Published

2017-04-01

Estimation of daily soil temperature via data mining techniques in semi-arid climate conditions

Estimación de la temperatura diaria del suelo a través de técnicas de búsqueda y procesamiento de datos en condiciones climáticas semiáridas

DOI:

https://doi.org/10.15446/esrj.v21n2.49829

Keywords:

Soil temperature, Data mining, M5 tree model, ANFIS, ANN (en)
Temperatura del suelo, minería de datos, modelo tipo árbol M5 (es)

Downloads

Authors

  • Mohammad Taghi Sattari Dr Mohammad Taghi Sattari Assistant Professor Department of Water Engineering Faculty of Agriculture University of Tabriz Tabriz, Iran
  • Esmaeel Dodangeh Department of Watershed Management, Sari Agricultural Sciences and Natural Resources University, Sari, Iran
  • John Abraham University of St. Thomas, School of Engineering 2115 Summit Ave St. Paul, MN 55105-1079

This paper investigates the potential of data mining techniques to predict daily soil temperatures at 5-100 cm depths for agricultural purposes. Climatic and soil temperature data from Isfahan province located in central Iran with a semi-arid climate was used for the modeling process. A subtractive clustering approach was used to identify the structure of the Adaptive Neuro-Fuzzy Inference System (ANFIS), and the result of the proposed approach was compared with artificial neural networks (ANNs) and an M5 tree model. Result suggests an improved performance using the ANFIS approach in predicting soil temperatures at various soil depths except at 100 cm. The performance of the ANNs and M5 tree models were found to be similar. However, the M5 tree model provides a simple linear relation to predicting the soil temperature for the data ranges used in this study. Error analyses of the predicted values at various depths show that the estimation error tends to increase with the depth.

Este artículo investiga el potencial de las técnicas de búsqueda y procesamiento de datos para pronosticar las temperaturas diarias del suelo a profundidades que van de los 5 a los 100 cm con propósitos agrícolas. Se utilizó la información climática y de temperatura del suelo de la provincia Ishafan, ubicada en el centro de Irán y de clima semiárido, para el proceso de modelamiento. Se usó un enfoque de agrupamiento sustractivo para identificar la estructura del Sistema de Inferencia Neuronal Difuso Adaptado (ANFIS, del inglés Adaptive Neuro-Fuzzy Inference System) y el resultado del acercamiento propuesto se comparó con redes artificiales neuronales (ANN) y el modelo tipo árbol M5. Los resultados sugieren un desempeño mejorado al usar el enfoque ANFIS en la predicción de las temperaturas del suelo en varios puntos de profundidad, excepto en los 100 cm. El desempeño de las redes artificiales neuronales y los modelos de árbol M5 fueron similares. Sin embargo, el modelo tipo árbol M5 provee una relación linear simple para predecir los rangos de datos de la temperatura del suelo utilizados en este estudio. Los análisis de error de los valores predichos a varias profundidades muestran que la estimación de error tiende a incrementarse con la profundidad.

References

Adnan, R. M., Yuan, X., Kisi, O., & Anam, R. (2017). Improving accuracy of River flow forecasting using LSSVR with gravitational search algorithm. Advances in meteorology. doi.org/10.1155/2017/2391621.

Bhattacharya, B., & Solomatine, D. P. (2005). Neural networks and M5 model trees in modeling water level–discharge relationship. Neurocomputing, 63, 381–396.

Biabani, R., Meftah Halaghi, M., & Ghorbani, K. H. (2016). M5 model tree to predict temporal evolution of clear-water abutment scour. Journal of Geology, 6, 1045-1054.

Bonng, B. & Vanclev, K. (1992). Soil temperature nitrogen mineralization and carbon source-sink relationships in boreal forests. Canadian Journal of Forest Research, 22, 629-639.

Chio, J. S., Fermanian, T. W., Wehner, D. J. & Spomer, L. A. (1988). Effect of temperature, moisture and soil texture on DCPA degradation. Agronomy Journal, 80, 108-111.

