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.
Chlorophyll fluorescence (CF) is used to measure the physiological status of plants affected by biotic and abiotic stresses. Therefore, we aimed to identify the changes in CF parameters in grafted watermelon seedlings exposed to salt, drought, and high and low temperatures. Grafted watermelon seedlings at the true three-leaf stage were subjected to salinity levels (0, 50, 100, 150, and 200 mM) and temperature [low (8°C), moderate (24°C), and high (40°C)] stresses for 12 days under controlled environmental conditions independently. Eight CF parameters were measured at 2-day intervals using the FluorCam machine quenching protocol of the FluorCam machine. The seedlings were also exposed to drought stress for 3 days independent of salinity and temperature stress; CF parameters were measured at 1-day intervals. In addition, growth parameters, proline, and chlorophyll content were evaluated in all three experiments. The CF parameters were differentially influenced depending on the type and extent of the stress conditions. The results showed a notable effect of salinity levels on CF parameters, predominantly in maximum quantum yield (Fv/Fm), non-photochemical quenching (NPQ), the ratio of the fluorescence decrease (Rfd), and quantum yield of non-regulated energy dissipation in PSII [Y(NO)]. High temperature had significant effects on Rfd and NPQ, whereas low temperature showed significant results in most CF parameters: Fv/Fm, Y(NO), NPQ, Rfd, the efficiency of excitation capture of open photosystem II (PSII) center (Fv′/Fm′), and effective quantum yield of photochemical energy conversion in PSII [Y(PSII)]. Only NPQ and Rfd were significantly influenced by severe drought stress. Approximately, all the growth parameters were significantly influenced by the stress level. Proline content increased with an increase in stress levels in all three experiments, whereas the chlorophyll (a and b) content either decreased or increased depending upon the stressor. The results provided here may be useful for understanding the effect of abiotic stresses on CF parameters and the selection of index CF parameters to detect abiotic stresses in grafted watermelon seedlings.
It is necessary to develop a resilient food supply that will withstand unexpected future shocks and deliver the required amounts of nutrients to consumers. By increasing the sustainability of food and agriculture, the food system will be able to handle challenges such as climate change, declining agricultural resources, growing population/urbanization, pandemics, and recessions/shortages. Micronutrient deficiency, otherwise called hidden hunger, is one of the major malnutrition consequences worldwide, particularly in middle- or low- income countries. Unlike essential mineral or nutrient compounds, micronutrients could be less of a priority due to their small levels of requirement. However, insufficient micronutrients caused critical adverse health symptoms and are excessively vital for young children’s development. Therefore, there have been numerous attempts to enhance minerals and nutrients in food crops, including biofortification, food fortification, and supplementation. Based on several interventions involving micronutrients, modern technology, such as nanotechnology, can be applied to enhance sustainability and to reduce the food system’s environmental impact. Previous studies have addressed various strategies or interventions to mitigate major micronutrient deficiency including iron, iodine, zinc, and vitamin A. Comparably small amounts of studies have addressed vitamin B12 deficiency and its fortification in food crops. Vitamin B12 deficiency causes serious adverse health effects, including in the nervous or blood systems, and occurs along with other micronutrient deficiencies, such as folate, iron, and zinc, worldwide, particularly in middle- and low-income countries. Mitigation for B12 deficiency has mainly focused on developing pharmacological and medical treatments such as vitamin B12 serum or supplements. Further studies are required to undertake a sustainable approach to fortify vitamin B12 in plant-based food sources for public health worldwide. This review paper highlights nanoparticle application as a promising technology for enhancing vitamin B12 without conventional genetic modification requirements. The nanoparticle can efficiently deliver the mineral/nutrient using coating techniques to targeted sites into the plant. This is mainly because nanoparticles have better solubility and permeability due to their nano size with high surface exposure. Vitamin B12-coated nanoparticles would be absorbed, translocated, and accumulated by the plant and eventually enhance the bioavailability in food crops. Furthermore, by reducing adverse environmental effects, such as leaching issues that mainly occur with conventional fertilizer usage, it would be possible to develop more sustainable food fortification.
Published work indicates that high percentage of blue light can enhance pigment levels but decreases growth, while addition of far-red light to growth light can increase quantum efficiency and photosynthesis in leafy greens. Combining high-energy blue light with low-energy far-red light may increase both vegetative growth and pigment levels. However, the effect of high-energy blue and low-energy far-red light on the vegetative growth and pigments synthesis is unclear. This information can be potentially useful for enhancing the levels of pigments with nutritional value (e.g., beta-carotene and anthocyanins) in the produce grown in vertical farms. We grew romaine lettuce (cv. Amadeus) under similar light intensity (approximately 130 μmol⋅m–2⋅s–1) but different proportions of red: blue: far-red including 90:10: 0 (“High-R”), 50: 50: 0 (“High-B”), and 42: 42: 16 (“High-B+FR”) for 31 days. Results indicated that canopy area and leaf photosynthetic rate of lettuce plants was reduced in the High-B, thereby reducing plant growth. We did not observe photosynthesis enhancement in the High-B+FR. Instead, plants clearly showed photomorphogenic effects. The phytochrome photostationary state (PSS) decreased with far-red addition, resulting in reduced leaf number per plant. This was likely to shift the allocation of resources toward elongation growth for shade avoidance. Further, we observed an increase in the area of individual leaves, canopy area, and shoot dry weight in the High-B+FR. However, these appear to be an indirect consequence of decreased leaf number per plant. Our results also indicate that changes in expansion growth at individual leaf scale largely regulated pigment concentration in plants. As individual leaf area became smaller (e.g., High-B) or larger (e.g., High-B+FR), the levels of pigments including chlorophylls and beta-carotene increased or decreased, respectively. Area of individual leaves also positively influenced canopy area (and likely light interception) and shoots dry weight (or vegetative growth). Our study provides additional insights into the effects of high-energy blue and low-energy far-red light on individual leaf number and leaf growth, which appear to control plant growth and pigment levels in lettuce.
Frontiers in Plant Science
Agricultural Innovation in the Age of Climate Change: A 4.0 Approach