Nutrient Solution Flowing Environment Affects Metabolite Synthesis Inducing Root Thigmomorphogenesis of Lettuce (Lactuca sativa L.) in Hydroponics

The principal difference between hydroponics and other substrate cultivation methods is the flowing liquid hydroponic cultivation substrate. Our previous studies have revealed that a suitable flowing environment of nutrient solution promoted root development and plant growth, while an excess flow environment was unfavorable for plants. To explain the thigmomorphogenetic response of excess flow-induced metabolic changes, six groups of lettuce (Lactuca sativa L.), including two flow conditions and three time periods, were grown. Compared with the plants without flow, the plants with flow showed decreased root fresh weight, total root length, root surface area, and root volume but increased average root diameter and root density. The roots with flow had more upregulated metabolites than those without flow, suggesting that the flow may trigger metabolic synthesis and activity. Seventy-nine common differential metabolites among six groups were screened, and enrichment analysis showed the most significant enrichment in the arginine biosynthesis pathway. Arginine was present in all the groups and exhibited greater concentrations in roots with flow than without flow. It can be speculated from the results that a high-flowing environment of nutrient solution promotes arginine synthesis, resulting in changes in root morphology. The findings provide insights on root thigmomorphogenesis affected by its growing conditions and help understand how plants respond to environmental mechanical forces.

Process-Based Crop Modeling for High Applicability with Attention Mechanism and Multitask Decoders

Crop models have been developed for wide research purposes and scales, but they have low compatibility due to the diversity of current modeling studies. Improving model adaptability can lead to model integration. Since deep neural networks have no conventional modeling parameters, diverse input and output combinations are possible depending on model training. Despite these advantages, no process-based crop model has been tested in full deep neural network complexes. The objective of this study was to develop a process-based deep learning model for hydroponic sweet peppers. Attention mechanism and multitask learning were selected to process distinct growth factors from the environment sequence. The algorithms were modified to be suitable for the regression task of growth simulation. Cultivations were conducted twice a year for 2 years in greenhouses. The developed crop model, DeepCrop, recorded the highest modeling efficiency (= 0.76) and the lowest normalized mean squared error (= 0.18) compared to accessible crop models in the evaluation with unseen data. The t-distributed stochastic neighbor embedding distribution and the attention weights supported that DeepCrop could be analyzed in terms of cognitive ability. With the high adaptability of DeepCrop, the developed model can replace the existing crop models as a versatile tool that would reveal entangled agricultural systems with analysis of complicated information.

Fruit quality and volatile compounds of greenhouse sweet peppers as affected by the LED spectrum of supplementary interlighting

BACKGROUND

Seasonal low light intensity and short photoperiods lead to decreased yield, size, and quality of fruits in the Northern Hemisphere. Recently, supplemental lighting using light-emitting diodes (LEDs) has been introduced to overcome such problems. However, most studies have focused on plant growth or fruit yield but not on taste. This study aimed to evaluate the quality and volatile compounds of greenhouse sweet pepper fruits under three different lighting conditions: natural light only (NL), NL with red/blue interlighting (RB), and NL with red/blue/far-red interlighting (RBFR).

RESULTS

The size, color, firmness, and soluble sugar concentration of the sweet pepper fruit were investigated, and sensory evaluation was conducted by nine trained panelists. Individual fruit fresh weights were higher in the order of RBFR, NL, and RB, with mean values of 219.1, 201.7, and 197.4 g, respectively. Additionally, the composition of volatile compounds demonstrated a distinct clustering pattern by light treatment, implying that the LED interlighting spectra affected the overall taste of sweet pepper fruits. Sensory evaluation indicated that sweetness was higher in the order of RBFR, RB, and NL, with values of 5.28, 4.36, and 3.72, respectively. The soluble sugar results showed the same order as that for the sensory evaluation of sweetness, i.e., RBFR, RB, and NL, with values of 5071, 4647, and 3978 μg ^-1 fresh weight, respectively.

CONCLUSION

Adding far-red to RB interlighting could improve the fruit quality attributes, fruit taste perception, and soluble sugars of sweet peppers compared to those under RB or solely NL. © 2023 Society of Chemical Industry.

