• Journal of Climate Change Research
• /
• v.7 no.2
• /
• pp.193-203
• /
• 2016

The importance of forecasting agricultural production is receiving attention while climate change is accelerating. This study suggested three types of crop yield forecasting model for major vegetable crops by using downscaled meteorological information of main production area on farmland level, which identified as limitation from previous studies. First, this study conducted correlation analysis with seven types of farm level downscaled meteorological informations and reported crop yield of main production area. After, we selected three types of meteorological factors which showed the highest relation with each crop species and regions. Parameters were deducted from meterological factor with high correlation but crop species number was neglected. After, crop yield of each crops was estimated by using the three suggested types of models. Chinese cabbage showed high accuracy in overall, while the accuracy of daikon and onion was quiet revised by neglecting the outlier. Chili and garlic showed differences by region, but Kyungbuk chili and Chungnam, Kyungsang garlic appeared significant accuracy. We also selected key meteorological factor of each crops which has the highest relation with crop yield. If the factor had significant relation with the quantity, it explains better about the variations of key meteorological factor. This study will contribute to establishing the methodology of future studies by estimating the crop yield of different species by using farmland meterological information and relatively simplify multiple linear regression models.

• Journal of Korea Multimedia Society
• /
• v.23 no.10
• /
• pp.1250-1257
• /
• 2020

The early detection of diseases is important in agriculture because diseases are major threats of reducing crop yield for farmers. The shape and color of plant leaf are changed differently according to the disease. So we can detect and estimate the disease by inspecting the visual feature in leaf. This study presents a vision-based leaf classification method for detecting the diseases of tomato crop. ResNet-50 model was used to extract the visual feature in leaf and classify the disease of tomato crop, since the model showed the higher accuracy than the other ResNet models with different depths. We propose a new ensemble approach using several DCNN classifiers that have the same structure but have been trained at different ranges in the DCNN layers. Experimental result achieved accuracy of 97.19% for PlantVillage dataset. It validates that the proposed method effectively classify the disease of tomato crop.

• Journal of Korea Multimedia Society
• /
• v.25 no.11
• /
• pp.1653-1671
• /
• 2022

Crop diseases affect crop production, more than 30 billion USD globally. We proposed a classification study of crop species and diseases using deep learning algorithms for corn, cucumber, pepper, and strawberry. Our study has three steps of species classification, disease detection, and disease classification, which is noteworthy for using captured images without additional processes. We designed deep learning approach of deep learning convolutional neural networks based on Mask R-CNN model to classify crop species. Inception and Resnet models were presented for disease detection and classification sequentially. For classification, we trained Mask R-CNN network and achieved loss value of 0.72 for crop species classification and segmentation. For disease detection, InceptionV3 and ResNet101-V2 models were trained for nodes of crop species on 1,500 images of normal and diseased labels, resulting in the accuracies of 0.984, 0.969, 0.956, and 0.962 for corn, cucumber, pepper, and strawberry by InceptionV3 model with higher accuracy and AUC. For disease classification, InceptionV3 and ResNet 101-V2 models were trained for nodes of crop species on 1,500 images of diseased label, resulting in the accuracies of 0.995 and 0.992 for corn and cucumber by ResNet101 with higher accuracy and AUC whereas 0.940 and 0.988 for pepper and strawberry by Inception.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.20 no.2
• /
• pp.214-227
• /
• 2018

An object oriented crop model was developed to perform crop growth simulation taking into account complex interaction between biotic and abiotic factors in an agricultural ecosystem. A set of classes including Atmosphere class, Plant class, Soil class, and Grower class were designed to represent weather, crop, soil, and crop management, respectively. Objects, which are instance of class, were linked to construct an integrated system for crop growth simulation. In a case study, yield of corn and soybean, which was obtained at an experiment farm in Rural Development Administration from 1984 to 1986, were compared with yield simulated using the integrated system. The integrated system had relatively low error rate of corn yield, e.g., <4%, under sole and intercropping conditions. In contrast, the system had a relatively large underestimation error for above ground biomass except for grain compared with those observed for corn and soybean. For example, estimates of biomass of corn leaf and stem was 31% lower than those of observed values. Although the integrated system consisted of simple models, the system was capable of simulating crop yield under an intercropping condition. This result suggested that an existing process-based model would be used to have more realistic simulation of crop growth once it is reengineered to be compatible to the integration system, which merits further studies for crop model improvement and implementation in object oriented paradigm.

• Journal of Plant Biology
• /
• v.26 no.3
• /
• pp.161-171
• /
• 1983

To test whether the Grime's model on relationship between maximum standing crop plus litter (350~750g/$m^2$) and species density (10~30/0.25$m^2$) fit well or not, a total of 52 samples, with 4 replicate plots (0.5m$\times$0.5m each) per sample, was collected from various forests, grass lands and coastal salt marshes in midwestern part of central Korean peninsula from September to October in 1982. The result agrees well with the model for grass lands salt marshes, that is, shape of curve for the maximum standing crop (minus litter) against species density indicates normal distribution. The number of species was 11 for the grassland and 7 for the salt marshes within the range of 300g to 700g per square meter for the maximum standing crop. In forest stands, however, as the maximum standing crop of herbs increased the species density decreased. The Grime's model does not seem to fit with the resutls on forest stands of this study. It is examined further the relationships among the maximum standing crop, species density and eleven soil properties, and the possible cause of this discrepancy was disscused.

