Spatial prediction of major soil properties using Random Forest techniques - A case study in semi-arid tropics of South India

Dharumarajan, S.; Hegde, Rajendra; Singh, Surendra

doi:10.1016/j.geodrs.2017.07.005

Cited by 127 publications

(38 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…in a relatively cool environment the stabilization of soil organic matter is more efficient). Besides climatic variables, remote sensing vegetation indices (NDVI, EVI) and land use information may also have greater predictive value in SOC models (DHARUMARAJAN et al, 2017). Only SILVA et al (2016) found that parent material plays a decisive role in determining soil characteristics and that geology has a stronger effect on SOC than climate under humid-semi-arid conditions.…”

Section: Discussionmentioning

confidence: 99%

The role of geology in the spatial prediction of soil properties in the watershed of Lake Balaton, Hungary

Kassai¹,

Sisák²

2018

Geol Cro

View full text Add to dashboard Cite

There is no standard methodology which allows the incorporation of geological information into digital soil mapping (DSM) despite the great potential of geology as environmental covariate in DSM. To fill this gap, in this study, a geochemical parent material classification scheme was tested on the watershed area of Lake Balaton, for which soil maps at a finer scale have not yet been created. A parent material map was prepared on the basis of a 1:100 000 surface geology map in order to make the incorporation of soil modelling and mapping possible. Legacy data of 12400 soil sample points was used in order to examine the role of geology in the quantitative distribution of some soil properties and element content (liquid limit, soil organic carbon, pH (KCL) , CaCO 3 , Mg, Cu, Zn, Mn). Results confirm that the SiO 2 content of the parent material influences the properties of the derived soils. In the second part of the study Random Forest models were developed for three major soil properties (liquid limit, soil organic carbon, pH) with the use of additional environmental covariates: elevation, slope, aspect, curvature, topographic position index (TPI), annual average temperature, annual average precipitation, remote sensing based normalized difference vegetation index (NDVI) and land cover information. The performance and accuracy of the models were evaluated on the basis of the coefficient of determination (R 2) and root mean square error (RMSE), calculated on a randomly selected validation dataset (20% of the database). The models performed with R 2 values of 0.72, 0.6 and 0.68 for liquid limit, soil organic carbon and pH respectively. The importance of variables was also examined in the RF models, and this demonstrated that while geology is among the best-performing predictors, in neither case is it the most important variable. Ninety metre resolution maps of the three major soil properties were compiled by making spatial predictions with the RF models developed here. For validation of the maps, an independent soil database was used, which showed that the prediction performed well on the cultivated area where the concordance correlation coefficients (CCC) were 0.73, 0.73 and 0.69 for liquid limit, pH and soil organic carbon respectively.

show abstract

Section: Discussionmentioning

confidence: 99%

The role of geology in the spatial prediction of soil properties in the watershed of Lake Balaton, Hungary

Kassai¹,

Sisák²

2018

Geol Cro

View full text Add to dashboard Cite

show abstract

“…Random Forest (RF) model is a non-parametric technique that has been successfully applied to soil properties prediction (Wiesmeier et al, 2011;Castro Franco et al, 2015;Hengl et al, 2015;Chagas et al, 2016;Yang et al, 2016;Dharumarajan;Hedge;Singh, 2017;Silva et al, 2017;Blanco et al, 2018;Wang et al, 2018a). The model combines a set of decision trees to improve the accuracy of prediction of a given environmental variable, where each tree is generated by bootstrap samples (random sampling with substitution), leaving one-third of training samples, called Out-of-Bag (OOB) data, for using in the model's performance evaluation (Breiman, 2001;Liaw;Wiener, 2002).…”

