Estimation of different soil properties using fast and inexpensive color sensor data

Document Type : Original Article

Authors

1 Faculty of Desert Studies, Semnan University, Semnan, Iran

2 Department of Geosciences, Soil Science and Geomorphology, University of Tübingen, 72070 Tübingen, Germany.

Abstract

Soil color is one of the obvious characteristics of soil that usually has much to do with other soil properties. The NixTMPro color sensor can detect different amounts of soil color and allow you to check different soil properties. This sensor is less sensitive to the user's environmental and mental conditions than the conventional method of Mansell manual to determine the color of the soil, and it is effortless to use. Therefore, in this study, NixTMPro color sensor was used for fast and cheap estimation of different soil properties. For this purpose, 150 soil samples were collected from the semi-arid study area of Qazvin province. Values related to each soil characteristic were measured in the laboratory. Then, using this color sensor, the spectra of each color system were recorded for each soil sample. Two methods were used for this purpose. In the first method, by examining the correlation between the variables of the color system, an attempt was made to introduce a standard color system with the highest correlation coefficient with all soil properties. In the second method, all variables of different color systems were examined by the method of recursive feature elimination, which selects the features that have the highest accuracy by choosing the most important features. According to the results of both methods and to introduce a standard color system, in this study, CIEL*a*b color system was used to estimate soil properties. Because this system showed the highest degree of correlation with different soil properties. Then, using the random forest algorithm, the values related to each soil feature were estimated. Soil properties include sand, silt, clay, salinity, calcium carbonate (CaCO3), organic matter and soil bulk density. According to the results of random forest forecast, the amount of root mean square error (RMSE), mean error (ME), ratio of performance to interquartile distance (PRIQ), and the value of correlation coefficient (r) for each soil feature were determined. For sand, silt and clay particles, the amount of RMSE was 10.07, 6.28, 7.26%, and the correlation was 0.70, 0.49, and 0.77, respectively. PRIQ statistics for sand particles (2.09), clay (2.37), and calcium carbonate (1.78) are at an excellent and acceptable level. The RMSE values of organic matter, calcium carbonate and soil bulk density were 0.57, 0.02, 0.11%, and the correlation coefficient were 0.55, 0.58, and 0.70, respectively. Based on these results, it can be said that the spectra obtained from the NixTM Pro color sensor can be helpful in the rapid prediction of soil properties.

