The Experts below are selected from a list of 70692 Experts worldwide ranked by ideXlab platform
Budiman Minasny - One of the best experts on this subject based on the ideXlab platform.
-
Open Digital Mapping as a cost-effective method for Mapping peat thickness and assessing the carbon stock of tropical peatlands
Geoderma, 2018Co-Authors: Budiman Minasny, Satyanto Krido Saptomo, Budi Indra Setiawan, Alexander B. McbratneyAbstract:Tropical peatland holds a large amount of carbon in the terrestrial ecosystem. Indonesia, responding to the global climate issues, has legislation on the protection and management of the peat ecosystem. However, this effort is hampered by the lack of fine-scale, accurate maps of peat distribution and its thickness. This paper presents an open Digital Mapping methodology, which utilises open data in an open-source computing environment, as a cost-effective method for Mapping peat thickness and estimating carbon stock in Indonesian peatlands. The Digital Mapping methodology combines field observations with factors that are known to influence peat thickness distribution. These factors are represented by multi-source remotely-sensed data derived from open and freely available raster data: Digital elevation models (DEM) from SRTM, geographical information, and radar images (Sentinel and ALOS PALSAR). Utilising machine-learning models from an open-source software, we derived spatial prediction functions and mapped peat thickness and its uncertainty at a grid resolution of 30 m. Peat volume can be calculated from the thickness map, and based on measurements of bulk density and carbon content, carbon stock for the area was estimated. The uncertainty of the estimates was calculated using error propagation rules. We demonstrated this approach in the eastern part of Bengkalis Island in Riau Province, covering an area around 50,000 ha. Results showed that Digital Mapping method can accurately predict the thickness of peat, explaining up to 98% of the variation of the data with a median relative error of 5% or an average error of 0.3 m. The accuracy of this method depends on the number of field observations. We provided an estimate of the cost and time required for map production, i.e. 2 to 4 months with a cost between $0.3 and $0.5/ha for an area of 50,000 ha. Obviously, there is a tradeoff between cost and accuracy. The advantages and limitations of the method were further discussed. The methodology provides a blueprint for a national-scale peat Mapping.
-
Digital Mapping of soil classes and continuous soil properties
2018Co-Authors: Brendan P Malone, Budiman Minasny, Nathan P Odgers, Uta Stockmann, Alex B McbratneyAbstract:Soil is often described as mantling the land more or less continuously with the exception being where there is bare rock and ice (Webster and Oliver 2006). Our understanding of soil variation in any region is usually based on only a small number of observations made in the field. Across the spatial domain of the region of interest, predictions of the spatial distribution of soil properties are made at unobserved locations based on the properties of the small number of soil observations. There are two principal approaches for making predictions of soil at unobserved locations. The first approach subdivides the soil coverage into discrete spatial units within which the soils conform to the characteristics of a class in some soil classification (Heuvelink and Webster 2001). The second approach treats soils as a suite of continuous variables and attempts to describe the way these variables vary across the landscape (Heuvelink and Webster 2001). The second approach is necessarily quantitative, as it requires numerical methods for interpolation between the locations of actual soil observations.
-
Digital Mapping of soil classes using decision tree and auxiliary data in the ardakan region iran
Arid Land Research and Management, 2014Co-Authors: Ruhollah Taghizadehmehrjardi, John Triantafilis, Budiman Minasny, F Sarmadian, Mahmoud OmidAbstract:Digital soil Mapping (DSM) involves acquisition of field soil observations and matching them with environmental variables that can explain the distribution of soils. The harmonization of these data sets, through computer-based methods, are increasingly being found to be as reliable as traditional soil Mapping practices, but without the prohibitive costs. Therefore, the present research developed decision tree models for spatial prediction of soil classes in a 720 km2 area located in an arid region of central Iran, where traditional soil survey methods are difficult to undertake. Using the conditioned Latin hypercube sampling method, the locations of 187 soil profiles were selected, which were then described, sampled, analyzed, and allocated to six Great Groups according to the USDA Soil Taxonomy system. Auxiliary data representing the soil forming factors were derived from a Digital elevation model (DEM), Landsat 7 ETM+ images, and a map of geomorphology. The accuracy of the decision tree models was evalu...
