical conductivity (ECa) and laboratory measurements of SOM and SMC from twenty-two core samples were acquired at the St. Michael restored wetland near Defiance, Ohio. The correlations between ECa, SOM, and SMC were explored for predicting the spatial distribution of SOM and SMC. We used a Beta Variational AutoEncoder (β-VAE) approach to synthetically generate over 70,000 training data from the original twenty-two data from soil cores. The training data samples were taken from the latent space. The XGBoost algorithm was then trained on the β-VAE generated data and used to predict the spatial distribution of SOM and SMC at the site. We also validated the accuracy of the XGBoost predictions using an original holdout model validation technique. Results and discussions The generated synthetic data using the β-VAE include both soil attributes and ECa, which are larger and more diverse than the original training set with an absolute mean reconstructed error for SMC and SOM ranging from 0.018 to 0.022 and 0.026 to 0.041, respectively. This indicates that the β-VAE successfully generated a realistic synthetic dataset and overcame the technical barrier of using limited datasets. In addition, using generated data to expand the original training data helps the XGBoost model make more accurate predictions compared to training on the original data. The XGBoost prediction performance yielded average Lin’s concordance correlation coefficient (LCCC) values of 0.82 and 0.85 for SOM and SMC and a ratio of performance to deviation (RPD) values of 1.92 and 2.22 respectively, indicating a good performance. Conclusions This study validated the use of β-VAE to successfully generate synthetic wetland soil datasets with attributes of the original field data that can be effectively used to train the machine learning XGBoost model. The proposed framework offers an efficient solution for mapping the spatial variability of soil property in data-scarce wetland soil environments.

show abstract

Geospatial and temporal assessment of the variability of soil organic matter and electrical conductivity in irrigated semi-arid area

Tibhirine

Namr

Bouasria

et al. 2023

Geology, Ecology, and Landscapes

View full text Add to dashboard Cite

Prediction of Soil Organic Carbon at Field Scale by Regression Kriging and Multivariate Adaptive Regression Splines Using Geophysical Covariates

Cited by 10 publications

References 49 publications

Geometric anisotropic Semi-variogram analysis of ozone levels in Daerah Istimewa Yogyakarta, Indonesia

Geometric anisotropic Semi-variogram analysis of ozone levels in Daerah Istimewa Yogyakarta, Indonesia

Predicting wetland soil properties using machine learning, geophysics, and soil measurement data

Geospatial and temporal assessment of the variability of soil organic matter and electrical conductivity in irrigated semi-arid area

Contact Info

Product

Resources

About