Using Machine Learning Models to Predict Hydroponically Grown Lettuce Yield

Ali Mokhtar; Wessam El-Ssawy; Hongming He; Nadhir Al-Anasari; Saad Sh Sammen; Yeboah Gyasi-Agyei; Mohamed Abuarab

doi:10.3389/fpls.2022.706042

Using Machine Learning Models to Predict Hydroponically Grown Lettuce Yield

Front Plant Sci. 2022 Mar 3:13:706042. doi: 10.3389/fpls.2022.706042. eCollection 2022.

Authors

Ali Mokhtar^{1

2

3}, Wessam El-Ssawy^{1

4}, Hongming He^{2

3}, Nadhir Al-Anasari⁵, Saad Sh Sammen⁶, Yeboah Gyasi-Agyei⁷, Mohamed Abuarab¹

Affiliations

¹ Department of Agricultural Engineering, Faculty of Agriculture, Cairo University, Giza, Egypt.
² State Key Laboratory of Soil Erosion and Dry Land Farming on Loess Plateau, Institute of Soil and Water Conservation, Chinese Academy of Sciences and Ministry of Water Resources at Northwest University of Agriculture and Forestry, Xianyang, China.
³ School of Geographic Sciences, East China Normal University, Shanghai, China.
⁴ Irrigation and Drainage Department, Agricultural Engineering Research Institute, Agricultural Research Center, Giza, Egypt.
⁵ Department of Civil Engineering, Environmental and Natural Resources Engineering, Lulea University of Technology, Lulea, Sweden.
⁶ Department of Civil Engineering, College of Engineering, University of Diyala, Baquba, Iraq.
⁷ School of Engineering and Built Environment, Griffith University, Nathan, QLD, Australia.

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.

Keywords: DNN; deep learning; food safety 2; machine learning; yield prediction.