-
Digital Mapping of soil organic carbon contents and stocks in Denmark
PLoS ONE, 2014Co-Authors: Kabindra Adhikari, Rania Bou Kheir, Mette B. Greve, Alfred E. Hartemink, Budiman Minasny, Mogens H. GreveAbstract:Estimation of carbon contents and stocks are important for carbon sequestration, greenhouse gas emissions and national carbon balance inventories. For Denmark, we modeled the vertical distribution of soil organic carbon (SOC) and bulk density, and mapped its spatial distribution at five standard soil depth intervals (0-5, 5-15, 15-30, 30-60 and 60-100 cm) using 18 environmental variables as predictors. SOC distribution was influenced by precipitation, land use, soil type, wetland, elevation, wetness index, and multi-resolution index of valley bottom flatness. The highest average SOC content of 20 g kg-1 was reported for 0-5 cm soil, whereas there was on average 2.2 g SOC kg-1 at 60-100 cm depth. For SOC and bulk density prediction precision decreased with soil depth, and a standard error of 2.8 g kg-1 was found at 60-100 cm soil depth. Average SOC stock for 0-30 cm was 72 t ha-1 and in the top 1 m there was 120 t SOC ha-1. In total, the soils stored approximately 570 Tg C within the top 1 m. The soils under agriculture had the highest amount of carbon (444 Tg) followed by forest and semi-natural vegetation that contributed 11% of the total SOC stock. More than 60% of the total SOC stock was present in Podzols and Luvisols. Compared to previous estimates, our approach is more reliable as we adopted a robust quantification technique and mapped the spatial distribution of SOC stock and prediction uncertainty. The estimation was validated using common statistical indices and the data and high-resolution maps could be used for future soil carbon assessment and inventories.
-
Digital Mapping of a soil drainage index for irrigated enterprise suitability in Tasmania, Australia
Soil Research, 2014Co-Authors: D. B. Kidd, Brendan P Malone, Budiman Minasny, Alexander B. Mcbratney, M. A. WebbAbstract:An operational Digital Soil Assessment was developed to inform land suitability modelling in newly commissioned irrigation schemes in Tasmania, Australia. The Land Suitability model uses various soil parameters, along with other climate and terrain surfaces, to identify suitable areas for various agricultural enterprises for a combined 70 000-ha pilot project area in the Meander and Midlands Regions of Tasmania. An integral consideration for irrigable suitability is soil drainage. Quantitative measurement and Mapping can be resource-intensive in time and associated costs, whereas more ‘traditional’ Mapping approaches can be generalised, lacking the detail required for statistically validated products. The project was not sufficiently resourced to undertake replicated field-drainage measurements and relied on expert field drainage estimates at ~930 sites (260 of these for independent validation) to spatially predict soil drainage for both areas using various terrain-based and remotely sensed covariates, using three approaches: (a) decision tree spatial modelling of discrete drainage classes; (b) regression-tree spatial modelling of a continuous drainage index; (c) regression kriging (random-forests with residual-kriging) spatial modelling of a continuous drainage index. Method b was chosen as the best approach in terms of interpretation, and model training and validation, with a concordance coefficient of 0.86 and 0.57, respectively. A classified soil drainage map produced from the ‘index’ showed good agreement, with a linearly weighted kappa coefficient of 0.72 for training, and 0.37 for validation. The index Mapping was incorporated into the overall land suitability model and proved an important consideration for the suitability of most enterprises.
Brendan P Malone - One of the best experts on this subject based on the ideXlab platform.