Non-Destructive Monitoring of Crop Fresh Weight and Leaf Area with a Simple Formula and a Convolutional Neural Network

Crop fresh weight and leaf area are considered non-destructive growth factors due to their direct relation to vegetative growth and carbon assimilation. Several methods to measure these parameters have been introduced; however, measuring these parameters using the existing methods can be difficult. Therefore, a non-destructive measurement method with high versatility is essential. The objective of this study was to establish a non-destructive monitoring system for estimating the fresh weight and leaf area of trellised crops. The data were collected from a greenhouse with sweet peppers (Capsicum annuum var. annuum); the target growth factors were the crop fresh weight and leaf area. The crop fresh weight was estimated based on the total system weight and volumetric water content using a simple formula. The leaf area was estimated using top-view images of the crops and a convolutional neural network (ConvNet). The estimated crop fresh weight and leaf area exhibited average R² values of 0.70 and 0.95, respectively. The simple calculation was able to avoid overfitting with fewer limitations compared with the previous study. ConvNet was able to analyze raw images and evaluate the leaf area without additional sensors and features. As the simple calculation and ConvNet could adequately estimate the target growth factors, the monitoring system can be used for data collection in practice owing to its versatility. Therefore, the proposed monitoring system can be widely applied for diverse data analyses.

Prediction of Phenolic Contents Based on Ultraviolet-B Radiation in Three-Dimensional Structure of Kale Leaves

Ultraviolet-B (UV-B, 280-315 nm) radiation has been known as an elicitor to enhance bioactive compound contents in plants. However, unpredictable yield is an obstacle to the application of UV-B radiation to controlled environments such as plant factories. A typical three-dimensional (3D) plant structure causes uneven UV-B exposure with leaf position and age-dependent sensitivity to UV-B radiation. The purpose of this study was to develop a model for predicting phenolic accumulation in kale (Brassica oleracea L. var. acephala) according to UV-B radiation interception and growth stage. The plants grown under a plant factory module were exposed to UV-B radiation from UV-B light-emitting diodes with a peak at 310 nm for 6 or 12 h at 23, 30, and 38 days after transplanting. The spatial distribution of UV-B radiation interception in the plants was quantified using ray-tracing simulation with a 3D-scanned plant model. Total phenolic content (TPC), total flavonoid content (TFC), total anthocyanin content (TAC), UV-B absorbing pigment content (UAPC), and the antioxidant capacity were significantly higher in UV-B-exposed leaves. Daily UV-B energy absorbed by leaves and developmental age was used to develop stepwise multiple linear regression models for the TPC, TFC, TAC, and UAPC at each growth stage. The newly developed models accurately predicted the TPC, TFC, TAC, and UAPC in individual leaves with R ² > 0.78 and normalized root mean squared errors of approximately 30% in test data, across the three growth stages. The UV-B energy yields for TPC, TFC, and TAC were the highest in the intermediate leaves, while those for UAPC were the highest in young leaves at the last stage. To the best of our knowledge, this study proposed the first statistical models for estimating UV-B-induced phenolic contents in plant structure. These results provided the fundamental data and models required for the optimization process. This approach can save the experimental time and cost required to optimize the control of UV-B radiation.

Electron transport and photosynthetic performance in Fragaria × ananassa Duch. acclimated to the solar spectrum modified by a spectrum conversion film

Functional films have been used in greenhouses to improve the light environment for plant growth. Among them, a spectrum conversion film converting the green light of incident sunlight into red light has been reported to increase the crop productivity. However, the results are not always consistent, and the reasons for the improvement are not fully understood. The objectives of this study were to reveal the cumulative effects of a green-to-red spectrum conversion film (SCF) on the electron transport and photosynthetic performance of Fragaria × ananassa Duch. The photosynthetic efficiency, leaf optical properties, chlorophyll content, chlorophyll fluorescence, growth, and fruit qualities when the plant was grown under a transparent polyethylene film (PE) and SCF were evaluated. The sunlight modified by SCF did not change the leaf optical properties and chlorophyll content but significantly increased the chlorophyll fluorescence parameters related to reduction end electron acceptors at PSI acceptor side and the efficiency of electron transport. Without an increase in nonphotochemical quenching, the effective quantum yields of PSII and PSI of leaves grown under SCF were significantly higher than those parameters when grown under PE. Forty eight days after transplanting, the photosynthetic efficiency and photosynthetic rates of leaves and whole plants increased significantly under SCF compared to PE. The vegetative growth was not affected by SCF, but the fruit weight, sweetness, acidity, and firmness under SCF were significantly improved. These results indicated that sunlight modified by SCF stimulates electron flow and improves photosynthetic capacity and fruit quality of Fragaria × ananassa Duch.