Chiu, S. (1994). Fuzzy model identification based on cluster estimation. Journal of Intelligent and Fuzzy Systems, 2, 762–767.

Elshorbagy, A., & Parasuraman, K. (2008). On the relevance of using artificial neural networks for estimating soil moisture content. Journal of Hydrology, 362, 1– 18.

Esmaeilzadeh, B., & Sattari, M. T. (2015). Monthly Evapotranspiration Modeling using Intelligent Systems in Tabriz, Iran. Agriculture Science Developments, 4(3), 35-40.

Gao, Z., Bian, L., Hu, Y., Wang, L. & Fan, J. (2007). Determination of soil temperature in an arid region. Journal of Arid Environments, 71, 157-168.

Gaumont-Guay, D., Black, T. A., Griffis, T. J., Barr, A. G., Jassal, R. S. & Nesic, Z. (2006). Interpreting the dependence of soil respiration on soil temperature and water content in a boreal aspen stand. Agricultural and Forest Meteorology, 140, 220–235.

Hecht-Nielsen, R. (1990). Neurocomputing. Addison-Wesley, Menlo Park, CA, USA.

Jang, J. S. R. (1993). ANFIS: adaptive-network-based fuzzy inference system. IEEE Transactions Systems, Man, and Cybernetics, 23(3), 665–685.

Kang, S., Kim, S., Oh, S. & Lee, D. (2000a). Predicting spatial and temporal patterns of soil temperature based on topography, surface cover, and air temperature. Forest Ecology and Management, 136, 173-184.

Lippmann, R.P. (1987). An introduction to computing with neural nets. IEEE ASSP Magazine, 4–22.

Pal, M. & Surinder, D. (2009). M5 model tree based modelling of reference evapotranspiration. Hydrological Processes, 23, 1437–1443.

Pal, M., Singh N. K., & Tiwari, N. K. (2012). M5 Model Tree for Pier Scour Prediction Using Field Dataset. KSCE, 16(6), 1079-1084.

Quinlan, J. R. (1992). Learning with continuous classes. In: Proc. AI’92 (Fifth Australian Joint Conf. on Artificial Intelligence) (ed. by A. Adams & L. Sterling), 343–348. World Scientific, Singapore.

Raju, K. G. (2001). Prediction of soil temperature by using Artificial Neural Networks Algorithms. Nonlinear Analysis, 47, 1737-1748.

Sattari, M. T., Pal, M., Apaydin, H., & Ozturk, F. (2013a). M5 Model Tree Application in Daily River Flow Forecasting in Sohu Stream, Turkey. Water Resources, 40(3), 233-242.

Sattari, M. T., Pal, M., Yurekli, K., & Unlukara, A. (2013b). M5 model trees and neural network based modelling of ET0 in Ankara, Turkey. Turkish Journal of Engineering and Environmental Sciences, 37, 211-219.

Sayagavi, V. G., Charhate, S., & Magar, R. (2016). Estimation of discharge using LS-SVM and Model trees. Journal of water resources and ocean science, 5(6), 78-86.

Shannon, E. B., Kurt, S. P., David, D. R. & Andrew, J. B. (2000). Predicting Daily Mean Soil Temperature from Daily Mean Air Temperature in Four Northern Hard Wood Forest Stands. Forest Science, 46, 297-301.

Shiri, J., & Kishi, O. (2011). Comparison of genetic programming with neuro-fuzzy systems for predicting. Computers & Geosciences, 37, 1692-1701.

Shortridge, J. E., Guikema, S. D., & Zaitchik, B. F. (2016). Machine learning methods for empirical streamflow simulation: a comparison of model accuracy, interpretability, and uncertainty in seasonal watersheds. Hydrology and Earth System Sciences, 20, 2611-2628.

Schnier, S. T. (2016). Data driven analyses of watersheds as coupled human-nature systems. University of Illinois, Urbana, Illinois.

Shu, C., & Ouarda TBMJ. (2008). Regional flood frequency analysis at ungauged sites using the adaptive neuro-fuzzy inference system. Journal of Hydrology, 349, 31-43.

