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.
The current study was conducted during two seasons, 2018 and 2019, to determine the optimal coupling of hydroponic systems with magnetized water levels (MWLs) to improve irrigation water characteristics, water productivity and lettuce production quality. Three hydroponic nutrient film technique (NFT; tower aeroponic and pyramidal aeroponic) systems and three levels of magnetic units (magnetized water level 1; MWL1 = 3800 gauss, level 2; MWL2 = 5250 gauss, level 3; MWL3 = 6300 gauss, and regular water (RW) was represented as a control) were tested. There was an increase in total dissolved solids (TDS) and a decrease in pH of water by increasing the magnetic level over time during the irrigation period. Maximum contents of nitrogen (N; 72.8 ppm), phosphorus (P; 223.3 ppm), and potassium (K; 425.0 ppm) were recorded in nutrient solution under irrigation with MWL3. The increase in magnetic intensity resulted in lower water consumption in all hydroponic systems compared to control. On the other hand, tower and pyramidal systems consumed less water compared to the NFT system. Maximum water consumption (3719.7 and 4175.4 m 3 ha -1 for both seasons, respectively) was observed in the NFT system under RW. Maximum water productivity was recorded with the integration of NFT system + MWL3 (83.4 kg m -3 ) in the first season and tower system + MWL3 (71.2 kg m -3 ) in the second season. In addition, the highest leaf performance curves and lettuce yield (414 g per head) and its quality (3.50, 0.46, and 7.40 mg L -1 for N, P, and K contents) were recorded with the integration of the NFT system + MWL3 compared to other treatments.
Due to the scarcity of water, it is necessary to develop an environmentally friendly method for increasing water productivity and crop production. An experiment was conducted to assess the effects of different magnetic levels (magnetic water level 1 (MWL 1) = 3800 Gauss, magnetic water level 2 (MWL 2) = 5250 Gauss, and magnetic water level 3 (MWL 3) = 6300 Gauss, as well as normal water (NW) as a control) in combination with three soilless culture systems (a nutrient film technique (NFT) hydroponics system, a tower aeroponics system, and a pyramidal aeroponics system. The results showed that the utilization of magnetic water had significant effects on the yield and growth of strawberry plants The tower aeroponic system under MWL 3 produced the highest yield and water productivity, with increases of 80.9% and 89%, respectively, over the control. The tower aeroponic system under MWL 3 produced the highest yield and water productivity, with increases of 80.9% and 89%, respectively, over the control. In addition, as compared to the NW, the NFT system increased yield and water productivity by 71.1% and 79.3%, respectively, whilst the pyramidal system increased yield and water productivity by 66.87% and 82%, respectively. Furthermore, when compared to the control, the combination of the NFT system and magnetic water level 3 (MWL 3) resulted in the most leaves, largest stem diameter, and largest leaf area of the strawberry plants resulted in the most leaves, stem diameter, and leaf area of strawberry plants. In comparison to all other treatments, this combination produced the best fruit quality and yield, as well as its constituents, such as titratable acidity, total soluble solids, and fruit hardness. This study found that combining magnetic therapy with soilless culture techniques resulted in increased yield and water productivity. In addition, water and fertigation solution usage in the NFT, tower, and pyramidal systems dropped by 4.8%, 6%, and 4.8%, respectively. Furthermore, it enhanced plant morphology and plant quality.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.