Sensor data fusion for soil health assessment

Abstract Assessment of soil health involves determining how well a soil is performing its biological, chemical, and physical functions relative to its inherent potential. Due to high cost, labor requirements, and soil disturbance, traditional laboratory analyses cannot provide high resolution soil health data. Therefore, sensor-based approaches are important to facilitate cost-effective, site-specific management for soil health. In the Central Claypan Region of Missouri, USA, visible and near-infrared (VNIR) diffuse reflectance spectroscopy has successfully been used to estimate biological components of soil health as well as Soil Management Assessment Framework (SMAF) scores. In contrast, estimation models for important chemical and physical aspects of soil health have been less successful with VNIR spectroscopy. The primary objective of this study was to apply a sensor fusion approach to estimate soil health indicators and SMAF scores using VNIR spectroscopy in conjunction with soil apparent electrical conductivity (EC a ), and penetration resistance measured by cone penetrometer (i.e., cone index, CI). Soil samples were collected from two depths (0–5 and 5–15 cm) at 108 locations within a 10-ha research site encompassing different cropping systems and landscape positions. Soil health measurements and VNIR spectral data were obtained in the laboratory, while CI and EC a data were obtained in situ. Calibration models were developed with partial least squares (PLS) regression and model performance was evaluated using coefficient of determination (R 2 ) and root mean square error (RMSE). Models integrating EC a and CI with VNIR reflectance data improved estimates of the overall SMAF score (R 2  = 0.78, RMSE = 7.21%) relative to VNIR alone (R 2  = 0.69, RMSE = 8.41%), reducing RMSE by 14%. Improved models were also achieved for estimates of the individual chemical, biological, and physical soil health scores, demonstrating reductions in RMSE of 2.8, 5.4, and 10.0%, respectively. The results of this study illustrate the potential for rapid quantification of soil health by fusing VNIR sensor data with auxiliary data obtained from complementary sensors.

[1]  E. Rhine,et al.  Improving the Berthelot Reaction for Determining Ammonium in Soil Extracts and Water , 1998 .

[2]  J. W. Hummel,et al.  EVALUATION OF REFLECTANCE METHODS FOR SOIL ORGANIC MATTER SENSING , 1991 .

[3]  Cristine L. S. Morgan,et al.  Simulated in situ characterization of soil organic and inorganic carbon with visible near-infrared diffuse reflectance spectroscopy , 2009 .

[4]  Won Suk Lee,et al.  IMPROVING PHOSPHORUS SENSING BY ELIMINATING SOIL PARTICLE SIZE EFFECT IN SPECTRAL MEASUREMENT , 2005 .

[5]  J. D. Mcneill,et al.  Rapid, Accurate Mapping of Soil Salinity by Electromagnetic Ground Conductivity Meters , 2012 .

[6]  Douglas L. Karlen,et al.  The Soil Management Assessment Framework , 2004 .

[7]  J. W. Hummel,et al.  DESIGN AND VALIDATION OF AN ON-THE-GO SOIL STRENGTH PROFILE SENSOR , 2006 .

[8]  W. Dean Hively,et al.  Strategies for soil quality assessment using VNIR gyperspectral spectroscopy in a western Kenya Chronosequence , 2012 .

[9]  J. Doran,et al.  Measurement and use of pH and electrical conductivity for soil quality analysis. , 1996 .

[10]  Yufeng Ge,et al.  VisNIR spectra of dried ground soils predict properties of soils scanned moist and intact , 2014 .

[11]  Douglas L. Karlen,et al.  Protocol for indicator scoring in the soil management assessment framework (SMAF) , 2009, Renewable Agriculture and Food Systems.

[12]  P. Duchaufour,et al.  pH and lime requirement. , 1980 .

[13]  Xue-yu Hu.  Application of Visible/Near-Infrared Spectra in Modeling of Soil Total Phosphorus , 2013 .

[14]  C. Hurburgh,et al.  Near-Infrared Reflectance Spectroscopy–Principal Components Regression Analyses of Soil Properties , 2001 .

[15]  Kenneth A. Sudduth,et al.  Estimating a Soil Quality Index with VNIR Reflectance Spectroscopy , 2015 .

[16]  Peter Schulze Lammers,et al.  Sensor Fusion for Precision Agriculture , 2011 .

[17]  W. Dean Hively,et al.  Strategies for Soil Quality Assessment Using Visible and Near‐Infrared Reflectance Spectroscopy in a Western Kenya Chronosequence , 2012 .

[18]  Mark D. Tomer,et al.  A preliminary watershed scale soil quality assessment in north central Iowa, USA , 2008 .

[19]  M. E. Austin.  Land resource regions and major land resource areas of the United States (exclusive of Alaska and Hawaii) , 1965 .

[20]  Kenneth A. Sudduth,et al.  Soil property sensing for site-specific crop management , 1996 .

[21]  D. Corwin,et al.  Apparent soil electrical conductivity measurements in agriculture , 2005 .

[22]  Won Suk Lee,et al.  Comparison of Ultraviolet, Visible, and Near Infrared Sensing for Soil Phosphorus , 2007 .

