International Scientific Journal


At present, the underground brine deposit of Lop Nor salt lake in Xinjiang, while is rich in solar energy resource and can be one high efficient solar thermal utilization area, has become an important potash production base in China. During the development of salt lake brine, the collection methods are different according to the concentration of ions in different locations. In order to solve the problems of low accuracy and high calculation cost in prediction of salt field ion concentration, a data mining method based on random forest is applied in this paper. To build the model, we collected K+, SO42–, Cl–, and other two kinds of ions, among which the features included the collection time, collection locality and the number of salt pond. We used several methods to train and test the sample data, evaluated the experimental results using a variety of performance metrics and compared it with other methods at the same time. The results revealed that the optimal random forest model yielded the mean square error and coefficient of determination values of 0.073 and 0.940, which performed relatively better than support vector machine and extremely randomized trees.
PAPER REVISED: 2019-01-25
PAPER ACCEPTED: 2019-02-05
CITATION EXPORT: view in browser or download as text file
THERMAL SCIENCE YEAR 2019, VOLUME 23, ISSUE Issue 5, PAGES [2623 - 2630]
  1. Lv,F. L., et al.,, The discussion on sedimentary characteristics, phased evolution and controlling factors of saline lake in Asia interior: Records from deep drill cores of LDK01 in Lop Nur, Xinjiang, northwestern China, ACTA PETROLOGICA SINICA 31(2015), 9, pp. 2770-2782.
  2. XU, H., et al., Distribution Characteristics of the Main Ions in Luobei Area of Luobupo Salt Lake
  3. Sun, Ming-guang, et al., Potassium-rich brine deposit in Lop Nor basin, Xinjiang, China, Scientific reports 8 (2018), 1, pp. 7676.
  4. Kong, D. Y. , et al., Seasonal change of water absorption capability and moisture content of the top salt-crust in Lop Nur dry lake, Acta Geoscientica Sinica 37(2016), 2, pp.185-192.
  5. Qiu, Xinhong , et al., Removal of borate by layered double hydroxides prepared through microwave-hydrothermal method. Journal of Water Process Engineering 17(2017) , pp. 271-276.
  6. Chen, Fengxi , et al. Ionothermal synthesis of Fe3O4 magnetic nanoparticles as efficient heterogeneous Fenton-like catalysts for degradation of organic pollutants with H2O2. Journal of Hazardous Materials 322.Pt A(2017) , pp. 152-162.
  7. Mao, YW , et al. Microstructure analysis of graphite/Cu joints brazed with (Cu-50TiH2)+B composite filler. Fusion Engineering and Design 100(2015) , pp. 152-158.
  8. Miao, Ling , et al. Cooking carbon with protic salt: Nitrogen and sulfur self-doped porous carbon nanosheets for supercapacitors. Chemical Engineering Journal 347(2018) , pp. 233-242.
  9. Chao, J. I. , et al., Separation properties of magnesium and lithium from brine with high Mg~(2+)/Li~+ ratio by DK nanofiltration membrane, Membrane Science and Technology 42.4(2014), pp. 607-615.
  10. Chen, X. U. , et al., Predict chloride concentration in concrete based on neural network, Concrete(2010).
  11. Hanxin, Chen , et al., Fault Identification of Gearbox Degradation with Optimized Wavelet Neural Network. Shock and Vibration 20 (2013), 2, pp. 247-262.
  12. Parveen, N., et al., Development of SVR-based model and comparative analysis with MLR and ANN models for predicting the sorption capacity of Cr (VI), Process Safety and Environmental Protection 107 (2017),pp. 428-437.
  13. Xiong, F. Q., et al., Integrated prediction model of iron concentration in goethite method to remove iron process, Control and Decision 27.3 (2012),pp. 329-334.
  14. Suykens, Johan AK, and Joos Vandewalle., Least squares support vector machine classifiers, Neural processing letters9.3 (1999), pp. 293-300.
  15. Liu, J., et al., Predicting the content of camelina protein using FT-IR spectroscopy coupled with SVM model, Cluster Computing (2018),pp. 1-6.
