Spatial variability of soil organic carbon under different land use using radial basis function (RBF)

Soil organic carbon (SOC) plays an important role in maintaining and improving soil fertility and quality, in addition to mitigating climate change. Understanding SOC spatial variability is fundamental for describing soil resources and predicting SOC. In this study, SOC content and SOC mass were estimated based on a soil survey of a small watershed in the Dan River, China. The spatial heterogeneity of SOC distribution and the impacts of land-use types, elevation, slope, and aspect on SOC were also assessed. Field sampling was carried out based on a 100 m by 100 m grid system overlaid on the topographic map of the study area, and samples were collected in three soil layers to a depth of 40 cm. In total, 222 sites were sampled and 629 soil samples were collected. The results showed that classical kriging could successfully interpolate SOC content in the watershed. Contents of SOC showed strong spatial heterogeneity based on the values of the coefficient of variation and the nugget ratio, and this was attributed largely to the type of land use. The range of the semi-variograms increased with increasing soil depth. The SOC content in the soil profile decreased as soil depth increased, and there were significant (P < 0.01) differences among the three soil layers. Land use had a great impact on the SOC content. ANOVA indicated that the spatial variation of SOC contents under different land use types was significant (P < 0.05). The SOC mass of different land-use types followed the order grassland > forestland > cropland. Mean SOC masses of grassland, forestland, and cropland at a depth of 0–40 cm were 5.87, 5.61, and 5.07 kg m–2, respectively. The spatial variation of SOC masses under different land-use types was significant (P < 0.05). ANOVA also showed significant (P < 0.05) impact of aspect on SOC mass in soil at 0–40 cm. Soil bulk density played an important role in the assessment of SOC mass. In conclusion, carbon in soils in the source area of the middle Dan River would increase with conversion from agricultural land to forest or grassland.

Download Full-text

Assessing the Intensity of Urban Land Use Based on Radial Basis Function Network

2010 2nd International Workshop on Database Technology and Applications ◽

10.1109/dbta.2010.5659097 ◽

2010 ◽

Author(s):

Weisheng Xu ◽

Sheng Chang ◽

Jiangfeng Li

Keyword(s):

Land Use ◽

Radial Basis Function ◽

Basis Function ◽

Radial Basis Function Network ◽

Urban Land ◽

Urban Land Use ◽

Radial Basis ◽

Function Network

Download Full-text

Improved Support Vector Machine Enabled Radial Basis Function and Linear Variants for Remote Sensing Image Classification

Sensors ◽

10.3390/s21134431 ◽

2021 ◽

Vol 21 (13) ◽

pp. 4431

Author(s):

Abdul Razaque ◽

Mohamed Ben Haj Frej ◽

Muder Almi’ani ◽

Munif Alotaibi ◽

Bandar Alotaibi

Keyword(s):

Remote Sensing ◽

Land Use ◽

Support Vector Machine ◽

Radial Basis Function ◽

Image Classification ◽

Basis Function ◽

State Of The Art ◽

Support Vector ◽

Generalization Problem ◽

Radial Basis

Remote sensing technologies have been widely used in the contexts of land cover and land use. The image classification algorithms used in remote sensing are of paramount importance since the reliability of the result from remote sensing depends heavily on the classification accuracy. Parametric classifiers based on traditional statistics have successfully been used in remote sensing classification, but the accuracy is greatly impacted and rather constrained by the statistical distribution of the sensing data. To eliminate those constraints, new variants of support vector machine (SVM) are introduced. In this paper, we propose and implement land use classification based on improved SVM-enabled radial basis function (RBF) and SVM-Linear for image sensing. The proposed variants are applied for the cross-validation to determine how the optimization of parameters can affect the accuracy. The accuracy assessment includes both training and test sets, addressing the problems of overfitting and underfitting. Furthermore, it is not trivial to determine the generalization problem merely based on a training dataset. Thus, the improved SVM-RBF and SVM-Linear also demonstrate the outstanding generalization performance. The proposed SVM-RBF and SVM-Linear variants have been compared with the traditional algorithms (Maximum Likelihood Classifier (MLC) and Minimum Distance Classifier (MDC)), which are highly compatible with remote sensing images. Furthermore, the MLC and MDC are mathematically modeled and characterized with new features. Also, we compared the proposed improved SVM-RBF and SVM-Linear with the current state-of-the-art algorithms. Based on the results, it is confirmed that proposed variants have higher overall accuracy, reliability, and fault-tolerance than traditional as well as latest state-of-the-art algorithms.

