• 한국초지조사료학회지
• /
• 제41권4호
• /
• pp.287-294
• /
• 2021

본 연구는 기계학습을 통한 수량예측모델을 이용하여 이상기상에 따른 WCM의 DMY 피해량을 산출하기 위한 목적으로 수행하였다. 수량예측모델은 WCM 데이터 및 기상 데이터를 수집 후 가공하여 8가지 기계학습을 통해 제작하였으며 실험지역은 경기도로 선정하였다. 수량예측모델은 기계학습 기법 중 정확성이 가장 높은 DeepCrossing (R²=0.5442, RMSE=0.1769) 기법을 통해 제작하였다. 피해량은 정상기상 및 이상기상의 DMY 예측값 간 차이로 산출하였다. 정상기상에서 WCM의 DMY 예측값은 지역에 따라 차이가 있으나 15,003~17,517 kg/ha 범위로 나타났다. 이상기온, 이상강수량 및 이상풍속에서 WCM의 DMY 예측값은 지역 및 각 이상기상 수준에 따라 차이가 있었으며 각각 14,947~17,571 kg/ha, 14,986~17,525 kg/ha 및 14,920~17,557 kg/ha 범위로 나타났다. 이상기온, 이상강수량 및 이상풍속에서 WCM의 피해량은 각각 -68~89 kg/ha, -17~17 kg/ha 및 -112~121 kg/ha 범위로 피해로 판단할 수 없는 수준이었다. WCM의 정확한 피해량을 산출하기 위해서는 수량예측모델에 이용하는 이상기상 데이터 수의 증가가 필요하다.

• 한국농림기상학회지
• /
• 제3권1호
• /
• 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.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.207-209
• /
• 2003

Quantifying crop production is one of the most important applications of remote sensing in which the temporal and up-to-date data can play very important role in avoiding any immediate insufficiency in agricultural production. A combination of climatic data and biophysical parameters derived from Landsat7 ETM+ was used to develop a mathematical model for wheat yield forecast in different geographically wide Wheat growing districts in Egypt. Leaf Area Index (LAI) and fraction of Absorbed Photosynthetically Active Radiation (fAPAR) with temperature were used in the modeling. The model includes three sub-models representing the correlation between the reported yield and each individual variable. Simulation results using district statistics showed high accuracy of the derived correlations to estimate wheat production with a percentage standard error (%S.E.) of 1.5% in El- Qualyobia district and average (%S.E.) of 7% for the whole wheat areas.

• 대한원격탐사학회지
• /
• 제33권5_2호
• /
• pp.617-620
• /
• 2017

농작물 작황 추정은 생산량 예측을 통한 수급 조절, 가격 예측, 농가 소득 보전을 위한 정책 수립 등에 중요한 판단자료로 활용된다. 급변하는 국내외 여건에서 작물의 안정생산과 식량안보, 생태계 지속성 평가를 위해 원격탐사 등 국가차원의 미래기술 개발 노력이 요구되고 있다. 농촌진흥청은 2010년부터 국내외 주요 곡물생산지대 작황 평가를 위한 원격탐사, 작물모형, 농업기상 분야 원천기술 개발을 위해 노력해왔다. 본 특별호는 농촌진흥청에서 지난 8년간 국내외 작황 평가를 위해 수행해 온 원격탐사, 작물모형, 농업기상 분야의 연구개발 성과 및 연계된 이들 분야 간 융복합 연구 수행 현황을 정리하고 향후 연구 방향을 제시하고자 발간하게 되었다.

• 한국작물학회지
• /
• 제50권4호
• /
• pp.268-275
• /
• 2005

Early predictions of crop yields call provide information to producers to take advantages of opportunities into market places, to assess national food security, and to provide early food shortage warning. The objectives of this study were to identify the most useful parameters for estimating yields and to compare two model selection methods for finding the 'best' model developed by multiple linear regression. This research was conducted in two 65ha corn/soybean rotation fields located in east central South Dakota. Data used to develop models were small temporal variability information (STVI: elevation, apparent electrical conductivity $(EC_a)$, slope), large temporal variability information (LTVI : inorganic N, Olsen P, soil moisture), and remote sensing information (green, red, and NIR bands and normalized difference vegetation index (NDVI), green normalized difference vegetation index (GDVI)). Second order Akaike's Information Criterion (AICc) and Stepwise multiple regression were used to develop the best-fitting equations in each system (information groups). The models with $\Delta_i\leq2$ were selected and 22 and 37 models were selected at Moody and Brookings, respectively. Based on the results, the most useful variables to estimate corn yield were different in each field. Elevation and $EC_a$ were consistently the most useful variables in both fields and most of the systems. Model selection was different in each field. Different number of variables were selected in different fields. These results might be contributed to different landscapes and management histories of the study fields. The most common variables selected by AICc and Stepwise were different. In validation, Stepwise was slightly better than AICc at Moody and at Brookings AICc was slightly better than Stepwise. Results suggest that the Alec approach can be used to identify the most useful information and select the 'best' yield models for production fields.

• 한국농공학회논문집
• /
• 제53권3호
• /
• pp.75-82
• /
• 2011

This study refers to the derivation of simple crop yield prediction equation by using KOMPSAT-2 derived vegetation index. For a 1.25 ha small farm area located in the middle part of South Korea, the KOMPSAT-2 panchromatic and multi-spectral images of 31th August 2008, 17th November 2008, and 10th September 2009 were used. The field spectral reflectance during growing period for the 6 crops (rice, potato, corn, red pepper, garlic, and bean) were measured using ground spectroradiometer and the yield was investigated. Among the 6 vegetation indices (VI), the NDVI and ARVI between measured and image derived showed high relationship with the coefficient of determination of 0.85 and 0.95 respectively. Using the 3 years field data, the NDVI and ARVI regression curves were derived, and the yields were tried to compare with the maximum VIs value.

