• Korean Journal of Agricultural and Forest Meteorology
• /
• v.24 no.4
• /
• pp.201-217
• /
• 2022

The United States is one of the largest producers of major crops such as wheat, maize, and soybeans, and is a major exporter of these crops. Therefore, it is important to estimate the crop production of the country in advance based on reliable long- term weather forecast information for stable crops supply and demand in Korea. The purpose of this study is to improve the seasonal predictability of the agro-climatic indices over the United States by using regional-scale daily temperature. For long-term numerical weather prediction, a dynamical downscaling is performed using Weather Research and Forecasting (WRF) model, a regional climate model. As the initial and lateral boundary conditions of WRF, the global hourly prediction data obtained from the Pusan National University Coupled General Circulation Model (PNU CGCM) are used. The integration of WRF is performed for 22 years (2000-2021) for period from June to December of each year. The empirical quantile mapping, one of the bias correction methods, is applied to the timeseries of downscaled daily mean, minimum, and maximum temperature to correct the model biases. The uncorrected and corrected datasets are referred WRF_UC and WRF_C, respectively in this study. The daily minimum (maximum) temperature obtained from WRF_UC presents warm (cold) biases over most of the United States, which can be attributed to the underestimated the low (high) temperature range. The results show that WRF_C simulates closer to the observed temperature than WRF_UC, which lead to improve the long- term predictability of the temperature- based agro-climatic indices.

• Horticultural Science & Technology
• /
• v.33 no.6
• /
• pp.911-922
• /
• 2015

This study was carried out to evaluate growth characteristics of Kimchi cabbage cultivated in various highland areas, and to create a predicting model for the production of highland Kimchi cabbage based on the growth parameters and climatic elements. Regression model for the estimation of head weight was designed with non-destructive measured growth variables (NDGV) such as leaf length (LL), leaf width (LW), head height (HH), head width (HW), and growing degree days (GDD), which was $y=6897.5-3.57{\times}GDD-136{\times}LW+116{\times}PH+155{\times}HH-423{\times}HW+0.28{\times}HH{\times}HW{\times}HW$, ($r^2=0.989$), and was improved by using compensation terms such as the ratio (LW estimated with GDD/measured LW ), leaf growth rate by soil moisture, and relative growth rate of leaf during drought period. In addition, we proposed Excel spreadsheet model for simulation of yield prediction of highland Kimchi cabbage. This Excel spreadsheet was composed four different sheets; growth data sheet measured at famer's field, daily average temperature data sheet for calculating GDD, soil moisture content data sheet for evaluating the soil water effect on leaf growth, and equation sheet for simulating the estimation of production. This Excel spreadsheet model can be practically used for predicting the production of highland Kimchi cabbage, which was calculated by (acreage of cultivation) ${\times}$ (number of plants) ${\times}$ (head weight estimated with growth variables and GDD) ${\times}$ (compensation terms derived relationship of GDD and growth by soil moisture) ${\times}$ (marketable head rate).

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.54 no.1
• /
• pp.29-35
• /
• 2009

The aim of the present study was to update the calibration that is used for the measurement of the total nitrogen content in the rice plant samples by using the visible and near infrared spectrum. Before the equation merge, correlation coefficient of calibration equation for nitrogen content on each rice parts was 0.945 (Leaf), 0.928 (Stem), and 0.864 (Whole plant), respectively. In the calibration models created by each part in the rice plant under the various regression method, the calibration model for the leaf was recorded with relatively high accuracy. Among of those, the calibration equation developed by Partial least squares (PLS) method was more accurate than the Multiple linear regression (MLR) method. The calibration equation was sensitive based on variety and location variations. However, we have merged and enlarged various of the samples that made not only to measure the nitrogen content more accurately, but also later sampling populations became more diversified. After merging, $R^2$ value becomes more accurate and significantly to 0.950 (L.), 0.974 (S.), 0.940 (W.). Also, after removal of outlier, R2 values increased into 0.998, 0.995, and 0.997. In view of the results so far achieved, Standard error of prediction (SEP) and SEP (C) were reduced in the stem and whole plant. Biases were reduced in the leaf, stem as well as whole plant. Slopes were high in the stem. Standard deviation reduced in the stem but $R^2$ was high in the stem and whole plant. Result was indicated that calibration equation make update, and updating robust calibration equation from merge function and multi-variate calibration.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.24 no.2
• /
• pp.78-82
• /
• 2022

Phenology determines the timing of crop development, and the timing of phenological events is strongly influenced by the temperature during the growing season. In process-based model, leaf area is simulated dynamically by coupling of morphology and phenology module. Therefore, the prediction of leaf appearance rate and final leaf number affects the performance of whole crop model. The dataset for the model equation was collected from SPA R chambers with five different temperature treatments. Beta distribution function (proposed by Yan and Hunt (1999)) was used for describing the leaf appearance rate as a function of temperature. The optimum temperature and the critical value were estimated to be 26.0℃ and 35.3℃, respectively. For evaluation of the model, the accumulated number of onion leaves observed in a temperature gradient chamber was compared with model estimates. The model estimate is the result of accumulating the daily increase in the number of onion leaves obtained by inputting the daily mean temperature during the growing season into the temperature model. In this study, the coefficient of determination (R²) and RMSE value of the model were 0.95 and 0.89, respectively.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.46 no.1
• /
• pp.87-97
• /
• 2004

