Rapidly changing environmental factors due to climate change are increasing the uncertainty of crop growth, and the importance of crop yield prediction for food security is becoming increasingly evident in Republic of Korea. Traditionally, crop yield prediction models have been developed by using statistical techniques such as regression models and correlation analysis. However, as machine learning technique develops, it is able to predict the crop yield more accurate than the statistical techniques. This study aims at proposing the onion yield prediction framework to accurately predict the onion yield by using various environmental factor data. Temperature, humidity, precipitation, solar radiation, and wind speed are considered as climate factors and irrigation water and nitrogen application rate are considered as soil factors. To improve the performance of the prediction model, ensemble learning technique is applied to the proposed framework. The coefficient of determination of the proposed stacked ensemble framework is 0.96, which is a 24.68% improvement over the coefficient of determination of 0.77 of the existing single machine learning model. This framework can be applied to the particular farmland so that each farm can get their customized prediction model, which is visualized by the web system.

PURPOSES : This study aimed to perform real-time on-site construction volume management by using Internet of things (IoT) technology consisting of 3D scanning, image acquisition, wireless communication systems, and mobile apps for new and maintenance construction of concrete bridge deck overlays. METHODS : LiDAR was used to scan the overlay before and after construction to check the overlay volume. An enhanced inductively coupled plasma (ICP) method was applied to merge the LiDAR data scanned from multiple locations to reduce noise, and an anisotropic filter was applied for efficient three-dimensional shape modeling of the merged LiDAR data. The construction volume counter of the mobile mixer was directly photographed using an IP camera, and the data were transmitted to a central server via the LTE network. The video images were transmitted to the central server and optical character recognition (OCR) was used to recognize the counter number and store it. The system was built such that the stored information could be checked in real time in the field or at the office. RESULTS : As a result of using LiDAR to check the amount of overlay construction, the error from the planned amount was 0.6%. By photographing the counter of the mobile mixer using an IP camera and identifying the number on the counter using OCR to check the quantity, the results showed that there was a 2% difference from the planned quantity. CONCLUSIONS : Although the method for checking the amount of construction on site using LiDAR remains limited, it has the advantage of storing and managing the geometric information of the site more accurately. Through the IoT-based on-site production management system, we were able to identify the amount of concrete used in real time with relative accuracy.

진해만은 우리나라 남해 연안의 주요 어장으로서, 여전히 전체 수산생산량에서 적지 않은 기여를 창출하고 있다. 그러나, 수십 년간 산업개발과 고수온과 같은 환경변화로 인하여 진해만의 해양생태계는 과거와 달라지고 있다. 본 연구는 2005년부터 2022년 까지 진해만 연안 5개 시군구의 수산생산량, 폐기량, 평균영양단계 및 어업균형지수를 분석하였으며, ARIMA 모델을 이용하여 2027년까 지 단기적인 변동 추세를 함께 관찰하였다. 그 결과, 고성지역은 2027년까지 지속적으로 수산생산량이 감소할 것으로 예측되었다. 통영 지역은 이매패류의 부산물 처리가 필요한 것으로 평가된다. 해양생태계 지표의 경우, 통영지역에서는 대형 어류 생산 비중이 회복되고, 어업균형지수가 0 이상을 나타내어 해양생태계 구조가 안정적인 것으로 나타났다. 마지막으로 IPCC의 기후변화 시나리오에 따라 2060 년까지 진해만의 부어성 어종 6종의 생산량 변동 추이를 비교하였으며, 2020년대 초반 2만 ton 부근까지 감소했던 생산량은 2020년대와 2040년대에 4만 ton 부근 가까이 회복한 후, 2060년까지 점진적인 감소 경향을 나타내는 것으로 예측되었다.

The production of the North Korea fisheries industry has been steadily falling since it reached its peak in the 1980s. The production of thefisheries industry is an important indicator of the current status and changes in the North Korea fisheries industry as a whole. This study reviewed the production volume of the North Korea fishery and derived changes and characteristics of the North Korea fisheries from the standpoint of production changes. Changes in North Korea's fisheries industry in the situation of falling production are as follows. First, the production of capture fisheries has fallen sharply. Second, the production of seaweed farming increased. In particular, the production of kelp farming has increased rapidly since the 1970s. Third, North Korea is trying to diversify its production means to cope with the decline in production. The characteristics of the North Korea fisheries from the viewpoint of falling production are as follows. First, the proportion of seaweed aquaculture in the fishery output is excessively high. In particular, the proportion of kelp is high. Second, production facilities are concentrated in the East Sea. Third, there is little production of fish farming using deep-sea fishing and sea sponges. Fourth, the production of the fisheries industry is falling continuously in the long term.