• 한국농공학회지
• /
• 제35권2호
• /
• pp.73-80
• /
• 1993

A simplified physiologically-based dynamic model, SIMRIW was selected for predicting the growth and yield of rice. The applicability of the model to the rice cultivars and weather conditions in the Republic of Korea was evaluated. Parameters of the model were calibrated using actual rice yields in Suweon region and an optimization scheme, Constrained Rosenbrock Algorithm. The simulated results from the calibrated model were in good agreement with the field data. The model with parameters calibrated for Suweon was applied to other five regions for the evaluation of transferability, but the simulated results fell short of satisfaction. However, the model is found to be applied to real-time prediction of the growth and yield of rice crop, which is believed to be useful for timely rice crop management, agricultural policy making, and optimal irrigation water management.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 1999년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.107-114
• /
• 1999

The large-scale distribution of crops Is usually determined by climate. We present the results of a climate-crop prediction based on spatial bio-physical process model approach, implemented in a GIS (Geographic Information System) environment using several regional and global agriculture-environmental databases. The model utilizes daily climate data like temperature, rainfall, solar radiation being generated stocastically by in-built model weather generator to determine the daily biomass and finally the crop yield. Crops are characterized by their specific growing period requirements, photosynthesis, respiration properties and harvesting index properties. Temperature and radiation during the growing period controls the development of each crop. The model simulates geographic/spatial distribution of climate by which a crop-growing belt can also be determined. The model takes both irrigated and non-irrigated area crop productivity into account and the potential increase in productivity by the technical means like mechanization is not considered. All the management input given at the base year 1995 was kept same for the next twenty-year changes until 2015. The simulated distributions of crops under current climatic conditions coincide largely with the current agricultural or specific crop growing regions. Simulation with assumed weather generated derived climate change scenario illustrate changes in the agricultural potential. There are large regional differences in the response across the country. The north-south and east-west regions responded differently with projected climate changes with increased and decreased productivity depending upon the crops and scenarios separately. When water was limiting or facilitating as non-irrigated and irrigated area crop-production effects of temperature rise and higher $CO_2$ levels were different depending on the crops and accordingly their production. Rise in temperature led to yield reduction in case of maize and rice whereas a gain was observed for wheat crop, doubled $CO_2$ concentration enhanced yield for all crops and their several combinations behaved differently with increase or decrease in yields. Finally, with this spatial modeling approach we succeeded in quantifying the crop productivity which may bring regional disparities under the different climatic scenarios where one region may become better off and the other may go worse off.

• 한국작물학회:학술대회논문집
• /
• 한국작물학회 2022년도 추계학술대회
• /
• 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.

• 한국농림기상학회지
• /
• 제24권3호
• /
• pp.164-178
• /
• 2022

주요 곡물 생산 지역에 대한 작황 계절 예측을 위해 작물모형과 기상 예보자료들이 활용되고 있다. 이 때, 작물모형의 입력자료로 활용되는 기상자료의 불확실성이 작황 예측 결과에 영향을 줄 수 있다. 본 연구에서는 기상 예보자료에 따른 작물모형 결과에 미치는 영향을 알아보고자 하였다. 주요 곡물 생산 지역인 미국의 콘벨트 지역을 대상으로 중규모 수치예보 모형인 Weather Research and Forecasting (WRF)로 10km 해상도의 계절 예측 자료를 생산하였다. 보다 상세한 기상 예보자료 생산을 가정하기 위해 통계적 기법인 Parameter-elevation Regressions on Independent Slopes Model (PRISM) 기법을 활용하여 WRF 자료를 기반으로 5km 해상도로 예측 자료를 생산하였다. WRF와 PRISM 계절 예측 자료로 CROPGRO-SOYBEAN 모형을 구동하여 두 기상 예보자료에 따른 작물 생육 모의 결과를 얻었다. 2011~2018 기간에 대하여 4월 10일부터 8일 간격으로 11개의 파종일을 설정하였으며, 3개의 콩 성숙군에 대한 품종 모수가 사용되었다. 기상 자료의 불확실성을 파악하기 위해 작물 재배기간 동안의 누적 생육도일과 누적 일사량을 비교하였다. 예측된 수량 및 성숙일 등의 주요 변수들을 비교하였다. 두 기상 자료로부터 얻어진 변수들 사이의 일치도 통계량 계산을 위해 root mean square error (RMSE), normalized root mean square error (NRMSE) 및 structural similarity(SSIM) index가 사용되었다. WRF와 PRISM에서 계산된 누적 생육도일 사이의 일치도가 낮았던 연도에 콩 성숙일 모의 값에 대한 오차가 크게 나타났다. 콩 모의 수량 또한 성숙일 및 온도의 오차가 크게 나타났던 연도에 상대적으로 낮은 일치도를 가졌다. 또한 파종일이 수량 및 성숙일 예측의 일치도에 상당한 영향을 미치는 것으로 나타났다. 이러한 결과는 WRF와 PRISM 자료 사이에 온도 자료의 불확실성이 작황 예측의 불확실성에 영향을 주었으며, 재배 시기에 따라 그 불확도의 크기가 상이할 수 있음을 암시하였다. 따라서 신뢰도 높은 작황 예측 자료 생산을 위해 작물별 재배기간을 고려한 불확실성 평가 등의 추가적인 연구가 진행되어야 할 것으로 보인다.