Modeling the Effective Parameters on Accuracy of Soil Electrical Conductivity Measurement Systems Using RBF Neural Network

ماشین های کشاورزی

Article 11, Volume 9, Issue 1 - Serial Number 17, 2019, Pages 139-154   

Document Type: Research Article

DOI: 10.22067/jam.v9i1.66489

Authors

J. Baradaran Motie¹; M. H. Aghkhani^{* 1}; A. Rohani¹; A. Lakziyan²

¹Mechanic of Biosystems Engineering, Ferdowsi University of Mashhad, Mashhad, Iran

²Soil Science, Ferdowsi University of Mashhad, Mashhad, Iran

Abstract

Introduction
Presently, the loss of ground water levels and the increase in dissolved salts have given importance to the determination of salinity and the management of their variations in irrigated farms. Soil electrical conductivity is an indirect method to measure soil salts. The direct electrode contact method (Wenner method) is one of the widely used methods to rapidly measure soil ECa in farms. However, soil scientists prefer soil actual electrical conductivity (saturated extract electrical conductivity) (ECe) as an indicator of soil salinity, though its measurement is only possible in the laboratory. The aim of this study was to find a relationship between the prediction of soil actual electrical conductivity (ECe) in terms of temperature, moisture, bulk density and apparent electrical conductivity of soil (ECa). Thereby, the estimation of ECe would allow the partial calculation of ECa that is dependent upon soil salinity and dissolved salts.
Materials and Methods
This study used RBF neural network in Box-Behnken statistical design to explore the impacts of effective parameters on direct contact method in the measurement of soil ECa and provided a model to estimate ECe from ECa, temperature, moisture content and bulk density. In this study soil apparent electrical conductivity (ECa) was measured by direct contact (Wenner) method. The present study considered four most effective factors: ECa (saturated paste extract EC), moisture, bulk density, and temperature (Baradaran Motie et al., 2010). Given the characteristics of farming soils in Khorasan Razavi Province (Iran), the maximum and minimum of each independent variable were assumed as 0.5-6 mS.cm-1 for ECe, 5-25% for moisture content, 1-1.8 g.cm^-3 for bulk density, and 2-37°C for soil temperature. Considering the experimental design, three moisture levels (5, 15 and 25%), three salinity levels (0.5, 3.25 and 6 mS.cm^-1), three temperature levels (2, 19 and 37°C) and three compaction levels with bulk densities of 1, 1.4 and 1.8 g.cm^-3 were assumed in 27 trials with predetermined arrangement on the basis of Box-Behnken technique. 13 common algorithms were explored in MATLAB software package for the training of the artificial neural network in order to find the optimum algorithm (Table 4). The input layer of the network designed by integrating a Randomized Complete Block Design (RCBD) with k-fold cross-validation. Using k-fold cross-validation, 20 different datasets were generated for training and validation of RBF neural network.
Results and Discussion
A combination of an RCBD and k-fold cross-validation was used. The results of both training and validation phases should be considered in the selection of training algorithm. In addition, R² of T1 training algorithm had a much lower standard deviation than other training algorithms. The lower standard deviation is, the more capable the algorithm would be in learning from different datasets. Considering all aspects, trainbr (T2) training algorithm was found to have the best performance among all 13 training algorithms of the neural network. Table 7 tabulates the results of means comparison for R2 of RBF model for both training and validation phases resulted from the application of some combinations of S and L2 factors as interaction. As can be observed, R² = 0.99 for all of them with no significant difference. However, the magnitude of order differed between training and validation phases. Given the importance of the training phase, L2=9 and S=0.1 were regarded as the optimum values.
The sensitivity analysis of the network revealed that soil ECa, moisture, bulk density, and temperature had the highest to lowest impact on the estimation of soil ECe, respectively. This model can improve the precision of soil ECa measurement systems in the estimation and preparation of soil salinity maps. Furthermore, this model can save in time of data analysing and soil EC mapping because it does not need data recollection for the calibration of systems. A validation prose was done with a 60 field collected data set. The results of validation show R²=0.986 between predicted and measured ECa.
Conclusion
The present research focused on improving the precision of soil ECe measurement on the basis of easily accessible parameters (ECa, temperature, moisture, and bulk density). In conventional methods of soil EC mapping, the systems only measure soil ECa and then calibrate it to ECe by collecting some samples and using statistical methods. In this study, Soil ECe was estimated with R² = 0.99 by a multivariate artificial neural network model with the inputs, including ECa, temperature, moisture, and bulk density of soil without any need to collect further soil samples and calibration process. The Bayesian training algorithm was introduced as the best training algorithm for this neural network. Thereby, soil EC variation maps can be prepared with higher precision to estimate the spatial spread of salinity in farms. Also, the results imply that soil ECa, moisture, bulk density and temperature have the highest to lowest effectiveness on the estimation of soil ECe, respectively.
 

