Applying Hybrid Models Based on Deep Machine Learning in Smart Agriculture (Case study: Forecasting the Future Price of Pistachios)

Document Type : Research Article

Authors

• M.R. Haj-Seyedjavadi ¹
• R. Heydari ²

¹ Researcher, Agricultural Planning, Economics and Rural Development Research Institute (APERDRI), Tehran, Iran

² Agricultural Planning, Economics and Rural Development Research Institute (APERDRI), Tehran, Iran

https://doi.org/10.22067/jead.2023.79545.1165

Abstract

Introduction
The agricultural sector is one of the most basic and vital component in the social and economic structures of any country. Today, with increasing in the world's population and needing to provide food on the other hand, and increasing in the price fluctuations of agricultural products on the other hand, traditional agriculture is no longer responsible for the sustainable food security of the world population. In recent years, the occurrence of two incidents of the spread of the corona virus and the outbreak of war in Ukraine, have made the price of agricultural products extremely unstable. Today, even many farmers and agricultural associations in developing countries are not aware of the changes in market prices and the latest technological developments in the field of agricultural product prices, and they do not have the ability to discover the optimal price for selling their products. In such a situation, the use of intelligent models in order to accurately forecast the price of agricultural goods is vitally important for farmers and agricultural sector activists.
Smart agriculture is an emerging concept that involves the integration of advanced technologies to collect and analyze data in order to solve the challenges and problems of the agricultural sector. In the meantime, forecasting the price of agricultural products involves with some basic challenges; including: 1) Data of agricultural product price is mostly non-linear, unstable, non-normal, and noisy and follows chaotic behavior, 2) There is uncertainty in the forecasted data obtained from different models, 3) In the studies related to price forecasting, the "publishable base model" is not provided in order to provide the forecasted price values. Therefore, the aim of this study is to provide a non-linear hybrid intelligent model for accurate forecasting of the future price of pistachios in the field of smart agriculture through managing the multidimensional nature of data, considering uncertainty in the forecasting data and finally building a publishable base model in the field of product price prediction.
The hybrid model proposed in this study has the following innovations; 1) the deep learning neural network model and the Auto-Encoder network have been used to forecast the agricultural product price and determine the optimal lag of price as an input variable simultaneously, 2) The Monte Carlo method has been used as a non-parametric method to provide a confidence interval and calculate the most likely price that can happen, 3) The practical application of price forecasting models, i.e., "publishable base model" is presented in order to provide forecasted price values.
 
 
Materials and Methods
The implementation of the proposed hybrid model in this study includes the steps of "data preparation", "data feature engineering", "training and testing the final deep learning neural network model", "building the optimal base model", "creating the most likely price scenarios" using the Monte Carlo method and "inferring new prices or making out-of-sample forecasting" with new data sets” by feeding new price data into the deep learning neural network model. In the proposed hybrid model, data mining techniques are used, including Wavelet Transform (WT), Long-Short Term Memory (LSTM), Auto-Encoder network (AE), Monte Carlo-Markov chain (MCMC) simulation method and the concept of "inferring new prices".
In the data preparation stage, using methods such as data smoothing, data rebuilding, correction of duplicate data in several consecutive days, and correction of missing data, the continuous set of pistachio future price time series is prepared to enter the primary model. Also, the wavelet transform function has been used for de-noising the data, the Auto-Encoder network has been used to determine the optimal lag, the Monte Carlo-Markov chain simulation has been used to create the most probable price scenarios, and the deployment concept has been used for out-of-sample forecasting with new data sets. The data used in this study is the time series of the daily price of pistachio futures on the Iran Commodity Exchange in the period from 10/13/2019 to 12/14/2021 in Rials per kilogram.
 
