Estimation of soil pH with geochemical indices in forest soils

Autoři: Wei Wu aff001;  Hong-Bin Liu aff002
Působiště autorů: College of Computer and Information Science, Southwest University, Beibei, Chongqing, China aff001;  College of Resources and Environment, Southwest University, Beibei, Chongqing, China aff002
Vyšlo v časopise: PLoS ONE 14(10)
Kategorie: Research Article
doi: 10.1371/journal.pone.0223764


Soil pH is a critical soil quality index and controls soil microbial activities, soil nutrient availability, and plant roots growth and development. The current study aims to evaluate various pedotransfer functions for predicting soil pH using different geochemical indices (CaO, ratios of Al2O3, Fe2O3, TiO2, SiO2, MgO, and K2O to CaO) in forest soils. Various models including empirical functions (quadratic, cubic, sigmoid, logarithmic) and artificial neural network with these geochemical indices were assessed by independent testing set. Mean bias error (MBE), root mean square error (RMSE), mean absolute percentage error (MAPE), mean absolute error (MAE), coefficient of determination (R2), t-statistics (t-stat), and Akaike’s Information Criterion (AIC) were applied to evaluate the model performances. Additionally, a new indicator (global performance indictor, GPI) was originally introduced in this study and was used to rank these models. According to GPI, the sigmoid functions and ANNs performed better than others. On average, they could explain above 70% of the variability in soil pH. Both model structure and dataset shape impact on model performance. The best input was CaO for ANNs, sigmoid, and logarithmic functions. The ratios of K2O to CaO and Al2O3 to CaO were the best inputs for quadratic and cubic equations, respectively.

Klíčová slova:

Analysis of variance – Artificial neural networks – Forecasting – Geochemistry – Global positioning system – Mathematical functions – Soil pH – Plant roots


1. Brady NC, Weil RR. The Nature and Properties of Soils, 14th ed. Prentice Hall, Upper Saddle River, NJ (975 pp.), 2008.

2. McLean EO. Soil pH and lime requirement, In: Page A.L., et al. (Eds.), Methods of Soil Analysis Part 2—Chemical and Microbiological Properties, 2nd ed. ASA/SSSA, Madison, WI, pp. 199–223, 1982.

3. Reuss JO, Walthall PM, Roswall EC, Hopper RWE. Aluminum solubility, calcium-aluminum exchange, and pH in acid forest soils. Soil Sci. Soc. Am. J. 1990; 54: 374–380.

4. Bloom PR, Grigal DF. Modeling soil response to acidic deposition in nonsulfate adsorbing soils. J. Environ. Qual. 1985; 14: 489–495.

5. Magdoff FR, Bartlett RJ. Soil pH buffering revisited. Soil Sci. Soc. Am. J. 1985; 49 (1): 145–148.

6. Blosser DL, Jenny H. Correlations of soil pH and percent base saturation as influenced by soil forming factors. Soil Sci. Soc. Am. P. 1971; 35 (6): 1017–1018.

7. Lukens WE, Nordt LC, Stinchcomb GE, Driese SG, Tubbs JD. Reconstructing pH of paleosols using geochemical proxies. J. Geol. 2018; 126: 427–449.

8. Nordt LC, Driese SG. A modern soil characterization approach to reconstructing physical and chemical properties of paleo-vertisols. Am. J. Sci. 2010; 310: 37–64.

9. FAO. Soil Map of the World, Revised Legend. Rome, Italy, 1988

10. CGS. Specification for multi-purpose regional geochemical survey (DD200501), in: China Geological Survey (Ed.), Beijing (in Chinese), 2005

11. Guo PT, Wu W, Sheng QK, Li MF, Liu HB, Wang ZY. Prediction of soil organic matter using artificial neural network and topographic indicators in hilly areas, Nutr. Cycl. Agroecosys. 2013; 95: 333–344.

12. Guo PT, Shi Z, Li MF, Luo W, Cha ZZ. A robust method to estimate foliar phosphorus of rubber trees with hyperspectral reflectance. Ind. Crop. Prod. 2018; 126: 1–12.

13. Kanungo DP, Sharma S, Pain A. Artificial neural network (ANN) and regression tree (CART) applications for the indirect estimation of unsaturated soil shear strength parameters. Front. Earth Sci-Prc. 2014; 8 (3): 439–456.

14. Mba L, Meukam P, Kemajou A. Application of artificial neural network for predicting hourly indoor air temperature and relative humidity in modern building in humid region. Energ. Buildings. 2016; 121: 32–42.

15. Lim HS, Kang YT. Estimation of finish cooling temperature by artificial neural networks of backpropagation during accelerated control cooling process. Int. J. Heat Mass Tran. 2018; 126: 579–588.

16. Antiwi P, Li J, Meng J, Deng K, Quashie FK, Li J, et al. Feedforward neural network model estimating pollutant removal process within mesophilic upflow anaerobic sludge bioreactor treating industrial starch processing wastewater. Bioresource Technol. 2018; 257:102–112.

17. Singh VK, Tiwari KN. Prediction of greenhouse micro-climate using artificial neural network. Appl. Ecol. Env. Res. 2017; 15(1): 767–778.

18. Minasny B, McBratney AB. The Neuro-m method for fitting neural network parametric pedotransfer functions. Soil Sci. Soc. Am. J. 2002; 66: 352–361.

19. Akaike H. Information theory and an extension of maximum likelihood principle. p. 267–281. In Petrov B.N. and Csáki F. (ed). Second International Symposium on Information Theory. Akadémia Kiadó, Budapest, 1973.

20. Willmott CJ, Matsuura K. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Clim. Res. 2005; 30: 79–82.

21. Loh WY. Classification and regression trees. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 1, 14–23, 2011.

22. Zou X, Zhao J, Povey MJW, Holmes M, Mao H. Variables selection methods in near-infrared spectroscopy. Anal. Chim. Acta. 2010; 667: 14–32. doi: 10.1016/j.aca.2010.03.048 20441862

23. Burnham KP, Anderson DR. Model selection and multimodel inference: a practical information-theoretic approach, Berlin: Springer, 1998.

24. Hegyi G, Garamszegi LZ. Using information theory as a substitute for stepwise regression in ecology and behavior. Behav. Ecol. Sociobiol. 2011; 65 (1): 69–76.

25. Mundry R. Issues in information theory-based statistical inference-commentary from a frequentist’s perspective. Behav. Ecol. Sociobiol. 2011; 65(1): 57–68.

26. Slessarev EW, Lin Y, Bingham NL, Johnson JE, Dai Y, Schimel JP, et al. Water balance creates a threshold in soil pH at global scale. Nature 2016; 540: 567–569. doi: 10.1038/nature20139 27871089

Článek vyšel v časopise


2019 Číslo 10