Keywords

Main Subjects

References

Aitkenhead M.J., Coull M., Towers W., Hudson G. and Black, H.I.J. 2013. Prediction of soil characteristics and colour using data from the National Soils Inventory of Scotland. Geoderma, 200: 99-107.
Anderson, S. 2005. Soils: Genesis and Geomorphology. Cambridge University Press, Cambridge, 13 817p.
Barthès B.G., Kouakoua E., Clairotte M., Lallemand J., Chapuis-Lardy L., Rabenarivo M. and Roussel, S. 2019. Performance comparison between a miniaturized and a conventional near infrared reflectance (NIR) spectrometer for characterizing soil carbon and nitrogen. Geoderma 338: 422-429.
Baumgardner M.F., Silva L.F., Biehl L.L., Stoner Baumgardner M.F., Silva L.F., Biehl L.L. and Stoner E.R. 1986. Reflectance properties of soils. Advances in agronomy, 38: 1-44.
Bellon-Maurel V., Fernandez-Ahumada E., Palagos B., Roger J.M. and McBratney A. 2010. Critical review of chemometric indicators commonly used for assessing the quality of the prediction of soil attributes by NIR spectroscopy. TrAC Trends in Analytical Chemistry, 29(9): 1073-1081.
Dos Santos J.C.B., Le Pera E., de Souza Júnior V.S., de Oliveira C.S., Juilleret J., Corrêa M.M. and de Azevedo A.C. 2018. Porosity and genesis of clay in gneiss saprolites: the relevance of saprolithology to whole regolith pedology. Geoderma, 319: 1-13.
Gee G.W. and Or D. 2002. 2.4 Particle‐size analysis. Methods of soil analysis: Part 4 physical methods, Soil Science Society of America Book Series, pp. 255-293
Hastie T., Tibshirani R., Friedman J.H. and Friedman, J.H. 2009. The elements of statistical learning: data mining inference, and prediction. New York, springer, 758p.
Ibáñez-Asensio S., Marques-Mateu A., Moreno-Ramón H. and Balasch, S. 2013. Statistical relationships between soil colour and soil attributes in semiarid areas. Biosystems Engineering, 116(2): 120-129.
Jha G., Sihi D., Dari B., Kaur H., Nocco M.A., Ulery A. and Lombard K. 2021. Rapid and inexpensive assessment of soil total iron using Nix Pro color sensor. Agricultural & Environmental Letters, 6(3): e20050.
Kirillova N.P., Sileva T.M., Ul’yanova T.Y., Smirnova I.E., Ul’yanova A.S. and Burova E.K. 2018. Color diagnostics of soil horizons (by the example of soils from Moscow region). Eurasian Soil Science, 51(11): 1348-1356.
Kirillova N.P., Vodyanitskii Y.N. and Sileva, T.M. 2015. Conversion of soil color parameters from the Munsell system to the CIE-L* a* b* system. Eurasian soil science 48(5): 468-475.
Kirillova N.P., Grauer-Gray J., Hartemink A.E., Sileova T.M., Artemyeva Z.S. and Burova E.K. 2018. New perspectives to use Munsell color charts with electronic devices. Computers and Electronics in Agriculture 155: 378-385.
Kuhn M. and Johnson K. 2013. Applied predictive modeling. New York, Springer, 600p.
Levin N., Ben‐Dor E. and Singer, A. 2005. A digital camera as a tool to measure colour indices and related properties of sandy soils in semi‐arid environments. International Journal of Remote Sensing, 26(24): 5475-5492.
Marqués-Mateu Á., Moreno-Ramón H., Balasch S. and Ibáñez-Asensio, S. 2018. Quantifying the uncertainty of soil colour measurements with Munsell charts using a modified attribute agreement analysis. Catena, 171: 44-53.
Mikhailova E.A., Stiglitz R.Y., Post C.J., Schlautman M.A., Sharp J.L. and Gerard P.D. 2017. Predicting soil organic carbon and total nitrogen in the Russian Chernozem from depth and wireless color sensor measurements. Eurasian Soil Science 50(12): 1414-1419.
Mikhailova E., Stiglitz R., Post C., Schlautman M.A., Sharp J. and Gerard, P. 2017. Developing Predictive Soil Organic C and N Models for Glaciated Soils Using Quantitative Color Sensor Measurements. ASA, CSSA and SSSA International Annual (2017), (Abs.)
Minasny B. and McBratney, A.B. 2008. Regression rules as a tool for predicting soil properties from infrared reflectance spectroscopy. Chemometrics and intelligent laboratory systems 94(1): 72-79.
Mouazen A.M., Karoui R., Deckers J., De Baerdemaeker J. and Ramon H. 2007. Potential of visible and near-infrared spectroscopy to derive colour groups utilising the Munsell soil colour charts. Biosystems Engineering, 97(2): 131-143.
Mukhopadhyay S. and Chakraborty S. 2020. Use of diffuse reflectance spectroscopy and Nix pro color sensor in combination for rapid prediction of soil organic carbon. Computers and Electronics in Agriculture, 176: 105630.
Nasrollahi M., Zolfaghari A.A. and Yazdani M.R. 2021. Spatial and temporal properties of reference evapotranspiration and its related climatic parameters in the main agricultural regions of Iran. Pure and Applied Geophysics, 178(10): 4159-4179.
Niazi N.K., Singh B. and Minasny B. 2015. Mid-infrared spectroscopy and partial least-squares regression to estimate soil arsenic at a highly variable arsenic-contaminated site. International Journal of Environmental Science and Technology, 12(6): 1965-1974.
Raeesi M., Zolfaghari A.A., Yazdani M.R., Gorji M. and Sabetizade M. 2019. Prediction of soil organic matter using an inexpensive colour sensor in arid and semiarid areas of Iran. Soil Research, 57(3):276-286.
Resende M., Curi N., Rezende S.D., Corrêa G.F. and Ker J.C. 2014. Pedologia base para distinção de ambientes. rev. ampl. Lavras: Editora UFLA
Rezende É.A., 2021. Estudo da influência da Zona de Cisalhamento de Três Corações na ocorrência de voçorocamentos. Revista de Geografia-PPGEO-UFJF, 11(1): 120-135.
Sabetizade M., Gorji M., Roudier P., Zolfaghari A.A. and Keshavarzi, A. 2021. Combination of MIR spectroscopy and environmental covariates to predict soil organic carbon in a semi-arid region. Catena, 196: 104844.
Staff S.S. 2014. Keys to soil taxonomy. 13th Ed. United States Department of Agriculture: Washington, DC, USA, 436p.
Stiglitz R., Mikhailova E., Post C., Schlautman M. and Sharp J. 2016. Evaluation of an inexpensive sensor to measure soil color. Computers and Electronics in Agriculture, 121: 141-148.
Stiglitz R., Mikhailova E., Post C., Schlautman M. and Sharp J. 2017. Using an inexpensive color sensor for rapid assessment of soil organic carbon. Geoderma, 286: 98-103.
Stiglitz R.Y., Mikhailova E.A., Sharp J.L., Post C.J., Schlautman M.A., Gerard P.D. and Cope M.P. 2018. Predicting soil organic carbon and total nitrogen at the farm scale using quantitative color sensor measurements. Agronomy, 8(10): 212.
Swetha R.K. and Chakraborty, S. 2021. Combination of soil texture with Nix color sensor can improve soil organic carbon prediction. Geoderma, 382: 114775.
Thompson J.A., Pollio A.R. and Turk, P.J. 2013. Comparison of Munsell soil color charts and the GLOBE soil color book. Soil Science Society of America Journal, 77(6): 2089-2093.
Walkley A. and Black I.A. 1934. An examination of the Degtjareff method for determining soil organic matter, and a proposed modification of the chromic acid titration method. Soil science, 37(1): 29-38.
Wilding L.P. 1985. Spatial variability: its documentation, accomodation and implication to soil surveys. In Soil spatial variability, Las Vegas NV, 30 November-1 December, 1984: 166-194
Willmott C.J. and Matsuura K. 2005. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate research, 30(1): 79-82.
Applied Soil Research
Volume 11, Issue 2 - Serial Number 2
September 2023
Pages 28-45

Files

History

  • Receive Date: 21 November 2021
  • Revise Date: 28 June 2022
  • Accept Date: 11 July 2022

Share

How to cite

Statistics