Adding Far-Red to Red, Blue Supplemental Light-Emitting Diode Interlighting Improved Sweet Pepper Yield but Attenuated Carotenoid Content

Supplemental interlighting is commonly used in modern greenhouses to improve light deficiency, but the light spectrum affects fruit quality and color change. This study aimed to analyze the effect of interlighting with red, blue, and additional far-red light on the fruit qualities and carotenoid contents of red and yellow sweet peppers (Capsicum annuum L.). Three light treatments were applied: natural light (NL), NL with red + blue LED interlighting (71 μmol m^-2 s^-1) (RB), and RB with far-red light (55 μmol m^-2 s^-1) (RBFR). Ascorbic acid, free sugars, and individual carotenoid content were quantified with HPLC analysis. Fruits were sampled on 2020.11.14 (Group 1) and 2021.01.03 (Group 2) from the plants grown under average light intensities of 335.9 and 105.6 μmol m^-2 s^-1, respectively. In the overall period, total yields in RB and RBFR were 22 and 33% higher than those in NL in red fruits and 2 and 21% higher in yellow fruits, respectively. In both colored fruits, ascorbic acid, total soluble sugar, and carotenoid content were higher in RB and RBFR than NL. In Group 1, ascorbic acid and total soluble sugar were significantly different between RB and RBFR only in red fruits. In Group 2, ascorbic acids in red and yellow fruits were 9 and 3% higher in RBFR than RB but total soluble sugars were 4 and 2% lower, respectively. Carotenoid contents in red and yellow fruits were 3.0- and 2.1-fold higher in RB and 2.0- and 1.4-fold higher in RBFR than those in NL, respectively. In this study, interlighting had a significant impact on fruit quality in Group 2, mainly due to the increase in the ratio of interlighting to total light by seasonal changes. In particular, red and yellow fruit yields were 9% and 19% higher in RBFR than RB, but carotenoid contents were 26 to 9% lower, respectively. This result exhibited that additional far-red lighting has a trade-off relationship between fruit yield and carotenoid content. Thus, it is necessary to provide an adequate light spectrum according to a specific cultivation purpose, such as improving yield or accumulating plastids in fruits.

Theoretical and Experimental Analyses of Nutrient Control in Electrical Conductivity-Based Nutrient Recycling Soilless Culture System

An electrical conductivity (EC)-based closed-loop soilless culture system is practical for in-field deployment. Literature on the closed-loop soilless culture nutrient management premise the limitations in managing recycled nutrients under dynamic changes in individual nutrient uptake concentrations. However, recent systems analysis studies predicting solutions for nutrient fluctuation stabilization in EC-based closed-loop soilless culture systems suggest that the system may have a deterministic side in nutrient variation. This study aims to derive a nutrient control principle in an EC-based nutrient recycling soilless culture system by theoretical and experimental analyses. An integrated model of solutes such as K⁺, Ca²⁺, and Mg²⁺ and water transport in growing media, automated nutrient solution preparation, and nutrient uptake was designed. In the simulation, the intrinsic characteristics of nutrient changes among open-, semi- closed-, and closed-loop soilless cultures were compared, and stochastic simulations for nutrient control were performed in the closed-loop system. Four automated irrigation modules for comparing nutrient changes among the soilless culture systems were constructed in the greenhouse. Sweet pepper plants were used in the experiment. In the experimental analysis, nutrient concentration conversion to the proportion between nutrients revealed distinctive trends of nutrient changes according to the treatment level of drainage recycling. Theoretical and experimental analyses exhibited that nutrient variations in open-, semi- closed-, and closed-loop soilless culture systems can be integrated as a function of nutrient supply to the system's boundary areas. Furthermore, stochastic simulation analysis indicated that the nutrient ratio in the soilless culture system reveals the nutrient uptake parameter-based deterministic patterns. Thus, the nutrient ratio in the closed-loop soilless culture could be controlled by the long-term feedback of this ratio. We expect that these findings provide theoretical frameworks for systemizing nutrient management techniques in EC-based closed-loop soilless culture systems.