Section: Machine Learning Algorithms For Ko Predictionmentioning

confidence: 99%

Land-use influence on the soil hydrology: An approach in upper Grande River basin, Southeast Brazil

et al. 2019

View full text Add to dashboard Cite

Brazil is a large country that depends on the hydroelectricity generation hydropower dams. The Upper Grande River Basin (UGRB) is one of the most important Brazilian hydrological regions in terms of water availability and electric energy production. Therefore, studies of water availability are indispensable for a better and more successful decision making in water resources management in the region. This study objective to approach the land-use influence on the soil hydrology in the Upper Grande River Basin, a strategic headwater basin of southeastern Brazil. This study uses hydrological indicators (baseflow/runoff (BF/R) and overland flow/runoff (OF/R)) extracted from eight watersheds, varying the size and localization in the region, to support the results found. Soil saturated hydraulic conductivity (Ko) was determined in situ using a constant flow permeameter, totaling 224 sampled points. Five machine learning algorithms were compared in their performance to predict Ko (Random Forest, Support Vector Machine, Gradient Boosting, Linear Regression, Regularization) using terrain attributes as covariates. The tested methods for predicting Ko resulted in a relatively low coefficient of determination (R2) due to the high spatial variability of this soil hydrologic attribute. The hydrological indicator BF/R was sensitive to land-use changes in the watersheds. The greatest Ko values were associated with native forest and the least values area associated with pasture and rupestrian field.

show abstract

“…Regression Trees are tree-based models that have been widely used in DSM (Taghizadeh-Mehrjardi et al, 2016). Random Forest may also be used for both regression and classification purposes (Dharumarajan et al, 2017). Random Forest operates via a resampling approach or boosting, where for regression, the prediction is the average of the individual tree outputs, whereas in classification, the trees vote by majority on the correct classification mode (Grimm et al, 2008).…”

Section: Introductionmentioning

confidence: 99%

Digital Soil Mapping With Regression Tree Classification Approaches by Rs and Geomorphometry Covariate in the Qazvin Plain, Iran

Mousavi

Sarmadian

Rahmani

et al. 2019

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Digital soil mapping applies soil attributes, Remote sensing and Geomorphometrics indices to estimate soil types and properties at unobserved locations. This study carried out in order to comparison two data mining algorithms such as Random Forest (RF) and Boosting Regression tree (BRT) and two features selection principal component analysis (PCA) and variance inflation factor (VIF) for predicting soil taxonomy class at great group and subgroup levels. A total of 61 soil profile observation based on stratified random determined and digged in area with approximately 16660 hectares.19 RS indices and geomorphometrics covariates derivated from Landsate-8 imagery and DEM with 30 meters' resolution in ERDAS IMAGINE 2014 and SAGA GIS version 7.0 software's. Also to run four Data mining algorithms scenarios (PCA-RF, VIF-RF, PCA-BRT, VIF-BRT) from "Randomforest" and "C.5" packages were used in R studio software. 80% and 20% from soil profiles were applied for calibrating and validating. The results showed that in PCA and VIF approaches, eight covariates such as (Relative slope position, diffuse insolation, modified catchment, normalized height, RVI, Standard height, TWI, Valley depth) and six covariates (NDVI, DVI, Catchment area, DEM, Salinity index, Standard height) were selected. The validation results based on overall accuracy and kappa index for scenarios at great group level indicated that 88,93,62, 54 and 75,83,51,45 percentages and for subgroup level had 70, 77, 54, 47 and 60, 71, 43, 37 percentages, respectively. Generally, VIF-RF had accuracy rather than from other scenarios at two categorical level in this study area.

show abstract

Spatial prediction of major soil properties using Random Forest techniques - A case study in semi-arid tropics of South India

Cited by 127 publications

References 40 publications

The role of geology in the spatial prediction of soil properties in the watershed of Lake Balaton, Hungary

The role of geology in the spatial prediction of soil properties in the watershed of Lake Balaton, Hungary

Land-use influence on the soil hydrology: An approach in upper Grande River basin, Southeast Brazil

Digital Soil Mapping With Regression Tree Classification Approaches by Rs and Geomorphometry Covariate in the Qazvin Plain, Iran

Contact Info

Product

Resources

About