The paper presents the results from the applications of the Water Erosion Prediction Project (WEPP) model to a single plot, and also a small watershed in the Mid Korean Peninsula which is comprised of hillslopes and channels along the water courses. Field monitoring was carried out to obtain total runoff, peak runoff and sediment yield data from research sites. For the plot of 0.63 ha in size, cultivated with com, the relative error of the simulated total runoff, peak runoff rates, and sediment yields using WEPP ranged from -16.6 to 22％, from -15.6 to 6.0％, and from 23.9 to 356.4％ compared to the observed data, respectively. The relative errors for the upland watershed of 5.1 ha ranged from -0.7 to 11.1 ％ for the total runoff, from -6.6 to 35.0 ％ for the sediment yields. The simulation results seem to justify that WEPP is applicable to the Korean dry croplands if the parameters are correctly defined. The results from WEPP applications showed that the major source areas contributing sediment yield most are downstream parts of the watershed where runoff concentrated. It was suggested that cultural practice be managed in such a way that the soil surface could be fully covered by crop during rainy season to minimize sediment yield. And also, best management practices were recommended based on WEPP simulations.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.3
• /
• pp.617-624
• /
• 2017

The production of cabbage, which is mainly cultivated in open field, varies greatly depending on weather conditions, and the price fluctuation is largely due to the presence of a substitute crop. Previous studies predicted the production of cabbage using actual weather data, but in this study, we predicted the wholesale price using unstructured agricultural meteorological data on the web. From January 2009 to October 2016, we collected documents including the cabbage on the portal site, and extracted keywords related to weather in the collected documents. We compared the forecast wholesale prices of simple models and unstructured agricultural weather models at the time of shipment. The simple model is AR model using only wholesale price, and the unstructured agricultural weather model is AR model using unstructured agricultural weather data additionally. As a result, the performance of unstructured agricultural weather model was has been found to be more accurate prediction ability.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.19 no.3
• /
• pp.102-109
• /
• 2017

A temperature-based Beta function model was developed for corn hybrids (Zea mays L.). The beta function based on the hourly temperature was fitted to the phenology data (silking date) obtained for six years from 2008 through 2013 at four survey sites. Using the Beta function model, silking dates for two corn hybrids with the different ecotype ('Danok3', 'Ilmichal') were estimated over two years from 2014 through 2015 at four sites, and then the performance of the model was evaluated based on the data for the same period. The silking dates estimated by the model were predicted earlier than those observed at survey sites. Still, the correlation between estimates and observation was relatively high (r=0.859). The accuracy of the model differed by the survey site and the year, which was likely due to the considerably large standard deviation of the parameter calibrated in this study.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.53 no.1
• /
• pp.15-20
• /
• 2008

Near infrared reflectance spectroscopy (NIRS) is a rapid and accurate analytical method for determining the composition of agricultural products and feeds. This study was conducted to measure anthocyanin contents in black colored soybean by using NIRS system. Total 300 seed coat of black colored soybean samples previously analyzed by HPLC were scanned by NIRS and over 250 samples were selected for calibration and validation equation. A calibration equation calculated by MPLS(modified partial least squares) regression technique was developed in which the coefficient of determination for anthocyanin pigment C3G, D3G and Pt3G content was 0.952, 0.936, and 0.833, respectively. Each calibration equation was applied to validation set that was performed with the remaining samples not included in the calibration set, which showed high positive correlation both in C3G and D3G content file. In case Pt3G, the prediction model was needed more accuracy because of low $R^2$ value in validation set. This results demonstrate that the developed NIRS equation can be practically used as a rapid screening method for quantification of C3G and D3G contents in black colored soybean.

• Smart Media Journal
• /
• v.12 no.10
• /
• pp.63-70
• /
• 2023

Recently, energy consumption for heating costs, which is 35% of smart farm energy costs, has increased, requiring energy consumption efficiency, and the importance of new and renewable energy is increasing due to concerns about the realization of electricity bills. Renewable energy belongs to hydropower, wind, and solar power, of which solar energy is a power generation technology that converts it into electrical energy, and this technology has less impact on the environment and is simple to maintain. In this study, based on the greenhouse heat storage tank and heat pump data, the factors that affect the heat storage tank are selected and a heat storage tank supply temperature prediction model is developed. It is predicted using Long Short-Term Memory (LSTM), which is effective for time series data analysis and prediction, and XGBoost model, which is superior to other ensemble learning techniques. By predicting the temperature of the heat pump heat storage tank, energy consumption may be optimized and system operation may be optimized. In addition, we intend to link it to the smart farm energy integrated operation system, such as reducing heating and cooling costs and improving the energy independence of farmers due to the use of solar power. By managing the supply of waste heat energy through the platform and deriving the maximum heating load and energy values required for crop growth by season and time, an optimal energy management plan is derived based on this.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.5
• /
• pp.911-918
• /
• 2024

This study developed and evaluated the performance of a machine learning-based model for predicting cucumber fruit set using cucumber growth data. In this study, plant height, node number, internode length, stem thickness, leaf length, leaf width, leaf count, and female flower count were used as independent variables, and the fruit set was set as the dependent variable to develop a prediction model. Various machine learning algorithms, including Linear Regression, Random Forest, XGBoost, Support Vector Regression (SVR), and K-Nearest Neighbors (KNN), were applied, and model performance was evaluated based on Mean Squared Error (MSE) and the coefficient of determination (R²). As a result, the Random Forest algorithm demonstrated the best performance, with an MSE of 3.91 and an R² of 0.828, effectively capturing the non-linear relationships in the cucumber growth data. In particular, the Random Forest model showed robustness against outliers and proved to be highly effective in predicting fruit set.