Keywords

Apparent electrical conductivity; Extract electrical conductivity; RBF neural network; Soil salinity

References

1. ASTM Standard D1557. 2009. Standard Test Methods for Laboratory Compaction Characteristics of Soil Using Modified Effort, ASTM International, West Conshohocken, PA, DOI: 10.1520/D1557-09.

2. Bai, W., L. Kong, and A. Guo. 2013. Effects of physical properties on electrical conductivity of compacted lateritic soil. Journal of Rock Mechanics and Geotechnical Engineering 5 (5): 406-411.

3. Baradaran Motie, J., M. H. Aghkhani, M. H. Abbaspour-fard, and A. Lakzian. 2010. Determining soil EC based on Wenner method with plate type probes as a component of precision farming, First international conference of soil and root relationship (LANDCON1005), 24-26 May 2010, Ardabil, Iran.

4. Baradaran Motie, J., M. H. Aghkhani, M. H. Abbaspour-fard, and A. lakzian. 2011. Design, Construction and Assessment of Soil Electrical Conductivity Mapper. Journal of Agricultural Machinery Engineering 1 (1): 25-33. (In Farsi).

5. Corwin, D. L., and S. M. Lesch. 2003. Application of Soil Electrical Conductivity to Precision Agriculture: Theory, Principles, and Guidelines. Agronomy Journal 95 (3): 455-471.

6. Ehsani, R., and M. Sullivan. 2002. Soil Electrical Conductivity (EC) Sensors. Ohio state university. Extension factsheet. Food, Agricultural and Biological Engineering, AEX-565-02.

7. Hartman, E., J. D. Keeler, and J. M Kowalski. 1990. Layered neural networks with Gaussian hidden units as universal approximations, Neural Computation 2 (2): 210-215.

8. Hashemi Nejad, Y., M. Gholami, and V. Soltani. 2012. Optimize water consumption through precise control of soil salinity in a lasting environment. Journal of Soil and Water Conservation 1 (3): 59-67. (In Farsi).

9. Kashi, H., S. Emamghoi zadeh, H. Ghorbani, and S. Hashemi. 2013. Estimation of Soil Infiltration in Agricultural and Pasture Lands using Artificial Neural Networks and Multiple Regressions. Quarterly Journal of Environmental Erosion Research 3: 19-34. (In Farsi).

10. Kelly, B. F. J. 1997. Electrical Properties of Sediments and the Geophysical Detection of Groundwater Contamination, The University of New South Wales Sydney.

11. Khanjani, T., M. Ataei, and P. Moallem. 2016. Wind Speed Prediction Based on Chaos Theory using RBF Neural Networks. Computational Intelligence in Electrical Engineering 7 (3): 87-96. (In Farsi).

12. Khazaii, M., S. H. Sadeghi, and S. K., Mirnia. 2013. Application of Artificial Neural Network and Regression Models in Sediment Yield in Plots Located in Disturbed and Undisturbed Plots in Educational and Research Forest Watershed of Tarbiat Modares University, Iran. Iranian Journal of Watershed Management Science and Engineering 7 (21): 13-20. (In Farsi).

13. Liaghat, A. 1993. Effect of clay type and clay content on moisture content and bulk soil electrical conductivity as measured using time domain reflectometry, Master of Science thesis, Department of agricultural engineering, macdonald campus of Mc-Gill University, Canada.

14. Lilienthal, H., Ch. Itter, J. Rogasik, and E. Schnug. 2005. Comparison of different geo-electric measurement techniques to detect in-field variability of soil parameter. LandbauforschungVölkenrode 55 (4): 237-243.

15. Loke, M. H., J. E. Chambers, D. F. Rucker, O. Kuras, and P. B. Wilkinson. 2013. Recent developments in the direct-current geoelectrical imaging method. Journal of Applied Geophysics 95: 135-156.

16. Lund, E. D., C. D. Christy, and P. E. Drummond. 1999. Practical applications of soil electrical conductivity mapping, 2nd European Conference on Precision Agriculture. July 1999.

17. Lund, E. D., C. D. Christy, and P. E. Drummond. 2000. Using yield and soil electrical conductivity (EC) maps to derive crop production performance information. In Proceedings of the 5th International Conference on Precision Agriculture, Bloomington, Minnesota, USA, 16-19 July, 2000 (pp. 1-10). American Society of Agronomy.

18. Mahrooghy, M., J. Aanstoos, R. A. Nobrega, K. Hasan, and N. H. Younan. 2016. A Neural Network Approach to Soil Electrical Conductivity Estimation on Earthen Levees Using Spaceborne X-band SAR Imagery. Photogrammetric Engineering & Remote Sensing 82 (7): 509-519.

