• 한국측량학회지
• /
• 제34권4호
• /
• pp.383-390
• /
• 2016

Remote sensing data has been widely used in the estimation of crop yields by employing statistical methods such as regression model. Machine learning, which is an efficient empirical method for classification and prediction, is another approach to crop yield estimation. This paper described the corn yield estimation in Iowa State using four machine learning approaches such as SVM (Support Vector Machine), RF (Random Forest), ERT (Extremely Randomized Trees) and DL (Deep Learning). Also, comparisons of the validation statistics among them were presented. To examine the seasonal sensitivities of the corn yields, three period groups were set up: (1) MJJAS (May to September), (2) JA (July and August) and (3) OC (optimal combination of month). In overall, the DL method showed the highest accuracies in terms of the correlation coefficient for the three period groups. The accuracies were relatively favorable in the OC group, which indicates the optimal combination of month can be significant in statistical modeling of crop yields. The differences between our predictions and USDA (United States Department of Agriculture) statistics were about 6-8 %, which shows the machine learning approaches can be a viable option for crop yield modeling. In particular, the DL showed more stable results by overcoming the overfitting problem of generic machine learning methods.

• 한국기후변화학회지
• /
• 제6권1호
• /
• pp.21-31
• /
• 2015

Various crop models have been extensively used for estimation of the crop yields. Compared to the other models, the EPIC model uses a unified approach to simulate more than 100 types of crops. It has been successfully applied in simulating crop yields for various combinations of weather conditions, soil properties, crops, and management schemes in many countries. The objective of this study was to estimate the rice and maize yield in South Korea using the EPIC model. The input datasets for the 30 types in the 11 categories were created for the EPIC model. The EPIC model simulated rice and maize yields. The performance of the EPIC model was evaluated with the goodness-of-fit measures including Root Mean Square Error (RMSE), Relative Error (RE), Nash-Sutcliffe Efficiency Coefficient (NSEC), Mean Absolute Error (MAE), and Pearson Correelation Coefficient (r). The rice yield showed to more high accuracy than maize yield on four type of method without NSEC. Theses results showed that the EPIC model better simulated rice yields than maize yields. The results suggest that the EPIC crop model can be useful to estimate crop yield in South Korea.

• 대한원격탐사학회지
• /
• 제22권3호
• /
• pp.183-197
• /
• 2006

Combinations of visible and near-infrared (NIR) bands in an image are widely used for estimating vegetation vigor and productivity. Using this approach to understand within-field grain crop variability could allow pre-harvest estimates of yield, and might enable mapping of yield variations without use of a combine yield monitor. The objective of this study was to estimate within-field variations in crop yield using vegetation indices derived from hyperspectral images. Hyperspectral images were acquired using an aerial sensor on multiple dates during the 2003 and 2004 cropping seasons for corn and soybean fields in central Missouri. Vegetation indices, including intensity normalized red (NR), intensity normalized green (NG), normalized difference vegetation index (NDVI), green NDVI (gNDVI), and soil-adjusted vegetation index (SAVI), were derived from the images using wavelengths from 440 nm to 850 nm, with bands selected using an iterative procedure. Accuracy of yield estimation models based on these vegetation indices was assessed by comparison with combine yield monitor data. In 2003, late-season NG provided the best estimation of both corn $(r^2\;=\;0.632)$ and soybean $(r^2\;=\;0.467)$ yields. Stepwise multiple linear regression using multiple hyperspectral bands was also used to estimate yield, and explained similar amounts of yield variation. Corn yield variability was better modeled than was soybean yield variability. Remote sensing was better able to estimate yields in the 2003 season when crop growth was limited by water availability, especially on drought-prone portions of the fields. In 2004, when timely rains during the growing season provided adequate moisture across entire fields and yield variability was less, remote sensing estimates of yield were much poorer $(r^2<0.3)$.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.917-919
• /
• 2003

This paper demonstrates that RADARSAT ScanSAR data can be an important data source of radar remote sensing for monitoring crop systems and estimation of rice yield for large areas in tropic and sub-tropical regions. Experiments were carried out to show the effectiveness of RADARSAT ScanSAR data for rice yield estimation in whole province of Guangdong, South China. A methodology was developed to deal with a series of issues in extracting rice information from the ScanSAR data, such as topographic influences, levels of agro-management, irregular distribution of paddy fields and different rice cropping systems. A model was provided for rice yield estimation based on the relationship between the backscatter coefficient of multi-temporal SAR data and the biomass of rice.

• 한국작물학회:학술대회논문집
• /
• 한국작물학회 1998년도 춘계 학술대회지
• /
• pp.101-102
• /
• 1998

• 한국토양비료학회지
• /
• 제47권2호
• /
• pp.92-99
• /
• 2014

The crop growing conditions make accurate predictions of yield ahead of harvest time difficult. Such predictions are needed by the government to estimate, ahead of time, the amount of crop required to be imported to meet the expected domestic shortfall. Corn and soybean especially are widely cultivated throughout the world and a staple food in many regions of the world. On the other hand, the CASA (Carnegie-Ames-Stanford Approach) model is a process-based model to estimate the land plant NPP (Net Primary Productivity) based on the plant growing mechanism. In this paper, therefore, a methodology for the estimation of corn/soybean yield ahead of harvest time is developed specifically for the growing conditions particular to Iowa and Illinois. The method is based on CASA model using MODIS data, and uses Net Primary Productivity (NPP) to predict corn/soybean yield. As a result, NPP at DOY 217 (in Illinois) and DOY 241 (in Iowa) tend to have high correlation with corn/soybean yields. The corn/soybean yields of Iowa in 2013 was estimated to be 11.24/3.55 ton/ha and Illinois was estimated to be 10.09/3.06 ton/ha. Errors were 6.06/17.58% and -10.64/-7.07%, respectively, compared with the yield forecast of the USDA. Crop yield distributions in 2013 were presented to show spatial variability in the state. This leads to the conclusion that NPP changes in the crop field were well reflected crop yield in this study.

