- PII
- 10.31857/S0869780923050028-1
- DOI
- 10.31857/S0869780923050028
- Publication type
- Status
- Published
- Authors
- Volume/ Edition
- Volume / Issue number 5
- Pages
- 88-96
- Abstract
- The selection of a method for dividing the raw data into training and test subsets in models based on artificial neural networks (ANN) is an insufficiently studied problem of continuous space-time field interpolation. In particular, selecting the best training subset for modeling the spatial distribution of elements in the topsoil is not a trivial task, since the sampling points are not equivalent. They contain a different amount of “information” in point of each specific model, therefore, when modeling, it is advisable to use most of the points containing information which is “useful” for this model. Incorrect data division may lead to inaccurate and highly variable model characteristics, high variance and bias in the generated results. The raw data included contents of chromium (Cr) and manganese (Mn) in the topsoil in residential areas of Noyabrsk (a city in Russian subarctic zone). A three-stage algorithm for extracting raw data with a division into training and test subsets has been developed for modeling the spatial distribution of heavy metals. According to the algorithm, the initial data set was randomly divided into training and test subsets. For each training subset, an ANN based on multilayer perceptron (MLP) was built and trained. MLP was used to model the spatial distribution of heavy metals in the upper soil layer, which took into account spatial heterogeneity and learning rules. The MLP structure was chosen by minimizing the root mean square error (RMSE). The networks with the lowest RMSE were selected, and the number of hits into the training subset of each point in space was calculated. By the number of hits in the training subset, all points were divided into three classes: “useful”, “ordinary” and “useless”. Taking this information into account, at the stage of the raw data division it possible to increase the accuracy of the predictive model.
- Keywords
- <i>моделирование</i> <i>искусственные нейронные сети</i> <i>обучающее подмножество</i> <i>почва</i> <i>тяжелые металлы</i>
- Date of publication
- 19.09.2025
- Year of publication
- 2025
- Number of purchasers
- 0
- Views
- 13
References
- 1. Буевич А.Г., Субботина И.Е., Шичкин А.В. и др. Оценка пространственного распределения хрома в субарктическом Ноябрьске с использованием кокригинга, генерализованной регрессионной нейронной сети, многослойного персептрона и гибридной техники // Геоэкология. 2019. № 2. С. 77–86.
- 2. Буторова А.С., Сергеев А.П., Шичкин А.В. и др. Метод встречного прогнозирования пространственного ряда на примере содержания пыли в снеговом покрове // Геоинформатика. 2022. № 1. С. 32–39.
- 3. Войткевич Г.В., Мирошников А.Е., Поваренных А.С., Прохоров В.Г. Краткий справочник по геохимии. М.: Недра, 1977. 184 с.
- 4. Добровольский Г.В., Урусевская И.С. География почв. 2-е изд., перераб. и доп. М.: Изд-во МГУ, Изд-во “КолосС”, 2004. 460 с.
- 5. Сает Ю.Е. Геохимия окружающей среды [Кол. авт.: Ю.Е. Сает, Б.А. Ревич, Е.П. Янин и др.]. М.: Недра, 1990. С. 84–108.
- 6. AMAP. Snow, Water, Ice and Permafrost. Summary for Policy-makers / Arctic Monitoring and Assessment Programme (AMAP). Oslo, Norway. 2017. 20 p.
- 7. Baglaeva E.M., Sergeev A.P., Shichkin A.V., Buevich A.G. The Effect of Splitting of Raw Data into Training and Test Subsets on the Accuracy of Predicting Spatial Distribution by a Multilayer Perceptron // Mathematical Geosciences. 2020. V. 52. P. 111–121.
- 8. Dai F., Zhoua O., Lva Z., Wang X., Liu G. Spatial prediction of soil organic matter content integrating artificial neural network and ordinary kriging in Tibetan Plateau // Ecological Indicators. 2014. V. 45. P. 184–194.
