• Journal of Bio-Environment Control
• /
• v.15 no.4
• /
• pp.296-305
• /
• 2006

The heterogeneity of crop transpiration is important to clearly understand the microclimate mechanisms and to efficiently handle the water resource in greenhouses. A computational fluid dynamic program (Fluent CFD version 6.2) was developed to study the internal climate and crop transpiration distributions of greenhouses. Additionally, the global solar radiation model and a crop heat exchange model were programmed together. Those models programmed using $C^{++}$ software were connected to the CFD main module using the user define function (UDF) technology. For the developed CFD validity, a field experiment was conducted at a $17{\times}6 m^2$ plastic-covered mechanically ventilated single-span greenhouse located at Pusan in Korea. The CFD internal distributions of air temperature, relative humidity, and air velocity at 1m height were validated against the experimental results. The CFD computed results were in close agreement with the measured distributions of the air temperature, relative humidity, and air velocity along the greenhouse. The averaged errors of their CFD computed results were 2.2%,2.1%, and 7.7%, respectively.

• Korean Journal of Soil Science and Fertilizer
• /
• v.50 no.5
• /
• pp.422-433
• /
• 2017

Unmanned Aerial Vehicle (UAV) has several advantages over conventional remote sensing techniques. They can acquire high-resolution images quickly and repeatedly. And with a comparatively lower flight altitude, they can obtain good quality images even in cloudy weather. In this paper, we developed for estimating garlic growth at field scale model in major cultivation regions. We used the $NDVI_{UAV}$ that reflects the crop conditions, and seven meteorological elements for 3 major cultivation regions from 2015 to 2017. For this study, UAV imagery was taken at Taean, Changnyeong, and Hapcheon regions nine times from early February to late June during the garlic growing season. Four plant growth parameters, plant height (P.H.), leaf number (L.N.), plant diameter (P.D.), and fresh weight (F.W.) were measured for twenty plants per plot for each field campaign. The multiple linear regression models were suggested by using backward elimination and stepwise selection in the extraction of independent variables. As a result, model of cold type explain 82.1%, 65.9%, 64.5%, and 61.7% of the P.H., F.W., L.N., P.D. with a root mean square error (RMSE) of 7.98 cm, 5.91 g, 1.05, and 3.43 cm. Especially, model of warm type explain 92.9%, 88.6%, 62.8%, 54.6% of the P.H., P.D., L.N., F.W. with a root mean square error (RMSE) of 16.41 cm, 9.08 cm, 1.12, 19.51 g. The spatial distribution map of garlic growth was in strong agreement with the field measurements in terms of field variation and relative numerical values when $NDVI_{UAV}$ was applied to multiple linear regression models. These results will also be useful for determining the UAV multi-spectral imagery necessary to estimate growth parameters of garlic.

• Journal of Bio-Environment Control
• /
• v.27 no.1
• /
• pp.27-33
• /
• 2018

This study was performed to review the domestic and international smart farm service model based on the convergence of agriculture and information & communication technology and derived various factors needed to improve the Korean smart greenhouse. Studies on modelling of crop growth environment in domestic smart farms were limited. And it took a lot of time to build research infrastructure. The cloud-based research platform as an alternative is needed. This platform can provide an infrastructure for comprehensive data storage and analysis as it manages the growth model of cloud-based integrated data, growth environment model, actuators control model, and farm management as well as knowledge-based expert systems and farm dashboard. Therefore, the cloud-based research platform can be applied as to quantify the relationships among various factors, such as the growth environment of crops, productivity, and actuators control. In addition, it will enable researchers to analyze quantitatively the growth environment model of crops, plants, and growth by utilizing big data, machine learning, and artificial intelligences.

• Journal of Bio-Environment Control
• /
• v.21 no.3
• /
• pp.271-275
• /
• 2012

The average annual and winter ambient air temperatures in Korea have risen by $0.7^{\circ}C$ and $1.4^{\circ}C$, respectively, during the last 30 years. The continuous rise in temperature presents a challenge in growing certain horticultural crops. Chinese cabbage, one most important cool season crop, may well be used as a model to study the influence of climate change on plant growth, because it is more adversely affected by elevated temperatures than warm season crops. This study examined the influence of transplanting time, nitrogen fertilizer level and climate parameters, including air temperature and growing degree days (GDD), on the performance of a Chinese cabbage cultivar (Chunkwang) during the spring growing season to estimate crop yield under the unfavorable environmental conditions. The chinese cabbage plants were transplanted from Apr. 8 to May 13, 2011 when 3~4 leaves were occurred, at internals of 7 days and cultivated with 3 levels of nitrogen fertilization. The data from plants transplanted on Apr. 22 and 29, 2012 were used for the prediction of yield as affected by planting date and nitrogen fertilization for spring production. In our study, plant dry weight was higher when the seedlings were transplanted on 15th (168 g) than on 22nd (139 g) of April. There was no significant difference in the yield when plants were grown with different levels of nitrogen fertilizer. The values of correlation coefficient ($R^2$) between GDD and number of leaves, and between GDD and dry weight of the above-ground plant parts were 0.9818 and 0.9584, respectively. Nitrogen fertilizer did not provide a good correlation with the plant growth. Results of this study suggest that the GDD values can be used as a good indicator in predicting the top biomass yield of Chinese cabbage.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.3
• /
• pp.125-132
• /
• 2023

