Forecasting Root-Zone Electrical Conductivity of Nutrient Solutions in Closed-Loop Soilless Cultures via a Recurrent Neural Network Using Environmental and Cultivation Information

In existing closed-loop soilless cultures, nutrient solutions are controlled by the electrical conductivity (EC) of the solution. However, the EC of nutrient solutions is affected by both growth environments and crop growth, so it is hard to predict the EC of nutrient solution. The objective of this study was to predict the EC of root-zone nutrient solutions in closed-loop soilless cultures using recurrent neural network (RNN). In a test greenhouse with sweet peppers (Capsicum annuum L.), data were measured every 10 s from October 15 to December 31, 2014. Mean values for every hour were analyzed. Validation accuracy (R2) of a single-layer long short-term memory (LSTM) was 0.92 and root-mean-square error (RMSE) was 0.07, which were the best results among the different RNNs. The trained LSTM predicted the substrate EC accurately at all ranges. Test accuracy (R2) was 0.72 and RMSE was 0.08, which were lower than values for the validation. Deep learning algorithms were more accurate when more data were added for training. The addition of other environmental factors or plant growth data would improve model robustness. A trained LSTM can control the nutrient solutions in closed-loop soilless cultures based on predicted future EC. Therefore, the algorithm can make a planned management of nutrient solutions possible, reducing resource waste.

[1]  Kuldip K. Paliwal,et al.  Capturing non‐local interactions by long short‐term memory bidirectional recurrent neural networks for improving prediction of protein secondary structure, backbone angles, contact numbers and solvent accessibility , 2017, Bioinform..

[2]  J. L. Bot,et al.  Impacts of N-deprivation on the yield and nitrogen budget of rockwool grown tomatoes , 2001 .

[3]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[4]  Davood Toghraie,et al.  Designing an artificial neural network to predict dynamic viscosity of aqueous nanofluid of TiO2 using experimental data , 2016 .

[5]  Sebastian Engell,et al.  Model Predictive Control Using Neural Networks [25 Years Ago] , 1995, IEEE Control Systems.

[6]  Tomislav Bolanča,et al.  Modeling of policies for reduction of GHG emissions in energy sector using ANN: case study—Croatia (EU) , 2017, Environmental Science and Pollution Research.

[7]  Juan Ignacio Montero,et al.  Evaluation and modelling of greenhouse cucumber-crop transpiration under high and low radiation conditions , 2005 .

[8]  Jin Gao,et al.  Transfer Learning Based Visual Tracking with Gaussian Processes Regression , 2014, ECCV.

[9]  Louis D. Albright,et al.  PREDICTIVE NEURAL NETWORK MODELING OF pH AND ELECTRICAL CONDUCTIVITY IN DEEP–TROUGH HYDROPONICS , 2002 .

[10]  T. Miyamoto,et al.  Effects of Liquid-phase Electrical Conductivity, Water Content, and Surface Conductivity on Bulk Soil Electrical Conductivity1 , 1976 .

[11]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

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

[13]  Hoo-Chang Hoo-Chang Shin Shin,et al.  Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning , 2016, Ieee Transactions on Medical Imaging.

[14]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[15]  D. Savvas,et al.  SW—Soil and Water: Automated Replenishment of Recycled Greenhouse Effluents with Individual Nutrients in Hydroponics by Means of Two Alternative Models , 2002 .

[16]  Jürgen Schmidhuber,et al.  LSTM: A Search Space Odyssey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[17]  Luca Incrocci,et al.  Simulation of crop water and mineral relations in greenhouse soilless culture , 2011, Environ. Model. Softw..

[18]  Jung Eek Son,et al.  Application of a modified irrigation method using compensated radiation integral, substrate moisture content, and electrical conductivity for soilless cultures of paprika , 2016 .

[19]  Paul J. Kramer,et al.  THE RELATION BETWEEN RATE OF TRANSPIRATION AND RATE OF ABSORPTION OF WATER IN PLANTS , 1937 .