-
Digital Mapping of soil classes and continuous soil properties
2018Co-Authors: Brendan P Malone, Budiman Minasny, Nathan P Odgers, Uta Stockmann, Alex B McbratneyAbstract:Soil is often described as mantling the land more or less continuously with the exception being where there is bare rock and ice (Webster and Oliver 2006). Our understanding of soil variation in any region is usually based on only a small number of observations made in the field. Across the spatial domain of the region of interest, predictions of the spatial distribution of soil properties are made at unobserved locations based on the properties of the small number of soil observations. There are two principal approaches for making predictions of soil at unobserved locations. The first approach subdivides the soil coverage into discrete spatial units within which the soils conform to the characteristics of a class in some soil classification (Heuvelink and Webster 2001). The second approach treats soils as a suite of continuous variables and attempts to describe the way these variables vary across the landscape (Heuvelink and Webster 2001). The second approach is necessarily quantitative, as it requires numerical methods for interpolation between the locations of actual soil observations.
-
Digital Mapping of a soil drainage index for irrigated enterprise suitability in Tasmania, Australia
Soil Research, 2014Co-Authors: D. B. Kidd, Brendan P Malone, Budiman Minasny, Alexander B. Mcbratney, M. A. WebbAbstract:An operational Digital Soil Assessment was developed to inform land suitability modelling in newly commissioned irrigation schemes in Tasmania, Australia. The Land Suitability model uses various soil parameters, along with other climate and terrain surfaces, to identify suitable areas for various agricultural enterprises for a combined 70 000-ha pilot project area in the Meander and Midlands Regions of Tasmania. An integral consideration for irrigable suitability is soil drainage. Quantitative measurement and Mapping can be resource-intensive in time and associated costs, whereas more ‘traditional’ Mapping approaches can be generalised, lacking the detail required for statistically validated products. The project was not sufficiently resourced to undertake replicated field-drainage measurements and relied on expert field drainage estimates at ~930 sites (260 of these for independent validation) to spatially predict soil drainage for both areas using various terrain-based and remotely sensed covariates, using three approaches: (a) decision tree spatial modelling of discrete drainage classes; (b) regression-tree spatial modelling of a continuous drainage index; (c) regression kriging (random-forests with residual-kriging) spatial modelling of a continuous drainage index. Method b was chosen as the best approach in terms of interpretation, and model training and validation, with a concordance coefficient of 0.86 and 0.57, respectively. A classified soil drainage map produced from the ‘index’ showed good agreement, with a linearly weighted kappa coefficient of 0.72 for training, and 0.37 for validation. The index Mapping was incorporated into the overall land suitability model and proved an important consideration for the suitability of most enterprises.
-
Digital Mapping of soil salinity in ardakan region central iran
Geoderma, 2014Co-Authors: Ruhollah Taghizadehmehrjardi, Budiman Minasny, F Sarmadian, Brendan P MaloneAbstract:Abstract Salinization and alkalinization are the most important land degradation processes in central Iran. In this study we modelled the vertical and lateral variation of soil salinity (measured as electrical conductivity in saturation paste, ECe) using a combination of regression tree analysis and equal-area smoothing splines in a 72,000 ha area located in central Iran. Using the conditioned Latin hypercube sampling method, 173 soil profiles were sampled from the study area, and then analysed for ECe and other soil properties. Auxiliary data used in this study to represent predictive soil forming factors were terrain attributes (derived from a Digital elevation model), Landsat 7 ETM + data, apparent electrical conductivity (ECa)—measured using an electromagnetic induction instrument (EMI), and a geomorphologic surfaces map. To derive the relationships between ECe (from soil surface to 1 m) and the auxiliary data, regression tree analysis was applied. In general, results showed that the ECa surfaces are the most powerful predictors for ECe at three depth intervals (i.e. 0–15, 15–30 and 30–60 cm). In the 60–100 cm depth interval, topographic wetness index was the most important parameter used in regression tree model. Validation of the predictive models at each depth interval resulted in R 2 values ranging from 78% (0–15 cm) to 11% (60–100 cm). Thus we can recommend similar applications of this technique could be used for Mapping soil salinity in other parts in Iran.
