Neural network analysis of interdependences of the top-soil parameters

S. I. Bartsev ; A. A. Pochekutov ; I. V. Priputina

Matematičeskaâ biologiâ i bioinformatika, Tome 7 (2012) no. 1, pp. 19-29.

Résumé

To test a possibility of reduction of soil parameters number used for description of total amount of soil organic matter, a neural network analysis of regional soil databases was carried out. It was shown, that two to three soil parameters are sufficient for the prediction of amount of soil organic matter. Herewith, to implement this prediction, a neural network can consist of less then four neurons. The obtained results indicate that it is possible to represent explicated dependencies in terms of relatively simple mathematical formulae. In turn, this gives promise to expect, if not a simplicity of a possible mathematical model of soil forming, a simple form of a dependence of steady states of the model on soil parameters considered in this work.

Bibliographie

[1] Smagin A.V., Sadovnikova N.B., Smagina M.V., Glagolev M.V., Shevchenko E.M., Khaidapova Dyu.D., Guber A.K., Modelirovanie dinamiki organicheskogo veschestva pochv, Izd-vo MGU, M., 2001, 120 pp.

[2] Titlyanova A.A., Tesarzhova M., Rezhimy biologicheskogo krugovorota, Nauka, Novosibirsk, 1991, 150 pp.

[3] Olson J.S., “Energy storage and balance of producers and decomposers in ecological systems”, Ecology, 44 (1963), 322–331 | DOI

[4] Lenton T.M., “Land and ocean carbon cycle feedback effects on global warming in a simple Earth system model”, Tellus, 52 (2000), 1159–1188 | DOI

[5] Chertov O.G., Komarov A.S., Nadporozhskaya M.A., “Modeli dinamiki organicheskogo veschestva pochv”, Modelirovanie dinamiki organicheskogo veschestva v lesnykh ekosistemakh, eds. Kudeyarov V.N., Nauka, M., 2007, 19–33

[6] Thuries L., Pansu M., Feller C. Herrmann P., Remy J.-C., “Kinetics of added organic matter decomposition in a Mediterranean soil”, Soil Biology Biochemistry, 33 (2001), 997–1010 | DOI

[7] Chertov O.G., Komarov A.S., Nadporozhskaya M.A., “ROMUL – model dinamiki organicheskogo veschestva v lesnykh i torfyanykh pochvakh i ee programmnaya realizatsiya”, Modelirovanie dinamiki organicheskogo veschestva v lesnykh ekosistemakh, ed. Kudeyarov V.N., Nauka, M., 2007, 62–70

[8] Ryzhova I.M., “Analiz chuvstvitelnosti sistemy pochva–rastitelnost k izmeneniyam parametrov krugovorota ugleroda na osnove matematicheskoi modeli”, Pochvovedenie, 1993, no. 10, 52–56

[9] Ryzhova I.M., “Analiz ustoichivosti pochv na osnove teorii nelineinykh dinamicheskikh sistem”, Pochvovedenie, 2003, no. 5, 583–590

[10] Smagin A.V., “Rezhimy funktsionirovaniya dinamicheskikh biokosnykh sistem”, Pochvovedenie, 1999, no. 12, 1433–1447

[11] Lin H., “Three principles of soil change and pedogenesis in time and space”, Soil Science Society of America Journal, 75:6 (2011) | DOI

[12] Wosten, J.H.M., Pachepsky Ya.A., Rawls W.J., “Pedotransfer functions: bridging the gap between available basic data and missing soil hydraulic characteristics”, Journal of Hydrology, 251 (2001), 123–150 | DOI

[13] Shein E.V., Arkhangelskaya T.A., “Pedotransfernye funktsii: sostoyanie, problemy, perspektivy”, Pochvovedenie, 2006, no. 10, 1205–1217 | Zbl

[14] Minasny B., “Predicting soil properties”, Jurnal Ilmu Tanah dan Lingkungan, 7:1 (2007), 54–67

[15] Minasny B., McBratney A.B., Bristow K.L., “Comparison of different approaches to the development of pedotransfer functions for water–retention curves”, Geoderma, 93 (1999), 225–253 | DOI

