Prediction the inside variables of even-span glass greenhouse with special structure by artificial neural network (MLP-RBF) models

ماشین های کشاورزی

Article 8, Volume 10, Issue 2 - Serial Number 20, 2020, Pages 213-227   

Document Type: Research Article

DOI: 10.22067/jam.v10i2.72346

Authors

M. Hamdani¹; M. Taki¹; M. Rahnama^{* 1}; A. Rohani²; M. Rahmati-Joneidabad³

¹Department of Agricultural Machinery and Mechanization, Agricultural Sciences and Natural Resources University of Khuzestan ,Mollasani, Iran

²Department of Biosystems, Faculty of Agriculture, Ferdowsi University of Mashhad, Mashhad, Iran

³Department of Horticulture, Agricultural Sciences and Natural Resources University of Khuzestan, Mollasani, Iran

Abstract

Introduction
Controlling greenhouse microclimate not only influences the growth of plants, but is also critical in the spread of diseases inside the greenhouse. The microclimate parameters are inside air, roof, crop and soil temperature, relative humidity, light intensity, and carbon dioxide concentration. Predicting the microclimate conditions inside a greenhouse and enabling the use of automatic control systems are the two main objectives of greenhouse climate model. The microclimate inside a greenhouse can be predicted by conducting experiments or by using simulation. Static and dynamic models and also artificial neural networks (ANNs) are used for this purpose as a function of the metrological conditions and the parameters of the greenhouse components. Usually thermal simulation has a lot of problems to predict the inside climate of greenhouse and the error of simulation is higher in literature. So the main objective of this paper is comparison between two types of artificial neural networks (MLP and RBF) for prediction 4 inside variables in an even-span glass greenhouse and help the development of simulation science in estimating the inside variables of intelligent greenhouses.
Materials and Methods
In this research, different sensors were used for collecting the temperature, solar, humidity and wind data. These sensors were used in different positions inside the greenhouse. After collecting the data, two types of ANNs were used with LM and Br training algorithms for prediction the inside variables in an even-span glass greenhouse in Mollasani, Ahvaz. MLP is a feed-forward layered network with one input layer, one output layer, and some hidden layers. Every node computes a weighted sum of its inputs and passes the sum through a soft nonlinearity. The soft nonlinearity or activity function of neurons should be non-decreasing and differentiable. One type of ANN is the radial basis function (RBF) neural network which uses radial basis functions as activation functions. An RBF has a single hidden layer. Each node of the hidden layer has a parameter vector called center. This center is used to compare with the network input vector to produce a radially symmetrical response. Responses of the hidden layer are scaled by the connection weights of the output layer and then combined to produce the network output. There are many types of cross-validation, such as repeated random sub-sampling validation, K-fold cross-validation, K×2 cross-validation, leave-one-out cross-validation and so on. In this study, we pick up K-fold cross- validation for selecting parameters of model. The K-fold cross-validation is a technique of dividing the original sample randomly into K sub-samples. Different performance criteria have been used in literature to assess model’s predictive ability. The mean absolute percentage error (MAPE), root mean square error (RMSE) and coefficient of determination (R2) are selected to evaluate the forecast accuracy of the models in this study.
Results and Discussion
The results of neural networks optimization models with different networks, dependent on the initial random values of the synaptic weights. So, the results in general will not be the same in two different trials even if the same training data have been used. So in this research K-fold cross validation was used and different data samples were made for train and test of ANN models. The results showed that trainlm for both of MLP and RBF models has the lower error than trainbr. Also MLP and RBF were trained with 40 and 80% of total data and results indicated that RBF has the lowest sensitivity to the size data. Comparison between RBF and MLP model showed that, RBF has the lowest error for prediction all the inside variables in greenhouse (Ta, Tp, Tri, Rha). In this paper, we tried to show the fact that innovative methods are simple and more accurate than physical heat and mass transfer method to predict the environment changes. Furthermore, this method can use to predict other changes in greenhouse such as final yield, evapotranspiration, humidity, cracking on the fruit, CO₂ emission and so on. So the future research will focus on the other soft computing models such as ANFIS, GPR, Time Series and … to select the best one for modeling and finally online control of greenhouse in all climate and different environment.
Conclusion
This research presents a comparison between two models of Artificial Neural Network (RBF-MLP) to predict 4 inside variables (Ta, Tp, Tri, Rha) in an even-span glass greenhouse. Comparison of the models indicated that RBF has lower error. The range of RMSE and MAPE factors for RBF model to predict all inside variables were between 0.25-0.55 and 0.60-1.10, respectively. Besides the results showed that RBF model can estimate all the inside variables with small size of data for training. Such forecasts can be used by farmers as an appropriate advanced notice for changes in temperatures. Thus, they can apply preventative measures to avoid damage caused by extreme temperatures. More specifically, predicting a greenhouse temperature can not only provide a basis for greenhouse environmental management decisions that can reduce the planting risks, but also could be as a basic research for the feedback-feed-forward type of climate control strategy.

