Forecasting root-zone electrical conductivity of nutrient solutions in closed-loop soilless cultures using a recurrent neural network

Soilless cultures can improve crop yield and quality compared to soil cultures.
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 root-zone EC of 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 Oct. 15 to Dec. 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 was 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 improved model robustness.
A trained LSTM can be applied to control nutrient solutions in closed-loop soilless cultures based on predicting future EC. Therefore, the algorithm can make a planned management of nutrient solutions possible, reducing resource waste.

XXX International Horticultural Congress IHC2018: III International Symposium on Innovation and New Technologies in Protected Cultivation

T. Moon, T.I. Ahn, J.E. Son

black box modeling, environmental factor, long short-term memory, machine learning, sweet pepper

https://doi.org/10.17660/ActaHortic.2020.1271.39