Accurate Imputation of Greenhouse Environment Data for Data Integrity Utilizing Two-Dimensional Convolutional Neural Networks

Greenhouses require accurate and reliable data to interpret the microclimate and maximize resource use efficiency. However, greenhouse conditions are harsh for electrical sensors collecting environmental data. Convolutional neural networks (ConvNets) enable complex interpretation by multiplying the input data. The objective of this study was to impute missing tabular data collected from several greenhouses using a ConvNet architecture called U-Net. Various data-loss conditions with errors in individual sensors and in all sensors were assumed. The U-Net with a screen size of 50 exhibited the highest coefficient of determination values and the lowest root-mean-square errors for all environmental factors used in this study. U-Net50 correctly learned the changing patterns of the greenhouse environment from the training dataset. Therefore, the U-Net architecture can be used for the imputation of tabular data in greenhouses if the model is correctly trained. Growers can secure data integrity with imputed data, which could increase crop productivity and quality in greenhouses.

Quantitative Analysis of UV-B Radiation Interception in 3D Plant Structures and Intraindividual Distribution of Phenolic Contents

Ultraviolet-B (UV-B) acts as a regulatory stimulus, inducing the dose-dependent biosynthesis of phenolic compounds such as flavonoids at the leaf level. However, the heterogeneity of biosynthesis activation generated within a whole plant is not fully understood until now and cannot be interpreted without quantification of UV-B radiation interception. In this study, we analyzed the spatial UV-B radiation interception of kales (Brassica oleracea L. var. Acephala) grown under supplemental UV-B LED using ray-tracing simulation with 3-dimension-scanned models and leaf optical properties. The UV-B-induced phenolic compounds and flavonoids accumulated more, with higher UV-B interception and younger leaves. To distinguish the effects of UV-B energy and leaf developmental age, the contents were regressed separately and simultaneously. The effect of intercepted UV-B on flavonoid content was 4.9-fold that of leaf age, but the effects on phenolic compound biosynthesis were similar. This study confirmed the feasibility and relevance of UV-B radiation interception analysis and paves the way to explore the physical and physiological base determining the intraindividual distribution of phenolic compound in controlled environments.

Quantitative Analysis of UV-B Radiation Interception and Bioactive Compound Contents in Kale by Leaf Position According to Growth Progress

UV-B (280-315 nm) radiation has been used as an effective tool to improve bioactive compound contents in controlled environments, such as plant factories. However, plant structure changes with growth progress induce different positional distributions of UV-B radiation interception, which cause difficulty in accurately evaluating the effects of UV-B on biosynthesis of bioactive compounds. The objective of this study was to quantitatively analyze the positional distributions of UV-B radiation interception and bioactive compound contents of kales (Brassica oleracea L. var. acephala) with growth progress and their relationships. Short-term moderate UV-B levels did not affect the plant growth and photosynthetic parameters. Spatial UV-B radiation interception was analyzed quantitatively by using 3D-scanned plant models and ray-tracing simulations. As growth progressed, the differences in absorbed UV-B energy between leaf positions were more pronounced. The concentrations of total phenolic compound (TPC) and total flavonoid compound (TFC) were higher with more cumulative absorbed UV-B energy. The cumulative UV energy yields for TFC were highest for the upper leaves of the older plants, while those for TPC were highest in the middle leaves of the younger plants. Despite the same UV-B levels, the UV-B radiation interception and UV-B susceptibility in the plants varied with leaf position and growth stage, which induced the different biosynthesis of TFC and TPC. This attempt to quantify the relationship between UV-B radiation interception and bioactive compound contents will contribute to the estimation and production of bioactive compounds in plant factories.

Spatial and Temporal Bioactive Compound Contents and Chlorophyll Fluorescence of Kale (Brassica oleracea L.) Under UV-B Exposure Near Harvest Time in Controlled Environments

UV-B irradiation has been used to enhance the secondary metabolite content in plants, but its spatial effect on plants has not been considered. The objective of this study was to compare spatial photosynthetic traits and bioactive compound accumulation in kale (Brassica oleracea L. var Acephala) according to the distribution and length of UV-B exposure near harvest. Plants were exposed to UV-B of 0-3, 3-6 and 6-9 W m^-2 for 4 h per day at 5 days (Exp. 1) and 4.2 W m^-2 at 5, 4, 3, 2 or 1 days (Exp. 2) before harvest. In spatial distribution, the higher the UV-B intensity, the lower the mean F_v /F_m (maximal photochemical efficiency of PSII) and the higher the concentration of total flavonoid compound (TFC). With UV-B stress, F_v /F_m and fluorescence transient parameters decreased except for DI₀ /CS (dissipated energy flux per cross section) and PI_abs (performance index of PSII). When exposed to UV-B radiation for 2 days before harvest, the total phenolic compounds and TFC per plant were highest, not always proportional to the local F_v /F_m but affected by dry weight. Short-term UV-B stress near harvest would be more efficient for the accumulation of bioactive compounds by minimizing the loss of plant weight.