-
Digital Mapping of soil carbon
Advances in Agronomy, 2013Co-Authors: Budiman Minasny, Brendan P Malone, Alex B Mcbratney, Ichsani WheelerAbstract:There is a global demand for soil data and information for food security and global environmental management. There is also great interest in recognizing the soil system as a significant terrestrial sink of carbon. The reliable assessment of soil carbon (C) stocks is of key importance for soil conservation and in mitigation strategies for increased atmospheric carbon. In this article, we review and discuss the recent advances in Digital Mapping of soil C. The challenge to map carbon is demonstrated with the large variation of soil C concentration at a field, continental, and global scale. This article reviews recent studies in Mapping soil C using Digital soil Mapping approaches. The general activities in Digital soil Mapping involve collection of a database of soil carbon observations over the area of interest; compilation of relevant covariates (scorpan factors) for the area; calibration or training of a spatial prediction function based on the observed dataset; interpolation and/or extrapolation of the prediction function over the whole area; and finally validation using existing or independent datasets. We discuss several relevant aspects in Digital Mapping: carbon concentration and carbon density, source of data, sampling density and resolution, depth of investigation, map validation, map uncertainty, and environmental covariates. We demonstrate harmonization of soil depths using the equal-area spline and the use of a material coordinate system to take into consideration the varying bulk density due to management practices. Soil C Mapping has evolved from 2-D Mapping of soil C stock at particular depth ranges to a semi-3-D soil map allowing the estimation of continuous soil C concentration or density with depth. This review then discusses the dynamics of soil C and the consequences for prediction and Mapping of soil C change. Finally, we illustrate the prediction of soil carbon change using a semidynamic scorpan approach.
Mojtaba Zeraatpisheh - One of the best experts on this subject based on the ideXlab platform.
-
Digital Mapping of soil organic carbon using ensemble learning model in mollisols of hyrcanian forests northern iran
Geoderma Regional, 2020Co-Authors: Samaneh Tajik, Shamsollah Ayoubi, Mojtaba ZeraatpishehAbstract:Abstract This study was conducted to evaluate the efficacy of the ensemble machine learning model to predict the spatial variation of soil organic carbon (SOC) concentration in a deciduous forest ecosystem in northern Iran. To do this, a total of 153 soil samples by applying regular systematic sampling grid at two depths (0–10 and 10–20 cm) were collected. Two scenarios through Digital soil Mapping (DSM) were considered to establish the predictive models for estimating SOC including (i) combination of selected topographic attributers (T), remotely sensed data (R), and soil properties (S) (TRS) and (ii) combination of topographic attributes and remotely sensed data (TR). The ensemble model for predicting of SOC was consisted of six machine learning algorithms: partial least squares regression (PLSR), generalized linear model (GLM), recursive partitioning and regression trees (rpart), support vector machines (SVM), random forest (RF) and k-nearest neighbors (kNN). The 10-fold cross-validation with three replications was employed to evaluate the performance of models by root mean square error (RMSE) and the coefficient of determination (R2). The results showed that SOC was varied from 2.05 to 13.16% with a mean of 5.67% in first depth (0--10 cm) and from 1.56 to 9.56% with a mean of 3.99% in second depth (10–20 cm). According to the RMSE and R2 results ensemble machine learning model, first scenario (TRS) showed higher performance (higher R2 and lower RMSE) than second scenario (TR) for prediction of SOC in first depth (R2 = 0.74, RMSE = 0.78%) and second depth (R2 = 0.65, RMSE = 0.90%). Also, in the best scenario (TRS) for individual models, results of validation revealed that GLM, SVM and RF for the first depth and PLSR, GLM, SVM, and RF for the second depth were the most accurate machine learning algorithms in ensemble modeling based on RMSE. Our finding indicated that soil properties had an important contribution to the spatial variability of SOC in the studied forest soil. Moreover, topographic attributes and vegetation indexes were found to be auxiliary attributes in the modeling of SOC and could use for quick and cost-effective assessment of SOC concentration in order to management practices in forest soils.