  16. Liu J , et al. Intelligent predicting of salt pond's ion concentration based on support vector regression and neural network. Neural Computing and Applications (2019), pp.1-15.
  17. Breiman, Leo., Random forests, Machine learning 45 (2001), 1, pp. 5-32.
  18. Azar, A. T., et al., A random forest classifier for lymph diseases, Computer methods and programs in biomedicine 113 (2014), 2, pp. 465-473.
  19. Huynh, T., et al., Estimating CT image from MRI data using structured random forest and auto-context model, IEEE transactions on medical imaging 35.1 (2016), pp. 174-183.
  20. Keramati, A., et al., Developing a prediction model for customer churn from electronic banking services using data mining, Financial Innovation 2 (2016), 1, pp. 10.
  21. Pandya, Rutvija, and Jayati Pandya., C5. 0 algorithm to improved decision tree with feature selection and reduced error pruning, International Journal of Computer Applications 117 (2015), 16, pp. 18-21.
  22. Singh, Sonia, and Priyanka Gupta., Comparative study ID3, cart and C4. 5 decision tree algorithm: a survey, Int J Adv Inf Sci Technol
  23. Song, Yan-Yan, and L. U. Ying., Decision tree methods: applications for classification and prediction, Shanghai archives of psychiatry 27 (2015), 2, pp. 130.
  24. Manek, A. S., et al., Aspect term extraction for sentiment analysis in large movie reviews using Gini Index feature selection method and SVM classifier, World wide web 20 (2017), 2, pp. 135-154.
  25. Toma, T., et al., Learning predictive models that use pattern discovery—A bootstrap evaluative approach applied in organ functioning sequences, Journal of biomedical informatics 43.4 (2010), pp. 578-586.
  26. Wang, Z. L., et al., Flood hazard risk assessment model based on random forest, Journal of Hydrology 527 (2015), pp. 1130-1141.
  27. Hlihor, R. M., et al., Experimental analysis and mathematical prediction of Cd (II) removal by biosorption using support vector machines and genetic algorithms, New biotechnology 32 (2015), 3, pp. 358-368.
  28. André, S., et al., Developing global regression models for metabolite concentration prediction regardless of cell line, Biotechnology and bioengineering 114 (2017), 11, pp. 2550-2559.
  29. Yuntao WU, et al., HOSVD-based subspace algorithm for multidimensional frequency estimation without pairing parameters. Chin J Electron 23(2014), 4, pp. 729-734
  30. Wang Z, et al., Trilateral constrained sparse representation for Kinect depth hole filling. Pattern Recognit Lett 65 (2015), pp.95-102
  31. Liu H, et al., Distributed source localization under anchor position uncertainty. Chin J Electron 23 (2014), 1, pp. 93-96
  32. Zhong L, et al., OHRank: an algorithm integrating mentality and influence of opinion holder for opinion mining. Chin J Electron 22 (2013), 4, pp. 655-660
  33. Peng, Li , et al. A robust method for estimating image geometry with local structure constraint. IEEE Access 99(2018), PP. 1-10.
  34. Lu, Tao , et al. Robust Face Super-Resolution via Locality-constrained Low-rank Representation. IEEE Access (2017), pp. 1-10.
  35. Wang Z, et al., Trilateral constrained sparse representation for Kinect depth hole filling
  36. YunTao W, et al., Utilizing Principal Singular Vectors for 2D DOA Estimation in Single Snapshot Case with Uniform Rectangular Array
  37. YunTao W, et al., HOSVD-Based Subspace Algorithm for Multidimensional Frequency Estimation Without Pairing Parameters, Chinese Journal of Electronics, 23 (2014), 4, pp. 729-734
  38. Nagelkerke, Nico JD., A note on a general definition of the coefficient of determination, Biometrika 78 (1991),3, pp. 691-692

© 2022 Society of Thermal Engineers of Serbia. Published by the Vinča Institute of Nuclear Sciences, National Institute of the Republic of Serbia, Belgrade, Serbia. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International licence