This study was conducted to determine the optimal spring seeding dates for alfalfa yield and feed value. The experiment was conducted annually for three years (2021~2023) at the field in the Department of Animal Resources Development, NIAS, located in Cheonan. The treatments involved six seeding dates ranging from February 24 to April 14, with 10days intervals. Alfalfa was harvested four times a year at the early flowering stage. Dry matter yield showed a tendency to decrease with delayed the seeding date. However, depending on the climatidc condisions in the seeding year, the dry matter yield on March 14 or 24 was comparable to that on February 24. Annual dry matter yield varied, influenced by the daylight conditions each year. The average feed value did not significantly differ within in the same year with delayed seeding dates (p>0.05). Therefore, the most stable period for alfalfa spring seeding in the central area of South Korea is considered to be from February 24 to April 4, with February 24 indentified as the optimal date.

식량 작물의 확보 및 생산량 예측은 국가 발전에 있어 필수적이며, 국가 경제뿐만 아니라 전 세계 식량 안보에 기여 한다. 최근 환경오염으로 인한 이상기후는 식량 작물 생산량에 직ㆍ간접적으로 부정적 영향을 끼치고 있어, 작물 수확량 예측 불확실성이 높아지고 있다. 특히, 노지 작물의 경우 생산량 감소와 품질 저하 문제가 화두 되고 있다. 이러한 문제는 농가들뿐만 아니라 소비자들에게도 큰 피해를 안겨주고 있다. 이러한 생산량 예측 이슈를 해결하기 위해 최근에는 인공지능 기술이 농업 분야에도 활발히 적용되고 있다. 작물 수확량의 정확한 예측을 위한 머신러닝 기반 연구가 집중적으로 수행되고 있다. 따라서, 본 연구에서는 이와 같은 인공지능 기반의 노지 작물 수확량 예측 기술(머신러닝, 딥러닝, 하이브리드 모델 등) 현황 및 작물 수확량에 가장 영향을 많이 끼치는 모델 파라미터 등을 조사하였다.

This study was conducted with the aim of confirming the impact and relative contribution of extreme weather to dry matter yield (DMY) of silage corn in the central inland region of Korea. The corn data (n=1,812) were obtained from various reports on the new variety of adaptability experiments conducted by the Rural Development Administration from 1978 to 2017. As for the weather variables, mean aerial temperature, accumulated precipitation, maximum wind speed, and sunshine duration, were collected from the Korean Meteorological Administration. The extreme weather was detected by the box plot, the DMY comparison was carried out by the t-test with a 5% significance level, and the relative contribution was estimated by R2 change in multiple regression modeling. The DMY of silage corn was reduced predominantly during the monsoon in summer and autumn, with DMY damage measuring 1,500-2,500 kg/ha and 1,800 kg/ha, respectively. Moreover, the relative contribution of the damage during the monsoons in summer and autumn was 40% and 60%, respectively. Therefore, the impact of autumn monsoon season should be taken into consideration when harvesting silage corn after late August. This study evaluated the effect of extreme weather on the yield damage of silage corn in Korea and estimated the relative contribution of this damage for the first time.

본 연구는 우리나라에서 수수-수단그라스 교잡종 (sorghum bicolor L.: SSH)에 대해 극단기상과 정상기상 간 생산량을 비교할 목적으로 수행하였다. SSH 데이터 (n=1,025)는 농촌진흥청의 신품종 적응성 실험보고서(1979 ―2019)로부터 수집하였다. 기상자료는 기상청으로부터 평균기온, 최저기온, 최고기온, 최대 강수량, 누적 강수량, 최대풍속, 평균풍속 및 일조시간을 10일 기준으로 계산하 여 수집하였다. 극단기상과 정상기상 간 구별을 위해 상 자 그림을 이용하여 탐색하였다. 극단기상과 정상기상 간 생산량 차이는 5% 유의수준 하에서 t-검정 및 ANOVA를 통해 확인하였다. 그 결과, 극단기상은 극단적으로 강한 바람을 동반한 봄 가뭄, 극단적으로 높은 강우량을 기록 하는 여름장마와 가을장마가 두드러졌다. 예측 생산량 피 해(kg/ha)는 각각 1,961―6,541, 2,161―4,526 및 508― 5,582로 나타났다. 본 연구는 우리나라의 SSH에 대한 취 약성 및 피해 산정에 도움이 되는 기초자료로서 극단기상 과 정상기상 사이의 생산량 차이를 확인하는 데 의의가 있다.

