• 농업과학연구
• /
• 제43권4호
• /
• pp.537-546
• /
• 2016

The development of models for agriculture systems, especially for crop production, has supported the prediction of crop yields under various environmental change scenarios and the selection of better crop species or cultivar. Crop models could be used as tools for supporting reasonable nutrient management approaches for agricultural land. This paper outlines the simplified structure of main crop models (crop growth model, crop-soil model, and crop-soil-environment model) frequently used in agricultural systems and shows diverse application of their simulated results. Crop growth models such as LINTUL, SUCROS, could provide simulated data for daily growth, potential production, and photosynthesis assimilate partitioning to various organs with different physiological stages, and for evaluating crop nutrient demand. Crop-Soil models (DSSAT, APSIM, WOFOST, QUEFTS) simulate growth, development, and yields of crops; soil processes describing nutrient uptake from root zone; and soil nutrient supply capability, e.g., mineralization/decomposition of soil organic matter. The crop model built for the DSSAT family software has limitations in spatial variability due to its simulation mechanism based on a single homogeneous field unit. To introduce well-performing crop models, the potential applications for crop-soil-environment models such as DSSAT, APSIM, or even a newly designed model, should first be compared. The parameterization of various crops under different cultivation conditions like those of intensive farming systems common in Korea, shortened crop growth period, should be considered as well as various resource inputs.

• 산업경영시스템학회지
• /
• 제44권3호
• /
• pp.33-38
• /
• 2021

Recently, transfer learning techniques with a base convolutional neural network (CNN) model have widely gained acceptance in early detection and classification of crop diseases to increase agricultural productivity with reducing disease spread. The transfer learning techniques based classifiers generally achieve over 90% of classification accuracy for crop diseases using dataset of crop leaf images (e.g., PlantVillage dataset), but they have ability to classify only the pre-trained diseases. This paper provides with an evaluation scheme on selecting an effective base CNN model for crop disease transfer learning with regard to the accuracy of trained target crops as well as of untrained target crops. First, we present transfer learning models called CDC (crop disease classification) architecture including widely used base (pre-trained) CNN models. We evaluate each performance of seven base CNN models for four untrained crops. The results of performance evaluation show that the DenseNet201 is one of the best base CNN models.

• 한국작물학회지
• /
• 제49권5호
• /
• pp.394-406
• /
• 2004

A split-plot designed experiment including four rice varieties and 10 nitrogen levels was conducted in 2003 at the Experimental Farm of Seoul National University, Suwon, Korea. Before heading, hyperspectral canopy reflectance (300-1100nm with 1.55nm step) and nine crop variables such as shoot fresh weight (SFW), leaf area index, leaf dry weight, shoot dry weight, leaf N concentration, shoot N concentration, leaf N density, shoot N density and N nutrition index were measured at 54 and 72 days after transplanting. Grain yield, total number of spikelets, number of filled spikelets and 1000-grain weight were measured at harvest. 14,635 narrow-band NDVIs as combinations of reflectances at wavelength ${\lambda}l\;and\;{\lambda}2$ were correlated to the nine crop variables. One NDVI with the highest correlation coefficient with a given crop variable was selected as the NDVI of the best fit for this crop variable. As expected, models to predict crop variables before heading using the NDVI of the best fit had higher $r^2$ (>10\%)$ than those using common broad- band NDVI red or NDVI green. The models with the narrow-band NDVI of the best fit overcame broad- band NDVI saturation at high LAI values as frequently reported. Models using NDVIs of the best fit at booting showed higher predictive capacity for yield and yield component than models using crop variables.

• Journal of Information Processing Systems
• /
• 제20권2호
• /
• pp.149-158
• /
• 2024

Traditional manual identification of crop leaf diseases is challenging. Owing to the limitations in manpower and resources, it is challenging to explore crop diseases on a large scale. The emergence of artificial intelligence technologies, particularly the extensive application of deep learning technologies, is expected to overcome these challenges and greatly improve the accuracy and efficiency of crop disease identification. Crop leaf disease identification models have been designed and trained using large-scale training data, enabling them to predict different categories of diseases from unlabeled crop leaves. However, these models, which possess strong feature representation capabilities, require substantial training data, and there is often a shortage of such datasets in practical farming scenarios. To address this issue and improve the feature learning abilities of models, this study proposes a deep transfer learning adaptation strategy. The novel proposed method aims to transfer the weights and parameters from pre-trained models in similar large-scale training datasets, such as ImageNet. ImageNet pre-trained weights are adopted and fine-tuned with the features of crop leaf diseases to improve prediction ability. In this study, we collected 16,060 crop leaf disease images, spanning 12 categories, for training. The experimental results demonstrate that an impressive accuracy of 98% is achieved using the proposed method on the transferred ResNet-50 model, thereby confirming the effectiveness of our transfer learning approach.

