Firefly Algorithm and Genetic Algorithm Performance in Cation Exchange Capacity Prediction by Artificial Neural Networks

آب و خاک

Article 8, Volume 31, Issue 5 - Serial Number 55, November 2018, Pages 1456-1466   

Document Type: Research Article

DOI: 10.22067/jsw.v31i5.64271

Authors

moslem servati^* ; Hamidreza Momtaz

Urmia University

Abstract

Introduction: Cation Exchange Capacity (CEC) refers to the amount of negative charges available on the soil colloids surface. Clay and organic colloids carry a negative charge on their surfaces. Cations are attracted to the colloids by electrostatic bonds. Therefore, the charge of the soil is zero. For fertility map planning and commonly indicator of soil condition, CEC is an essential property. CEC is commonly measured on the fine earth fraction (soil particles less than 2 mm in size). CEC could be obtained directly but its measurement is difficult and expensive in the arid and semi-arid regions with high amounts of gypsum and lime. Pedotransfer functions (PTFs) are appropriate tools to estimate CEC from more readily measured properties such as texture, organic carbon, gravel, pH and etc. Regression PTFs, artificial neural networks (ANN), and hybrids technique (HA) could be used to developing pedotransfer functions. The prior research revealed that could provide superior predictive performance when developed ANN model. Furthermore, ANN technique has no comprehensive method to select network learning algorithm and stopping algorithm in the minimum local. Therefore, application of optimization algorithms such as Genetic (GA) and firefly (FA) is necessary. The Purpose of the present study was to evaluate the performance of FA and GA to predict the soil cation exchange capacity by ANN technique based on easily-measured soil properties.
Materials and Methods: 220 soil samples were collected from 39 soil profiles located in Golfaraj (Jolfa) area of East Azarbaijan province. The study site lies from 45° 30ʹ to 45° 53ʹ east longitudes and from 38° 42ʹ to 38° 46ʹ north latitudes. Then, soil samples were air-dried and passed through a 10 mesh sieve for removing gravels and root residues. Soil textural class, organic matter content and CEC were, respectively, determined by hydrometer, Walkley and Black, and bower methods. The artificial neural network (ANN), artificial neural network-Genetic algorithm (ANN-GA) and artificial neural network-Firefly algorithms (ANN-FA) models were applied to predict the soil cation exchange capacity on the basis of the easily-measured soil properties. In ANN-GA and ANN-FA models, soil CEC was estimated via an artificial neural network and were then optimized using a genetic algorithm and firefly algorithm. The Genetic algorithms are commonly used to generate high-quality solutions to be optimized by relying on crossover, mutation and selection operators. The firefly algorithm is modeled by the light attenuation over fireflies’ mutual gravitation, instead of the phenomenon of the fireflies light. The schema of flashes is frequently unique for specific types. The techniques’ results were then compared by four parameter, i.e., correlation coefficient (R2), root mean square errors (RMSE), Nash–Sutcliffe (NES) and Geometric mean error ratio (GMRE).
Results and Discussion: The correlation coefficients of soil characteristic factors with CEC were analyzed through correlation matrix analysis. According to this analysis, the factors which had insignificant influence on the CEC were excluded. The clay, silt, sand and organic matter content were selected as input data. The parameter of the best deployment for MLP network could be used to predict CEC in the studied site. This model comprised 4 neurons (sand, silt, clay percentage and OM) in input layer. The optimum number of neurons in hidden layer was estimated to be 5. Additionally, the most efficient activity function in hidden layer was Axon sigmoid. Results showed that three CEC models performed reasonably well. ANN-FA model had the highest R2 (0.94), lowest RMSE (1.31 Cmol+ Kg-1) and highest Nash–Sutcliffe coefficient (0.53) in training stage and high R2 (0.97), lowest RMSE (1.06 Cmol+ Kg-1) and highest Nash–Sutcliffe coefficient (0.59) in test stage. ANN-GA model had also higher R2 (0.91), lower RMSE (1.77 Cmol+ Kg-1) and higher Nash–Sutcliffe coefficient (0.45) in training stage and higher R2 (0.93), lower RMSE (1.50 Cmol+ Kg-1) and higher Nash–Sutcliffe coefficient (0.48) in test stage indicating good performance of the model as compared with ANN models. The results showed that both ANN and Hybrid algorithm methods performed poorly in extrapolating the minimum and maximum amount of CEC soil properties data. In addition, the comparison of ANN-FA, ANN-GA results with ANN models revealed that ANN-FA was more efficient than the others.
Conclusions: The results of present study illustrated that ANN model can predict CEC with acceptable limits. Therefore, FA and GA algorithms provide superior predictive performance when is combined with ANN model. Firefly algorithm as a new method is utilized to optimize the amount of the weights by minimizing the network error. Final results revealed that this suggested technique improves the modeling performance.

Keywords

Easily-measured properties; Hybrid algorithm; Optimizations

References

1- Andonie R. 2010. Extreme Data Mining: Inference from small data sets, International Journal of Computes Communications and Control, 5(3):‌280-291.