Climate change is a major global problem. Oysters, one of the most representative farmed fish in Korea, are attracting attention as candidates for blue carbon, an alternative to carbon neutrality. This study is analyzed by the SSP scenarios to determine the impact of oyster aquaculture production according to climate change. Based on the analysis, future productions of oysters are predicted by the SSP scenario. Significant differences by the SSP scenario are confirmed through predictive power tests among scenarios. Regression analysis was conducted from January 2001 to December 2014. As a result of the analysis, water temperature, water temperature quadratic term, salinity, salinity quadratic term, and month × water temperature cross term were estimated as significant variables. Oyster production which is predicted by the SSP scenario based on the significant variables from 2015 to 2022 was compared with actual production. The model with the highest predictive power was selected by RMSE and MAPE criteria. The predictive power was compared with the MDM test to determine which model was superior. As a result, based on RMSE and MAPE, the SSP1-2.6 scenario was selected as the best model and the SSP1-2.6, SSP2-4.5, and SSP3-7.0 scenarios all showed the same predictive power based on the MDM test. In conculusion, this study predicted oyster aquaculture production by 2030, not the distant future, due to the short duration of the analytical model. This study was found that oyster aquaculture production increased in all scenarios and there was no significant difference in predictive power by the SSP scenario.

This study was conducted to estimate the damage of Whole Crop Corn (WCC; Zea Mays L.) according to abnormal climate using machine learning as the Representative Concentration Pathway (RCP) 4.5 and present the damage through mapping. The collected WCC data was 3,232. The climate data was collected from the Korea Meteorological Administration's meteorological data open portal. The machine learning model used DeepCrossing. The damage was calculated using climate data from the automated synoptic observing system (ASOS, 95 sites) by machine learning. The calculation of damage was the difference between the dry matter yield (DMY)normal and DMYabnormal. The normal climate was set as the 40-year of climate data according to the year of WCC data (1978-2017). The level of abnormal climate by temperature and precipitation was set as RCP 4.5 standard. The DMYnormal ranged from 13,845-19,347 kg/ha. The damage of WCC which was differed depending on the region and level of abnormal climate where abnormal temperature and precipitation occurred. The damage of abnormal temperature in 2050 and 2100 ranged from -263 to 360 and -1,023 to 92 kg/ha, respectively. The damage of abnormal precipitation in 2050 and 2100 was ranged from -17 to 2 and -12 to 2 kg/ha, respectively. The maximum damage was 360 kg/ha that the abnormal temperature in 2050. As the average monthly temperature increases, the DMY of WCC tends to increase. The damage calculated through the RCP 4.5 standard was presented as a mapping using QGIS. Although this study applied the scenario in which greenhouse gas reduction was carried out, additional research needs to be conducted applying an RCP scenario in which greenhouse gas reduction is not performed.

This study aimed to confirm the importance ratio of climate and management variables on production of orchardgrass in Korea (1982―2014). For the climate, the mean temperature in January (MTJ, ℃), lowest temperature in January (LTJ, ℃), growing days 0 to 5 (GD 1, day), growing days 5 to 25 (GD 2, day), Summer depression days (SSD, day), rainfall days (RD, day), accumulated rainfall (AR, mm), and sunshine duration (SD, hr) were considered. For the management, the establishment period (EP, 0―6 years) and number of cutting (NC, 2nd―5th) were measured. The importance ratio on production of orchardgrass was estimated using the neural network model with the perceptron method. It was performed by SPSS 26.0 (IBM Corp., Chicago). As a result, EP was the most important variable (100%), followed by RD (82.0%), AR (79.1%), NC (69.2%), LTJ (66.2%), GD 2 (63.3%), GD 1 (61.6%), SD (58.1%), SSD (50.8%) and MTJ (41.8%). It implies that EP, RD, AR, and NC were more important than others. Since the annual rainfall in Korea is exceed the required amount for the growth and development of orchardgrass, the damage caused by heavy rainfall exceeding the appropriate level could be reduced through drainage management. It means that, when cultivating orchardgrass, factors that can be controlled were relatively important. Although it is difficult to interpret the specific effect of climates on production due to neural networking modeling, in the future, this study is expected to be useful in production prediction and damage estimation by climate change by selecting major factors.

