• Korean Journal of Soil Science and Fertilizer
• /
• v.50 no.6
• /
• pp.509-519
• /
• 2017

Crop simulation models are valuable tools for estimating crop yield, environmental factors and management practices. The objective of this study was to evaluate the effect of soil types on barley productivity using CERES (Crop Environment REsource Synthesis)-barley, cropping system model. So the behavior of the model under various soil types and climatic conditions was evaluated. The results of the sensitivity analysis in temperature, $CO_2$, and precipitation showed that soil types had a direct impact on the simulated yield of CERES-barley model. We found that barley yield in clay soils would be more sensitive to precipitation and $CO_2$ in comparison with temperature. And the model showed limited accuracy in simulating water and nitrogen stress index for soil types. In general, the barley grown on clay soils were less sensitive to water stress than those grown on sandy soils. Especially it was found that the CERES model underestimated the effect of water stress in high precipitation which led to overprediction of crop yield in clay soils. In order to solve these problems and successfully forecast grain yield, further studies on the modification of the water stress response of crops should be considered prior to use of the CERES-barley model for yield forecasting.

• Water Engineering Research
• /
• v.4 no.3
• /
• pp.111-126
• /
• 2003

Meteorological data are often needed to evaluate the long-term effects of proposed hydrologic changes. The evaluation is frequently undertaken using deterministic mathematical models that require daily weather data as input including precipitation amount, maximum and minimum temperature, relative humidity, solar radiation and wind speed. Stochastic generation of the required weather data offers alternative to the use of observed weather records. The precipitation is modeled by a Markov Chain-exponential model. The other variables are generated by multivariate model with means and standard deviations of the variables conditioned on the wet or dry status of the day as determined by the precipitation model. Ultimately, the objective of this paper is to compare Richardson's model and the improved weather generation model in their ability to provide daily weather data for the crop model to study potential impacts of climate change on the irrigation needs and crop yield. However this paper does not refer to the improved weather generation model and the crop model. The new weather generation model improved will be introduced in the Journal of KWRA.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2000.11a
• /
• pp.12-27
• /
• 2000

During the recent decades, he problem of climate variability and change has been in the forefront of scientific problems. The objective of this study was to assess the impact of climate variability on crop growth and yield. The growth duration was the main impact of climate variability on crop yield. Phyllochronterval was shortened in the global worming situations. A simple model to describe developmental traits was provided from heading data of directly seeded rice cultivars and temperature data. Daily mean development rate could be explained by the average temperature during the growth stage. Simple regression equation between daily mean development rate(x) and the average temperature(y) during the growth period as y = ax + b. It can be simply modified as x = 1/a $\ast$ (y-b). The parameters of the model could depict the thermo sensitivity of the cultivars. On the base of this model, the three doubled CO2 GCM scenarios were assessed. The average of these would suggest a decline in rice production of about 11% if we maintained the current cultivars. Future cultivar's developmental traits could be suggested by the two model parameters.

• Korean Journal of Soil Science and Fertilizer
• /
• v.46 no.6
• /
• pp.434-444
• /
• 2013

In order to evaluate drought risk at upland according to climate change scenario (RCP8.5), we have carried out the simulation using agricultural water balance estimation model, called AFKAE0.5, at 66 weather station sites in 2020, 2046, 2050, 2084, and 2090. Total Drought Risk Index between the first month (f) and last month (l) (TDRI(f/l)) and maximum continuous drought risk index (MCDRI(f/l)) were defined as the index for analyzing pattern and strength of drought simulated by the model. Based on distribution maps of MCDRI (1/12), drought strength was predicted to be most severe in 2084 for all regions. Some regions showed severe risk of drought meaning over 20 days of MCDRI (1/12) in the other years, while MCDRI (1/12) in other regions did not reach 5 days. Even though maximum value of TDRI (1/12) in 2090 was greater than in 2050, more severe drought risk in 2050 than in 2090 was predicted based on MCDRI (4/6). It implies that drought risk should be assessed for each crop with its own growing season.

• Journal of Agricultural Extension & Community Development
• /
• v.19 no.3
• /
• pp.699-727
• /
• 2012

Conditions of farm crop switching are affected by several important external factors such as agricultural products import opening, policy support, and climate change. Farming environment is always changing; barriers to imports are becoming lower and lower because of FTA and others, and climate change affects a boundary line of cultivation. Those situations give farmers motivation to change crops in order to cope with them. In addition, crop switching has been done in response to the local government measures about purchase of local agricultural products according to the local food and the expansion of organic agricultural products in school meal. Even though the favorable environment toward crop switching has been created, there are not many researches or outcomes regarding crop switching. Only few studies focus on the list of decision-making in crop switching, and locally suitable crop selection is not treated. In order to utilize crop switching as a farm management strategy, the proper frame should be studied and practical researches on application possibility also need. Therefore, study on crop switching is in a timely, proactive manner because farms catch the chance of expansion of school meal by changing crops. This paper applies HERO model used for venture foundation process to crop switching process. Success factors of HERO model are comprised of Habitate, Entrepreneurship, Resource, and Opportunity, and these phased application factors are applied to crop switching process. By doing so, each phase success factor of crop switching can be uncovered. Three farm organizations supplying organic agricultural products to schools are studied in Gyeonggi province. As a result, the stabilization stage cannot be achieved because of the habitate conditions and social conditions with low risk bearing of crop switching and current school meal systems are the main problems to block the diversification of risks. In order to succeed in crop switching, constructing the habitate in local districts or in systems of school meal is more effective than supporting each farm.

