• Korean Journal of Agricultural and Forest Meteorology
• /
• v.24 no.4
• /
• pp.305-317
• /
• 2022

To investigate the blossom infection risk of fire blight on pears, the program Maryblyt has been executed from 2018 to 2022 based on meteorological data from central-Korean cities where fire blight has occurred as well as from southern Korean cities where the disease has not yet occurred. In the past five years, years with the highest risk of pear blossom blight were 2022 and 2019. To identify the optimal time for spraying, we studied the spray mode according to the Maryblyt model and recommend spraying streptomycin on the day after a "High" warning and then one day before forecasted precipitation during the blossom period. Maryblyt also recommends to initiate surgical controls from mid-May for canker blight symptoms on pear trees owing to over-wintering canker in Korea. Web-cam pictures from pear orchards at Cheonan, Icheon, Sangju, and Naju during the flowering period of pear trees were used for comparing real data and constructing a phenological model. The actual starting dates of flowering at southern cities such as Sangju and Naju were consistently earlier than those calculated by the model. It is thus necessary to improve the forecasting model to include field risks by recording the actual flowering period and the first day of the fire blight symptoms, according to the farmers, as well as mist or dew-fall, which are not easily identifiable from meteorological records.

• Journal of the Korean Geographical Society
• /
• v.41 no.2 s.113
• /
• pp.168-187
• /
• 2006

Windy meteorological conditions and dried fire fuels due to higher atmospheric instability and dryness in the lower troposphere can exacerbate fire controls and result in more losses of forest resources and residential properties due to enhanced large wildland fires. Long-term (1979-2005) climatology of the Haines Index reconstructed in this study reveals that spatial patterns and intra-annual variability of the atmospheric instability and dryness in the lower troposphere affect the frequency of wildland fire incidences over the Korean Peninsula. Exponential regression models verify that daily high Haines Index and its monthly frequency has statistically significant correlations with the frequency of the wildland fire occurrences during the fire season (December-April) in South Korea. According to the climatic maps of the Haines Index created by the Geographic Information System (GIS) using the Digital Elevation Model (DEM), the lowlands below 500m from the mean sea level in the northwestern regions of the Korean Peninsula demonstrates the high frequency of the Haines Index equal to or greater than five in April and May. The annual frequency of the high Haines Index represents an increasing trend across the Korean Peninsula since the mid-1990s, particularly in Gyeongsangbuk-do and along the eastern coastal areas. The composite of synoptic weather maps at 500hPa for extreme events, in which the high Haines Index lasted for several days consecutively, illustrates that the cold low pressure system developed around the Sea of Okhotsk in the extreme event period enhances the pressure gradient and westerly wind speed over the Korean Peninsula. These results demonstrate the need for further consideration of the spatial-temporal characteristics of vertical atmospheric components, such as atmospheric instability and dryness, in the current Korean fire prediction system.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_1
• /
• pp.1449-1463
• /
• 2020

As recent global warming and climate changes become more serious, the importance of CO2 absorption by forests is increasing to cope with the greenhouse gas issues. According to the UN Framework Convention on Climate Change, it is required to calculate national CO2 absorptions at the local level in a more scientific and rigorous manner. This paper presents the gridded expansion of forest flux observations and mapping of daily CO2 absorption by the forests in Korea using numerical weather prediction data and satellite images. To consider the sensitive daily changes of plant photosynthesis, we built a machine learning model to retrieve the daily RACA (reference amount of CO2 absorption) by referring to the climax forest in Gwangneung and adopted the NIFoS (National Institute of Forest Science) lookup table for the CO2 absorption by forest type and age to produce the daily AACA (actual amount of CO2 absorption) raster data with the spatial variation of the forests in Korea. In the experiment for the 1,095 days between Jan 1, 2013 and Dec 31, 2015, our RACA retrieval model showed high accuracy with a correlation coefficient of 0.948. To achieve the tier 3 daily statistics for AACA, long-term and detailed forest surveying should be combined with the model in the future.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.141-154
• /
• 2019