Siek, M. & Solomantine, D. P. (2007). Tree-like machine learning models in hydrologic forecasting: optimality and expert knowledge. Geophysical Research Abstracts, 9, 2-5.

Solomantine, D. P. & Dulal, K. N. (2003). Model trees as an alternative to neural networks in rainfall-runoff modeling. Hydrological Sciences Journal, 48, 455-472.

Stravs, L., & Brilly, M. (2007). Development of a low flow forecasting model using the M5 machine learning method. Hydrological Sciences Journal, 52, 466–477.

Tang, Z., & Fishwick, P. A. (1993). Feedforward neural nets as models for time series forecasting. ORSA Journal of Computing, 5(4), 374–385.

Timlin, D. J., Pachepsky, Y., Acock, B. A., S'imunek, J., Flerchinger, G. & Whisler, F. (2002). Error analysis of soil temperature simulations using measured and estimated hourly weather data with 2DSOIL. Agricultural Systems, 72, 215–239.

Tuntiwaranuruk, U., Thepa, S., Tia, S., & Bhumiratana, S. (2006). Modeling of soil temperature and moisture with and without rice husks in an agriculture greenhouse. Renewable Energy, 31, 1934–1949.

Tyronese, J., Katrina, M., Mohamed, S., Tommy, C. & Peter, R. (2008). Measuring soil temperature and moisture using wireless MEMS sensors. Measurement, 41, 381–390.

Winegardner, D. L. (1996). An Introduction to Soils for Environmental Professionals. Boca Raton, Fla.: Lewis Publishers.

Wong, F. S. (1991). Time series forecasting using backpropagation neural networks. Neurocomputing 2, 147–159.

Yang, C. C., Prasher, S. O., Mehuys, G. R. & Patni, N. K. (1997). Application of artificial neural networks for simulation of soil temperature. Transactions of the ASAE, 40, 649-656.

Zadeh, L. A. (1965). Fuzzy sets. Information Control, 8, 338–353.

How to Cite

APA

Sattari, M. T., Dodangeh, E. and Abraham, J. (2017). Estimation of daily soil temperature via data mining techniques in semi-arid climate conditions. Earth Sciences Research Journal, 21(2), 85–93. https://doi.org/10.15446/esrj.v21n2.49829

ACM

[1]
Sattari, M.T., Dodangeh, E. and Abraham, J. 2017. Estimation of daily soil temperature via data mining techniques in semi-arid climate conditions. Earth Sciences Research Journal. 21, 2 (Apr. 2017), 85–93. DOI:https://doi.org/10.15446/esrj.v21n2.49829.

ACS

(1)
Sattari, M. T.; Dodangeh, E.; Abraham, J. Estimation of daily soil temperature via data mining techniques in semi-arid climate conditions. Earth sci. res. j. 2017, 21, 85-93.

ABNT

SATTARI, M. T.; DODANGEH, E.; ABRAHAM, J. Estimation of daily soil temperature via data mining techniques in semi-arid climate conditions. Earth Sciences Research Journal, [S. l.], v. 21, n. 2, p. 85–93, 2017. DOI: 10.15446/esrj.v21n2.49829. Disponível em: https://revistas.unal.edu.co/index.php/esrj/article/view/49829. Acesso em: 6 oct. 2022.

Chicago

Sattari, Mohammad Taghi, Esmaeel Dodangeh, and John Abraham. 2017. “Estimation of daily soil temperature via data mining techniques in semi-arid climate conditions”. Earth Sciences Research Journal 21 (2):85-93. https://doi.org/10.15446/esrj.v21n2.49829.

Harvard

Sattari, M. T., Dodangeh, E. and Abraham, J. (2017) “Estimation of daily soil temperature via data mining techniques in semi-arid climate conditions”, Earth Sciences Research Journal, 21(2), pp. 85–93. doi: 10.15446/esrj.v21n2.49829.