• 한국농림기상학회지
• /
• 제21권3호
• /
• pp.167-174
• /
• 2019

작물 생육모형은 기존의 경험적 작물모형과는 달리 벼의 생장과정을 모의 할 수 있는 장점이 있다. 이러한 작물생육 모형들은 80년대 후반부터 적극적으로 국내도입이 이루어 졌다. 유럽에서 개발된 MACROS로 부터 시작하여 이후 Oryza1 및 Oryza2000 모형과 북미에서 개발된 DSSAT 계열의 모형인 CERES-RICE 모형을 도입하게 되었다. 각각의 모형들은 최초에는 단순히 품종수 적합 후 특정지역에의 수량을 모의하는데 활용되었으나 2000년대에 이르러서는 국내에 적합한 작물모형으로 발전시킬 수 있는 단계에 이르게 되었다. 그러나, 작물생육모형을 기후변화 영향평가를 위한 용도로 주로 사용하였고 실용적인 수준에서의 활용은 미미하였다. 일부 농가 적용을 위한 시도가 있었으나 널리 활용되지는 못하였다. 이러한 활용상의 문제점은 기상자료의 공간해상도가 문제가 가장 크며, 그 다음으로는 각 지역별이 품종에 대한 품종모수 자료가 부족하기 때문이다. 이러한 활용상의 문제점을 극복하기 위해서는 기상관측의 공간해상력을 높이기 위한 관측소의 확대 또는 공간 내삽법이 필요할 것으로 생각된다. 또한 신품종이 일정 재배면적 이상 확대될 경우 이에 대해 품종모수를 적합할 제도적 기술적 방법이 필요하다. 작물모형의 활용 확대를 위해서는 기상 또는 토양 분야와도 연결이 필요하다. 이를 위해서는 군락의 증산 속도와 토양모형에 정보가 필요하며 이는 군락 광합성 관련 부분과 토양 특성에 대해서 새로운 접근이 필요함을 의미한다.

• Asian-Australasian Journal of Animal Sciences
• /
• 제25권4호
• /
• pp.462-470
• /
• 2012

The availability and efficient use of the feed resources in India are the primary drivers to maximize productivity of Indian livestock. Feed security is vital to the livestock management, extent of use, conservation and productivity enhancement. Assessment and forecasting of livestock feed resources are most important for effective planning and policy making. In the present study, 40 years of data on crop production, land use pattern, rainfall, its deviation from normal, area under crop and yield of crop were collected and modeled to forecast the likely production of feed resources for the next 20 years. The higher order auto-regressive (AR) models were used to develop efficient forecasting models. Use of climatic variables (actual rainfall and its deviation from normal) in combination with non-climatic factors like area under each crop, yield of crop, lag period etc., increased the efficiency of forecasting models. From the best fitting models, the current total dry matter (DM) availability in India was estimated to be 510.6 million tonnes (mt) comprising of 47.2 mt from concentrates, 319.6 mt from crop residues and 143.8 mt from greens. The availability of DM from dry fodder, green fodder and concentrates is forecasted at 409.4, 135.6 and 61.2 mt, respectively, for 2030.

• 대한원격탐사학회지
• /
• 제40권1호
• /
• pp.93-101
• /
• 2024

Accurate field crop classification is essential for various agricultural applications, yet existing methods face challenges due to diverse crop types and complex field conditions. This study aimed to address these issues by combining support vector machine (SVM) models with multi-seasonal unmanned aerial vehicle (UAV) images, texture information extracted from Gray Level Co-occurrence Matrix (GLCM), and RGB spectral data. Twelve high-resolution UAV image captures spanned March-October 2021, while field surveys on three dates provided ground truth data. We focused on data from August (-A), September (-S), and October (-O) images and trained four support vector classifier (SVC) models (SVC-A, SVC-S, SVC-O, SVC-AS) using visual bands and eight GLCM features. Farm maps provided by the Ministry of Agriculture, Food and Rural Affairs proved efficient for open-field crop identification and served as a reference for accuracy comparison. Our analysis showcased the significant impact of hyperparameter tuning (C and gamma) on SVM model performance, requiring careful optimization for each scenario. Importantly, we identified models exhibiting distinct high-accuracy zones, with SVC-O trained on October data achieving the highest overall and individual crop classification accuracy. This success likely stems from its ability to capture distinct texture information from mature crops.Incorporating GLCM features proved highly effective for all models,significantly boosting classification accuracy.Among these features, homogeneity, entropy, and correlation consistently demonstrated the most impactful contribution. However, balancing accuracy with computational efficiency and feature selection remains crucial for practical application. Performance analysis revealed that SVC-O achieved exceptional results in overall and individual crop classification, while soybeans and rice were consistently classified well by all models. Challenges were encountered with cabbage due to its early growth stage and low field cover density. The study demonstrates the potential of utilizing farm maps and GLCM features in conjunction with SVM models for accurate field crop classification. Careful parameter tuning and model selection based on specific scenarios are key for optimizing performance in real-world applications.

• 한국유기농업학회지
• /
• 제25권2호
• /
• pp.279-293
• /
• 2017

This study suggests the yield forecast models for autumn chinese cabbage and radish using crop growth and development information. For this, we construct 24 alternative yield forecast models and compare the predictive power using root mean square percentage errors. The results shows that the predictive power of model including crop growth and development informations is better than model which does not include those informations. But the forecast errors of best forecast models exceeds 5%. Thus it is important to establish reliable data and improve forecast models.

• 한국농림기상학회:학술대회논문집
• /
• 한국농림기상학회 2011년도 학술발표회
• /
• pp.12-14
• /
• 2011

Crop growth simulation models have been developed as research and management tools. When these models are needed to incorporate new knowledge on phenology and physiology of crops, programming languages have been used for development and documentation of these models. However, researchers may have limited skill in programming languages. Furthermore, software developer may find it challenging to improve the crop models because documentation of the models are rarely available. The Unified Modeling Language (UML) can provide a simple approach for development and documentation of model. A template for implementation of the model can be obtained using the UML, which would facilitate code re-use and model improvement.

• 한국멀티미디어학회논문지
• /
• 제25권11호
• /
• 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.