19. Montgomery, Douglas C. Design and analysis of experiments. Hoboken, NJ: Wiley, 2009.

20. Nazari, P., Sh. Mahmoudi, and A. Pazira. 2017. Study of salinity changes in parts of Turkman Sahra lands using interpolation methods. Journal of Soil and Water Conservation 6 (3): 89-98. (In Farsi).

21. Olteanu, C., C. Turcu, F. Olteanu, S. Zamfira, G. Oltean, and B. Braun. 2008. Mechatronic system for measuring and tracking of maps concerning soil agro-productive parameters, 6th International DAAAM Baltic Conference Industrial Engineering 24-26 April 2008, Tallinn, Estonia.

22. Pan, L., V. I. Adamchuk, S. Prasher, R. Gebbers, R. S. Taylor, and M. Dabas. 2014. Vertical soil profiling using a galvanic contact resistivity scanning approach. Sensors 14 (7): 13243-13255.

23. Pfannkuch, H. O. 1972. On the Correlation of Electrical Conductivity Properties of Porous Systems with Viscous Flow Transport Coefficients in Fundamentals of Transport Phenomena in Porous Media. Developments in Soil Science 2: 42-54.

24. Phonphan, W., N. K. Tripathi, T. Tipdecho, and A. Eiumnoh. 2014. Modelling electrical conductivity of soil from backscattering coefficient of microwave remotely sensed data using artificial neural network. Geocarto International 29 (8): 842-859.

25. Rezae Arshad, R., Gh. Sayyad, M. Mazloom, M. Shorafa, and A. Jafarnejady. 2012. Comparison of Artificial Neural Networks and Regression Pedotransfer Functions for Predicting Saturated Hydraulic Conductivity in Soils of Khuzestan Province. Journal of Water and Soil Science 16 (60): 107-118. (In Farsi).

26. Rhoades, J. D., D. L. Corwin, and S. M. Lesch. 1999. Geospatial measurements of soil electrical conductivity to assess soil salinity and diffuse salt loading from irrigation. Assessment of non-point source pollution in the vadose zone: 197-215.

27. Rhoades, J. D., N. A. Manteghi, P. J. Shouse, and W. J. Alves. 1989. Soil electrical conductivity and soil salinity: New formulations and calibrations. Soil Science Society of America Journal 53 (2): 433-439.

28. Seifi, M. R., R. Alimardani, and A. Sharifi. 2010. Design and development of a portable soil electrical conductivity detector. Asian Journal of Agricultural Sciences 2 (4): 168-173.

29. Silva, P. L., and Z. Bassiouni. 1988. Hydrocarbon Saturation Equation in Shaly Sands According to the S-B Conductivity Model. SPE Formation Evaluation 3 (03): 503-509.

30. Sudduth, K. A., S. T. Drummond, and N. R. Kitchen. 2001. Accuracy issues in electromagnetic induction sensing of soil electrical conductivity for precision agriculture. Computers and Electronics in Agriculture 31 (3): 239-264.

31. Sudduth, K. A., N. R. Kitchen, G. A. Bollero, D. G. Bullock, and W. J. Wiebold. 2003. Comparison of electromagnetic induction and direct sensing of soil electrical conductivity. Agronomy Journal 95 (3): 472-482.

32. Sudduth, K. A., D. B. Myers, N. R. Kitchen, and S. T. Drummond. 2013. Modeling soil electrical conductivity–depth relationships with data from proximal and penetrating ECa sensors. Geoderma 199: 12-21.

33. Sudduth, K. S., J. W. Hummel, N. R. Kitchen, and S. T. Drummond. 2000. Evaluation of a soil conductivity sensing penetrometer. Presented at the 2000 ASAE Annual International Meeting, Paper No.00 1043, American Society of Agricultural Engineers. 2950 Niles Road, St. Joseph, MI 49085-9659, USA.

34. Toumelin, E., and C. Torres-Verdin. 2005. Influence of oil saturation and wettability on rock resistivity measurements: a uniform pore-scale approach. In SPWLA 46th Annual Logging Symposium. Society of Petrophysicists and Well-Log Analysts.

35. Waxman, M. H., and L. J. M. Smits. 1968. Electrical conductivities in oil-bearing shaly sands. Society of Petroleum Engineers Journal 8 (02): 107-122.

36. Wenner, F. 1915. A method for measuring earth resistivity. Journal of the Washington Academy of Sciences 5 (16): 561-563.

37. Zarif Neshat, S., A. Rohani, M. Etefagh, and M. H. Saedi Rad. 2012. Predictions of apple bruise volume by using RBF artificial neural network and comparison it with regression. Journal of Food Processing and Preservation 4 (2): 45-65. (In Farsi).