Using Machine Learning Models to Predict Hydroponically Grown Lettuce Yield

Abstract

Prediction of crop yield is an essential task for maximizing the global food supply, particularly in developing countries. This study investigated lettuce yield (fresh weight) prediction using four machine learning (ML) models, namely, support vector regressor (SVR), extreme gradient boosting (XGB), random forest (RF), and deep neural network (DNN). It was cultivated in three hydroponics systems (i.e., suspended nutrient film technique system, pyramidal aeroponic system, and tower aeroponic system), which interacted with three different magnetic unit strengths under a controlled greenhouse environment during the growing season in 2018 and 2019. Three scenarios consisting of the combinations of input variables (i.e., leaf number, water consumption, dry weight, stem length, and stem diameter) were assessed. The XGB model with scenario 3 (all input variables) yielded the lowest root mean square error (RMSE) of 8.88 g followed by SVR with the same scenario that achieved 9.55 g, and the highest result was by RF with scenario 1 (i.e., leaf number and water consumption) that achieved 12.89 g. All model scenarios having Scatter Index (SI) (i.e., RMSE divided by the average values of the observed yield) values less than 0.1 were classified as excellent in predicting fresh lettuce yield. Based on all of the performance statistics, the two best models were SVR with scenario 3 and DNN with scenario 2 (i.e., leaf number, water consumption, and dry weight). However, DNN with scenario 2 requiring less input variables is preferred. The potential of the DNN model to predict fresh lettuce yield is promising, and it can be applied on a large scale as a rapid tool for decision-makers to manage crop yield.

Estimation of groundwater quality using an integration of water quality index, artificial intelligence methods and GIS: Case study, Central Mediterranean Region of Turkey

“…MR is the worst predictive parameter. This may be related to the significant correlation between the input and output variables (Mokhtar et al 2022). The more significant the correlation between the input and output variables, the higher the performance of the models (Trabelsi and Ali 2022).…”

An Analytical Framework on Utilizing Various Integrated Multi-Trophic Scenarios for Basil Production

“…Also, some authors [ 10 ] concluded that the lack of “know-how” and proper real-time water quality monitoring infrastructure could be a significant drawback for integrating aquaponics techniques into already existing RAS. According to other studies [ 11 , 12 ], the prediction of crop yield could improve significantly the production and commercialization strategy of aquaponic facilities, increasing their competitiveness and maximizing food supply at a suitable time and in the places where the market demand for food products rises.…”

“…By analysing the already published papers existing in WoS database which used nitrogen compounds for developing soft sensors, it can be revealed that a number of 26 papers were published within 2015–2021, most of them focusing on NH 4 + , followed by NO 3 − and TN. Recent studies [ 11 , 34 , 35 , 36 , 37 ] have focused on using machine learning (ML) to optimize aquaponics systems’ operational management. Thus, some authors [ 34 ] used an ML-based IoT system for optimizing nutrient supply in commercial aquaponic operations and identified NH 4 and Ca as top nutrient predictors in am tilapia-lettuce coupled aquaponic system, reducing, therefore, the cost involved in regulating nutrient parameters with over 75%.…”

“…Recent study [ 36 ] concluded that in order to predict the optimal nutrients required for fish and plant growth in a single aquaponic set-up, Monte-Carlo (MC) techniques can be used for synthetic data generation, followed by power-transforming the numerical predictors and clipping the highest and lowest quantiles of data as feature engineering methods, while the Linear Support Vector Machine (SVM) with penalty parameter set to 1 was chosen as the ideal classifier. Prediction models based on ML, using ANN and ANFIS techniques, have been extended to target fish and plants [ 11 ] biomass as dependent variables [ 37 ], simplifying, therefore, the operational management within aquaponics systems. As a result, lettuce yield (fresh weight) prediction was developed [ 11 ] using four machine learning (ML) models, namely, support vector regressor (SVR), extreme gradient boosting (XGB), random forest (RF), and deep neural network (DNN).…”

intelligent crop growth monitoring system using IoT and machine learning

“…Before to think machine like human they should first learn like human because the mind of human takes a decision on the basis of past experience. There are many application of ML in hydroponics like controlling the crop growth, checking the nutrients values of solution and electrical conductivity values and so on [5].…”