• Korean Journal of Remote Sensing
• /
• v.37 no.4
• /
• pp.719-731
• /
• 2021

This study proposes a two-stage hybrid classification model for crop classification using multi-temporal remote sensing images; the model combines feature embedding by using an autoencoder (AE) with a convolutional neural network (CNN) classifier to fully utilize features including informative temporal and spatial signatures. Long short-term memory (LSTM)-based AE (LAE) is fine-tuned using class label information to extract latent features that contain less noise and useful temporal signatures. The CNN classifier is then applied to effectively account for the spatial characteristics of the extracted latent features. A crop classification experiment with multi-temporal unmanned aerial vehicle images is conducted to illustrate the potential application of the proposed hybrid model. The classification performance of the proposed model is compared with various combinations of conventional deep learning models (CNN, LSTM, and convolutional LSTM) and different inputs (original multi-temporal images and features from stacked AE). From the crop classification experiment, the best classification accuracy was achieved by the proposed model that utilized the latent features by fine-tuned LAE as input for the CNN classifier. The latent features that contain useful temporal signatures and are less noisy could increase the class separability between crops with similar spectral signatures, thereby leading to superior classification accuracy. The experimental results demonstrate the importance of effective feature extraction and the potential of the proposed classification model for crop classification using multi-temporal remote sensing images.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 1999.08a
• /
• pp.438-446
• /
• 1999

Crop minimization of the top and bottom ends of hot rolled plate, in a plate, in a plate mill, has been investigated. The existing model to determine the edging pattern at the finishing rolling pass was not reasonable to get high width accuracy and rolling yields. New models including width prediction have been formulated by using neural network model of back propagation learning algorithm and statistical analysis based on the actual production rolling data to give the optimal pattern for minimizing trimming loss. Using these models, at a given rolling condition of broadside pass and finishing pass and the permissible condition of width variation, it was possible to minimize crip at the top and bottom ends according to optimum procedure in plate mill. An application to improve the plan view pattern reduced width variation by 23% and crop length by 30% on average with an effective fishtail crop shape.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.40 no.1
• /
• pp.43-48
• /
• 1998

In order to provide basic information for the estimation of evapotranspiration for grass (Joycia Japonica), both field lysimeter experiment and model prediction were performed to estimate daily ET Various methods were used to predict daily reference crop ET and crop coefficients. Measured mean daily ET during the 1997 growing season was 4.5mm Model predicted mean daily ET during the 1997 growing season varied from 3.6 to 4.7mm depending on the prediction model Crop coefficients varied from 0.96 to 1.27 depending on the prediction model Comparison of the seven reference crop ET prediction methods used in this study shows that the Penman-Monteith method gave the smallest ET while the Hargreaves method gave the largest ET. The crop coefficient by the corrected Penman method was 1.03, which is closest to 1.0, suggesting that this method may he the best prediction method.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2022.10a
• /
• pp.81-81
• /
• 2022

Recently, many studies on big data based smart farming have been conducted. Research to quantify morphological characteristics using image data from various crops in smart farming is underway. Rice is one of the most important food crops in the world. Much research has been done to predict and model rice crop yield production. The number of productive tillers per plant is one of the important agronomic traits associated with the grain yield of rice crop. However, modeling the basic growth characteristics of rice requires accurate data measurements. The existing method of measurement by humans is not only labor intensive but also prone to human error. Therefore, conversion to digital data is necessary to obtain accurate and phenotyping quickly. In this study, we present an image-based method to predict leaf number and evaluate tiller number of individual rice crop using YOLOv5 deep learning network. We performed using various network of the YOLOv5 model and compared them to determine higher prediction accuracy. We ako performed data augmentation, a method we use to complement small datasets. Based on the number of leaves and tiller actually measured in rice crop, the number of leaves predicted by the model from the image data and the existing regression equation were used to evaluate the number of tillers using the image data.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.39 no.4
• /
• pp.114-121
• /
• 1997

In order to provide basic information for the estimation of evapotranspiration in the ponded direct seeding paddy field, both field lysimeter experiment and model prediction were performed to estimate daily ET. Various methods were used to predict daily reference crop ET and crop coefficients. Measure4 mean daily ET during the 1995 growing season varied from 5.9 to 6.1 mm depending on the species, while it varied from 5.1 to 5.5 mm in 1996. Model predicted mean daily ET during the 1995 growing season varied from 3.9 to 4.9 mm depending on the prediction model, while it varied from 3.5 to 4.7 mm in 1996. The smaller ET values both measured and predicted in 1996 were caused by the low values of temperature, sunshine hours, and solar radiation. Crop coefficients varied from 1.20 to 1.50 in 1995 depending on the prediction model, while it varied from 1.10 to 1.47 in 1996. Comparison of the seven reference crop ET prediction methods used in this study shows that the Penman-Monteith method and the FAO-Radiation method gave the lowest ET while the corrected Penman method and the Hargreaves method gave the largest ET. Since crop coefficients vary to a large extent based on the prediction methods, reference crop ET prediction method should be carefully selected in irrigation planning.