Results and Discussion
The results of this study showed that 1) by using the wavelet theory to de-noise the data, the error rate of the price data was reduced and the data had a stable trend, 2) the results of the implementation of the Auto-Encoder network showed that the optimal lag of one can be used as an input variable to forecast the future price of pistachios, 3) The outcomes derived from employing Monte Carlo-Markov chain simulation, coupled with out-of-sample forecasting using the new dataset, reveal compelling insights into the future pricing of pistachios on the Iranian Commodity Exchange. According to the analysis, the most probable and sanguine projection places the future price at the price ceiling of 213 thousand Tomans. Impressively, the forecasted price exhibits a minimal variance of merely 0.7% from the actual observed price, attesting to the precision of the proposed model. The overall accuracy of the model stands commendably high at approximately 93%.
 
Conclusion
Based on the results, firstly, the forecasted price has a small error with the actual price and this small error shows the power of the built model in forecasting the future price trend of pistachios. Secondly, the alignment of the price resulting from the Monte Carlo simulation with the new price can also be used as a confidence index in risk management for traders and market participants. Thirdly, the process set is the most complete value chain in the production of price forecasting models. Therefore, the use of the proposed hybrid model and the use of the components used in it, i.e. wavelet transform function, Auto-Encoder network, deep learning neural network, Monte Carlo simulation and the concept of inferring new prices; are suggested.

Keywords

• Datamining
• Deep learning neural network
• Future price forecast
• Monte Carlo-Markov chain
• Wavelet theory