2- Akbarzadeh A., Taghizadeh Mehrjardi R., Rahimi Lak H., and Ramezanpour H. 2009. Application of artificial intelligence in modeling of soil properties (Case study: Roodbar Region, North of Iran), Environmental Research Journal, 3‌(2):‌19-24.

3- Amini M., Abbaspour K.C., Khademi H., Fathianpour N., Afyuni M., and Schulin R. 2005. Neural network models to predict cation exchange capacity in arid regions of Iran, European Journal of Soil Science, 53:‌748-757.

4- Asgari M.‌S., Khodadadi M., Sarmadian F., and Gzny R. 2009. The effectiveness of artificial neural networks in the yield of wheat, barley and maize, Journal of Agriculture, 85(1):‌62-71.

5- Bell M.A., and Van Kulen H. 1995. Soil pedotransfer function for four Mexican soils, Soil Science Society of America Journal, 59:‌865-871.

6- Carpena O., Lux A., and Vahtras K. 1972. Determination of exchangeable cations in calcareous soils, Journal of Soil Science, 33:‌194-199.

7- Doran J.W., and Parkin T.‌B. 1994. Defining and assessing soil quality. p. 543-569. In J.W Doran et al (Ed.) Defining Soil Quality for a Sustainable Environment, Soil Science Society American Special publication, Madison, Wisconsin, USA.

8- DuBose P., and Klimasauskas C. 1989. Introduction to Neural Networks with Examples and Applications, Neural Ware Inc, Pittsburgh.

9- Ghorbani H., Kashi H., Hafezi Moghadas N., and Emamgholizadeh S. 2015. Estimation of soil cation exchange capacity using multiple regression, artificial neural networks and adaptive neuro-fuzzy inference system models in Golestan Province, Iran. Communication in Soil Science and Plant Analysis, 46(6):‌763-780.

10- Holland J.H. 1984. The Georgians: Genealogies of Pioneer Settlers. Genealogical Publishing Com, Amesterdam.

11- Kashi H., Ghorbani H, Emamgholizadeh S., and Hashemi S.A.A. 2013. The Estimation of Soil Cation Exchange Capacity in Disturbed and Undisturbed Soils Using Artificial Neural Networks and Multiple Regressions, Journal of water and soil, 27:‌472-484.

12- Kashi H., Emamgholizadeh S., and Ghorbani H. 2014. Estimation of soil infiltration and cation exchange capacity based on multiple regression, ANN (RBF, MLP), and ANFIS Models, Soil Science and Plant Analysis, 45:‌1195-1213.

13- Keller A., Von steiger B., Van der Zee S.T., and Schulin R. 2001. A stochastic empirical model for regional heavy metal balances in agro ecosystems, Journal of Environmental Quality, 30:‌1976-1989.

14- Krogh L., Madsen H.B., and Greve M.‌H. 2000. Cation exchange capacity pedotransfer functions for Danish soils, Soil and Plant Science, 50:‌1-12.

15- Manrique L.A., Jones C.A., and Dyke P.T. 1991. Predicting cation exchange capacity from soil physical and chemical properties, Soil Science Society of America Journal, 50:‌787-794.

16- Merdun H., Cinar O., and Apan M. 2006. Comparison of artificial neural network and regression pedotransfer function for prediction of soil water retention and saturated hydraulic conductivity, Soil and Tillage Research, 90:-108-116.

17- McBratney A.B., Minasny B., Cattle S. R., and Vervoort R.W. 2002. From pedotransfer functions to soil inference systems, Geoderma, 109:‌41-73.

18- Mirzaee S., Ghorbani-dashtaki Sh., Mohammadi J., Asadzadeh F., and Kerry R. 2017. Modeling WEPP erodibility parameters in calcareous soils in northwest Iran, Ecological Indicators, 74:‌302-310.

19- Oberthur T., Doberman A., and Neue H.V. 1996. How good is a reconnaissance soil map for agronomic purpose?, Soil Use and Management, 12:33-43.

20- Schaap M.G., and Bouten W. 1996. Modelling water retention curves of sandy soils using neural networks, Water Research, 32: 3033-3040.

21- Tang L., Zeng G.‌M., Nourbakhsh F. and Shen G.‌L. 2008. Artificial neural network approach for predicting cation exchange capacity in soil based on physico-chemical properties, Environmental Engineering Science, 26(2):‌1-10.

22- USDA. 2014. Keys to Soil Taxonomy. 12th edition, Soil Survey Staff, Natural Resource Conservation Service.

23- Yang, X. S. 2008. Nature-Inspired Metaheuristic Algorithms, Luniver Press, UK.

24- Yang X.S. 2009. Firefly Algorithms for Multimodal Optimization. P. 169-178. In Stochastic Algorithms. Foundations and Applications, SAGA, Lecture Notes in Computer Sciences, Cambridge, UK.