[20]  Daniela de Carvalho Lopes,et al.  Development and evaluation of an automated system for fertigation control in soilless tomato production , 2014 .

[21]  K. Paek,et al.  Effects of Hydroponic Solution EC, Substrates, PPF and Nutrient Scheduling on Growth and Photosynthetic Competence During Acclimatization of Micropropagated Spathiphyllum plantlets , 2005, Plant Growth Regulation.

[22]  D. Hershey,et al.  Leachate Electrical Conductivity and Growth of Potted Poinsettia with Leaching Fractions of 0 to 0.4 , 1991 .

[23]  Christos Lykas,et al.  Electrical Conductivity and pH Prediction in a Recirculated Nutrient Solution of a Greenhouse Soilless Rose Crop , 2006 .

[24]  Tuomas Virtanen,et al.  Sound event detection using spatial features and convolutional recurrent neural network , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[25]  Jung-Eek Son,et al.  Analysis of Changes in Ion Concentration with Time and Drainage Ratio under EC-based Nutrient Control in Closed-loop Soilless Culture for Sweet Pepper Plants (Capsicum annum L. 'Boogie') , 2010 .

[26]  Daniel J. Cantliffe,et al.  Fruit Yield and Quality of Greenhouse-grown Bell Pepper as Influenced by Density, Container, and Trellis System , 2004 .

[27]  Francisco J. Batlles,et al.  Estimation of hourly global photosynthetically active radiation using artificial neural network models , 2001 .

[28]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[29]  W. Voogt,et al.  Nutrient Management in Substrate Systems , 2007 .

[30]  David Reitter,et al.  Learning Simpler Language Models with the Differential State Framework , 2017, Neural Computation.

[31]  Bernd Hitzmann,et al.  Artificial neural network prediction of the biogas flow rate optimised with an ant colony algorithm , 2016 .

[32]  J. J. Jurinak,et al.  ESTIMATION OF ACTIVITY COEFFICIENTS FROM THE ELECTRICAL CONDUCTIVITY OF NATURAL AQUATIC SYSTEMS AND SOIL EXTRACTS , 1973 .

[33]  E. Greenwood,et al.  Evaporation from vegetation in landscapes developing secondary salinity using the ventilated-chamber technique: I. Comparative transpiration from juvenile Eucalyptus above saline groundwater seeps , 1979 .

[34]  A. Baille,et al.  A simplified model for predicting evapotranspiration rate of nine ornamental species vs. climate factors and leaf area , 1994 .

[35]  M. Noordwijk.  Synchronisation of supply and demand is necessary to increase efficiency of nutrient use in soilless horticulture , 1990 .

[36]  Stéphane Adamowicz,et al.  Modelling plant nutrition of horticultural crops: a review , 1998 .

[37]  C. Maucieri,et al.  Effects on Water Management and Quality Characteristics of Ozone Application in Chicory Forcing Process: A Pilot System , 2017 .

[38]  Analysis of yield components and dry matter production in a simplified soilless tomato culture system by using controlled-release fertilizers during summer–winter greenhouse production , 2016 .

[39]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[40]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[41]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[42]  Wojciech Zaremba,et al.  An Empirical Exploration of Recurrent Network Architectures , 2015, ICML.

[43]  D. T. Britto,et al.  Growth of a tomato crop at reduced nutrient concentrations as a strategy to limit eutrophication , 1998 .

[44]  N. Anderson.  Effects of Water , 2012 .

[45]  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 .

[46]  Dimitrios Savvas,et al.  Automated Composition Control of Nutrient Solution in Closed Soilless Culture Systems , 1999 .

[47]  A. Fargašová,et al.  Effect of Pb, Cd, Hg, As, and Cr on germination and root growth of Sinapis alba seeds , 1994, Bulletin of environmental contamination and toxicology.

[48]  G. Stutte.  Process and Product: Recirculating Hydroponics and Bioactive Compounds in a Controlled Environment , 2006 .

[49]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[50]  Gregory D. Hager,et al.  Transferring Face Verification Nets To Pain and Expression Regression , 2017, ArXiv.