[23]  Kristen S. Veum,et al.  Conservation effects on soil quality indicators in the Missouri Salt River Basin , 2015, Journal of Soil and Water Conservation.

[24]  Kenneth A. Sudduth,et al.  Soybean Root Distribution Related to Claypan Soil Properties and Apparent Soil Electrical Conductivity , 2007 .

[25]  F. Eivazi,et al.  Glucosidases and galactosidases in soils , 1988 .

[26]  E. Ozgoz,et al.  SOIL QUALITY AND SPATIAL VARIABILITY ASSESSMENT OF LAND USE EFFECTS IN A TYPIC HAPLUSTOLL , 2013 .

[27]  Ray R. Weil,et al.  Estimating active carbon for soil quality assessment: A simplified method for laboratory and field use , 2003 .

[28]  Kenneth A. Sudduth,et al.  Biological indicators of soil quality and soil organic matter characteristics in an agricultural management continuum , 2013, Biogeochemistry.

[29]  A. McBratney,et al.  Critical review of chemometric indicators commonly used for assessing the quality of the prediction of soil attributes by NIR spectroscopy , 2010 .

[30]  R. Lal,et al.  Soil Quality Indices for Evaluating Smallholder Agricultural Land Uses in Northern Ethiopia , 2015 .

[31]  Scott A. Staggenborg,et al.  Predicting soil pH and buffer pH in situ with a real-time sensor , 2007 .

[32]  Kenneth A. Sudduth,et al.  Modeling soil electrical conductivity–depth relationships with data from proximal and penetrating ECa sensors , 2013 .

[33]  R. H. Bray.  The Origin of Horizons in Claypan Soils , 1935 .

[34]  Kenneth A. Sudduth,et al.  Reflectance Spectroscopy Detects Management and Landscape Differences in Soil Carbon and Nitrogen , 2012 .

[35]  D. Karlen,et al.  A Soil Quality Assessment within the Iowa River South Fork Watershed , 2011 .

[36]  Keith D. Shepherd,et al.  Sensing landscape level change in soil fertility following deforestation and conversion in the highlands of Madagascar using Vis-NIR spectroscopy , 2006 .

[37]  M. Liebig,et al.  Evaluation of β-Glucosidase Activity as a Soil Quality Indicator for the Soil Management Assessment Framework , 2010 .

[38]  M. Mausbach,et al.  Soil Quality: A Concept, Definition, and Framework for Evaluation (A Guest Editorial) , 1997 .

[39]  D. Karlen,et al.  Bulk density as a soil quality indicator during conversion to no-tillage , 2004 .

[40]  D. Karlen,et al.  A Soil Management Assessment Framework (SMAF) Evaluation of Brazilian Sugarcane Expansion on Soil Quality , 2016 .

[41]  D. W. Nelson,et al.  Total Carbon, Organic Carbon, and Organic Matter , 1983, SSSA Book Series.

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

[43]  A. Franzluebbers.  Microbial activity in response to water-filled pore space of variably eroded southern Piedmont soils , 1999 .

[44]  D. Angers.  Changes in Soil Aggregation and Organic Carbon under Corn and Alfalfa , 1992 .

[45]  Newell R. Kitchen,et al.  Crop management effects on water infiltration for claypan soils , 2007 .

[46]  W. Graham,et al.  Evaluating Ecological Condition Using Soil Biogeochemical Parameters and Near Infrared Reflectance Spectra , 2006, Environmental monitoring and assessment.

[47]  J. Reeder,et al.  Potentially Mineralizable Nitrogen as an Indicator of Biologically Active Soil Nitrogen , 2015 .

[48]  Kenneth A. Sudduth,et al.  Fusion of Spectral and Electrochemical Sensor Data for Estimating Soil Macronutrients , 2016 .

[49]  Viacheslav I. Adamchuk,et al.  Review: Sensor systems for measuring soil compaction: Review and analysis , 2008 .

[50]  co-editors Jacob H. Dane and G. Clarke Topp,et al.  Methods of soil analysis. Part 4, Physical methods , 2016 .

[51]  Antoine Stevens,et al.  Assessment and monitoring of soil quality using near‐infrared reflectance spectroscopy (NIRS) , 2009 .

[52]  Kenneth A. Sudduth,et al.  Soil Phosphorus and Potassium Estimation by Reflectance Spectroscopy , 2016 .

[53]  M. Söderström,et al.  Exploring the predictability of soil texture and organic matter content with a commercial integrated soil profiling tool , 2015 .

[54]  G. Gee,et al.  Particle-size Analysis , 2018, SSSA Book Series.

[55]  D. Karlen,et al.  A Soil Quality and Metabolic Activity Assessment after Fifty‐Seven Years of Agricultural Management , 2013 .

[56]  Timothy B. Parkin,et al.  Quantitative Indicators of Soil Quality: A Minimum Data Set , 1996 .

[57]  R. Hoeft,et al.  Modern corn and soybean production , 2000 .

[58]  A. Mehlich.  Mehlich 3 soil test extractant: A modification of Mehlich 2 extractant , 1984 .