Download Full-text

Spatial variability and simulation of soil organic carbon under different land use systems: geostatistical approach

Agroforestry Systems ◽

10.1007/s10457-018-0244-4 ◽

2018 ◽

Vol 93 (4) ◽

pp. 1389-1398

Author(s):

O. O. Paul ◽

B. S. Sekhon ◽

S. Sharma

Keyword(s):

Land Use ◽

Organic Carbon ◽

Soil Organic Carbon ◽

Spatial Variability ◽

Land Use Systems ◽

Geostatistical Approach

Download Full-text

A dynamic adaptive radial basis function approach for total organic carbon content prediction in organic shale

Geophysics ◽

10.1190/geo2013-0154.1 ◽

2013 ◽

Vol 78 (6) ◽

pp. D445-D459 ◽

Cited By ~ 20

Author(s):

Maojin Tan ◽

Qiong Liu ◽

Songyang Zhang

Keyword(s):

Organic Carbon ◽

Total Organic Carbon ◽

Radial Basis Function ◽

Basis Function ◽

Nearest Neighbor ◽

Rbf Neural Network ◽

Organic Carbon Content ◽

Network Training ◽

Radial Basis ◽

Organic Shale

Total organic carbon (TOC) is an important parameter for characterizing shale gas and oil reservoirs. Estimation of TOC from well logs has previously been achieved by an empirical model. The radial basis function (RBF) neural network is a new quantitative method that can generate a smooth and continuous function of several input variables to approximate the unknown forward model. We investigated the basic principles of the RBF including network structure, basis function, network training method, and its application in the TOC prediction. The nearest neighbor algorithm was selected for the network training. Then, the Gaussian width was investigated to improve the TOC prediction accuracy through leave-one-out cross-validation. Finally, field cases of organic shale were studied for the TOC prediction, and the prediction results using the RBF method were compared with those of the [Formula: see text] method. Furthermore, according to sensitive attribute ranking, the impacts of different input logs on the predicted results were also investigated through various experiments, and the best network model was finally chosen. The error analysis between the prediction results and lab-measured TOC in some examples indicated that the new approach is more accurate than a single empirical regression method and more flexible than the [Formula: see text] method.

Download Full-text

Assessing spatial variability of soil organic carbon and total nitrogen in eroded hilly region of subtropical China

PLoS ONE ◽

10.1371/journal.pone.0244322 ◽

2020 ◽

Vol 15 (12) ◽

pp. e0244322

Author(s):

Jing Zhang ◽

Miao Zhang ◽

Shaoyan Huang ◽

Xuan Zha

Keyword(s):

Land Use ◽

Soil Erosion ◽

Organic Carbon ◽

Soil Organic Carbon ◽

Spatial Variability ◽

Total Nitrogen ◽

Erosion Control ◽

Slope Aspect ◽

Land Use Type ◽

Hilly Region

The hilly red soil region of southern China suffers from severe soil erosion that has led to soil degradation and loss of soil nutrients. Estimating the content and spatial variability of soil organic carbon (SOC) and soil total nitrogen (STN) and assessing the influence of topography and land-use type on SOC and STN after years of soil erosion control are important for vegetation restoration and ecological reconstruction. A total of 375 topsoil samples were collected from Changting County, and their SOC and STN distributions were studied by using descriptive statistics and geostatistical methods. Elevation, slope, aspect and land-use type were selected to investigate the impacts of natural and human factors on the spatial heterogeneity of SOC and STN. The mean SOC and STN concentrations were 15.85 and 0.98 g kg-1 with moderate spatial variations, respectively. SOC and STN exhibited relatively uniform distributions that decreased gradually from the outside parts to the center of the study area. The SOC and STN contents in the study area were still at moderate and low levels after years of erosion control, which suggests that soil nutrient improvement is a slow process. The lowest SOC and STN values were at lower elevations in the center of Changting County. The results indicated that the SOC and STN contents increased most significantly with elevation and slope due to the influence of topography on the regional natural environment and soil erosion in the eroded hilly region. No significant variations were observed among different slope directions and land-use types.

Download Full-text

A COMPARISON OF THE EFFECTIVENESS OF USING THE MESHLESS METHOD AND THE FINITE DIFFERENCE METHOD IN GEOSTATISTICAL ANALYSIS OF TRANSPORT MODELING

International Journal of Computational Methods ◽

10.1142/s0219876205000405 ◽

2005 ◽

Vol 02 (02) ◽

pp. 149-166 ◽

Cited By ~ 3

Author(s):

LEOPOLD VRANKAR ◽

GORAN TURK ◽

FRANC RUNOVC

Keyword(s):

Hydraulic Conductivity ◽

Finite Difference ◽

Spatial Variability ◽

Radial Basis Function ◽

Basis Function ◽

Meshless Method ◽

Input Data ◽

Basis Functions ◽

Transport Modeling ◽

Radial Basis

Disposal of radioactive waste in geological formations is a great concern with regards to nuclear safety. The general reliability and accuracy of transport modeling depends predominantly on input data such as hydraulic conductivity, water velocity, radioactive inventory, and hydrodynamic dispersion. The most important input data are obtained from field measurements, but they are not always available. One way to study the spatial variability of hydraulic conductivity is geostatistics. The numerical solution of partial differential equations (PDEs) has usually been obtained by finite difference methods (FDM), finite element methods (FEM), or finite volume methods (FVM). These methods require a mesh to support the localized approximations. The multiquadric (MQ) radial basis function method is a recent meshless collocation method with global basis functions. Solving PDEs using radial basis function (RBF) collocations is an attractive alternative to these traditional methods because no tedious mesh generation is required. We compare the meshless method, which uses radial basis functions, with the traditional finite difference scheme. In our case we determine the average and standard deviation of radionuclide concentration with regard to spatial variability of hydraulic conductivity that was modeled by a geostatistical approach.

Download Full-text