-
Digital Mapping of soil properties using multiple machine learning in a semi-arid region, central Iran
Geoderma, 2018Co-Authors: Mojtaba Zeraatpisheh, Azam Jafari, Samaneh Tajik, Shamsollah Ayoubi, Peter FinkeAbstract:Knowledge about distribution of soil properties over the landscape is required for a variety of land management applications and resources, modeling, and monitoring practices. The main aim of this research was to conduct a spatially prediction of the top soil properties such as soil organic carbon (SOC), calcium carbonate equivalent (CCE), and clay content using Digital soil Mapping (DSM) approaches in Borujen region, Chaharmahal-Va-Bakhtiari province, central Iran. To achieve this goal, a total of 334 soil samples were collected from 0 to 30 cm depth. Three non-linear models including Cubist (Cu), Random Forest (RF), Regression Tree (RT) and a Multiple Linear Regression (MLR) were used to link environmental covariates and the studied soil properties. The environmental covariates were obtained from a Digital elevation model (DEM) and satellite imagery (Landsat Enhanced Thematic Mapper; ETM). The model was calibrated and validated by the 10-fold cross-validation approach. Root mean square error (RMSE) and coefficient of determination (R2) were used to determine the performance of the models, and relative RMSE (RMSE%) was used to define prediction accuracy. According to the RMSE and R2, Cu and RF resulted in the most accurate predictions for CCE (R2= 0.30 and RMSE = 9.52) and clay contents (R2= 0.15 and RMSE = 7.86), respectively, while both of RF and Cu models showed the highest performance to predict SOC content (R2= 0.55). Results showed that remote sensing covariates (Ratio Vegetation Index and band 4) were the most important variables to explain the variability of SOC and CCE content, but only topographic attributes were responsible for clay content variation. According to RMSE% results, it could be concluded that the best model is not necessarily able to make the most accurate estimation. This study recommended that more observations and denser sampling should be carried out in the entire study area. Alternatively, stratified sampling by elevation in homogeneous sub-areas was recommended. The stratified sampling probably will increase the performance of models.
Shamsollah Ayoubi - One of the best experts on this subject based on the ideXlab platform.
-
Digital Mapping of soil drainage using remote sensing dem and soil color in a semiarid region of central iran
Geoderma Regional, 2020Co-Authors: Najmeh Asgari, José Lucas Safanelli, A. Jafari, Shamsollah Ayoubi, José Alexandre Melo Demattê, Ariane Francine Desiderio Da SilveiraAbstract:Abstract In this study, random forest (RF) and support vector machine (SVM) models were developed to evaluate different input variables for predicting and Mapping soil drainage classes in the a part of Charmahal & Bakhtiari Province, central Iran. Input variables included Digital elevation model (DEM) derived topographic attributes, remote sensing-derived vegetation indices and diffuse reflectance spectroscopy-derived soil color qualifiers (chroma and value). Three soil drainage classes, comprising poorly drained (PD), moderately well drained (MWD) and well drained (WD) were identified. Totally, 102 profiles were described and soil samples were collected from various genetic horizons. Results showed that the best classification results were acquired for two extreme drainage classes (WD and PD) with 100% user accuracy and the greatest misclassification for MWD. Chroma following NDVI and SAVI were the most efficient predictors of soil drainage. The best performance of models was acquired when the topographic attributes, NDVI, SAVI, chroma and value were included as input variables for predicting soil drainage classes. The prediction overall accuracy and the Kappa coefficient of drainage classification were 0.83 and 0.73 for RF and 0.86 and 0.74 for SVM, respectively. In overall, results indicated that color qualifiers combined with topographic attributes and vegetation indices can be employed to successfully predict soil drainage classes cost-effectively with acceptable overall accuracy.