In this study, we compared the performance of machine learning models for predicting Vapor Pressure Deficits (VPD) in greenhouses that affect pore function and photosynthesis as well as plant growth due to nutrient absorption of plants. For VPD prediction, the correlation between the environmental elements in and outside the greenhouse and the temporal elements of the time series data was confirmed, and how the highly correlated elements affect VPD was confirmed. Before analyzing the performance of the prediction model, the amount and interval of analysis time series data (1 day, 3 days, 7 days) and interval (20 minutes, 1 hour) were checked to adjust the amount and interval of data. Finally, four machine learning prediction models (XGB Regressor, LGBM Regressor, Random Forest Regressor, etc.) were applied to compare the prediction performance by model. As a result of the prediction of the model, when data of 1 day at 20 minute intervals were used, the highest prediction performance was 0.008 for MAE and 0.011 for RMSE in LGBM. In addition, it was confirmed that the factor that most influences VPD prediction after 20 minutes was VPD (VPD_y__71) from the past 20 minutes rather than environmental factors. Using the results of this study, it is possible to increase crop productivity through VPD prediction, condensation of greenhouses, and prevention of disease occurrence. In the future, it can be used not only in predicting environmental data of greenhouses, but also in various fields such as production prediction and smart farm control models.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.135-135
• /
• 2017

Greenhouse have been developed to provide the plants with good environmental conditions for cultivation crop, two major factors of which are the inside air temperature and humidity. The inside temperature are influenced by the heating systems, ventilators and for systems among others, which in turn are geverned by some type of controller. Likewise, humidity environment is the result of complex mass exchanges between the inside air and the several elements of the greenhouse and the outside boundaries. Most of the existing models are based on the energy balance method and heat balance equation for modelling the heat and mass fluxes and generating dynamic elements. However, greenhouse are classified as complex system, and need to make a sophisticated modeling. Furthermore, there is a difficulty in using classical control methods for complex process system due to the process are non linear and multi-output(MIMO) systems. In order to predict the time evolution of conditions in certain greenhouse as a function, we present here to use of recurrent neural networks(RNN) which has been used to implement the direct dynamics of the inside temperature and inside humidity of greenhouse. For the training, we used algorithm of a backpropagation Through Time (BPTT). Because the environmental parameters are shared by all time steps in the network, the gradient at each output depends not only on the calculations of the current time step, but also the previous time steps. The training data was emulated to 13 input variables during March 1 to 7, and the model was tested with database file of March 8. The RMSE of results of the temperature modeling was $0.976^{\circ}C$, and the RMSE of humidity simulation was 4.11%, which will be given to prove the performance of RNN in prediction of the greenhouse environment.

• Journal of Bio-Environment Control
• /
• v.17 no.2
• /
• pp.83-89
• /
• 2008

A wind tunnel test was conducted at Protected Horticulture Experiment Station of National Horticultural Research Institute in Busan to find the aerodynamic resistance and quadratic resistance coefficient of chrysanthemum in greenhouse. The internal plants of the CFD model has been designed as a porous media because of the complexity of its physical shapes. Then the aerodynamic resistance value should be input for analyzing CFD model that crop is considered while the value varies by crops. In this study, the aerodynamic resistance value of chrysanthemum canopy was preliminarily found through wind tunnel test. The static pressure at windward increased as wind velocity and planting density increased. The static pressure at leeward decreased as wind velocity increased but was not significantly affected by planting density. The difference of static pressure between windward and leeward increased as wind velocity and planting density increased. The aerodynamic resistance value of chrysanthemum canopy was found to be 0.22 which will be used later as the input data of Fluent CFD model. When the planting distances were $9{\times}9\;cm$, $11{\times}11\;cm$, and $13{\times}13\;cm$, the quadratic resistance coefficients of porous media were found to be 2.22, 1.81, and 1.07, respectively. These values will be used later as the input data of CFX CFD model.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2017.06a
• /
• pp.36-36
• /
• 2017