Optimal Duration of Drought Stress Near Harvest for Promoting Bioactive Compounds and Antioxidant Capacity in Kale with or without UV-B Radiation in Plant Factories

Among abiotic stresses, both drought and UV-B radiation effectively trigger the accumulation of secondary metabolites, and can be widely applied in plant factories. The objectives of this study were to investigate antioxidant accumulation under drought stress alone, or in combination with UV-B radiation near harvest, and to determine an optimal treatment time for maximum antioxidant production. Kale (Brassica oleracea L. var. acephala) plants were grown in a plant factory and harvested at 42 days after transplanting. The single and combination treatments lasted for 7 to 1 days and 4 to 2 days before harvest, respectively. The results of both F_v/F_m (maximal photochemical efficiency in photosystem II) and leaf water potential could ensure the function of photosynthesis and maintain normal leaf moisture in single drought treatments of less than 4 days. The total phenolic and flavonoid contents and antioxidant activities were significantly increased in both single and combination treatments for 3 to 4 days, compared to other treatments. The supplementary UV-B treatments showed no extra formation of antioxidants compared to the single drought treatments. As a result, drought for 3 days before harvest could achieve the highest potential value of kale as a source of natural antioxidants.

Long short-term memory for a model-free estimation of macronutrient ion concentrations of root-zone in closed-loop soilless cultures

BACKGROUND

Root-zone environment is considered difficult to analyze, particularly in interpreting interactions between environment and plant. Closed-loop soilless cultures have been introduced to prevent environmental pollution, but difficulties in managing nutrients can cause nutrient imbalances with an adverse effect on crop growth. Recently, deep learning has been used to draw meaningful results from nonlinear data and long short-term memory (LSTM) is showing state-of-the-art results in analyzing time-series data. Therefore the macronutrient ion concentrations affected by accumulated environment conditions can be analyzed using LSTM.

RESULTS

The trained LSTM can estimate macronutrient ion concentrations in closed-loop soilless cultures using environmental and growth data. The average training accuracy of six macronutrients was R² = 0.84 and the test accuracy was R² = 0.67 with RMSE = 1.48 meq L^-1. The used values of input interval and time step were 1 h and 168 (1 week), respectively. The accuracy was improved when the input interval became shorter, but not improved when the LSTM consisted of a multilayer structure. Regarding training methods, the LSTM improved the accuracy better than the non-LSTM. The trained LSTM showed relatively adequate accuracies and the interpolated ion concentrations showed variations similar to those seen during traditional cultivation.

CONCLUSIONS

We could analyze the nutrient balance in the closed-loop soilless culture, the model showed potential in estimating the macronutrient ion concentrations using environmental and growth factors measured in greenhouses. Since the LSTM is a powerful and flexible tool used to interpret accumulative changes, it is easily applicable to various plant and cultivation conditions. In the future, this approach can be used to analyze interactions between plant physiology and root-zone environment.

Forecasting Root-Zone Electrical Conductivity of Nutrient Solutions in Closed-Loop Soilless Cultures via a Recurrent Neural Network Using Environmental and Cultivation Information

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 EC of root-zone 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 October 15 to December 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 were 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 would improve model robustness. A trained LSTM can control the nutrient solutions in closed-loop soilless cultures based on predicted future EC. Therefore, the algorithm can make a planned management of nutrient solutions possible, reducing resource waste.