• Proceedings of the Korean Society of Agricultural Engineers Conference
• /
• 2000.10a
• /
• pp.193-199
• /
• 2000

In order to provide basic information for the estimation of reference crop evapotranspiration in the greenhouse, an lysimeter experiment was performed. Kenturky Blue Grass was used as a reference crop. Relationships between measured reference crop evapotranspiration and weather factors were analyzed. A multi-regression model was developed and tested.

• Korean Journal of Organic Agriculture
• /
• v.28 no.3
• /
• pp.367-386
• /
• 2020

The significance of this study was to analyze the quality value of organic livestock pork for the first time based on the results of managing and testing the cycling organic farming of black pork and vegetables within farm for two years. The results of analysis could be summarized as follows. First, the pork of experimental group with crop-livestock cycling farming showed the excellent quality and high consumer preference compared to the control group of general pork or pork from non-crop-livestock cycling organic farming. In the content ratio of Omega-3 as a representative essential fatty acid, it was 1.46 that was about 2.8 times more than general pork (0.52). In case of Omega-6, it had about 2.5 times more than general pork. Especially, the U/S ratio value which was the content ratio of Unsaturated Fatty Acid (UFA, U) of Saturated Fatty Acid (SFA, S), was largely shown in pork (2.93) from cycling organic farming. Second, it would be necessary to maintain the economies of scope shown in crop-livestock cycling organic farming, and the high quality value of livestock products. For this, there should be a value chain model that could realize the economies of scope and economies of scale at the same time based on scaling and diversification through cooperative organization between farmers. Through this, it would be possible to establish a cycling model called 'community cooperative agriculture' by forming local internal markets through cooperation of production-processing and integration of distribution-sale-consumption. For the managerial activation of this cooperative organization, the government should promote/support the small crop-livestock cycling organic farming cooperative organization in local unit. For securing the reliability of crop-livestock cycling organic agricultural products and crop-livestock cycling organic livestock products, it would be necessary to review the introduction of Participatory Guarantee System (PGS).

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.3 no.1
• /
• pp.37-43
• /
• 2001

Crop status monitoring and yield prediction at higher spatial resolution is a valuable tool in various decision making processes including agricultural policy making by the national and local governments. A prototype crop forecasting system was developed to project the size of rice crop across geographic areas nationwide, based on daily weather pattern. The system consists of crop models and the input data for 1,455 cultivation zone units (the smallest administrative unit of local government in South Korea called "Myun") making up the coterminous South Korea. CERES-rice, a rice crop growth simulation model, was tuned to have genetic characteristics pertinent to domestic cultivars. Daily maximum/minimum temperature, solar radiation, and precipitation surface on 1km by 1km grid spacing were prepared by a spatial interpolation of 63 point observations from the Korea Meteorological Administration network. Spatial mean weather data were derived for each Myun and transformed to the model input format. Soil characteristics and management information at each Myun were available from the Rural Development Administration. The system was applied to the forecasting of national rice production for the recent 3 years (1997 to 1999). The model was run with the past weather data as of September 15 each year, which is about a month earlier than the actual harvest date. Simulated yields of 1,455 Myuns were grouped into 162 counties by acreage-weighted summation to enable the validation, since the official production statistics from the Ministry of Agriculture and Forestry is on the county basis. Forecast yields were less sensitive to the changes in annual climate than the reported yields and there was a relatively weak correlation between the forecast and the reported yields. However, the projected size of rice crop at each county, which was obtained by multiplication of the mean yield with the acreage, was close to the reported production with the $r^2$ values higher than 0.97 in all three years.

• Journal of the Korea Society for Simulation
• /
• v.29 no.4
• /
• pp.1-7
• /
• 2020

Early detection and classification of crop diseases play significant role to help farmers to reduce disease spread and to increase agricultural productivity. Recently, many researchers have used deep learning techniques like convolutional neural network (CNN) classifier for crop disease inspection with dataset of crop leaf images (e.g., PlantVillage dataset). These researches present over 90% of classification accuracy for crop diseases, but they have ability to detect only the pre-trained diseases. This paper proposes an efficient disease inspection CNN model for new crops not used in the pre-trained model. First, we present a benchmark crop disease classifier (CDC) for the crops in PlantVillage dataset using VGG16. Then we build a modified crop disease classifier (mCDC) to inspect diseases for untrained crops. The performance evaluation results show that the proposed model outperforms the benchmark classifier.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.51 no.4
• /
• pp.362-368
• /
• 2006

A pot experiment was conducted to investigate the effects of soil burial depth on seedling emergences of rice (Oryza sativa) and Echinochloa spp. and to model such effects for mathematical prediction of seedling emergences. When the Gompertz curve was fitted at each soil depth, the parameter C decreased in a logistic form with increasing soil depth, while the parameter M increased in an exponential form and the parameter B appeared to be constant. The Gompertz curve was combined by incorporating the logistic model for the parameter C, the exponential model for the parameter M, and the constant for the parameter B. This combined model well described seedling emergence of rice and Echinochloa species as influenced by soil burial depth and predicted seedling emergence at a given time after sowing and a soil burial depth. Thus, the combined model can be used to simulate seedling emergence of crop sown in different soil depths and weeds present in various soil depths.