IEEE

[1]
M. T. Sattari, E. Dodangeh, and J. Abraham, “Estimation of daily soil temperature via data mining techniques in semi-arid climate conditions”, Earth sci. res. j., vol. 21, no. 2, pp. 85–93, Apr. 2017.

MLA

Sattari, M. T., E. Dodangeh, and J. Abraham. “Estimation of daily soil temperature via data mining techniques in semi-arid climate conditions”. Earth Sciences Research Journal, vol. 21, no. 2, Apr. 2017, pp. 85-93, doi:10.15446/esrj.v21n2.49829.

Turabian

Sattari, Mohammad Taghi, Esmaeel Dodangeh, and John Abraham. “Estimation of daily soil temperature via data mining techniques in semi-arid climate conditions”. Earth Sciences Research Journal 21, no. 2 (April 1, 2017): 85–93. Accessed October 6, 2022. https://revistas.unal.edu.co/index.php/esrj/article/view/49829.

Vancouver

1.
Sattari MT, Dodangeh E, Abraham J. Estimation of daily soil temperature via data mining techniques in semi-arid climate conditions. Earth sci. res. j. [Internet]. 2017Apr.1 [cited 2022Oct.6];21(2):85-93. Available from: https://revistas.unal.edu.co/index.php/esrj/article/view/49829

Download Citation

CrossRef Cited-by

CrossRef citations7

1. Olufemi P. Abimbola, George E. Meyer, Aaron R. Mittelstet, Daran R. Rudnick, Trenton E. Franz. (2021). Knowledge‐guided machine learning for improving daily soil temperature prediction across the United States. Vadose Zone Journal, 20(5) https://doi.org/10.1002/vzj2.20151.

2. Marina Püpke Marone, Maria Fernanda Zaneli Campanari, Fabio Trigo Raya, Gonçalo Amarante Guimarães Pereira, Marcelo Falsarella Carazzolle. (2022). Fungal communities represent the majority of root-specific transcripts in the transcriptomes of Agave plants grown in semiarid regions. PeerJ, 10, p.e13252. https://doi.org/10.7717/peerj.13252.

3. Olufemi P. Abimbola, Aaron R. Mittelstet, Tiffany L. Messer, Elaine D. Berry, Shannon L. Bartelt-Hunt, Samuel P. Hansen. (2020). Predicting Escherichia coli loads in cascading dams with machine learning: An integration of hydrometeorology, animal density and grazing pattern. Science of The Total Environment, 722, p.137894. https://doi.org/10.1016/j.scitotenv.2020.137894.

4. Mohammad Taghi Sattari, Anca Avram, Halit Apaydin, Oliviu Matei. (2020). Soil Temperature Estimation with Meteorological Parameters by Using Tree-Based Hybrid Data Mining Models. Mathematics, 8(9), p.1407. https://doi.org/10.3390/math8091407.

5. Maryam Bayatvarkeshi, Suraj Kumar Bhagat, Kourosh Mohammadi, Ozgur Kisi, M. Farahani, A. Hasani, Ravinesh Deo, Zaher Mundher Yaseen. (2021). Modeling soil temperature using air temperature features in diverse climatic conditions with complementary machine learning models. Computers and Electronics in Agriculture, 185, p.106158. https://doi.org/10.1016/j.compag.2021.106158.

6. Olufemi Abimbola, Aaron Mittelstet, Tiffany Messer, Elaine Berry, Ann van Griensven. (2020). Modeling and Prioritizing Interventions Using Pollution Hotspots for Reducing Nutrients, Atrazine and E. coli Concentrations in a Watershed. Sustainability, 13(1), p.103. https://doi.org/10.3390/su13010103.

7. S. Jebamalar, Jaslin J. Christopher, M. Angelina Thanga Ajisha. (2021). Random input based prediction and transfer of heat in soil temperature using artificial neural network. Materials Today: Proceedings, 45, p.1540. https://doi.org/10.1016/j.matpr.2020.08.091.


Dimensions

PlumX

Downloads

Download data is not yet available.

Article abstract page views

755