딥러닝을 이용한 벼 도복 면적 추정

반호영,백재경,상완규,김준환,서명철,Ban, Ho-Young,Baek, Jae-Kyeong,Sang, Wan-Gyu,Kim, Jun-Hwan,Seo, Myung-Chul 한국작물학회 2021 한국작물학회지 Vol.66 No.2

Rice lodging is an annual occurrence caused by typhoons accompanied by strong winds and strong rainfall, resulting in damage relating to pre-harvest sprouting during the ripening period. Thus, rapid estimations of the area of lodged rice are necessary to enable timely responses to damage. To this end, we obtained images related to rice lodging using a drone in Gimje, Buan, and Gunsan, which were converted to 128 × 128 pixels images. A convolutional neural network (CNN) model, a deep learning model based on these images, was used to predict rice lodging, which was classified into two types (lodging and non-lodging), and the images were divided in a 8:2 ratio into a training set and a validation set. The CNN model was layered and trained using three optimizers (Adam, Rmsprop, and SGD). The area of rice lodging was evaluated for the three fields using the obtained data, with the exception of the training set and validation set. The images were combined to give composites images of the entire fields using Metashape, and these images were divided into 128 × 128 pixels. Lodging in the divided images was predicted using the trained CNN model, and the extent of lodging was calculated by multiplying the ratio of the total number of field images by the number of lodging images by the area of the entire field. The results for the training and validation sets showed that accuracy increased with a progression in learning and eventually reached a level greater than 0.919. The results obtained for each of the three fields showed high accuracy with respect to all optimizers, among which, Adam showed the highest accuracy (normalized root mean square error: 2.73%). On the basis of the findings of this study, it is anticipated that the area of lodged rice can be rapidly predicted using deep learning.

고온과 한발이 콩의 수량 및 품질에 미치는 영향

신평,상완규,김준환,이윤호,백재경,권동원,조정일,서명철,Shin, Pyeong,Sang, Wan-Gyu,Kim, Jun-Hwan,Lee, Yun-ho,Baek, Jae-Kyeong,Kwon, Dong-Won,Cho, Jung-Il,Seo, Myung-Chul 한국작물학회 2020 한국작물학회지 Vol.65 No.4

Currently, many studies are being conducted to cope with climate changes due to global warming and abnormal weather. The objective of this study was to investigate the effects of weather on the growth, yield components, and quality of soybeans using weather data from 2017 and 2018. The average temperature in 2018 was higher than that in 2017 from R1 to R5 of the growth stage for all cultivars. On the other hand, precipitation in 2018 was reduced compared to that in 2017 for Daewon and Daepung-2ho. It was observed that the flowering date in 2018 was earlier than that in 2017 for Daewon and Daepung-2ho, but the flowering date for Pungsannamul in 2018 was similar to that in 2017. Simulating soil water content with the estimation model (AFKAE0.5) determined that there were fewer drought dates in 2017 than those in 2018, and drought lasted from R1 to early R5 of the growth stage in 2018. Soybean growth in 2017 was better than that in 2018, and seed yield and 100-seed weight of soybean were higher in 2017 than those in 2018 for all cultivars. The seed size in 2017 was larger than that in 2018 for all cultivars. Oil content in 2017 was higher than that in 2018; in particular, the difference between both years was observed for Daewon and Daepung-2ho. Protein content was higher in 2018 than that in 2017; however, there were different levels for each cultivar. Thus, these results indicate that the yield component and quality of soybeans are affected by high temperature and drought.

상승된 이산화탄소와 온도 그리고 한발 영향에 따른 감자의 군락 형태와 무기영양 변화

이윤호,조현숙,김준환,상완규,신평,백재경,서명철,Lee, Yun-Ho,Cho, Hyeoun-Suk,Kim, Jun-Hwan,Sang, Wan-Gyu,Shin, Pyong,Baek, Jae-Kyeong,Seo, Myung-Chul 한국작물학회 2018 한국작물학회지 Vol.63 No.2