Keywords

Neural Network; Even-span greenhouse; Modeling; intelligent greenhouses

References

1. Ben Ali, R. E., M. Aridhi, and A. Mami. 2016. Fuzzy Logic Controller of temperature and humidity inside an agricultural greenhouse. IEEE Journals & Magazines.

2. Boaventura, L., C. Couto, and A. E. B. Ruano. 2000. A greenhouse climate multivariable predictive controller, Acta Horticulturae, ISHS 534: 269-276.

3. Bot G. P. A. 1983. Greenhouse Climate: From Physical Processes to a Dynamic Model. Ph.D. dissertation, Wageningen Agricultural University, Wageningen, The Netherlands, 240 pp.

4. Coelho, J. P., J. Boaventura, and P. B. Moura Oliveira. 2002. Solar radiation prediction methods applied to improve greenhouse climate control, in: World Congress of Computers in Agriculture and Natural Resources, 13-15 March. pp. 154-161.

5. Dariouchy, A., E. Aassif, K. Lekouch, L. Bouirden, and G. Maze. 2009. Prediction of the intern parameters tomato greenhouse in a semi-arid area using a time-series model of artificial neural networks. Measurement 42: 456-463.

6. Ehret, D., L. Hill, B. D. T. Helmer, and D. R. Edward. 2011. Neural network modeling of greenhouse tomato yield, growth and water use from automated crop monitoring data. Computers and Electronics in Agriculture 79: 82-89.

7. Falamarzi, Y., N. Palizdan, Y. F. Huang, and T. S. Lee. 2014. Estimating evapotranspiration from temperature and wind speed data using artificial and wavelet neural networks (WNNs). Agricultural Water Management 140: 26-36.

8. Feng, L. X., Q. L. Lin, M. G. Qi, and W. Gang. 2016. Modeling Greenhouse Temperature by Means of PLSR and BPNN. 35th Chinese Control Conference. July 27-29, Chengdu, China.

9. Ferreira, P. M., E. A. Faria, and A. E. Ruano. 2002. Neural network models in greenhouse air temperature prediction. Neurocomputing 43 (1-4): 51-75.

10. Gupta, R., G. N. Tiwari, G. N. Kumar, and Y. Gupta. 2012. Calculation of total solar fraction for different orientation of greenhouse using 3D-shadow analysis in Auto-CAD. Energy and Buildings 47: 27-34.

11. He, F., and C. Ma. 2010. Modeling greenhouse air humidity by means of artificial neural network and principal component analysis. Computers and Electronics in Agriculture 71S (2010): S19-S23.

12. Hill, J. 2006. Dynamic modeling and energy use in a nursery greenhouse. MSc thesis.

13. Lachouri, C. E., K. H. Mansouri, M. M. Lafifi, and A. Belmeguenai. 2016. Adaptive Neuro-Fuzzy Inference Systems for Modeling Greenhouse Climate. International Journal of Advanced Computer Science and Applications 7: 12-18.