생물환경조절학회지 30권 3호에 게재된 논문의 그래프를 수정합니다.

본 연구에서는 ‘설향’ 딸기를 두 작기(2020－2021년, 2021 －2022년)에 걸쳐 재배하면서 외부 광환경과 생육도일온도 가 작물 생산량에 미치는 영향을 분석하였다. 2년 동안 온실 내 환경 관리, 양액 관리 등은 동일하게 하였다. 재배기간 중 주 간의 온실 온습도는 두 작기에서 유사하게 관리되었고, 야간 의 온습도는 통계적으로 차이가 있었으나 작물 생육 범위를 벗어나지 않았다. 일사량은 9월과 10월에 첫 번째 작기의 일 평균 일사량이 많아 누적일사량도 많았으며, 11월부터는 2월 까지는 두 번째 작기의 일사량, 3월에는 다시 첫 번째 작기의 일사량이 많은 것으로 나타나 1월부터의 누적일사량은 두 번 째 작기에서 많은 것으로 나타났다. 딸기의 최적 일장 조건인 8시간 이상의 일장이 나타난 일은 두 작기 간 큰 차이가 없었고, 변화 양상은 누적일사량의 변화와 유사하게 나타났다. 누 적일사량과 생육도일온도는 상관관계가 커 생육도일온도가 딸기의 생산량과 당도에 미치는 영향을 조사해 본 결과의 초 기의 누적일사량과 생육도일온도가 적었던 두 번째 작기에서 초기 수확량은 적었으나 누적일사량 및 생육도일온도가 증가 함에 따라 후기에 수확량이 첫 번째 작기보다 많았으며 잠재 적 최대 생산량도 큰 것으로 나타났다. 당도는 생육도일온도 가 증가함에 따라 감소하였으며, 이는 촉성딸기의 특성으로 판단된다. 추후 연구를 통해 단순 수확량뿐만 아니라 작물 생 육, 꽃눈분화 및 출뢰시기를 조사, 분석하여 생육도일온도가 작 물 생육에 미치는 영향을 다각도로 분석하는 연구도 필요하다 고 판단된다.

난자의 성숙과정과 노화에 관한 이해는 인공수정과 체외수정 최적기를 판단하기 위하여 가장 중요한 연구내용으로 알려져 있다. 이러한 기작은 번식 호르몬들에 의하여 조절되는 것으로 알려져 있으나 난자 세포질 변화에 관한 내용은 잘 알려져 있지 않다. 본 연구에서는 산화질소물(nitric oxide, NO)이 난자 성숙과정에서 증가하는 것을 밝혔으며 난자의 미성숙단계(germinal vesicle stage, GV)와 난자핵막붕괴단계(germinal vesicle breakdown, GVBD) 및 성숙완료단계(metaphase II, MII)단계에서 생산되는 NO의 양을 비교하였다. 또한, 난자를 체외에서 배양할 때, MII단계로 성숙되지 않는 성장 단계의 난자에서는 NO의 증가 현상을 관찰할 수 없었고, 세포질이 불균일한 노화된 난자에서는 NO가 증가된 상태로 유지되는 특성이 있음을 밝혔다. 이러한 결과는 NO의 작용이 난자의 성숙과정과 난자 노화과정에서 중요한 기능을 담당하고 있음을 보여주고 있다.

Strawberry is a stand-out cultivating fruit in Korea. The optimum production of strawberry is highly dependent on growing environment. Smart farm technology, and automatic monitoring and control system maintain a favorable environment for strawberry growth in greenhouses, as well as play an important role to improve production. Moreover, physiological parameters of strawberry plant and it is surrounding environment may allow to give an idea on production of strawberry. Therefore, this study intends to build a machine learning model to predict strawberry’s yield, cultivated in greenhouse. The environmental parameter like as temperature, humidity and CO2 and physiological parameters such as length of leaves, number of flowers and fruits and chlorophyll content of ‘Seolhyang’ (widely growing strawberry cultivar in Korea) were collected from three strawberry greenhouses located in Sacheon of Gyeongsangnam-do during the period of 2019-2020. A predictive model, Lasso regression was designed and validated through 5-fold cross-validation. The current study found that performance of the Lasso regression model is good to predict the number of flowers and fruits, when the MAPE value are 0.511 and 0.488, respectively during the model validation. Overall, the present study demonstrates that using AI based regression model may be convenient for farms and agricultural companies to predict yield of crops with fewer input attributes.

