Spatial prediction of soil surface texture in a semiarid region using random forest and multiple linear regressions

Abstract Soil texture is an essential and extremely variable physical property that strongly influences many other soil properties that are highly relevant for agricultural production, e.g., fertility and water retention capacity. In plain areas, terrain properties derived from a digital elevation model are not effective for digital soil mapping, and the variation in the properties of such areas remains a challenge. In this regard, remote sensing can facilitate the mapping of soil properties. The purpose of this study was to evaluate the efficiency of using of data obtained from the Thematic Mapper (TM) sensor of Landsat 5 for digital soil mapping in a semi-arid region, based on multiple linear regression (MLR) and a random forest model (RFM). To this end, 399 samples of the soil surface layer (0–20 cm) were used to predict the sand, silt and clay contents, using the bands 1, 2, 3, 4, 5 and 7, the Normalized Difference Vegetation Index (NDVI), the grain size index (GSI), and the relationships between bands 3 and 2, bands 3 and 7, and bands 5 and 7 (clay index) of the Landsat 5 TM sensor as covariates. Among these covariates, only band 1 (b1), the relationship between bands 5 and 7 (b5/b7) for sand, silt and clay, and band 4 (b4) for silt were not significantly correlated according to Pearson's correlation analysis. The validation of the models showed that the properties were best estimated using the RFM, which explained 63% and 56% of the spatial variability of sand and clay, respectively, whereas the MLR explained 30% of the spatial variation of silt. An analysis of the relevance of the variables predicted by the RFM showed that the covariates b3/b7, b5, NDVI and b2 explained most of the variability of the considered properties. The RFM proved to be more advantageous than the MLR with respect to insensitivity to overfitting and the presence of noise in the data. In addition, the RFM produced more realistic distribution maps of the soil properties than did the MLR, taking into account that the estimated values of the soil attributes were in the same range as the calibration data, while the MLR model estimates were out of the range of the calibration data.

[1]  Philippe Lagacherie,et al.  A regional-scale assessment of digital mapping of soil attributes in a tropical hillslope environment , 2014 .

[2]  V. L. Mulder,et al.  The use of remote sensing in soil and terrain mapping — A review , 2011 .

[3]  Lênio Soares Galvão,et al.  Detection of sandy soil surfaces using ASTER‐derived reflectance, emissivity and elevation data: potential for the identification of land degradation , 2008 .

[4]  Philippe Lagacherie,et al.  Evaluating Digital Soil Mapping approaches for mapping GlobalSoilMap soil properties from legacy data in Languedoc-Roussillon (France) , 2015 .

[5]  J. Iqbal,et al.  Evaluation of Landsat TM5 Multispectral Data for Automated Mapping of Surface Soil Texture and Organic Matter in GIS , 2014 .

[6]  J. G. S. Júnior,et al.  Modelos espectrais terrestres e orbitais na determinação de teores de atributos dos solos: potencial e custos , 2011 .

[7]  D. R. Cutler,et al.  Utah State University From the SelectedWorks of , 2017 .

[8]  Martin Hitziger,et al.  Comparison of three supervised learning methods for digital soil mapping: Application to a complex terrain in the Ecuadorian Andes , 2014 .

[9]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[10]  R. V. Rossel,et al.  Using data mining to model and interpret soil diffuse reflectance spectra. , 2010 .

[11]  Modelling soil particle-size distribution in the region 'Centre' (France) , 2014 .

[12]  B. Stenberg,et al.  Near‐infrared spectroscopy for within‐field soil characterization: small local calibrations compared with national libraries spiked with local samples , 2010 .

[13]  E. Ben-Dor,et al.  Laboratory, field and airborne spectroscopy for monitoring organic carbon content in agricultural soils , 2007 .

[14]  J. Demattê,et al.  Spectral Reflectance Methodology in Comparison to Traditional Soil Analysis , 2006 .

