A Novel Machine Learning Approach: Soil Temperature Ordinal Classification (STOC)

Abstract

Soil temperature prediction is an important task since soil temperature plays an important role in agriculture and land use. Although some progress has been made in this area, the existing methods provide a regression or nominal classification task. However, ordinal classification is yet to be explored. To bridge the gap, this paper proposes a novel approach: Soil Temperature Ordinal Classification (STOC), which considers the relationships between the class labels during soil temperature level prediction. To demonstrate the effectiveness of the proposed approach, the STOC method using five different traditional machine learning methods (Decision Tree, Naive Bayes, K-Nearest Neighbors, Support Vector Machines, and Random Forest) was applied on daily values of meteorological and soil data obtained from 16 stations in three states (Utah, Alabama, and New Mexico) of United States at five soil depths (2, 4, 8, 20, and 40 inches) between the years of 2011 and 2020. The experiments show that the proposed STOC approach is an efficient method for soil temperature level (very low, low, medium, high, and very high) prediction. The applied STOC models (STOC.DT, STOC.NB, STOC.KNN, STOC.SVM, and STOC.RF) showed average accuracy rates of 90.95%, 77.09%, 90.84%, 89.94%, and 90.91% on the experimental datasets, respectively. It was observed from the experimental results that the STOC.DT method achieved the best soil temperature level prediction among the others.

Keywords

• agriculture
• classification
• decision tree
• machine learning
• random forest
• soil temperature level

References

1. Abimbola O P, Meyer G E, Mittlstet A R, Rudnick D R & Franz T E (2021). Knowledge-guided machine learning for improving daily soil temperature prediction across the United States. Vadose Zone Journal e20151: 1-18 https://doi.org/10.1002/vzj2.20151
2. Abyaneh H Z, Varkeshi M B, Golmohammadi G & Mohammadi K (2016). Soil temperature estimation using an artificial neural network and co-active neuro-fuzzy inference system in two different climates. Arabian Journal of Geosciences 9(2016): 1-9 https://doi.org/10.1007/s12517-016-2388-8
3. Alizamir M, Kim S, Kermani M Z, Heddam S, Shahrabadi A H & Gharabaghi B (2020b). Modelling daily soil temperature by hydro‑meteorological data at different depths using a novel data‑intelligence model: deep echo state network model. Artificial Intelligence Review 102: 1-28 https://doi.org/10.1007/s10462-020-09915-5
4. Alizamir M, Kisi O, Ahmed A N, Mert C, Fai C M, Kim S, Kim N W & Shafie A E (2020a). Advanced machine learning model for better prediction accuracy of soil temperature at different depths. PLOS ONE 15(4): 1-25 https://doi.org/10.1371/journal.pone.0231055
5. Bayatvarkeshi M, Bhagat S K, Mohammadi K, Kisi O, Farahani M, Hasani A, Deo R & Yaseen Z M (2021). Modeling soil temperature using air temperature features in diverse climatic conditions with complementary machine learning models. Computers and Electronics in Agriculture 185: 1-15 https://doi.org/10.1016/j.compag.2021.106158
6. Bonakdari H, Moeeni H, Ebtehaj I, Zeynoddin M, Mahoammadian A & Gharabaghi B (2019). New insights into soil temperature time series modeling: linear or nonlinear? Theoretical and Applied Climatology 135: 1157-1177 https://doi.org/10.1007/s00704-018-2436-2
7. Citakoglu H (2017). Comparison of artificial intelligence techniques for prediction of soil temperatures in Turkey. Theoretical and Applied Climatology 130: 545-556 https://doi.org/10.1007/s00704-016-1914-7
8. Delbari M, Sharifazari S & Mohammadi E (2019). Modeling daily soil temperature over diverse climate conditions in Iran—a comparison of multiple linear regression and support vector regression techniques. Theoretical and Applied Climatology 135: 991-1001 https://doi.org/10.1007/s00704-018-2370-3