Elevated atmospheric carbon dioxide concentration ($CO_2$) is a major component of climate change, and this increase can be expected to continue into the crop and food security in the future. In this study, Soil-Plant-Atmosphere-Research (SPAR) chambers were used to examine the effect of elevated $CO_2$, temperature, and drought on the canopy architecture and concentration of macronutrients in potatoes (Solanum tuberosum L.). Drought stress treatments were imposed on potato plants 40 days after emergence. Under AT+2.8C700 (30-year average temperature + $2.8^{\circ}C$ at $700{\mu}mol\;mol^{-1}$ of $CO_2$), at maximum leaf area, elevated $CO_2$, and no drought stress, a significant increase was observed in both the aboveground biomass and tuber, and for the developmental stage. Even though $CO_2$ and temperature had increased, AT+2.8C700DS (30-year average temperature + $2.8^{\circ}C$ at $700{\mu}mol\;mol^{-1}$ of $CO_2$ under drought stress) under drought stress showed that the leaf area index (LAI) and dry weight were reduced by drought stress. At maturity, potatoes grown under $CO_2$ enrichment and no drought stress exhibited significantly lower concentrations of N and P in their leaves, and of N, P, and K in tubers under AT+2.8C700. In contrast, elevated $CO_2$ and drought stress tended to increase the tuber Mg concentration under AT+2.8C700DS. Plants grown in AT+2.8C700 had lower protein contents than plants grown under ATC450 (30-year average temperature at $400{\mu}mol\;mol^{-1}$ of $CO_2$). However, plants grown under AT+2.8C700 showed higher tuber bulking than those grown under AT+2.8C700DS. These findings suggest that the increase in $CO_2$ concentrations and drought events in the future are likely to decrease the macronutrients and protein concentrations in potatoes, which are important for the human diet.

지상 고정형 작물 원격탐사 센서 자료와 표준 생육정보를 융합한 작물 모니터링 기법

김현기 ( Hyunki Kim ),문현동 ( Hyun-dong Moon ),류재현 ( Jae-hyun Ryu ),권동원 ( Dong-won Kwon ),백재경 ( Jae-kyeong Baek ),서명철 ( Myung-chul Seo ),조재일 ( Jaeil Cho ) 대한원격탐사학회 2021 대한원격탐사학회지 Vol.37 No.5

Accordingly, attention is also being paid to the agricultural use of remote sensing technique that non-destructively and continuously detects the growth and physiological status of crops. However, when remote sensing techniques are used for crop monitoring, it is possible to continuously monitor the abnormality of crops in real time. For this, standard growth information of crops is required and relative growth considering the cultivation environment must be identified. With the relationship between GDD (Growing Degree Days), which is the cumulative temperature related to crop growth obtained from ideal cultivation management, and the vegetation index as standard growth information, compared with the vegetation index observed with the spectral reflectance sensor (SRSNDVI& SRSPRI) in each rice paddy treated with standard cultivation management and non-fertilized, it was quantitatively identified as a time series. In the future, it is necessary to accumulate a database targeting various climatic conditions and varieties in the standard cultivation management area to establish a more reliable standard growth information.

RGB 작물 생육지수를 활용한 콩 한발 스트레스 판별기술 평가

상완규 ( Wan-gyu Sang ),김준환 ( Jun-hwan Kim ),백재경 ( Jae-kyeong Baek ),권동원 ( Dongwon Kwon ),반호영 ( Ho-young Ban ),조정일 ( Jung-il Cho ),서명철 ( Myung-chul Seo ) 한국농림기상학회 2021 한국농림기상학회지 Vol.23 No.4

본 연구는 콩의 한발 스트레스 판별에 대하여 RGB 영상에 기반한 작물 생육 지수의 적용 가능성과 한계점을 구명하기 위해 수행되었다. RGB 영상에서 추출한 생육 지수들과 한발 스트레스에 반응하는 대표적인 표현형 지표들(군락 피복도, 엽면적, 엽록소 함량 등)과의 높은 상관관계를 통해 영상 기반 생육 진단 모델개발의 가능성을 확인할 수 있었다. 다만 판별의 정확도와 해상도를 개선시키기 위해서는 향후 다양한 재배 조건에서 지속적인 성능 평가가 이루어져야 할 것이다. 본 연구의 결과는 향후 RGB 영상을 활용한 콩 환경 스트레스 판별에 있어서 영상 전처리, 영상 분석 방법, 생육 지수 정량화 기술 개발에 도움을 줄 수 있을 것이며, 개발된 생육 인자 예측 모델은 환경 스트레스 조기 진단을 통한 영농 의사결정 지원 모델의 개발에 기여할 수 있을 것으로 판단된다. Continuous monitoring of RGB (Red, Green, Blue) vegetation indices is important to apply remote sensing technology for the estimation of crop growth. In this study, we evaluated the performance of eight vegetation indices derived from soybean RGB images with various agronomic parameters under drought stress condition. Drought stress influenced the behavior of various RGB vegetation indices related soybean canopy architecture and leaf color. In particular, reported vegetation indices such as ExGR (Excessive green index minus excess red index), Ipca (Principal Component Analysis Index), NGRDI (Normalized Green Red Difference Index), VARI (Visible Atmospherically Resistance Index), SAVI (Soil Adjusted Vegetation Index) were effective tools in obtaining canopy coverage and leaf chlorophyll content in soybean field. In addition, the RGB vegetation indices related to leaf color responded more sensitively to drought stress than those related to canopy coverage. The PLS-DA (Partial Squares-Discriminant Analysis) results showed that the separation of RGB vegetation indices was distinct by drought stress. The results, yet preliminary, display the potential of applying vegetation indices based on RGB images as a tool for monitoring crop environmental stress.

