Information potential of the spectral response of Polish soils, in the NIR range, in the light of lucas database analyses. Soil properties vector model

• Autorzy: Gruszczyński Stanisław

Identyfikatory

DOI

10.14597/INFRAECO.2019.2.1.008

• Języki publikacji: EN

Abstrakty

EN

The paper presents simple machine learning models used for prediction of some soil properties based on the NIR spectral response. Data on mineral soils from Poland were taken from the LUCAS dataset. Machine learning model was used that is included in the category of so-called multilayer perceptron (MLP). The MLP model input was a vector of combined, transformed inputs made by means of the PLSR (partial last squares regression) algorithm (45 inputs in total). The output was a vector of properties, reduced to 9 components due to poor modelling effects of the P and K components. The estimation errors for texture, soil organic carbon (SOC) and carbonates can be considered acceptable from the point of view of their suitability in the development of cartographic documentation. It can be supposed that further regionalization will improve these results.

Słowa kluczowe

EN

near infrared spectroscopy; soil properties prediction; machine learning model

• Wydawca: Stowarzyszenie Infrastruktura i Ekologia Terenów Wiejskich
• Czasopismo: Infrastruktura i Ekologia Terenów Wiejskich
• Rocznik: 2019
• Tom: nr II/1
• Strony: 95--104
• Opis fizyczny: Bibliogr.18 poz., tab., wykr.

Twórcy

autor

Gruszczyński Stanisław

• AGH University of Science and Technology Faculty of Mining Surveying and Environmental Engineering, al. Mickiewicza 30 PL 30-059 Krakow Tel. [phone]

Bibliografia

• Conforti, M., Matteucci, G., Buttafuoco, G. (2018). ‘Using laboratory Vis-NIR spectroscopy for monitoring some forest soil properties’, J Soils Sediments, 18(3): 1009-1019.
• Fuentes, M., Hidalgo, C., González-Martín, I., Hernández-Hierro, JM., Govaerts, B., Sayre, KD., Etchevers, J. (2012). NIR Spectroscopy: An Alternative for Soil Analysis. Communications in Soil Science and Plant Analysis, 43(1-2): 346-356, DOI: 10.1080/00103624.2012.641471.
• Kania M., Gruba P., (2016): Estimation of selected properties of forest soils using nearinfrared spectroscopy (NIR), Soil Science Annual 67 (1/2016): 32-36.
• Kokaly, R.F., Clark, R.N., Swayze, G.A., Livo, K.E., Hoefen, T.M., Pearson, N.C., Wise, R.A., Benzel, W.M., Lowers, H.A., Driscoll, R.L., and Klein, A.J., 2017, USGS Spectral Library Version 7: U.S. Geological Survey Data Series 1035, 61 p., https://doi. org/10.3133/ds1035.
• Liu, L.; Ji, M.; Buchroithner, M. Combining Partial Least Squares and the GradientBoosting Method for Soil Property Retrieval Using Visible Near-Infrared Shortwave Infrared Spectra. Remote Sens. 2017, 9, 1299.
• Liu L, Ji M, Buchroithner M. Transfer Learning for Soil Spectroscopy Based on Convolutional Neural Networks and Its Application in Soil Clay Content Mapping Using Hyperspectral Imagery. Sensors (Basel). 2018;18(9):3169.
• McBratney A. B., Mendonça Santos M. L., Minasny B., 2003. ‘On digital soil mapping’, Geoderma, vol. 117, Issues 1-2, 2003, pp.3-52, ISSN 0016-7061.
• McBratney A. B., Minasny B., Cattle S. R., Vervoort W., 2002. ‘From pedotransfer functions to soil inference systems’, Geoderma, vol. 109, Issues 1-2, 2002, pp.41-73, ISSN 0016-7061.
• Mohamed E. S., Saleh A. M., Belal A. B., Abd_Allah Gad, 2018. ‘Application of nearinfrared reflectance for quantitative assessment of soil properties’, The Egyptian Journal of Remote Sensing and Space Science, vol. 21, Issue 1, pp.1-14, ISSN 1110-9823, https://doi.org/10.1016/j.ejrs.2017.02.001. (http://www.sciencedirect.com/science/article/pii/ S1110982317300327).
• Orgiazzi A., Ballabio C., Panagos P., Jones A., Fernández-Ugalde O., 2017. ‘LUCAS Soil, the largest expandable soil dataset for Europe: a review’, European Journal of Soil Science, 69, pp.140-153.
• Shenk, J.S., Westerhaus, M.O., Berzaghi, P. J., 1997. Investigation of a LOCAL calibration procedure for near infra-red instruments. J. Near Infrared Spectrosc. 5, 223- 232.
• Shi, Z., Ji, W., Viscarra Rossel, R. A., Chen, S., Zhou, Y., 2015. ‘Prediction of soil organic matter using a spatially constrained local partial least squares regression and the Chinese vis-NIR spectral library’. Eur J Soil Sci, 66: 679-687. DOI:10.1111/ejss.12272.
• Stenberg, B., Viscara Rossel, RA., Mounem Mouazen, A., Wetterlind, J. (2010). Visible and Near Infrared Spectroscopy in Soil Science. Advances in Agronomy (Sparks D.L. Editor) 107: 163-215. DOI: 10.1016/S0065-2113(10)07005-7.
• Stevens, A., Nocita, M., Toth, G., Montanarella, L., Van Wesemael, B. (2013). Prediction of Soil Organic Carbon at the European Scale by Visible and Near InfraRed Reflectance Spectroscopy. PLoS ONE 8(6): e66409. DOI:10.1371/journal.pone.0066409.
• Tóth, G., Jones, A., Montanarella, L. (2013). LUCAS Topsoil Survey. Methodology, data and results. JRC Technical Reports. Luxembourg. Publications Office of the European Union, EUR26102 - Scientific and Technical Research series. DOI: 10.2788/97922.
• Veres, M., Lacey, G., Graham, WT. (2015). Deep Learning Architectures for Soil Property Prediction’. Proceedings - 2015 12th Conference on Computer and Robot Vision, CRV 2015: 8-15. DOI: 10.1109/CRV.2015.15.
• Wetterlind, J., Stenberg, B.,Viscarra Rossel, RA. (2013). Soil analysis using visible and near infrared spectroscopy. [In:] Plant Mineral Nutrients:Methods and Protocols. (Maathuis F. J. M. editor), New York: Humana Press, Springer, pp 95-107. Published in serie: Methods in molecular biology, nr. 953.
• Zhang, Y., Min-Zan, L., Li-Hua Z., Yi Z., Xiaoshuai P. (2016). Soil nitrogen content forecasting based on real-time NIR spectroscopy. Computers and Electronics in Agriculture. 124: 29-36. DOI: 10.1016/j.compag.2016.03.016.

Uwagi

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).