9. Feng Y, Cui N, Hao W, Gao L & Gong D (2019). Estimation of soil temperature from meteorological data using different machine learning models. Geoderma 338(2019): 67-77 https://doi.org/10.1016/j.geoderma.2018.11.044
10. Frank E & Hall M (2001). A simple approach to ordinal classification. In: European Conference on Machine Learning 3-5 September, Freiburg, Germany, pp. 145-156 https://doi.org/10.1007/3-540-44795-4_13
11. Hao H, Yu F & Li Q (2020). Soil temperature prediction using convolutional neural network based on ensemble empirical mode decomposition. IEEE Access 9: 4084-4096 https://doi.org/10.1109/ACCESS.2020.3048028
12. Jiang L, Yuan P, Zhang Q & Liu Q (2020). A study of the Naive Bayes classification based on the Laplacian matrix. International Journal of Computer Science 47:4 713-722
13. Kisi O, Tombul M & Kermani M Z (2015). Modeling soil temperatures at different depths by using three different neural computing techniques. Theoretical and Applied Climatology 121: 377-387 https://doi.org/10.1007/s00704-014-1232-x
14. Li C, Zhang Y & Ren X (2020a). Modeling hourly soil temperature using deep BiLSTM neural network. Algorithms 13(7): 173-187 https://doi.org/10.3390/a13070173
15. Li Q, Hao H, Zhao Y, Ceng Q, Liu G, Zhang Y & Yu F (2020b). GANs-LSTM model for soil temperature estimation from meteorological: A new approach. IEEE Access 9: 59427-59443 https://doi.org/10.1109/ACCESS.2020.298299
16. Li Q, Zhao Y & Yu F (2020c). A novel multichannel long short-term memory method with time series for soil temperature modeling. IEEE Access 8: 182026-182043 https://doi.org/10.1109/ACCESS.2020.3028995
17. Mehdizadeh S, Behmanesh J & Khalili K (2018). Comprehensive modeling of monthly mean soil temperature using multivariate adaptive regression splines and support vector machine. Theoretical and Applied Climatology 133: 911-924 https://doi.org/10.1007/s00704-017-2227-1
18. Mehdizadeh S, Fathian F, Safari M J & Khosravi A (2020). Developing novel hybrid models for estimation of daily soil temperature at various depths. Soil & Tillage Research 197(2020): 1-12 https://doi.org/10.1016/j.still.2019.104513
19. Mim F S, Galib S M, Hasan M F & Jerin S A (2018). Automatic detection of mango ripening stages – An application of information technology to botany. Scientia Horticulturae 237: 156-163 https://doi.org/10.1016/j.scienta.2018.03.057
20. Nanda A, Sen S, Sharma A N & Sudheer K P (2020). Soil temperature dynamics at Hillslope scale—field observation and machine learning-based approach. Water 12(2020): 713-734 https://doi.org/10.3390/w12030713
21. Onwuka B & Mang B (2018). Effects of soil temperature on some soil properties and plant growth. Advances in Plants & Agriculture Research 8(1): 34-37 https://doi.org/10.15406/apar.2018.08.00288
22. Penghui L, Ewees A A, Beyaztas B H, Qi C, Salih S Q, Al-Ansari N, Bhagat S K, Yaseen Z M & Singh V P (2020). Metaheuristic optimization algorithms hybridized with artificial intelligence model for soil temperature prediction: Novel model. IEEE Access 8: 51884-51904 https://doi.org/10.1109/ACCESS.2020.2979822
23. Sanikhani H, Deo R C, Yaseen Z M, Eray O & Kisi O (2018). Non-tuned data intelligent model for soil temperature estimation: A new approach. Geoderma 330(2016): 52-64 https://doi.org/10.1016/j.geoderma.2018.05.030
24. Sattari M T, Avram A, Apaydin H & Matei O (2020). Soil temperature estimation with meteorological parameters by using tree-based hybrid data mining models. Mathematics 8(9): 1-21 https://doi.org/10.3390/math8091407
25. Shamshirband S, Esmaeilbeiki F, Zarehaghi D, Neyshabouri M, Samadianfard S, Ghorbani M A, Mosavi A, Nabipour N & Chau K W (2020). Comparative analysis of hybrid models of firefly optimization algorithm with support vector machines and multilayer perceptron for predicting soil temperature at different depths. Engineering Applications of Computational Fluid Mechanics 14(1): 939-953 https://doi.org/10.1080/19942060.2020.1788644
26. Tsai Y Z, Hsu K S, Wu H Y, Lin S I, Yu H L, Huang K T, Hu M C & Hsu S Y (2020). Application of random forest and ICON models combined with weather forecasts to predict soil temperature and water content in a greenhouse. Water 12(4): 1-23 https://doi.org/10.3390/w12041176
27. Wang X, Li W & Li Q (2021). A new embedded estimation model for soil temperature prediction. Scientific Programming 2021: 1-16 https://doi.org/10.1155/2021/5881018
28. Witten I H, Frank E, Hall M A & Pal C J (2016). Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann Publishers, Cambridge, MA, USA https://doi.org/10.1016/C2009-0-19715-5
29. Xing L, Li L, Gong J, Ren C, Liu J & Chen H (2018). Daily soil temperatures predictions for various climates in United States using data-driven model. Energy 160(2018): 430-440 https://doi.org/10.1016/j.energy.2018.07.004
30. Zeynoddin M, Ebtehaj I & Bonakdari H (2020). Development of a linear based stochastic model for daily soil temperature prediction: One step forward to sustainable agriculture. Computers and Electronics in Agriculture 176(2020): 1-24 https://doi.org/10.1016/j.compag.2020.105636