• Journal of Biosystems Engineering
• /
• 제26권5호
• /
• pp.475-480
• /
• 2001

Sensing soil organic matter is crucial for precision farming and environment friendly agriculture. Near infra-red(NIR) was utilized to measure the soil organic matter. Multivariate calibration methods, including stepwise multiple linear regression(MLR), principal components recession(PCR) and partial least squares regression(PLS), were applied to soil spectral reflectance data to predict the organic matter content. The effect of soil particle size and water content was studied. The range of soil organic matter contents was from 0.5 to 11%. Near infrared (NIR) region from 700 to 2,500nm was applied. For uniform soil particle size, result had good correlation (R$\^$2/ = 0.984, standard error of prediction= 0.596). The effect of soil particle size could be eliminated with 1st order derivative of the NIR signal. However. moist soil had a little lower correlation. R$\^$2/ was 0.95 and standard error of prediction was 0.94% using the PLS method. The results showed the possibility of soil organic matter measurement using NIR reflectance on the field.

• 인터넷정보학회논문지
• /
• 제20권1호
• /
• pp.11-16
• /
• 2019

노지 정밀농업에서 작물의 생육환경 측정을 위한 무선 센서 네트워크 기술이 중요시되고 있지만 무선 신호는 다양한 전파장애 요인들에 의해 통신 장애가 발생할 수 있다. 이 논문은 노지 관수를 위해 로라 기반 환경 모니터링과 일기예보 정보수집 시스템을 설계 및 구현하고 이를 테스트베드에 적용하였다. 그리고 장애물이 있는 환경과 장애물이 없는 환경, 비 오는 날과 비 오지 않은 날 각각에 대하여 사설 로라 네트워크의 패킷 손실률을 비교 분석하였으며, 장애물이 있는 로라 네트워크는 강우량이 많은 날은 패킷손실에 민감함을 알 수 있었다.

• 스마트미디어저널
• /
• 제11권7호
• /
• pp.94-103
• /
• 2022

Weeds bring disadvantages to crops since they can damage them, and a clean treatment with less pollution and contamination should be developed. Artificial intelligence gives new hope to agriculture to achieve smart farming. This study delivers an automated weeds growth point detection using deep learning. This study proposes a combination of semantic graphics for generating data annotation and U-Net with pre-trained deep learning as a backbone for locating the growth point of the weeds on the given field scene. The dataset was collected from an actual field. We measured the intersection over union, f1-score, precision, and recall to evaluate our method. Moreover, Mobilenet V2 was chosen as the backbone and compared with Resnet 34. The results showed that the proposed method was accurate enough to detect the growth point and handle the brightness variation. The best performance was achieved by Mobilenet V2 as a backbone with IoU 96.81%, precision 97.77%, recall 98.97%, and f1-score 97.30%.

• 한국근적외분광분석학회:학술대회논문집
• /
• 한국근적외분광분석학회 2001년도 NIR-2001
• /
• pp.1062-1062
• /
• 2001