Main Subjects

• Agricultural Economics

References

1. Akhbari, M. (2018). Project time and cost forecasting using Monte Carlo simulation and artificial neural networks. International Journal of Industrial Engineering and Production Research, 29(2), 231-239. http://doi.org/10.22068/ijiepr.29.2.223
2. Anjoy, P., & Paul, R.K. (2017). Wavelet based hybrid approach for forecasting volatile potato price. Journal of the Indian Society of Agricultural Statistics, 71(1), 7-14. http://www.isas.org.in/jsp/volume/vol/
3. Aworka, R., Cedric, L.S., Hamilton Adoni, W.Y., Zoueu, J.T., Mutombo, F.K., Mberi Kimpolo, Ch. L., Nahhal, T., & Krichen, M. (2022). Agricultural decision system based on advanced machine learning models for yield prediction: Case of East African countries. Journal of Smart Agricultural Technology, 2 100048, 1-9. http://doi.org/10.1016/j.atech.2022.100048
4. Cemgil, A.T. (2014). A tutorial introduction to Monte Carlo methods, Markov Chain Monte Carlo and particle filtering. Academic press library in signal processing, 1: 1065-1114, ISBN: 978-0-12- 396502-8. http://doi.org/10.1016/B978-0-12-396502-8.00019-X
5. David, A., & Spade, D.A. (2020). Markov chain Monte Carlo methods: theory and practice. Handbook of Statistics, 43. http://doi.org/10.1016/bs.host.2019.06.001
6. Ebrahimi, M., Talebnia, Gh., Vakilifard, H.R., & Nikuomaram, H. (2017). Application of Monte Carlo simulation - Markov chain in explaining working capital management strategy. Iranian Journal Quarterly Financial Accounting, 9(33), 1-22. (In Persian with English abstract)
7. Gao, R., Du, L., Duru, O., & Yuen, K.F. (2021). Time series forecasting based on echo state network and empirical wavelet transformation. Journal of Applied Soft Computing, 102, 107111. http://doi.org/10.1016/j.asoc.2021.107111
8. Ghaderzadeh, H., Ahmadzadeh, Kh., & Ganji, S. (2019). Determine the appropriate model to predict the price of Agricultural crops: A case of wheat, Alfa-Alfa and Potato crops. Iranian Journal of Agricultural Economics Research, 11(3), 23-40. (In Persian with English abstract)
9. Ghahremanzadeh, M., & Rashid Ghalam, M. (2015). Seasonal forecasting of meat prices in Iran: Application of periodic autoregressive model. Iranian Journal of Agricultural Economics and Development Research, 46(3), 469-480. https://doi.org/10.22059/ijaedr.2015.55520
10. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. https://www.amazon.com/
11. Greff, K., Srivastava, R.K., & Koutnik, J., Steunebrink, B.R., & Schmidhuber, J. (2017). LSTM: A Search Space Odyssey. IEEE Transactions on Neural Networks and Learning Systems, 28(10): 2222-2232. http://doi.org/10.48550/arXiv.1503.04069
12. Guo, L., & Wozniak, M. (2021). An image super-resolution reconstruction method with single frame character based on wavelet neural network in internet of things. Journal of Mobile Networks and Applications, 26, 390-403. http://doi.org/10.1007/s11036-020-01681-6.
13. Haj Seyed Javady, M.R., & Heydari, R. (2022). Designing the most suitable hybrid model for forecasting the future price of saffron in the agricultural commodity bourse. Iranian Journal of Agricultural Economics and Development Research, 53-2(4), 1023-1041. http://doi.org/10.22059/IJAEDR.2022.336850.669122
14. Haviluddin, S., Khosyi, T., & et (2021). A backpropagation neural network algorithm in agricultural product prices prediction. 3rd East Indonesia Conference on Computer and Information Technology (EIConCIT), ISTTS Surabaya, Indonesia. http://doi.org/10.1109/EIConCIT50028.2021.9431897
15. Hegde, J., Hulipalled, V.R., & Simha, J.B. (2021). Price prediction of agriculture commodities using machine learning and NLP. Second International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE 2021), http://doi.org/10.1109/ICSTCEE54422.2021.9708582
16. Heydari, R., & Haj Seyed Javady, M.R. (2022). The application of hybrid data mining model (genetic algorithm-wavelet-deep neural network-Monte Carlo method) for the price forecasting of agricultural products (Case study: future price of saffron in agricultural commodity exchange). Iranian Journal of Agricultural economics and Development, 30(120), 73-105. http://doi.org/10.30490/AEAD.2023.357440.1412
17. Hirapara, J., & Vanjara, D. (2022). A comparative study of data mining techniques for agriculture crop price prediction. 7^th International conference for Convergence in Technology (I2CT), Pune, India. Apr 2022, 1-6. http://doi.org/10.1109/I2CT54291.2022.982453