-
Digital Mapping of soil organic carbon using ensemble learning model in mollisols of hyrcanian forests northern iran
Geoderma Regional, 2020Co-Authors: Samaneh Tajik, Shamsollah Ayoubi, Mojtaba ZeraatpishehAbstract:Abstract This study was conducted to evaluate the efficacy of the ensemble machine learning model to predict the spatial variation of soil organic carbon (SOC) concentration in a deciduous forest ecosystem in northern Iran. To do this, a total of 153 soil samples by applying regular systematic sampling grid at two depths (0–10 and 10–20 cm) were collected. Two scenarios through Digital soil Mapping (DSM) were considered to establish the predictive models for estimating SOC including (i) combination of selected topographic attributers (T), remotely sensed data (R), and soil properties (S) (TRS) and (ii) combination of topographic attributes and remotely sensed data (TR). The ensemble model for predicting of SOC was consisted of six machine learning algorithms: partial least squares regression (PLSR), generalized linear model (GLM), recursive partitioning and regression trees (rpart), support vector machines (SVM), random forest (RF) and k-nearest neighbors (kNN). The 10-fold cross-validation with three replications was employed to evaluate the performance of models by root mean square error (RMSE) and the coefficient of determination (R2). The results showed that SOC was varied from 2.05 to 13.16% with a mean of 5.67% in first depth (0--10 cm) and from 1.56 to 9.56% with a mean of 3.99% in second depth (10–20 cm). According to the RMSE and R2 results ensemble machine learning model, first scenario (TRS) showed higher performance (higher R2 and lower RMSE) than second scenario (TR) for prediction of SOC in first depth (R2 = 0.74, RMSE = 0.78%) and second depth (R2 = 0.65, RMSE = 0.90%). Also, in the best scenario (TRS) for individual models, results of validation revealed that GLM, SVM and RF for the first depth and PLSR, GLM, SVM, and RF for the second depth were the most accurate machine learning algorithms in ensemble modeling based on RMSE. Our finding indicated that soil properties had an important contribution to the spatial variability of SOC in the studied forest soil. Moreover, topographic attributes and vegetation indexes were found to be auxiliary attributes in the modeling of SOC and could use for quick and cost-effective assessment of SOC concentration in order to management practices in forest soils.
-
Digital Mapping of soil properties using multiple machine learning in a semi-arid region, central Iran
Geoderma, 2018Co-Authors: Mojtaba Zeraatpisheh, Azam Jafari, Samaneh Tajik, Shamsollah Ayoubi, Peter FinkeAbstract:Knowledge about distribution of soil properties over the landscape is required for a variety of land management applications and resources, modeling, and monitoring practices. The main aim of this research was to conduct a spatially prediction of the top soil properties such as soil organic carbon (SOC), calcium carbonate equivalent (CCE), and clay content using Digital soil Mapping (DSM) approaches in Borujen region, Chaharmahal-Va-Bakhtiari province, central Iran. To achieve this goal, a total of 334 soil samples were collected from 0 to 30 cm depth. Three non-linear models including Cubist (Cu), Random Forest (RF), Regression Tree (RT) and a Multiple Linear Regression (MLR) were used to link environmental covariates and the studied soil properties. The environmental covariates were obtained from a Digital elevation model (DEM) and satellite imagery (Landsat Enhanced Thematic Mapper; ETM). The model was calibrated and validated by the 10-fold cross-validation approach. Root mean square error (RMSE) and coefficient of determination (R2) were used to determine the performance of the models, and relative RMSE (RMSE%) was used to define prediction accuracy. According to the RMSE and R2, Cu and RF resulted in the most accurate predictions for CCE (R2= 0.30 and RMSE = 9.52) and clay contents (R2= 0.15 and RMSE = 7.86), respectively, while both of RF and Cu models showed the highest performance to predict SOC content (R2= 0.55). Results showed that remote sensing covariates (Ratio Vegetation Index and band 4) were the most important variables to explain the variability of SOC and CCE content, but only topographic attributes were responsible for clay content variation. According to RMSE% results, it could be concluded that the best model is not necessarily able to make the most accurate estimation. This study recommended that more observations and denser sampling should be carried out in the entire study area. Alternatively, stratified sampling by elevation in homogeneous sub-areas was recommended. The stratified sampling probably will increase the performance of models.
Samaneh Tajik - One of the best experts on this subject based on the ideXlab platform.