- 9. Demyanov V., Gloaguen E., Kanevski M. A special issue on data science for geosciences // Mathematical Geosciences. 2020. V. 52. P. 1–3.
- 10. Fernandez J.M., Mayerle R. Sample selection via angular distance in the space of the arguments of an artificial neural network // Computers and Geosciences. 2018. V. 114. P. 98–106.
- 11. Frank R., Ishida K., Suda P. Metals in agricultural soils of Ontario // Canadian Journal of Soil Science. 1976. V. 56. P. 181–196.
- 12. Goovaerts P. Geostatistics in soil science: State of the art and perspectives // Geoderma. 1999. V. 89. P. 1–45.
- 13. Kabata-Pendias A. Trace elements in soils and plants / Taylor and Francis Group CRC Press. 2011. P. 201–260.
- 14. Liodakis S., Kyriakidis P., Gaganis P. Conditional Latin Hypercube Simulation of (Log)Gaussian Random Fields // Mathematical Geosciences. 2018. V. 50. P. 127–146.
- 15. Malof J.M., Reichman D., Collins L.M. How do we choose the best model? The impact of cross-validation design on model evaluation for buried threat detection in ground penetrating radar / Материалы конференции Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXIII. 2018. V. 10628. 106280C.
- 16. Nath A., Subbiah K. The role of pertinently diversified and balanced training as well as testing data sets in achieving the true performance of classifiers in predicting the antifreeze proteins // Neurocomputing. 2018. V. 272. P. 294–305.
- 17. Sakizadeh M., Mirzaei R., Ghorbani H. Support vector machine and artificial neural network to model soil pollution: a case study in Semnan Province, Iran // Neural Computing & Applications. 2017. V. 28. P. 3229–3238.
- 18. Sergeev A.P., Buevich A.G., Baglaeva E.M., Shichkin A.V. Combining spatial autocorrelation with machine learning increases prediction accuracy of soil heavy metals // Catena. 2019. V. 174. P. 425–435.
- 19. Shacklette H.T., Boerngen J.G. Element concentrations in soils and other surficial materials of the conterminous United States / U.S. Geological Survey professional paper // United states government printing office, Washington. 1984. 105 p.
- 20. Shaker R.R., Ehlinger T.J. Exploring non-linear relationships between landscape and aquatic ecological condition in southern Wisconsin: A GWR and ANN approach // International Journal of Applied Geospatial Research. 2014. V. 5(4). P. 1–20.
- 21. Sun C., Liu J., Wang Y., Sun L., Yu H. Multivariate and geostatistical analyses of the spatial distribution and sources of heavy metals in agricultural soil in Dehui, Northeast China // Chemosphere. 2013. V. 92 (5). P. 517–523.
- 22. Timofeeva Y.O., Kosheleva Y., Semal V., Burdukovskii M. Origin, baseline contents, and vertical distribution of selected trace lithophile elements in soils from nature reserves, Russian Far East // Journal of Soils and Sediments. 2018. V. 18 (3). P. 968–982.
- 23. Wieland R., Mirschel W., Zbell B., et al. A new library to combine artificial neural networks and support vector machines with statistics and a database engine for application in environmental modeling // Environmental Modelling & Software. 2012. V. 25. P. 412–420.
- 24. WMO. The Global Climate in 2015–2019 // World Meteorological Organization (WMO-№ 1249), Geneva, Switzerland. 2020. 24 p.
- 25. Worsham L., Markewitz D., Nibbelink N. Incorporating spatial dependence into estimates of soil carbon contents under different land covers // Soil Science Society of America Journal. 2010. V. 74. P. 635–646.
- 26. Ziggah Y.Y., Youjian H., Tierra A.R., Laari P.B. Coordinate Transformation between Global and Local Data Based on Artificial Neural Network with K-Fold Cross-Validation in Ghana // Earth Sciences Research Journal. 2019. V. 23 (1). P. 67–77.