기후변화에 따른 국내 벼 품종과 재배기술의 적응성에 관한 고찰

서명철,김준환,최경진,이윤호,상완규,조현숙,조정일,신평,백재경,Seo, Myung-Chul,Kim, Joon Hwan,Choi, Kyeong Jin,Lee, Yun-Ho,Sang, Wan-Gyu,Cho, Hyeon Suk,Cho, Jung-Il,Shin, Pyeong,Baek, Jae Kyeong 한국작물학회 2020 한국작물학회지 Vol.65 No.4

In recent years, the temperature of Korea has been rapidly increasing due to global warming. Over the past 40 years, the temperature of Korea has risen by about 1.26℃ compared to that in the early 1980s. By region, the west region of the Gangwon Province was the highest at 1.76℃ and the Jeonnam Province was the lowest at 0.96℃. As the temperature continues to rise, it is expected that the rice yield will decrease in the future using the current standard cultivation method. As a result of global warming, the periods in which rice cultivation could be possible in regions each year has increased compared those to the past, showing a wide variety from 110 days in Taebaek to 180 days in Busan and Gwangyang. In addition, the transplanting time was delayed by 3-5 days in all regions. The average annual yield of rice showed an increasing trend when we analyzed the average productivities of developed varieties for cooked rice since the 1980s, especially in the early 1990s, which showed a rapid increase in productivity. The relationship between the average temperature at the time of development and the rice yield was divided into the periods before and after 1996. The higher the average temperature, the lower the yield of the developed varieties until 1996. However, since 1996, the increase in the average temperature did not show a trend in the productivity of the developed varieties. The climate change adaptability of developed rice varieties was investigated by analyzing the results of growing crops nationwide from 1999 to 2016 and the change in the annual yields of developed varieties and recently developed varieties as basic data to investigate the growth status of the crops in the country. As a result of annual comparisons of the yields of Taebongbyeo (2000) and Ungwangbyeo (2004) developed in the early 2000s for Odaebyeo, which was developed in the 1980s, the annual yields were relatively higher in varieties in the 2000s despite the increase in temperature. The annual yields of Samgwangbyeo (2003) and Saenuribyeo (2007), which were recently developed as mid-late-type varieties, were higher than those of an earlier developed variety called Chucheongbyeo, which was developed in the 1970s. Despite the rapid increase in temperature, rice cultivation technology and variety development are well adapted to climate change. However, since the biological potential of rice could reach its limit, it is necessary to develop continuous response technology.

RGB 컬러 이미지를 이용한 콩의 군락 피복과 엽면적에 대한 저비용 평가

이윤호 ( Yun-ho Lee ),상완규 ( Wan-gyu Sang ),백재경 ( Jae-kyeong Baek ),김준환 ( Jun-hwan Kim ),조정일 ( Jung-il Cho ),서명철 ( Myung-chul Seo ) 한국농림기상학회 2020 한국농림기상학회지 Vol.22 No.1

This study compared RGB color images with canopy light interception (LI) and leaf area index (LAI) measurements for low cost and low labor. LAI and LI were measured from vertical gap fraction derived from top of digital image in soybean canopy cover (cv Daewonkong, Deapongkong and Pungsannamulkong). RGB color images, LAI, and LI were collected from V4.5 stage to R5stage. Image segmentation was based on excess green minus excess red index (ExG-ExR). There was a linear relationship between LAI measured with LI (r²=0.84). There was alinear relation ship between LI measured with canopy cover on image (CCI) (r²=0.94). There was a significant positive relationship(r²=0.74) between LAI and CCI at all grow ingseason. Therefore, it is expected that in the future, the RGB color image could be able to easily measure the LAI and the LI at low cost and low labor.