[16] Merdun Kh., “Alternativnye metody postroeniya pedotransfernykh funktsii dlya gidrofizicheskikh pochvennykh kharakteristik”, Pochvovedenie, 2010, no. 1, 71–82

[17] Sarmadain F., Taghizadeh Mehrjardi R., “Modeling of some soil properties using artifical neural network and multiple regression in Gorgan Province, North of Iran”, Global Journal of Environmental Research, 2:1 (2008), 30–35

[18] Keshavarzi A., Sarmadian F., “Comparison of artifical neural network and multivariate regression methods in predictiong soil cation exchange capacity”, International Journal of Environmental and Earth Sciences, 1:1 (2010), 25–30

[19] Parvizi Y., Gorji M, Mahdian M.H., Omid M., “Sensitivity analysis for determining priority of factors controlling SOC content in semiarid conditions of West of Iran”, World Academy of Science, Engineering and Technology, 71 (2010), 927–931

[20] Parvizi Y., Gorji M, Omid M. Mahdian MH, Amini M., “Determination of soil organic carbon variability of rainfed crop land in semi-arid region (Neural Network Approach)”, Modern Applied Science, 4:7 (2010), 25–33

[21] Ayoubi S., Karchegani P.M., “Determination the factors explaining variability of phisical soil organic carbon fractions using artifical neural networks”, International Journal of soil science URL: (data obrascheniya: 21.11.2011) http://scialert.net/qredirect.php?doi=ijss.0000.33577.33577&linkid=pdf

[22] Mouazen A.M., Kuang B., De Baerdemaeker, Ramon H., “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”, Geoderma, 158 (2010), 23–31 | DOI

[23] Ingleby H.R., Crowe T.G., “Neural network models for predicting organic matter content in Saskatchewan soils”, Canadian biosystems engineering, 43 (2001), 7.1–7.5

[24] Posch M., Reinds G.J., Slootweg J., “The European background database”, Modelling and mapping critical thresholds in Europe, RIVM Report 259101013/2003, CCE, Bilthoven. The Netherlands, 2003, 37–44; URL: (дата обращения: 21.11.2011) http://www.rivm.nl/cce

[25] Mirkes E.M., M63 Neiroinformatika, Uchebnoe posobie dlya studentov, IPTs KGTU, Krasnoyarsk, 2002, 347 pp.; URL: (дата обращения: 21.11.2011) http://www.softcraft.ru/neuro/ni/p00.shtml

[26] Rummelhart D.E., Hinton G.E., Williams R.J., “Learning representations by back-propagating errors”, Nature, 323 (1986), 533–536 | DOI

[27] Bartsev S. I., Okhonin V. A., Adaptivnye seti obrabotki informatsii, preprint No 59B Instituta fiziki SO AN SSSR, Institut fiziki SO AN SSSR, Krasnoyarsk, 1986, 20 pp.

[28] Okhonin V. A., Variatsionnyi printsip v teorii adaptivnykh setei, preprint No 61B Instituta fiziki SO AN SSSR, Institut fiziki SO AN SSSR, Krasnoyarsk, 1987, 18 pp.

[29] Bartsev S.I., Gilev S.E., Okhonin V.A., “Printsip dvoistvennosti v organizatsii adaptivnykh setei obrabotki informatsii”, Dinamika khimicheskikh i biologicheskikh sistem, Nauka, Novosibirsk, 1989, 6–55

[30] Gorban A.N., Obuchenie neironnykh setei, izd. SSSR–SShA SP «ParaGraph», M., 1990, 160 pp.

[31] Simonov K.V., Marchuk An.G., Okhonin V.A., Shchemel A.L., “Using of nonlinear regression with fuzzy input data for analysis of seismicity”, Bulletin of the Novosibirsk Computing Center, series: Mathematical Modeling in Geophysics, no. 7, NCC Publisher, Novosibirsk, 2002, 69–76

[32] Gorban A.N., “Obobschënnaya approksimatsionnaya teorema i vychislitelnye vozmozhnosti neironnykh setei”, Sibirskii zhurnal vychislitelnoi matematiki, 1 (1998), 11–24