This study aimed to analyze causality of climatic factors that affecting the yield of whole crop barley (WCB) by constructing a network within the natural ecosystem via the structural equation model. The WCB dataset (n=316) consisted of data on the forage information and climatic information. The forage information was collected from numerous experimental reports from New Cultivars of Winter Crops (1993-2012) and included details of fresh and dry matter yield, and the year and location of cultivation. The climatic information included details of the daily mean temperature, precipitation, and sunshine duration from the weather information system of the Korea Meteorological Administration. The variables were growing days, accumulated temperature, precipitation, and sunshine duration in the season for the period of seeding to harvesting. The data was collected over 3 consecutive seasons—autumn, winter, and the following spring. We created a causality network depicting the effect of climatic factors on production by structural equation modeling. The results highlight: (i) the differences in the longitudinal effects between autumn and next spring, (ii) the factors that directly affect WCB production, and (iii) the indirect effects by certain factors, via two or more paths. For instance, the indirect effect of precipitation on WCB production in the following spring season via its effect on temperature was remarkable. Based on absolute values, the importance of WCB production in decreasing order was: the following spring temperature (0.45), autumn temperature (0.35), wintering (-0.16), and following spring precipitation (0.04). Therefore, we conclude that other climatic factors indirectly affect production through the final pathway, temperature and growing days in the next spring, in the climate-production network for WCB including temperature, growing days, precipitation and sunshine duration.

전남지역의 완도, 진도, 해남을 대상으로 난대상록활엽수림 복원 시 붉가시나무 종실 공급과 묘목 양성에 대한 정보 필요성에 따라 붉가시나무의 종실 생산량 및 종실 형질 특성을 조사 분석하였다. 조사 분석을 위해 표면적 1㎡의 종자 트랩을 10개(완도 8개, 해남 1개, 진도 1개) 방형구에 방형구 당 3개씩 총 30개를 설치하였다. 2013년부터 2016년 까지 매년 8월에서 12월까지 매월 말 종자 트랩 내로 낙하한 종실을 수거하였으며, 낙하 종실을 수거해 건전, 충해, 부후, 쭉정이 등으로 구분 후 종실 생산량을 산정하였다. 건전 종실의 경우 각두를 제거한 종실의 길이, 지름, 무게 등 종실 형질을 측정하였다. 조사한 종실 생산량 및 종실 형질은 연별, 임분별, 월별, 처리구별 등을 연평균 값 비교분석 을 위해 Duncan의 다중검정 등을 실시하였다. 각 방형구 내 종자 트랩 낙하 종실량은 2013년에 5~350립/3㎡, 2014년에 17~551립/3㎡, 2015년에 5~454립/3㎡, 2016년에 14~705립/3㎡로 방형구 간에 차이가 큰 것으로 나타났으며, 이는 방형구내 임목 밀도 등으로 인한 수광량의 유입차로 추정진다. 전체 연도별 종실 생산량을 ha당 산정한 결과 각각 2013년에 335,000립, 2014년에 932,000립, 2015년에 556,000립, 2016년에 1,037,000립이었으며, 2년을 주기로 다소 차이가 나타났다. 종실 생산량 증감은 임분 간 동시성을 보여 붉가시나무는 임목 개체 간 결실 풍흉 및 결실 시기의 주기성이 뚜렷한 것으로 판단된다. 9월에 가장 많은 종실이 낙하하였으나 충해종실의 피해 또한 많은 것으로 나타나 종실의 조기 낙하를 방제한다면 결실 기간을 높여 충실 종실의 대량생산이 가능할 것으로 판단된다. 지역별 연평균 종실 길이의 경우 유의성이 없었으며, 종실 지름과 종실 무게의 경우 해남 종실이 완도, 진도 종실에 비해 유의적으로 평균값이 높게 나타났다. 월별 연평균 종실 형질은 유의적 차이는 보이지 않았으며, 11월의 연평균 종실 길이, 지름, 무게가 각각 19.72㎜, 12.23㎜, 1.64g으로 8월~11월 중 최대치를 보였다.