http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : 수폴 (검색결과 3 건)
- 무료
- 기관 내 무료
- 유료
-
-
Estimation of Reference Evapotranspiration Using Backpropagation Neural Network Model
김민영,최용훈,수잔 오샤네시,폴 콜레이지,김영진,전종길,이상봉 한국농공학회 2019 한국농공학회논문집 Vol.61 No.6
Evapotranspiration (ET) of vegetation is one of the major components of the hydrologic cycle, and its accurate estimation is important for hydrologicwater balance, irrigation management, crop yield simulation, and water resources planning and management. For agricultural crops, ET is oftencalculated in terms of a short or tall crop reference, such as well-watered, clipped grass (reference crop evapotranspiration, ETo). The Penman-Monteithequation recommended by FAO (FAO 56-PM) has been accepted by researchers and practitioners, as the sole ETo method. However, its accuracy iscontingent on high quality measurements of four meteorological variables, and its use has been limited by incomplete and/or inaccurate input data. Therefore, this study evaluated the applicability of Backpropagation Neural Network (BPNN) model for estimating ETo from less meteorological datathan required by the FAO 56-PM. A total of six meteorological inputs, minimum temperature, average temperature, maximum temperature, relativehumidity, wind speed and solar radiation, were divided into a series of input groups (a combination of one, two, three, four, five and six variables)and each combination of different meteorological dataset was evaluated for its level of accuracy in estimating ETo. The overall findings of this studyindicated that ETo could be reasonably estimated using less than all six meteorological data using BPNN. In addition, it was shown that the properchoice of neural network architecture could not only minimize the computational error, but also maximize the relationship between dependent andindependent variables. The findings of this study would be of use in instances where data availability and/or accuracy are limited.
-
다케오 사카이,수폴 루엔요스르에찰,이원창,Sakai Takeo,Luenyosluechaul Supol,Lee Won-Chang The Korean Society of Veterinary Clinics 1993 한국임상수의학회지 Vol.10 No.2
저자들은 일본국내의 종빈돈장에 대한 능력을 관찰코저 시도하여 1990년 1월부터 12월까지사이에 신내천현의 현대식 종빈돈장 일부를 연구대상으로 하여 조사하고, 그 결과를 수의임상통계학적으로 분석, 다음과 같이 적요 한다. 전산화시설에 의한 분석에서, 월평균 종빈돈의 출산은 355이었고, 종빈돈의 종부능력은 월평균 28회이었으며, 이유는 20.8일, 시장출하 비육은 18.8 그리고 연간 평균출산은 2.25이었다. 한편 출산후 포유중 사망률은 평균 17.8%이고, 수의임상적 증상을 나타낸 이환율은 0.2% (200 per 100,000)이었다. Veterinary clinicostatistical observation on the productive performance in a breeding sow herd in Japan during the period from January to December in 1990, in a modernized breeding sow herd in kanagawa prefecture, consist monthly, varied from 347 to 363 sows on production(average 355) and boar on service of between 26~29(average 28) shows computerized analysing figures of moderate high production results per year of 20.8 weaning pigs per sow or 18.8 fatteners at market weight per sow when continue their rearing within farm. Sows perform average 2.25 litters per sow that year. On other hand, morbidity rate of piglets with clinical signs and symptoms was 0.2%(morbidity rate : 200 per 100,000 population In piglets) on average in year and that of mortality rate in suckling from birth was 17.8%, respectively Finally, these information may be used or reference in further study of the field of veterinary clinicostatistics and medicine.
ScienceON
KISS연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
