Time-serial analysis of deep neural network models for prediction of climatic conditions inside a greenhouse

Abstract Greenhouses provide controlled environmental conditions for crop cultivation but require careful management to ensure ideal growing conditions. In this study, we tested three deep-learning-based neural network models (Artificial neural network, ANN; Nonlinear autoregressive exogenous model, NARX; and Recurrent neural networks – Long short-term memory, RNN-LSTM) to determine the best approach to predicting environmental changes in temperature, humidity, and CO2 within a greenhouse to improve management strategies. This study determined the prediction performance for time steps from 5 to 30 min and showed that the accuracy of the time-based algorithm gradually decreased as prediction time increased. The best model for all datasets was RNN-LSTM, even after 30 min, with an R2 of 0.96 for temperature, 0.80 for humidity, and 0.81 for CO2 concentration. The results of this study show that it is possible to apply deep-learning-based prediction models for more precisely managing greenhouse.

[1]  Carman K.M. Lee,et al.  A Comparison between Neural Networks and Traditional Forecasting Methods: A Case Study , 2009 .

[2]  Baihai Zhang,et al.  Modeling and simulation of a solar greenhouse with natural ventilation based on error optimization using fuzzy controller , 2016, CCC 2016.

[3]  Tarik Kousksou,et al.  Review on greenhouse microclimate and application: Design parameters, thermal modeling and simulation, climate controlling technologies , 2019, Solar Energy.

[4]  Andrew W. Senior,et al.  Long short-term memory recurrent neural network architectures for large scale acoustic modeling , 2014, INTERSPEECH.

[5]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[6]  Jaeyoung Choi,et al.  Fusion of Spectroscopy and Cobalt Electrochemistry Data for Estimating Phosphate Concentration in Hydroponic Solution , 2019, Sensors.

[7]  Jung Eek Son,et al.  Forecasting Root-Zone Electrical Conductivity of Nutrient Solutions in Closed-Loop Soilless Cultures via a Recurrent Neural Network Using Environmental and Cultivation Information , 2018, Front. Plant Sci..

[8]  Fathi Fourati,et al.  A greenhouse control with feed-forward and recurrent neural networks , 2007, Simul. Model. Pract. Theory.

[9]  Da-Wen Sun,et al.  Applications of computational fluid dynamics (CFD) in the modelling and design of ventilation systems in the agricultural industry: a review. , 2007, Bioresource technology.

[10]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[11]  Jorge Antonio Sánchez-Molina,et al.  Virtual Sensors for Designing Irrigation Controllers in Greenhouses , 2012, Sensors.

[12]  Chengwei Ma,et al.  Modeling greenhouse air humidity by means of artificial neural network and principal component analysis , 2010 .

[13]  Saroj Kumar Pandey,et al.  Recent Deep Learning Techniques, Challenges and Its Applications for Medical Healthcare System: A Review , 2019, Neural Processing Letters.

[14]  R. W. McClendon,et al.  Methods for Optimal Control of the Greenhouse Environment , 1992 .

[15]  K. Hasan,et al.  Comparative study of wavelet-ARIMA and wavelet-ANN models for temperature time series data in northeastern Bangladesh , 2017 .

[16]  Andreas Kamilaris,et al.  Deep learning in agriculture: A survey , 2018, Comput. Electron. Agric..

[17]  H.-J. Tantau,et al.  Non-linear constrained MPC: Real-time implementation of greenhouse air temperature control , 2005 .

[18]  E. Fitz-Rodríguez,et al.  Neural network predictive control in a naturally ventilated and fog cooled greenhouse , 2012 .

[19]  Alejandro Castaeda-Miranda,et al.  Smart frost control in greenhouses by neural networks models , 2017 .

[20]  L. Bouirden,et al.  Prediction of the intern parameters tomato greenhouse in a semi-arid area using a time-series model of artificial neural networks , 2009 .

[21]  Francisco Rodríguez,et al.  Evaluation of event-based irrigation system control scheme for tomato crops in greenhouses , 2017 .

[22]  Hongmin Li,et al.  Research and application of a combined model based on variable weight for short term wind speed forecasting , 2018 .

[23]  Qian Zhang,et al.  Attention-based recurrent neural networks for accurate short-term and long-term dissolved oxygen prediction , 2019, Comput. Electron. Agric..

[24]  Marcelo Teixeira,et al.  Generating action plans for poultry management using artificial neural networks , 2019, Comput. Electron. Agric..

[25]  Gurpreet Singh,et al.  Formulation and validation of a mathematical model of the microclimate of a greenhouse , 2006 .

[26]  M. Berenguel,et al.  Leaf area index estimation for a greenhouse transpiration model using external climate conditions based on genetics algorithms, back-propagation neural networks and nonlinear autoregressive exogenous models , 2017 .

[27]  Stefano Benni,et al.  Efficacy of greenhouse natural ventilation: Environmental monitoring and CFD simulations of a study case , 2016 .

[28]  Luiz Augusto da Cruz Meleiro,et al.  ANN-based soft-sensor for real-time process monitoring and control of an industrial polymerization process , 2009, Comput. Chem. Eng..