• 한국전자통신학회논문지
• /
• 제18권6호
• /
• pp.1269-1276
• /
• 2023

작물 수확량 예측은 토양, 비, 기후, 대기 및 이들의 관계와 같은 다양한 측면으로 인해 다국적 식사와 강력한 수요에 필수적이며, 기후 변화는 농업 생산량에 영향을 미친다. 본 연구에서는 온도, 강수량, 습도 등의 데이터 세트를 운영한다. 현재 연구는 농부와 농업인을 지원하기 위해 다양한 분류기를 사용한 기능 선택에 중점을 두고 있다. 특징 선택 접근법을 활용한 작물 수확량 추정은 96% 정확도를 나타내었다. 특징 선택은 기계학습 모델의 성능에 영향을 미친다. 현재 그래프 분류기의 성능은 81.5%를 나타내며, 특징 선택이 없는 Random Forest 회귀 분석은 78%의 정확도를 나타냈다. 또한, 특징 선택이 없는 의사결정 트리 회귀 분석은 67%의 정확도를 유지하였다. 본 논문은 제시된 10가지 알고리즘을 대상으로 특징 선택 중요성에 대한 실험결과를 나타내었다. 이러한 결과는 작물 분류 연구에 적합한 모델을 선택하는 데 도움이 될 것으로 기대된다.

• 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
• /
• 제63권2호
• /
• pp.158-163
• /
• 2018

Perilla (Perilla frutescens var.frutescens) is an annual plant of the Lamiaceae family, mainly grown for obtaining oil by press extraction after roasting the seeds. Oil yield is one of its important traits, but evaluating this yield is time-consuming, requires many seeds, and is hard to adjust to pedigrees in a breeding field. The objective of this study was to develop a method for selecting high-oil-yield lines in a breeding population without oil extraction. Twenty-three perilla cultivars were used for evaluating the oil yield and seed traits such as seed hardness, seed coat thickness, seed coat proportion and crude fat. After evaluation of the seed traits of 23 perilla cultivars, the ranges of oil yields, seed hardness, seed coat thickness, seed coat proportion, 100-seed weight, and crude fat were 24.68-38.75%, 157-1166 gf, $24-399{\mu}m$, 15.4-41.5%, 2.79-6.69 g, and 33.0-47.8%, respectively. In an analysis of correlation coefficients, the oil yield negatively correlated with seed length, seed width, the proportion of seed coat, seed hardness, and 1000-seed weight, but positively correlated with crude fat content. It was observed that as the seed coat proportion increased, the seed coat thickness, hardness, and 1000-seed weight also increased. Multiple linear regression (MLR) was employed to find major variables affecting the oil yield. Among the variables, traits crude fat content and seed coat proportion were assumed to be indirect parameters for estimating the potential oil yield, with respect to a significant positive correlation with the observed oil yield ($R^2=0.791$). Using these two parameters, an equation was derived to predict the oil yield. The results of this study show that various seed traits in 23 perilla cultivars positively or negatively correlated with the oil yield. In particular, crude fat and the seed coat proportion can be used for predicting the oil yield with the newly developed equation, and this approach will improve the efficiency of selecting prominent lines for the oil yield.

• 대한원격탐사학회지
• /
• 제33권5_2호
• /
• pp.733-740
• /
• 2017

본 총설에서는 작황조사 시험을 활용한 통계적 작황예측 방법에 대해 소개하고 이를 원격탐사를 이용한 방법과 비교하였다. 17개 지역에서 이루어지는 작황조사시험 기반으로 작황조사시험의 수량구성요소 중 등숙률을 일사량과 선형회귀식으로 예측하고 면적당 영화수는 작황조사의 실측값을 활용하여 수량을 재구성하는 방법으로 예측 결과를 얻어진다. 예측 결과는 비교적 정확하였는데 지난 2010년부터 2016년까지 가장 적은 오차는 1 kg/10a였으며 가장 큰 편차는 19 kg/10a 이었다. 크게 편차가 발생한 이유는 태풍에 의해 피해 때문이었다. 즉 작황조사를 이용한 통계적 방법은 재해에 의한 공간변이를 충분히 반영하지 못하는 약점이 있다. 반면 원격탐사는 이러한 재해에 의한 공간적 변이를 보다 잘 설명할 수 있는 장점이 있다. 따라서, 벼의 생육상황에 큰 문제가 없는 경우에는 두가지 접근법 모두 유효하고 재해가 발생하였을 때는 원격탐사가 더 정확할 수 있을 것으로 보인다.