14. Linker, R., and I. Seginer. 2004. Greenhouse temperature modeling: a comparison between sigmoid neural networks and hybrid models. Mathematics and Computers in Simulation 65: 19-29.

15. Manuel, A., R. Francisco, R. Armando, and B. Manuel. 2005. Discrete-time nonlinear FIR models with integrated variables for greenhouse indoor temperature simulation, in: Proceedings of the 44th IEEE Conference on Decision and Control, and the European Control Conference, CDC-ECC’05, pp. 4158-4162.

16. Rodriguez, J. D., A. Perez, and J. A. Lozano. 2010. A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceeding of the international joint conference on artificial intelligence, 32: 569-575.

17. Rohani, A., M. Taki, and M. Abdollahpour. 2018. A novel soft computing model (Gaussian process regression with K-fold cross validation) for daily and monthly solar radiation forecasting (Part: I). Renewable Energy 115: 411-422

18. Rohani, A., M. H. Abbaspour-Fard, and Sh. Abdolahpour. 2011. Prediction of tractor repair and maintenance costs using artificial neural network. Expert Sys. Applications 38: 8999-9007.

19. Sethi, V. P. 2009. On the selection of shape and orientation of a greenhouse: thermal modeling and experimental validation. Solar Energy 83: 21-38.

20. Sethi, V. P., and R. K. Dubey. 2008. Optimal space utilization of a greenhouse using multi-rack tray system: Thermal modeling and experimental validation. Energy Conversion and Management 49: 2890-2899.

21. Shukla, A., G. N. Tiwari, and M. S. Sodha. 2006. Thermal modeling for greenhouse heating by using thermal curtain and an earth–air heat exchanger. Building and Environment 41 (7): 843-850.

22. Singh, R. D., and G. N. Tiwari. 2010. Energy conservation in the greenhouse system: A steady state analysis. Energy 35: 2367-2373.

23. Taki, M., A. Rohani, M. Rahmati-Joneidabad. 2018b. Solar thermal simulation and applications in greenhouse. Information Processing in Agriculture 5: 83-113.

24. Taki, M., S. Abdanan Mehdizadeh, A. Rohani, M. Rahnama, and M. Rahmati-Joneidabad. 2018a. Applied machine learning in greenhouse simulation; new application and analysis. Information Processing in Agriculture, https://doi.org/10.1016/j.inpa.2018.01.003.

25. Taki, M., Y. Ajabshirchi, and A. Mahmoudi. 2012. Prediction of output energy for wheat production using artificial neural networks in Esfahan province of Iran. Journal of Agricultural Technology 8 (4): 1229-1242.

26. Taki, M., Y. Ajabshirchi, S. F. Ranjbar, A. Rohani, and M. Matloobi. 2017. Evaluation of heat transfer mathematical models and multiple linear regression to predict the inside variables in semi-solar greenhouse. Journal of Agricultural Machinery 7 (1): 2014-220. (In Farsi).

27. Taki, M., Y. Ajabshirchi, S. F. Ranjbar, A. Rohani, and M. Matloobi. 2016. Heat transfer and MLP neural network models to predict inside environment variables and energy lost in a semi-solar greenhouse. Energy and Buildings 110: 314-329.

28. Vadiee, A., and V. Martin. 2013. Energy analysis and thermo economic assessment of the closed greenhouse – The largest commercial solar building. Applied Energy http://dx.doi.org/10.1016/j.apenergy.2013.06.051.

29. Van Ooteghem, R. J. C. 2007. Optimal Control Design for a Solar Greenhouse, Systems and Control. Wageningen: Wageningen University.

30. Van Straten, G., G. Van Willigenburg, E. Van Henten, and R. Van Oothghem. 2011. Optimal control of greenhouse cultivation. CRC press, Taylor and Francis, New York.