• The Plant Pathology Journal
• /
• 제38권4호
• /
• pp.395-402
• /
• 2022

To predict rice blast, many machine learning methods have been proposed. As the quality and quantity of input data are essential for machine learning techniques, this study develops three artificial neural network (ANN)-based rice blast prediction models by combining two ANN models, the feed-forward neural network (FFNN) and long short-term memory, with diverse input datasets, and compares their performance. The Blast_Weathe long short-term memory r_FFNN model had the highest recall score (66.3%) for rice blast prediction. This model requires two types of input data: blast occurrence data for the last 3 years and weather data (daily maximum temperature, relative humidity, and precipitation) between January and July of the prediction year. This study showed that the performance of an ANN-based disease prediction model was improved by applying suitable machine learning techniques together with the optimization of hyperparameter tuning involving input data. Moreover, we highlight the importance of the systematic collection of long-term disease data.

• 한국환경농학회지
• /
• 제19권5호
• /
• pp.401-418
• /
• 2000

1. Production of the artificial zeolite from coal ash Coal fly ash is mainly composed of several oxides including $SiO_2$ and $Al_2O_3$ derived from inorganic compounds remained after burning. As minor components, $Fe_2O_3$ and oxides of Mg, Ca, P, Ti (trace) are also contained in the ash. These components are presented as glass form resulting from fusion in the process of the combustion of coal. In other word, coal ash may refer to a kind of aluminosilicate glass that is known to easily change to zeolite-like materials by hydrothermal reaction. Lots of hot seawater is disposing near thermal power plants after cooling turbine generator periodically. Using seawater in the hydrothermal reaction caused to produce low price artificial zeolite by reduction of sodium hydroxide consumption, heating energy and water cost. As coal ash were reacted hydrothermally, peaks of quartz and mullite in the ash were weakened and disappeared, and new Na-Pl peaks were appeared strengthily. Si-O-Si bonding of the bituminous coal ash was changed to Si-O-Al (and $Fe^{3+}$) bonding by the reaction. Therefore the produced Na-Pl type zeolite had high CEC of 276.7 $cmol^+{\cdot}kg^{-1}$ and well developed molecular sieve structure with low concentration of heavy metals. 2. Utilization of the artificial zeolite in agro-environment The artificial zeolite(1g) could remove 123.5 mg of zinc, 164.7 mg copper, 184.4 mg cadmium and 350.6 mg lead in the synthetic wastewater. The removability is higher 2.8 times in zinc, 3.3 times in copper, 4.7 times in cadmium and 4.8 times in lead than natural zeolite and charcoal powder. When the heavy metals were treated at the ratio of 150 $kg{\cdot}ha^{-1}$ to the rice plant, various growth inhibition were observed; brownish discoloration and death of leaf sheath, growth inhibition in culm length, number of panicles and grains, grain ripening and rice yield. But these growth inhibition was greatly alleviated by the application of artificial zeolite, therefore, rice yield increased $1.1{\sim}3.2$ times according to the metal kind. In addition, the concentration of heavy metals in the brown rice also lowered by $27{\sim}75%$. Artificial Granular Zeolites (AGZ) was developed for the purification of wastewater. Canon exchange capacity was 126.8 $cmol^+{\cdot}kg^{-1}$. AGZ had Na-Pl peaks mainly with some minor $C_3S$ peaks in X-ray diffractogram. In addition, AGZs had various pore structure that may be adhere the suspended solid and offer microbiological niche to decompose organic pollutants. AGZ could remove ammonium, orthophosphate and heavy metals simultaneously. Mixing ratio of artificial zeolite in AGZs was related positively with removal efficiency of $NH_4\;^+$ and negatively with that of $PO_4\;^{3-}$. Root growth of rice seedling was inhibited severely in the mine wastewater because of strong acidity and high concentration of heavy metals. As AGZ(1 kg) stayed in the wastewater(100L) for 4days, water quality turned into safely for agricultural usage and rice seedlings grew normally.

• 한국작물학회:학술대회논문집
• /
• 한국작물학회 2021년도 춘계학술대회
• /
• pp.119-119
• /
• 2021

• Journal of Forest and Environmental Science
• /
• 제35권1호
• /
• pp.25-30
• /
• 2019

The composition of artificial soil in a containerized seedling production plays an important role in seedling quality as well as environmental issues. We investigated the effects of different types of biomaterials and mixed ratio with artificial soil on the growth of Fraxinus rhynchophylla seedlings. Soil medium was supplemented with 3 levels (0%, 10%, 20%) of pine bark, mushroom sawdust and rice husk. Root collar diameter (RCD), height growth, and biomass have significantly increased when rice husk was applied. Compared with the control, RCD and height growth showed highest in 20% rice husk treatment with an increase of 5.7% and 17.6%, respectively. In contrast, the treatments of pine bark and mushroom sawdust showed lower results in growth parameters (RCD, height growth, and total biomass) than control. Seedling quality index was also highest at the 20% rice husk treatment, but there was not statistically different among treatments. Our results suggested rice husk can be substituted up to 20% of substrates for containerized F. rhynchophylla seedling production system.