Out of twenty common protein amino acids, there are many kinds of non protein amino acids (NPAAs) that exist as secondary metabolites and exert ecological functions in plants. Mimosine (Mim), one of those NPAAs derived from L. leucocephala acts as an iron chelator and reversely block mammalian cell cycle at G1/S phases. Cysteine (Cys) is decisive for protein and glutathione that acts as an indispensable sulfur grantor for methionine and many other sulfur-containing secondary products. Cys biosynthesis includes consecutive two steps using two enzymes-serine acetyl transferase (SAT) and O-acetylserine (thiol)lyase (OASTL) and appeared in plant cytosol, chloroplast, and mitochondria. In the first step, the acetylation of the ${\beta}$-hydroxyl of L-serine by acetyl-CoA in the existence of SAT and finally, OASTL triggers ${\alpha}$, ${\beta}$-elimination of acetate from OAS and bind $H_2S$ to catalyze the synthesis of Cys. Mimosine synthase, one of the isozymes of the OASTLs, is able to synthesize Mim with 3-hydroxy-4-pyridone (3H4P) instead of $H_2S$ for Cys in the last step. Thus, the aim of this study was to clone and characterize the cytosolic (Cy) OASTL gene from L. leucocephala, express the recombinant OASTL in Escherichia coli, purify it, do enzyme kinetic analysis, perform docking dynamics simulation analysis between the receptor and the ligands and compare its performance between Cys and Mim synthesis. Cy-OASTL was obtained through both directional degenerate primers corresponding to conserved amino acid region among plant Cys synthase family and the purified protein was 34.3KDa. After cleaving the GST-tag, Cy-OASTL was observed to form mimosine with 3H4P and OAS. The optimum Cys and Mim reaction pH and temperature were 7.5 and $40^{\circ}C$, and 8.0 and $35^{\circ}C$ respectively. Michaelis constant (Km) values of OAS from Cys were higher than the OAS from Mim. Inter fragment interaction energy (IFIE) of substrate OAS-Cy-OASTL complex model showed that Lys, Thr81, Thr77 and Gln150 demonstrated higher attraction force for Cys but 3H4P-mimosine synthase-OAS intermediate complex showed that Gly230, Tyr227, Ala231, Gly228 and Gly232 might provide higher attraction energy for the Mim. It may be concluded that Cy-OASTL demonstrates a dual role in biosynthesis both Cys and Mim and extending the knowledge on the biochemical regulatory mechanism of mimosine and cysteine.

• Horticultural Science & Technology
• /
• v.29 no.4
• /
• pp.345-351
• /
• 2011

This study was carried out to develop a model system using selection method for disease resistant plant breeding programs using a herbicide bialaphos-resistant patII gene as a gene-based marker. Spraying bialaphos could eliminate the susceptible plants from the segregating populations such as ${F_2}^{\prime}s$ and thereafter. Tomato cv. Momotaro-yoke was transformed with patII gene 60 independent transformants were acquired. Total 42 transformants were analyzed in transgene copy numbers by Southern blotting and the segregation ratios for the bialaphos resistance. Statistical analysis revealed that the transgene copy numbers and the segregation ratios were not always coincided, especially having the tendency of underestimating the real numbers of the transgenes in the multicopy lines. A two-stepwise screening method was applied to select $T_1$ tomato plants which linked the transgenic patII to a disease resistance gene (I2 and Ve). Based on the resistant to susceptible ratios, T-20 plant was finally selected due to the estimated linkage 12-13 cM between the patII gene to the I2 gene on chromosome 11. This newly developed system could be applied to any economical crop in breeding programs.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.5
• /
• pp.7-14
• /
• 2021

Tomato crops are highly affected by tomato diseases, and if not prevented, a disease can cause severe losses for the agricultural economy. Therefore, there is a need for a system that quickly and accurately diagnoses various tomato diseases. In this paper, we propose a system that classifies nine diseases as well as healthy tomato plants by applying various pretrained deep learning-based CNN models trained on an ImageNet dataset. The tomato leaf image dataset obtained from PlantVillage is provided as input to ResNet, Xception, and DenseNet, which have deep learning-based CNN architectures. The proposed models were constructed by adding a top-level classifier to the basic CNN model, and they were trained by applying a 5-fold cross-validation strategy. All three of the proposed models were trained in two stages: transfer learning (which freezes the layers of the basic CNN model and then trains only the top-level classifiers), and fine-tuned learning (which sets the learning rate to a very small number and trains after unfreezing basic CNN layers). SGD, RMSprop, and Adam were applied as optimization algorithms. The experimental results show that the DenseNet CNN model to which the RMSprop algorithm was applied output the best results, with 98.63% accuracy.