The concept of “precision agriculture” or “site-specific farming” is usually confined to the fields of soil science, crop science and agronomy. However, because plants grow in soil, animals eat plants, and humans eat animal products, it could be argued (perhaps with some poetic licence) that the fields of feed quality, animal nutrition and animal production should also be considered in this context. NIR spectroscopy has proved over the last 20 years that it can provide a firm foundation for quality measurement across all of these fields, and with the continuing developments in instrumentation, computer capacity and software, is now a major cog in the wheel of precision agriculture. There have been a few giant leaps and a lot of small steps in the impact of NIR on the animal world. These have not been confined to the amazing advances in hardware and software, although would not have occurred without them. Rapid testing of forages, grains and mixed feeds by NIR for nutritional value to livestock is now commonplace in commercial laboratories world-wide. This would never have been possible without the pioneering work done by the USDA NIR Forage Research Network in the 1980's, following the landmark paper of Norris et al. in 1976. The advent of calibration transfer between instruments, algorithms which utilize huge databases for calibration and prediction, and the ability to directly scan whole grains and fresh forages can also be considered as major steps, if not leaps. More adventurous NIR applications have emerged in animal nutrition, with emphasis on estimating the functional properties of feeds, such as in vivo digestibility, voluntary intake, protein degradability and in vitro assays to simulate starch digestion. The potential to monitor the diets of grazing animals by using faecal NIR spectra is also now being realized. NIR measurements on animal carcasses and even live animals have also been attempted, with varying degrees of success, The use of discriminant analysis in these fields is proving a useful tool. The latest giant leap is likely to be the advent of relatively low-cost, portable and ultra-fast diode array NIR instruments, which can be used “on-site” and also be fitted to forage or grain harvesters. The fodder and livestock industries are no longer satisfied with what we once thought was revolutionary: a 2-3 day laboratory turnaround for fred quality testing. This means that the instrument needs to be taken to the samples rather than vice versa. Considerable research is underway in this area, but the challenge of calibration transfer and maintenance of instrument networks of this type remains. The animal world is currently facing its biggest challenges ever; animal welfare, alleged effects of animal products on human health, environmental and economic issues are difficult enough, but the current calamities of BSE and foot and mouth disease are “the last straw” NIR will not of course solve all these problems, but is already proving useful in some of these areas and will continue to do so.

• 한국잡초학회지
• /
• 제18권2호
• /
• pp.154-160
• /
• 1998

본(本) 연구(硏究)는 벼 건답직파재배(乾畓直播栽培) 잡초방제(雜草防除)에 우수한 경엽처리형(莖葉處理型) 혼합제초제(混合除草劑)를 선발(選拔)하기 위해 3원(元) 2차(次) UPCCD계획법(計劃法)을 이용(利用)하여 건답직파재배(乾畓直播栽培)에서 문제(問題)가 되고 있는 피, 너도방동사니 등의 잡초(雜草)를 방제대상(防除對象)으로 cyhalofop, bispyribenzoxim, pyrazosulfuron 간(間)의 상호작용(相互作用) 및 혼합효과(混合效果)를 구명(究明)함과 아울러 제초제분야(除草劑分野)에서 UPCCD계획법(計劃法)의 활용가능성(活用可能性)을 검토(檢討)하였다. (1)제초제분야(除草劑分野)에서 직선(直線) 및 2차곡선(次曲線) 관계(關係)를 나타내는 반응(反應)또는 비수식(指數式), 대수식(對數式) 관계(關係)를 나타내는 반응(反應)이라도 혼합제초제(混合除草劑)의 처리량(處理量) 범위(範圍)를 적당(適當)히 선정(選定)하면 UPCC계획법(計劃法)을 응용(應用)하여 제초제간(除草劑間)의 상호작용(相互作用) 및 혼합제(混合劑)의 혼합효과(混合效果) 분석(分析)은 가능(可能)하였다. (2) 제초제(除草劑) cyhalofop, bispyribenzoxim 및 pyrazosulfuron 혼합처리시(混合處理時) 피에 대한 억제효과(抑制效果)는 cyhalofop, bispyribenzoxim, pyrazosulfuron 순(順)이었고 제초제간(除草劑間)에 상가작용(相加作用)이 존재하는 동시(同時)에 cyhalofop와 bispyribenzoxim 간(間)에 역상호작용(逆相互作用)이 존재하여 "부분적 상가작용(相加作用)"이 검정(檢定)되었다. (3) 너도방동사니에 대한 억제효과(抑制效果)는 pyrazosulfuron, bispyribenzoxim 순(順)이었고 cyhalofop의 억제효과(抑制效果)는 인정되지 않았으며, pyrazosulfuron과 bispyribenzoxim 간(間)에는 상가작용(相加作用)이 있었다. (4) 사마귀풀에 대한 억제효과(抑制效果)는 bispyribenzoxim, pyrazosulfuron 순(順)이었고 cyhalofop의 억제효과(抑制效果)는 인정되지 않았으며 bispyribenzoxim과 pyrazosulfuron 간(間)에 상가적작용(相加的作用)이 있었다. 피, 너도방동사니 및 사마귀풀 등의 3종(種) 잡초(雜草)의 $ED_{90}$을 나타내는 cyhalofop+bispyribenzoxim+pyrazosulfuron 적정혼합(適正混合) 처리량(處理量)은 100+12+10g ai/ha 이었다.