한국형 SPAR(Soil-Plant-Atmosphere-Research) 시스템에서 대용량 관측 자료의 처리 및 품질관리

상완규 ( Wan-gyu Sang ),김준환 ( Jun-hwan Kim ),신평 ( Pyong Shin ),백재경 ( Jae-kyeong Baek ),서명철 ( Myung-chul Seo ) 한국농림기상학회 2020 한국농림기상학회지 Vol.22 No.4

본 연구에서는 첨단 옥외환경조절시설인 SPAR 시스템의 작물 및 환경 관측 자료의 품질 관리와 보증방법을 최초로 제시하였다. 특히 실시간 군락 CO₂플럭스의 경우에는 수집되는 자료의 특성을 고려하여 이상치의 제거와 보정이 병행되어야 함을 확인하였다. 본 연구를 통해 구축된 자료 처리 방법들은 향후 SPAR 자료를 통한 작물 생육 모형 개선에 매우 중요하게 활용될 수 있을 것으로 보인다. SPAR 내 작물과 환경 관련 10분 평균 자료는 국립식량과학원 내 작물 연구 통합 정보시스템(Crop Research Information System, CRIS) 웹사이트(www2.nics.go.kr/cris)에서 이용 가능하다. In this study, we developed the quality control and assurance method of measurement data of SPAR (Soil-Plant-Atmosphere-Research) system, a climate change research facility, for the first time. It was found that the precise processing of CO₂ flux data among many observations were significantly important to increase the accuracy of canopy photosynthesis measurements in the SPAR system. The collected raw CO₂ flux data should first be removed error and missing data and then replaced with estimated data according to photosynthetic lig ht response curve model. Comparing the correlation between cumulative net assimilation and soybean biomass, the quality control and assurance of the raw CO₂ flux data showed an improved effect on canopy photosynthesis evaluation by increasing the coefficient of determination (R²) and lowering the root mean square error (RMSE). These data processing methods are expected to be usefully applied to the development of crop growth model using SPAR system.

유기물 종류별 연용에 따른 벼 재배시 토양탄소 함량 변화에 관한 연구

서명철(Myung Chul Seo),상완규(Wan-Gyu Sang),조정일(Jung-Il Cho),김준환(Jun-Hwan Kim),백재경(Jae-Kyeong Baek),권동원(Dong Won Kwon) 한국토양비료학회 2021 한국토양비료학회 학술발표회 초록집 Vol.2021 No.11

작물 재배기간 토양 탄소의 대부분은 유기물로 존재하며 토양양분 공급, 토양물리성 개선 등 중요한 역할을 한다. 또한 토양에 탄소를 저장하여 기후변화에 따른 온실가스 감축에 역할을 하여 그 역할이 더욱 더 중요해지고 있다. 토양탄소의 축적은 단기간 이루어지지 않고 장기간에 걸쳐 이루어 지기 때문에 이와 관련한 기초자료가 중요하다. 본 연구에서는 벼 재배 조건에서 7년간 볏짚, 헤어리베치, 가축분퇴비, 유박을 연용하였을 때 토양 탄소의 변화를 평가하였다. 초기 토양의 탄소함량은 7.9이었으며 볏짚을 연용하였을 경우 서서히 증가하여 11.5, 헤어리베치는 11.6, 가축분퇴비는 15.9 및 유박은 11.6 g/kg으로 증가하였다. 그러나 유기물의 투입량에 따라 증가속도는 차이가 있었으며 가축분 퇴비가 토양탄소 축적에 가장 적합한 것으로 평가되었다. 토양탄소 유기물 형태를 풀빅산, 휴믹산, 휴민으로 구분하여 평가한 결과 세가지 형태의 변화는 일정 범위에서 변동성을 가지며 증가 또는 감소 추세는 보이지 않았다. 지난 7년간의 유기물 연용에 따른 토양탄소의 변화량을 보았을 때 토양탄소의 중장기적 축적을 위해서는 퇴비의 시용이 필요하며 유기물의 연용을 통한 유기물 축적과 분해의 연차간 수지를 조절하는 것이 무엇보다 중요한 것으로 판단된다. 따라서 본 연구결과는 향후 토양탄소 축적을 위한 토양관리 방법을 제시하는데 중요한 기초자료로 활용될 수 있을 것이다.

사양토에서 유기물 종류가 벼 수량 및 토양탄소에 미치는 영향

조현숙(Hyeoun-Suk Cho),서명철(Myung-Chul Seo),김준환(Jun-Hwan Kim),상완규(Wan-gyu Sang),신평(Pyeong Shin),백재경(Jae-Kyeong Baek),조정일(Jung-Il Cho) 한국토양비료학회 2018 한국토양비료학회 학술발표회 초록집 Vol.2018 No.10