18. Hogg, D.W., & Foreman-Mackey, D. (2018). Data analysis recipes: using Markov chain Monte Carlo. The Astrophysical Journal Supplement Series, 236(1), 1-54. http://doi.org/10.3847/1538-4365/aab76e
19. Hoseini, S.M., Mazandarani zadeh, , & Nazari, B. (2021). Simultaneously management of surface and groundwater resources and increasing farmers' resilience to water scarcity by predicting the price of agricultural products and using GA (case study of irrigation and drainage network of Qazvin plain). Iranian Journal of Soil and Water Research, 52(2), 563-576. https://doi.org/10.22059/ijswr.2021.313809.668805
20. Joshi, A.M., & Patel, S. (2022). A CNN-Bidirectional LSTM approach for price forecasting of agriculture commodities in Gujarat. The International Conference on Applied Artificial Intelligence and Computing (ICAAIC 2022), 266-272. http://doi.org/10.1109/ICAAIC53929.2022.9793154
21. Kamilaris, A., Francesc, X., & Boldu, P. (2018). Deep learning in agriculture: A survey. Journal of Computers and Electronics in Agriculture, 147, 70-90. http://doi.org/10.1016/j.compag.2018.02.016
22. Karakoyun, E.S., & Cibikdiken, A.O. (2018). Comparison of ARIMA time series model and lstm deep learning algorithm for bitcoin price forecasting. The 13^th Multidisciplinary Academic conference in Prague (the 13^th MAC 2018).
23. Li, J., & Wang, J. (2020). Stochastic recurrent wavelet neural network with EEMD method on energy price prediction. Journal of Soft Computing, 24, 17133-17151. https://doi.org/10.1007/s00500-020-05007-2
24. Li, P., Hua, P., Gui, D., Niu, J., Pei, P., Zhang, J., & Krebs, P. (2020). A comparative analysis of artificial neural networks and wavelet hybrid approaches to long-term toxic heavy metal prediction. Journal of Scientific Reports, 10, 13439. http://doi.org/10.1038/s41598-020-70438-8
25. Liu, J.; Xu, L., Cao, X., Zhang, K., Zhang, Q., & Cai, Y. (2020). Review on the architectures and applications of deep learning in agriculture. 7^th International Conference on Information Science and Control Engineering (ICISCE), 1234-1240. http://doi.org/10.1109/ICISCE50968.2020.00250
26. Liu, X., Liu, H., Guo, Q., & Zhang, C. (2020). Adaptive wavelet transform model for time series data prediction. Journal of Soft Computing, 24, 5877-5884. http://doi.org/10.1007/s00500-019-04400-w
27. Maiti, S., & Tiwari, R.K. (2009). A hybrid Monte Carlo method based artificial neural networks approach for rock boundaries identification: a case study from the KTB Bore Hole. Journal of Pure and Applied Geophysics, 166, 2059-2090. http://doi.org/ 10.1007/s00024-009-0533-y
28. Mehtab, S., Sen, J., & Dutta, A. (2021). Stock price prediction using machine learning and LSTM-based deep learning models. Machine Learning and Metaheuristics Algorithms, and Applications, 88-106. Springer, http://doi.org/10.1007/978-981-16-0419-5_8
29. Mitra, D., & Paul, R.K. (2020). Forecasting of price of rice in India using long-memory time series model. Springer: National Academy Science Letters, 44, 289-293. http://doi.org/10.1007/s40009-020-01002-1
30. Moghadasi, R., & Jaleh Rajabi, M. (2013). Comparison of combined and conventional models in forecasting prices of wheat, corn and sugar. Iranian Journal of Agricultural Economics Research, 5(2), 1-22. (In Persian with English abstract)
31. Nassar, L., Okwuchi, I.E., Saad, M., Karray, F., & Ponnambalam, K. (2020). Deep learning based approach for fresh produce market price prediction. In 2020 International Joint Conference on Neural Networks (IJCNN) (pp. 1-7). IEEE. http://doi.org/10.1109/IJCNN48605.2020.9207537
32. North, M. (2012). Data Mining for the Masses. https://www. Amazon.com. https://docs.rapidminer.com.
33. Pablo, B. J., Hilda, C., & et al. (2016). Artificial neural network and Monte Carlo simulation in a hybrid method for time Series forecasting with generation of L-scenarios. 2016 Intl IEEE Conferences on Ubiquitous Intelligence and Computing, Advanced and Trusted Computing, Scalable… (UIC/ATC/ScalCom/CBDCom/IoP/SmartWorld). http://doi.org/10.1109/UIC-ATC-ScalCom-CBDCom-IoP-SmartWorld.2016.0110
34. Paul, R.K., Paul, A.K., & Bhar, L.M. (2020). Wavelet-based combination approach for modeling sub-divisional rainfall in India. Journal of Theoretical and Applied Climatology, 139(3-4), 949-963. http://doi.org/10.1007/s00704-019-03026-0