-
Digital Mapping of soil organic carbon using ensemble learning model in mollisols of hyrcanian forests northern iran
Geoderma Regional, 2020Co-Authors: Samaneh Tajik, Shamsollah Ayoubi, Mojtaba ZeraatpishehAbstract:Abstract This study was conducted to evaluate the efficacy of the ensemble machine learning model to predict the spatial variation of soil organic carbon (SOC) concentration in a deciduous forest ecosystem in northern Iran. To do this, a total of 153 soil samples by applying regular systematic sampling grid at two depths (0–10 and 10–20 cm) were collected. Two scenarios through Digital soil Mapping (DSM) were considered to establish the predictive models for estimating SOC including (i) combination of selected topographic attributers (T), remotely sensed data (R), and soil properties (S) (TRS) and (ii) combination of topographic attributes and remotely sensed data (TR). The ensemble model for predicting of SOC was consisted of six machine learning algorithms: partial least squares regression (PLSR), generalized linear model (GLM), recursive partitioning and regression trees (rpart), support vector machines (SVM), random forest (RF) and k-nearest neighbors (kNN). The 10-fold cross-validation with three replications was employed to evaluate the performance of models by root mean square error (RMSE) and the coefficient of determination (R2). The results showed that SOC was varied from 2.05 to 13.16% with a mean of 5.67% in first depth (0--10 cm) and from 1.56 to 9.56% with a mean of 3.99% in second depth (10–20 cm). According to the RMSE and R2 results ensemble machine learning model, first scenario (TRS) showed higher performance (higher R2 and lower RMSE) than second scenario (TR) for prediction of SOC in first depth (R2 = 0.74, RMSE = 0.78%) and second depth (R2 = 0.65, RMSE = 0.90%). Also, in the best scenario (TRS) for individual models, results of validation revealed that GLM, SVM and RF for the first depth and PLSR, GLM, SVM, and RF for the second depth were the most accurate machine learning algorithms in ensemble modeling based on RMSE. Our finding indicated that soil properties had an important contribution to the spatial variability of SOC in the studied forest soil. Moreover, topographic attributes and vegetation indexes were found to be auxiliary attributes in the modeling of SOC and could use for quick and cost-effective assessment of SOC concentration in order to management practices in forest soils.
-
Digital Mapping of soil properties using multiple machine learning in a semi-arid region, central Iran
Geoderma, 2018Co-Authors: Mojtaba Zeraatpisheh, Azam Jafari, Samaneh Tajik, Shamsollah Ayoubi, Peter FinkeAbstract:Knowledge about distribution of soil properties over the landscape is required for a variety of land management applications and resources, modeling, and monitoring practices. The main aim of this research was to conduct a spatially prediction of the top soil properties such as soil organic carbon (SOC), calcium carbonate equivalent (CCE), and clay content using Digital soil Mapping (DSM) approaches in Borujen region, Chaharmahal-Va-Bakhtiari province, central Iran. To achieve this goal, a total of 334 soil samples were collected from 0 to 30 cm depth. Three non-linear models including Cubist (Cu), Random Forest (RF), Regression Tree (RT) and a Multiple Linear Regression (MLR) were used to link environmental covariates and the studied soil properties. The environmental covariates were obtained from a Digital elevation model (DEM) and satellite imagery (Landsat Enhanced Thematic Mapper; ETM). The model was calibrated and validated by the 10-fold cross-validation approach. Root mean square error (RMSE) and coefficient of determination (R2) were used to determine the performance of the models, and relative RMSE (RMSE%) was used to define prediction accuracy. According to the RMSE and R2, Cu and RF resulted in the most accurate predictions for CCE (R2= 0.30 and RMSE = 9.52) and clay contents (R2= 0.15 and RMSE = 7.86), respectively, while both of RF and Cu models showed the highest performance to predict SOC content (R2= 0.55). Results showed that remote sensing covariates (Ratio Vegetation Index and band 4) were the most important variables to explain the variability of SOC and CCE content, but only topographic attributes were responsible for clay content variation. According to RMSE% results, it could be concluded that the best model is not necessarily able to make the most accurate estimation. This study recommended that more observations and denser sampling should be carried out in the entire study area. Alternatively, stratified sampling by elevation in homogeneous sub-areas was recommended. The stratified sampling probably will increase the performance of models.