Predicting Spatial Variations in Soil Nutrients with Hyperspectral Remote Sensing at Regional Scale

Rapid acquisition of the spatial distribution of soil nutrients holds great implications for farmland soil productivity safety, food security and agricultural management. To this end, we collected 1297 soil samples and measured the content of soil total nitrogen (TN), soil available phosphorus (AP) and soil available potassium (AK) in Zengcheng, north of the Pearl River Delta, China. Hyperspectral remote sensing images (115 bands) of the Chinese Environmental 1A satellite were used as auxiliary variables and dimensionality reduction was performed using Pearson correlation analysis and principal component analysis. The TN, AP and AK of soil were predicted in the study area based on auxiliary variables after dimensionality reduction, along with stepwise linear regression (SLR), support vector machine (SVM), random forest (RF) and back-propagation neural network (BPNN) models; 324 independent points were used to verify the predictive performance. The BPNN model, which demonstrated the best predictive accuracy among all methods, combined ordinary kriging (OK) with mapping the spatial variations of soil nutrients. Results show that the BPNN model with double hidden layers had better predictive accuracy for soil TN (root mean square error (RMSE) = 0.409 mg kg−1, R2 = 44.24%), soil AP (RMSE = 40.808 mg kg−1, R2 = 42.91%) and soil AK (RMSE = 67.464 mg kg−1, R2 = 48.53%) compared with the SLR, SVM and RF models. The back propagation neural network-ordinary kriging (BPNNOK) model showed the best predictive results of soil TN (RMSE = 0.292 mg kg−1, R2 = 68.51%), soil AP (RMSE = 29.62 mg kg−1, R2 = 69.30%) and soil AK (RMSE = 49.67 mg kg−1 and R2 = 70.55%), indicating the best fitting ability between hyperspectral remote sensing bands and soil nutrients. According to the spatial mapping results of the BPNNOK model, concentrations of soil TN (north-central), soil AP (central and southwest) and soil AK (central and southeast) were respectively higher in the study area. The most important bands (464–517 nm) for soil TN (b10, b14, b20 and b21), soil AP (b3, b19 and b22) and soil AK (b4, b11, b12 and b25) exhibited the best response and sensitivity according to the SLR, SVM, RF and BPNN models. It was concluded that the application of hyperspectral images (visible-near-infrared data) with BPNNOK model was found to be an efficient method for mapping and monitoring soil nutrients at the regional scale.

[1]  A. Walkley,et al.  AN EXAMINATION OF THE DEGTJAREFF METHOD FOR DETERMINING SOIL ORGANIC MATTER, AND A PROPOSED MODIFICATION OF THE CHROMIC ACID TITRATION METHOD , 1934 .

[2]  Gerard B. M. Heuvelink,et al.  About regression-kriging: From equations to case studies , 2007, Comput. Geosci..

[3]  William Stafford Noble,et al.  Support vector machine , 2013 .

[4]  A. Bouwman,et al.  Human alteration of the global nitrogen and phosphorus soil balances for the period 1970–2050 , 2009 .

[5]  P. Miller,et al.  Validation requirements for diffuse reflectance soil characterization models with a case study of VNIR soil C prediction in Montana , 2005 .

[6]  Christophe David,et al.  Nutrient recycling in organic farming is related to diversity in farm types at the local level , 2015 .

[7]  Lin Ma,et al.  Phosphorus in China's Intensive Vegetable Production Systems: Overfertilization, Soil Enrichment, and Environmental Implications. , 2013, Journal of environmental quality.

[8]  Xiang Yu,et al.  Evaluation of MLSR and PLSR for estimating soil element contents using visible/near-infrared spectroscopy in apple orchards on the Jiaodong peninsula , 2016 .

[9]  Nai-Yang Deng,et al.  Support Vector Machines: Optimization Based Theory, Algorithms, and Extensions , 2012 .

[10]  A. McBratney,et al.  Further results on prediction of soil properties from terrain attributes: heterotopic cokriging and regression-kriging , 1995 .

[11]  Meiling Liu,et al.  Integrating spectral indices with environmental parameters for estimating heavy metal concentrations in rice using a dynamic fuzzy neural-network model , 2011, Comput. Geosci..

[12]  L. Wilding,et al.  Spatial variability: its documentation, accommodation and implication to soil surveys , 1985 .

[13]  Hossein Asadi,et al.  Spatial variability of soil organic matter using remote sensing data , 2016 .

[14]  Çagdas Hakan Aladag,et al.  Estimation of pressuremeter modulus and limit pressure of clayey soils by various artificial neural network models , 2012, Neural Computing and Applications.

[15]  Ian J. Yule,et al.  Mapping of macro and micro nutrients of mixed pastures using airborne AisaFENIX hyperspectral imagery , 2016 .

[16]  Martial Bernoux,et al.  Mapping organic carbon stocks in eucalyptus plantations of the central highlands of Madagascar: A multiple regression approach , 2011 .

[17]  Austin M. Jensen,et al.  Assessment of Surface Soil Moisture Using High-Resolution Multi-Spectral Imagery and Artificial Neural Networks , 2015, Remote. Sens..

[18]  Philippe Lagacherie,et al.  Continuum removal versus PLSR method for clay and calcium carbonate content estimation from laboratory and airborne hyperspectral measurements , 2008 .

[19]  Alex B. McBratney,et al.  A comparison of prediction methods for the creation of field-extent soil property maps , 2001 .

[20]  Gabor Kereszturi,et al.  Integrating Airborne Hyperspectral, Topographic, and Soil Data for Estimating Pasture Quality Using Recursive Feature Elimination with Random Forest Regression , 2018, Remote. Sens..