[15]  Luis A. Garcia,et al.  Comparison of Ordinary Kriging, Regression Kriging, and Cokriging Techniques to Estimate Soil Salinity Using LANDSAT Images , 2010 .

[16]  F. Sabins.  Remote Sensing: Principles and Interpretation , 1987 .

[17]  J. Zullo,et al.  Quantification of tropical soil attributes from ETM+/LANDSAT‐7 data , 2007 .

[18]  Soil texture GlobalSoilMap products for the French region 'Centre' , 2014 .

[19]  Sabine Grunwald,et al.  Incorporation of spectral data into multivariate geostatistical models to map soil phosphorus variability in a Florida wetland , 2007 .

[20]  Yanjun Shen,et al.  Development of topsoil grain size index for monitoring desertification in arid land using remote sensing , 2006 .

[21]  H. Elsenbeer,et al.  Soil organic carbon concentrations and stocks on Barro Colorado Island — Digital soil mapping using Random Forests analysis , 2008 .

[22]  R. Lark,et al.  Cokriging particle size fractions of the soil , 2007 .

[23]  Qing Zhu,et al.  Spatial estimation of surface soil texture using remote sensing data , 2013 .

[24]  A. Karnieli,et al.  Mapping of several soil properties using DAIS-7915 hyperspectral scanner data - a case study over clayey soils in Israel , 2002 .

[25]  L. Hoffmann,et al.  Measuring soil organic carbon in croplands at regional scale using airborne imaging spectroscopy , 2010 .

[26]  Jacob Cohen.  Statistical Power Analysis for the Behavioral Sciences , 1969, The SAGE Encyclopedia of Research Design.

[27]  Dayton Dove,et al.  Spatial prediction of seabed sediment texture classes by cokriging from a legacy database of point observations , 2012 .

[28]  P. Kyriakidis,et al.  Error in a USGS 30-meter digital elevation model and its impact on terrain modeling , 2000 .

[29]  Sabine Chabrillat,et al.  Imaging Spectrometry for Soil Applications , 2008 .

[30]  Documenting GlobalSoilMap.net grid cells from legacy measured soil profile and global available covariates in Northern Tunisia , 2012 .

[31]  E. Ben-Dor,et al.  Estimation of Soil Properties by Orbital and Laboratory Reflectance Means and its Relation with Soil Classification , 2009 .

[32]  M. S. Moran,et al.  Opportunities and limitations for image-based remote sensing in precision crop management , 1997 .

[33]  B. Huwe,et al.  Uncertainty in the spatial prediction of soil texture: Comparison of regression tree and Random Forest models , 2012 .

[34]  Zhi-Wei Liu,et al.  Digital mapping of soil organic matter for rubber plantation at regional scale: An application of random forest plus residuals kriging approach , 2015 .

[35]  Alfred E. Hartemink,et al.  Digital Mapping of Soil Particle-Size Fractions for Nigeria Pedology , 2022 .

[36]  M. Wiesmeier,et al.  Digital mapping of soil organic matter stocks using Random Forest modeling in a semi-arid steppe ecosystem , 2011, Plant and Soil.

[37]  Michael E. Schaepman,et al.  Determining iron content in Mediterranean soils in partly vegetated areas, using spectral reflectance and imaging spectroscopy , 2007, Int. J. Appl. Earth Obs. Geoinformation.

[38]  R. V. Rossel,et al.  Soil organic carbon prediction by hyperspectral remote sensing and field vis-NIR spectroscopy: An Australian case study , 2008 .

[39]  R. D. Ramsey,et al.  Landsat Spectral Data for Digital Soil Mapping , 2008 .

[40]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[41]  Alex B. McBratney,et al.  Simultaneous estimation of several soil properties by ultra-violet, visible, and near-infrared reflectance spectroscopy , 2003 .

[42]  Budiman Minasny,et al.  Mapping continuous depth functions of soil carbon storage and available water capacity , 2009 .