Sweet Pepper (Capsicum annuum L.) Canopy Photosynthesis Modeling Using 3D Plant Architecture and Light Ray-Tracing

Canopy photosynthesis has typically been estimated using mathematical models that have the following assumptions: the light interception inside the canopy exponentially declines with the canopy depth, and the photosynthetic capacity is affected by light interception as a result of acclimation. However, in actual situations, light interception in the canopy is quite heterogenous depending on environmental factors such as the location, microclimate, leaf area index, and canopy architecture. It is important to apply these factors in an analysis. The objective of the current study is to estimate the canopy photosynthesis of paprika (Capsicum annuum L.) with an analysis of by simulating the intercepted irradiation of the canopy using a 3D ray-tracing and photosynthetic capacity in each layer. By inputting the structural data of an actual plant, the 3D architecture of paprika was reconstructed using graphic software (Houdini FX, FX, Canada). The light curves and A/C i curve of each layer were measured to parameterize the Farquhar, von Caemmerer, and Berry (FvCB) model. The difference in photosynthetic capacity within the canopy was observed. With the intercepted irradiation data and photosynthetic parameters of each layer, the values of an entire plant's photosynthesis rate were estimated by integrating the calculated photosynthesis rate at each layer. The estimated photosynthesis rate of an entire plant showed good agreement with the measured plant using a closed chamber for validation. From the results, this method was considered as a reliable tool to predict canopy photosynthesis using light interception, and can be extended to analyze the canopy photosynthesis in actual greenhouse conditions.

Growth and phenolic compounds of Lactuca sativa L. grown in a closed-type plant production system with UV-A, -B, or -C lamp

BACKGROUND

The production of high-quality crops based on phytochemicals is a strategy for accelerating the practical use of plant factories. Previous studies have demonstrated that ultraviolet (UV) light is effective in improving phytochemical production. This study aimed to determine the effect of various UV wavelengths on growth and phenolic compound accumulation in lettuce (Lactuca sativa L.) grown in a closed-type plant production system.

RESULTS

Seven days, 1 day and 0.25 day were determined as the upper limit of the irradiation periods for UV-A, -B, and -C, respectively, in the lettuce based on physiological disorders and the fluorescence parameter F(v)/F(m). Continuous UV-A treatment significantly induced the accumulation of phenolic compounds and antioxidants until 4 days of treatment without growth inhibition, consistent with an increase in phenylalanine ammonia lyase (PAL) gene expression and PAL activity. Repeated or gradual UV-B exposure yielded approximately 1.4-3.6 times more total phenolics and antioxidants, respectively, than the controls did 2 days after the treatments, although both treatments inhibited lettuce growth. Repeated UV-C exposure increased phenolics but severely inhibited the growth of lettuce plants.

CONCLUSION

Our data suggest that UV irradiation can improve the accumulation of phenolic compounds with antioxidant properties in lettuce cultivated in plant factories.

Nutrient solution cooling and its effect on temperature of leaf lettuce in hydroponic system

The heat transfer characteristics of a hydroponic system were experimentally verified after theoretical establishment and the effect of nutrient solution cooling on the plant temperature was investigated. About 96 percent of the total heat flow transferred from culture bed to nutrient solution was the conductive heat through planting board and partitioning materials. The average and maximum temperatures of the leaf lettuce decreased 0.6 and 1.5 degrees C., respectively, with cooling of nutrient solution by 6 degrees C. A numerical model for prediction of cooling load of nutrient solution in a hydroponic greenhouse was developed, and the results from the simulation model showed a good agreement with those from experiments. A mechanical cooling system using the counter flow type with double pipes was developed for cooling the nutrient solution. Also the heat transfer characteristics of the system were analyzed experimentally and theoretically, and compared with the other existing cooling systems of nutrient solution. The cooling capacities of three different systems, which used polyethylene tube in solution tank, stainless tube in solution tank, and the counter flow type with double pipes, were comparatively evaluated.

Experimental model and neural network based electrical conductivity estimation in soilless culture system

The optimum management of nutrient solution in soilless culture needs the accurate control of nutrient solution, especially in recycled soilless culture system. To keep the electrical conductivity (EC) of nutrient solution within the adequate range after application of combined fertilizers, theoretically derived EC prediction methods are required. In this study, the experimental EC prediction equation, an extended form of the Robinson and Stroke's theoretical equation only available for a binary electrolyte, was developed for predicting the EC of the nutrient solution containing many kinds of inorganic compounds. And the multilayer perceptron consisting of three layers with the back propagation learning algorithm was developed for EC prediction. It consists of nine variables in the input layer for the concentrations of seven macro elements, Na+ and Cl, and one variable in the output layer for the EC of nutrient solution. The predicted ECs by experimental model as well as neural networks for the nutrient solution were compared to the measured ones and showed good agreements.