35. Paul, R.K. (2015). ARIMAX-GARCH-WAVELET model for forecasting volatile data. Journal of Model Assisted Statistics and Applications, 10(3), 243–252. http://doi.org/10.3233/MAS-150328
36. Paul, R.K., & Garai, S. (2021). Performance comparison of wavelets-based machine learning technique for forecasting agricultural commodity prices. Journal of Soft Computing, 25, 12857 12873. http://doi.org/10.1007/s00500-021-06087-4
37. Pourreza Bilondi, M., & Khashei Siuki, A. (2015). Uncertainty analysis of artificial neural networks in simulation of saturated hydraulic conductivity using Monte-Carlo simulation. Iranian Journal of Irrigation and Drainage, 4(9), 655-664. (In Persian with English abstract)
38. Raflesia, S.P., Taufiqurrahman, T., Iriyani, S., & Lestarini, D. (2021). Agricultural commodity price forecasting using PSO-RBF neural network for farmers exchange rate improvement in Indonesia. Indonesian Journal of Electrical Engineering and Informatics, 9(3), 784-792. http://doi.org/10.52549/ijeei.v9i3.2723
39. RapidMiner Manual. (2021). Deployments. https://docs.rapidminer.com.
40. Rasheed, A., Younis, S., Ahmad, F., Qadir, J., & Kashif, M. (2022). District wise price forecasting of wheat in Pakistan using deep learning. Journal of arXiv-CS-Artificial Intelligence. http://doi.org/arxiv-2103.04781
41. Roondiwala, M., Patel, H., & Varma, Sh. (2017). Predicting stock prices using LSTM. International Journal of Science and Research, 6(4): 1753-1756.
42. Sabu, K.M., & Kumar, T.M. (2020). Predictive analytics in agriculture: forecasting prices of Arecanuts in Kerala. Journal of Procedia Computer Science, 171, 699-708. http://doi.org/1016/j.procs.2020.04.076
43. Samek, W., Wiegand, T., & Muller, K. R. (2017). Explainable artificial intelligence: Understanding, visualizing and interpreting deep learning models. arXiv preprint arXiv:1708.08296. http://doi.org/10.48550/arXiv.1708.08296
44. Shabri, A., & Samsudin, R. (2014). Daily crude oil price forecasting using hybridizing wavelet and artificial neural network model. Hindawi Publishing Corporation Mathematical Problems Engineering, Volume 2014, Article ID 201402, 10 pages. http://doi.org/10.1155/2014/201402
45. Sharma, A.K., & Rajawat, A.S. (2022). Crop yield prediction using hybrid deep learning algorithm for smart agriculture. The Second International Conference on Artificial Intelligence and Smart Energy (ICAIS-2022), http://doi.org/10.1109/ICAIS53314.2022.9743001
46. Siami Namini, S., & Siami Namin, K. (2018). Forecasting economics and financial time series: ARIMA vs. LSTM. arXiv preprint arXiv:1803.06386. http://doi.org/10.48550/arXiv.1803.06386
47. Speagle, J. (2020). A conceptual introduction to Markov chain Monte Carlo methods. arXiv:1909.12313. http://doi.org/10.48550/arXiv.1909.12313
48. Tohidi, A. (2015). Evaluation of artificial neural network-panel data hybrid model in predicting Iran’s dried fruits export prices. Quarterly Journal of Economics Quarterly, 12(3), 95-116. (In Persian with English abstract)
49. Vohra, A., Pandey, N., & Khatri, S.K. (2019). Decision making support system for prediction of Prices in agricultural commodity. International Conference on Artificial Intelligence (AICAI 2019), Dubai (United Arab Emirates), 345-348. http://doi.org/10.1109/AICAI.2019.8701273
50. Wang, J., & Li, X. (2018). A combined neural network model for commodity price forecasting with SSA. Journal of Soft Computing, 22, 5323-5333.
51. Wang, J., et al. (2018). Gaussian Process Kernels for Noisy Time Series: Application to Housing Price Prediction. International Conference on Neural Information Processing. Springer, Cham. http://doi.org/10.1007/978-3-030-04224-0_8
52. Wen, Y., Lin, P., & Nie. X. (2020). Research of stock price prediction based on PCA-LSTM model. IOP Conf. Series: Materials Science and Engineering 790 (2020) 012109. http://doi.org/10.1088/1757-899X/790/1/012109.
53. Weston, J., Elisseeff, A., & Scholkopf, B. (2003). Use of zero-norm with linear models and kernel methods. Journal of Machine Learning Research, 3(5), 1439-1461.
54. Wojtas, M.A., & Chen, K. (2020). Feature importance ranking for deep learning. 34^th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada, 5105–5114. http://doi.org/10.5555/3495724.3496153
55. Wu, D., Wang, X., & Wu, S. (2021). A hybrid method based on extreme learning machine and wavelet transform de-noising for stock prediction. Journal of Entropy, 23(4), 440. http://doi.org/10.3390/e23040440.
56. Iran Mercantile Exchange. (2022). https://www.ime.co.ir.