[21]  N. Holden,et al.  Determination of Soil Organic Matter and Carbon Fractions in Forest Top Soils using Spectral Data Acquired from Visible–Near Infrared Hyperspectral Images , 2012 .

[22]  Shi Zhou,et al.  In Situ Measurement of Some Soil Properties in Paddy Soil Using Visible and Near-Infrared Spectroscopy , 2014, PloS one.

[23]  Qing-Kai Sheng,et al.  Prediction of soil organic matter using artificial neural network and topographic indicators in hilly areas , 2013, Nutrient Cycling in Agroecosystems.

[24]  Liangpei Zhang,et al.  Adaptive Spatial Regularization Sparse Unmixing Strategy Based on Joint MAP for Hyperspectral Remote Sensing Imagery , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[25]  Jiabao Zhang,et al.  Determination of soil properties using Fourier transform mid-infrared photoacoustic spectroscopy , 2009 .

[26]  H. Ramon,et al.  Comparison among principal component, partial least squares and back propagation neural network analyses for accuracy of measurement of selected soil properties with visible and near infrared spectroscopy , 2010 .

[27]  M. Cho,et al.  Non-linear partial least square regression increases the estimation accuracy of grass nitrogen and phosphorus using in situ hyperspectral and environmental data , 2013 .

[28]  Tarin Paz-Kagan,et al.  Evaluating calibration methods for predicting soil available nutrients using hyperspectral VNIR data , 2018 .

[29]  Michael Vohland,et al.  Use of A Portable Camera for Proximal Soil Sensing with Hyperspectral Image Data , 2015, Remote. Sens..

[30]  M. Zasada,et al.  Applying geostatistics for investigations of forest ecosystems using remote sensing imagery , 2005 .

[31]  Lutgarde M. C. Buydens,et al.  Possibilities of visible–near-infrared spectroscopy for the assessment of soil contamination in river floodplains , 2001 .

[32]  Gabriel S. Amable,et al.  A Comparative Assessment of the Influences of Human Impacts on Soil Cd Concentrations Based on Stepwise Linear Regression, Classification and Regression Tree, and Random Forest Models , 2016, PloS one.

[33]  J. Mohammadi,et al.  Spatial Estimation of Saturated Hydraulic Conductivity from Terrain Attributes Using Regression, Kriging, and Artificial Neural Networks , 2011 .

[34]  Balwant Singh,et al.  Ultra-violet, visible, near-infrared, and mid-infrared diffuse reflectance spectroscopic techniques to predict several soil properties , 2005 .

[35]  I. Burud,et al.  Qualitative and quantitative mapping of biochar in a soil profile using hyperspectral imaging , 2016 .

[36]  A-Xing Zhu,et al.  Construction of Membership Functions for Soil Mapping using the Partial Dependence of Soil on Environmental Covariates Calculated by Random Forest , 2017 .

[37]  R. V. Rossel,et al.  Visible, near infrared, mid infrared or combined diffuse reflectance spectroscopy for simultaneous assessment of various soil properties , 2006 .

[38]  G. Tóth,et al.  Maps of heavy metals in the soils of the European Union and proposed priority areas for detailed assessment. , 2016, The Science of the total environment.

[39]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[40]  Marko Wagner,et al.  Geostatistics For Environmental Scientists , 2016 .

[41]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[42]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[43]  Samia Boukir,et al.  Relevance of airborne lidar and multispectral image data for urban scene classification using Random Forests , 2011 .

[44]  Erik Karltun,et al.  Soil nutrient build-up, input interaction effects and plot level N and P balances under long-term addition of compost and NP fertilizer , 2016 .

[45]  A. Konopka,et al.  FIELD-SCALE VARIABILITY OF SOIL PROPERTIES IN CENTRAL IOWA SOILS , 1994 .

[46]  Bing Li,et al.  Spatial prediction of soil nutrient in a hilly area using artificial neural network model combined with kriging , 2016 .

[47]  Yoel Shkolnisky,et al.  Change detection of soils under small-scale laboratory conditions using imaging spectroscopy sensors , 2014 .

[48]  Zhijing Yang,et al.  Linear vs. Nonlinear Extreme Learning Machine for Spectral-Spatial Classification of Hyperspectral Images , 2017, Sensors.

[49]  M. McKee,et al.  SOIL MOISTURE PREDICTION USING SUPPORT VECTOR MACHINES 1 , 2006 .

[50]  R. Pullanagari,et al.  Quantification of dead vegetation fraction in mixed pastures using AisaFENIX imaging spectroscopy data , 2017, Int. J. Appl. Earth Obs. Geoinformation.

[51]  Mohamad Sakizadeh,et al.  Support vector machine and artificial neural network to model soil pollution: a case study in Semnan Province, Iran , 2017, Neural Computing and Applications.

[52]  Qing Li,et al.  Hyperspectral Imaging Analysis for the Classification of Soil Types and the Determination of Soil Total Nitrogen , 2017, Sensors.

[53]  Wei Wu,et al.  A comparison of support vector machines, artificial neural network and classification tree for identifying soil texture classes in southwest China , 2018, Comput. Electron. Agric..

[54]  Bernd Huwe,et al.  Spatial soil nutrients prediction using three supervised learning methods for assessment of land potentials in complex terrain , 2017 .

[55]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[56]  Jianli Ding,et al.  Estimation of soil salt content (SSC) in the Ebinur Lake Wetland National Nature Reserve (ELWNNR), Northwest China, based on a Bootstrap-BP neural network model and optimal spectral indices. , 2018, The Science of the total environment.

[57]  E. Cowling,et al.  The Nitrogen Cascade , 2003 .

[58]  Chenghu Zhou,et al.  Differentiation of soil conditions over low relief areas using feedback dynamic patterns. , 2010 .