• 한국응용곤충학회지
• /
• 제41권2호
• /
• pp.85-89
• /
• 2002

멸강나방의 발육과 생식에 먹이(옥수수잎, 벼잎, 배추잎,양배추잎, 콩잎 그리고 누에인공사료)가 미치는 영향을 조사하였다. 알과 번데기기간은 먹이간에 유의성이 없었으나, 유충기간은 유의성이 있었다. 총발육기간(알에서 성충까지)은 옥수수잎에서 32.5일로 가장 짧았고 콩잎에서 46.6일로 가장 길었다. 부화 후 16일째의 유충 무게는 벼잎과 누에인공사료에서 무거웠던 반면, 고구마잎과 양배추잎에서는 가벼웠고 용화하지 못했다. 번데기 무게는 벼잎에서 가장 무거웠다. 부화유충에서 성충까지의 생존율은 옥수수잎에서 70.6%로 가장 높았고, 콩잎에서 39.8%로 가장 낮았다. 암컷 성충의 수명은 먹이간에 큰차이는 없었다. 암컷 한 마리당 평균 총산란수는 벼잎, 옥수수및, 누에인공사료에서 사육한 경우가 배추및, 콩잎보다 많았다. 1세대 순증가율(R$_{0}$)은 누에인공사료에서 1218.5로 가장 높았으며, 내적자연증가율(R$_{0}$)의 범위는 0.115-0.175로 옥수수잎에서 가장 높았다.

• 한국자원식물학회지
• /
• 제19권5호
• /
• pp.612-616
• /
• 2006

최근 GMO 작물의 재배, 생산이 날로 늘어나며 GMO 작물이 환경에 미칠 수 있는 많은 가능성들이 대두되고 있다. 특히 GMO 작물과 야생종과의 자연교잡에 의한 유전자 전이로, 잡초화의 문제점이 제기되며 생태계의 변화 및 파괴의 위험성이 우려되고 있다. 본 실험에서는 GM벼와 야생 및 근연종 사이의 교잡가능성 및 유전자 전이율을 조사하기 위한 유전자 이동의 분석 체계를 확립하고자 하였다. 벼의 개화시기에 GM벼와 야생 및 근연종 간의 인공교배 후 수확한 교잡 추정 종자를 발아시켜서 제초제를 처리하여 교잡종자를 선별하였다. 또한 GM 벼 및 야생 근연종벼들 간의 RAPD PCR 분석을 통해 선별한 marker를 사용하여 낙동 교잡벼와 샤레 교잡벼가 GM 벼와 교배된 식물체임을 확인하였다. PCR 분석을 수행한 결과 GM벼에서 도입된 trehalose-6-phosphate phosphatase (TPP) 유전자와 선별marker로 사용된 bar유전자가 GM벼 뿐만 아니라 샤레 교잡벼에도 존재하였으며, 결과적으로 GM벼의 bar 및 tpp 유전자가 잡초성벼인 샤레 교잡벼에 전이되었음을 검증할 수 있었다.

• 식물병과 농업
• /
• 제5권2호
• /
• pp.111-114
• /
• 1999

A bacterial disease of rice plant that rotted the sheath to brown was found in rice plants at Tanbuk Uisong Kyungbuk in June 1999, When the bacterial isolates from the diseased rice plants were inoculated to health plant by the artificial needle prick method the same symptoms were examined. According to its characteristics and pathogenicity on the his plant the causal bacterium was identified as Burkholderia glumae which is known as the pathogen of bacterial grain rot of rice.

• 한국작물학회:학술대회논문집
• /
• 한국작물학회 2021년도 춘계학술대회
• /
• pp.117-117
• /
• 2021

• Journal of Biosystems Engineering
• /
• 제22권3호
• /
• pp.333-342
• /
• 1997

The objective of this research was to develop model equations for measuring rice milling ratio by using visible / HIR spectroscopy. Twelve kinds of brown rice(n = 149) were milled to obtain various milling ratio ranged from 86% to 94%. Visible/NIR spectra were collected with a spectrophotometer with sample transport module. The reflectance and transmission spectra were measured in the range of 400~2, 500nm and 600~1, 400nm, respectively, with 2 nm intervals. Multiple linear regression(MLR), Partial least square (PLS), and Artificial neural network(ANN) were used to develop models. Model developed with reflectance spectra showed better prediction results then those with transmission spectra. The MLR model with six-wavelength obtained from first derivative spectra gave to the best results for measuring the rice milling ratio(SEP = 0.535, , $r^2$ = 0.980). The PLS model(SEP = 0.604, $r^2$= 0.976) and ANN model(SEP = 0.566, $r^2$= 0.978) also can be used to determine the rice milling ratio effectively.

• Applied Biological Chemistry
• /
• 제29권3호
• /
• pp.241-247
• /
• 1986

쌀밥 품질의 영향 요인을 규명하기 위하여 밥 짓기 과정중 밥과 밥물의 상호 관계를 분석하고, 저급의 장립종 밀양 23호의 밥맛 증진의 수단으로 새로운 밥짓기 방법을 제시하였다. 밥짓기 과정중 밥과 밥물의 높이 변화를 측정하였다. 끊는점 부근에서 밥물이 급격히 감소하고, 이어서 농축된 밥물이 밥알 표면에 엷은 피막층을 형성함을 관찰할 수 있었다. 피막 보강 물질로 찹쌀분 1,2%(W/W)를 첨가 한 후 밥짓기를 향한 결과, 피막이 크게 보강되었으며 이렇게 제조된 밥은 윤기와 외관이 향상되고 수분 함량이 증가하였으며 밥짓기중 가용성 쌀 고용분 함량의 용출을 감소시킬 수 있었다. 밥알 피막의 형성은 밥짓기의 최종단계에서 밥알의 진동과 밥물의 고형분 농도와 유관함을 보였고, 밥의 음질 결정의 중요 요소로 작용할 수 있음을 제안하였다.