• 생물환경조절학회지
• /
• 제31권3호
• /
• pp.152-162
• /
• 2022

본 연구는 데이터를 기반으로 한 인공지능 기계학습 기법을 활용하여 온실 내부온도 예측 시뮬레이션 모델을 개발을 수행하였다. 온실 시스템의 내부온도 예측을 위해서 다양한 방법이 연구됐지만, 가외 변인으로 인하여 기존 시뮬레이션 분석방법은 낮은 정밀도의 문제점을 지니고 있다. 이러한 한계점을 극복하기 위하여 최근 개발되고 있는 데이터 기반의 기계학습을 활용하여 온실 내부온도 예측 모델 개발을 수행하였다. 기계학습모델은 데이터 수집, 특성 분석, 학습을 통하여 개발되며 매개변수와 학습방법에 따라 모델의 정확도가 크게 변화된다. 따라서 데이터 특성에 따른 최적의 모델 도출방법이 필요하다. 모델 개발 결과 숨은층 증가에 따라 모델 정확도가 상승하였으며 최종적으로 GRU 알고리즘과 숨은층6에서 r² 0.9848과 RMSE 0.5857℃로 최적 모델이 도출되었다. 본 연구를 통하여 온실 외부 데이터를 활용하여 온실 내부온도 예측 모델 개발이 가능함을 검증하였으며, 추후 다양한 온실데이터에 적용 및 비교분석이 수행되어야 한다. 이후 한 단계 더 나아가 기계학습모델 예측(predicted) 결과를 예보(forecasting)단계로 개선하기 위해서 데이터 시간 길이(sequence length)에 따른 특성 분석 및 계절별 기후변화와 작물에 따른 사례별로 개발 모델을 관리하는 등의 다양한 추가 연구가 수행되어야 한다.

• 한국측량학회지
• /
• 제38권3호
• /
• pp.223-235
• /
• 2020

본 연구에서는 무인항공기 영상 기반의 정밀농업(precision agricultural) 구현에 있어 핵심 데이터 중 하나인 수치표고모델의 표고를 보정하기 위한 수치표고모델 표고 보정 방법론을 제시한다. 먼저 정사영상에 방사보정을 수행한 다음 ExG (Excess Green)를 생성한다. ExG에 Otsu 기법을 적용하여 산출된 임계값을 기준으로 비식생지역을 추출한다. 이어서, 비식생지역의 위치에 대응되는 수치표고모델의 표고를 표고 보정을 위한 데이터인 EIFs(Elevation Invariant Features)로 추출한다. 추출된 EIFs 간 차이값을 기반으로 정규화된 Z-score를 산출하여 포함된 특이치를 제거한다. 그리고 선형회귀식을 구성하여 수치표고모델의 표고를 보정함으로써 지상기준점 데이터 없이 고품질의 수치표고모델을 제작한다. 총 10장의 수치표고모델을 활용하여 제안기법을 검증하기 위해 표고 보정 전과 후의 최대/최소값, 평균/표준편차를 비교분석하였다. 또한, 검사점을 선정하여 RMSE (Root Mean Square Error)를 산출한 결과, 정확도는 평균 RMSE 0.35m로 도출되었다. 이를 통해 지상기준점 데이터 없이 고품질의 수치표고모델을 제작할 수 있음을 확인하였다.

• Journal of Ecology and Environment
• /
• 제38권3호
• /
• pp.327-334
• /
• 2015

We investigated the current and potential spatial distributions and habitable areas of Biston robustum and Camellia japonica in South Korea in order to provide useful data for the conservation of C. japonica and minimize the damage caused by B. robustum. It was predicted that, by 2070, although B. robustum would be widely distributed throughout the Korean Peninsula, except for the western and eastern coastal areas, it would be narrowly distributed along the Sokcho-si and Goseong-gun coastlines in Gangwon Province. C. japonica is currently located along the southern coastline but its critical habitable area is predicted to gradually disappear by 2070. Assessment of the potential distribution probabilities of B. robustum and C. japonica revealed that the area under the curve (AUC) values were 0.995 and 0.991, respectively, which indicate high precision and applicability of the model. Major factors influencing the potential distribution of B. robustum included precipitation of wettest quarter and annual precipitation (BIO16 and BIO12), whereas annual mean temperature and mean temperature of wettest quarter (BIO1 and BIO8) were important variables for explaining C. japonica distribution. Overlapping areas of B. robustum and C. japonica were $11,782km^2$, $5447km^2$, and $870km^2$ for the current, 2050-predicted, and 2070-predicted conditions, respectively, clearly showing a dramatic decrease in area. Although it is predicted that B. robustum would cause continuous damage to C. japonica in the southern part of the Korean Peninsula, such impacts might diminish over time and become negligible in the future.

• Journal of Ecology and Environment
• /
• 제38권1호
• /
• pp.15-23
• /
• 2015

This study was conducted in an effort to provide important clues pertaining to the conservation and restoration of Aporia crataegi by identifying the spatial distribution characteristics of the current habitats, prospective habitats, and future habitats of A. crataegi in accordance with climate changes. To determine the distribution of A. crataegi, data from a total of 36 collecting points throughout South Korea, North Korea, China, Japan, Mongolia, and Russia are used. The spatial distributions of the data were examined through MaxEnt modeling. The distribution probability rates exceeded 75% at 18 locations among the 36 species occurrence locations, with Gangwon province showing the highest distribution probability in South Korea. The precision of the MaxEnt model was remarkably high, with an AUC value of 0.982. The variables that affect the potential distribution of A. crataegi by more than 10% are the degree of temperature seasonality, the amount of precipitation in the warmest quarter, the annual mean temperature, and the amount of precipitation in the driest month, in that order of importance. It was found that the future potential distribution area of A. crataegi continuously moves northward over time up to 2070s. In addition, the area of the potential distribution showing a habitable probability rate that exceeds 75% in northeast Asia was $28,492km^2$, where the area of potential distribution in the north part of Korean peninsula was $20.404km^2$ in size. Thus, it is anticipated that the most important future habitats of A. crataegi in the northeast Asia will be North and South Hamgyeong provinces and Ryanggang province near Mt. Baekdoosan in the northern area of the Korean peninsula.

• 한국환경농학회지
• /
• 제39권2호
• /
• pp.142-169
• /
• 2020

BACKGROUND: A new analytical method has been developed to determine 261 pesticide residues in herbal medicines. METHODS AND RESULTS: The extraction of pesticides was carried out by modified method of the Korea Food Standards Codex sample extraction and determination was performed using GC-MS/MS and LC-MS/MS. During the pre-treatment process of the test method, Solid-liquid separation was changed to centrifugation. The method was validated by the precision and accuracy results. 261 pesticides spiked at three level 20, 50, 100 ug/kg in herbal medicines. The limit of quantification of method were 4-40 ug/kg for GC-MS/MS and 2-45 ug/kg for LC-MS/MS, respectively. Among the pesticides analysed by GC-MS/MS and LC-MS/MS, 244 pesticides (94% of total number) in chinese matrimony vine and 224 pesticides (86% of total number) in korean angelica root and 231 pesticides (89% of total number) in jujube and 214 (82% of total number) in cnidium showed recoveries in the range of 70-120% with RSD⪯20%. CONCLUSION: These results indicated that GC-MS/MS and LC-MS/MS analysis with the sample extraction in this study can be applied to multi-residue analysis of pesticides in herbal medicines.