Rapid growth of internet technology and social media is progressing. Data mining technology has evolved to enable unstructured document representations in a variety of applications. Sentiment analysis is an important technology that can distinguish poor or high-quality content through text data of products, and it has proliferated during text mining. Sentiment analysis mainly analyzes people's opinions in text data by assigning predefined data categories as positive and negative. This has been studied in various directions in terms of accuracy from simple rule-based to dictionary-based approaches using predefined labels. In fact, sentiment analysis is one of the most active researches in natural language processing and is widely studied in text mining. When real online reviews aren't available for others, it's not only easy to openly collect information, but it also affects your business. In marketing, real-world information from customers is gathered on websites, not surveys. Depending on whether the website's posts are positive or negative, the customer response is reflected in the sales and tries to identify the information. However, many reviews on a website are not always good, and difficult to identify. The earlier studies in this research area used the reviews data of the Amazon.com shopping mal, but the research data used in the recent studies uses the data for stock market trends, blogs, news articles, weather forecasts, IMDB, and facebook etc. However, the lack of accuracy is recognized because sentiment calculations are changed according to the subject, paragraph, sentiment lexicon direction, and sentence strength. This study aims to classify the polarity analysis of sentiment analysis into positive and negative categories and increase the prediction accuracy of the polarity analysis using the pretrained IMDB review data set. First, the text classification algorithm related to sentiment analysis adopts the popular machine learning algorithms such as NB (naive bayes), SVM (support vector machines), XGboost, RF (random forests), and Gradient Boost as comparative models. Second, deep learning has demonstrated discriminative features that can extract complex features of data. Representative algorithms are CNN (convolution neural networks), RNN (recurrent neural networks), LSTM (long-short term memory). CNN can be used similarly to BoW when processing a sentence in vector format, but does not consider sequential data attributes. RNN can handle well in order because it takes into account the time information of the data, but there is a long-term dependency on memory. To solve the problem of long-term dependence, LSTM is used. For the comparison, CNN and LSTM were chosen as simple deep learning models. In addition to classical machine learning algorithms, CNN, LSTM, and the integrated models were analyzed. Although there are many parameters for the algorithms, we examined the relationship between numerical value and precision to find the optimal combination. And, we tried to figure out how the models work well for sentiment analysis and how these models work. This study proposes integrated CNN and LSTM algorithms to extract the positive and negative features of text analysis. The reasons for mixing these two algorithms are as follows. CNN can extract features for the classification automatically by applying convolution layer and massively parallel processing. LSTM is not capable of highly parallel processing. Like faucets, the LSTM has input, output, and forget gates that can be moved and controlled at a desired time. These gates have the advantage of placing memory blocks on hidden nodes. The memory block of the LSTM may not store all the data, but it can solve the CNN's long-term dependency problem. Furthermore, when LSTM is used in CNN's pooling layer, it has an end-to-end structure, so that spatial and temporal features can be designed simultaneously. In combination with CNN-LSTM, 90.33% accuracy was measured. This is slower than CNN, but faster than LSTM. The presented model was more accurate than other models. In addition, each word embedding layer can be improved when training the kernel step by step. CNN-LSTM can improve the weakness of each model, and there is an advantage of improving the learning by layer using the end-to-end structure of LSTM. Based on these reasons, this study tries to enhance the classification accuracy of movie reviews using the integrated CNN-LSTM model.

• Korean Journal of Remote Sensing
• /
• v.14 no.1
• /
• pp.53-68
• /
• 1998

Observation of hydrometeors' behavior in the atmosphere is important to understand weather and climate. By conventional observations, we can get the distribution of water vapor at limited number of points on the earth. In this study, the precipitable water has been estimated from the split window channel data on GMS-5 based upon the technique developed by Chesters et al.(1983). To retrieve the precipitable water, water vapor absorption parameter depending on filter function of sensor has been derived using the regression analysis between the split window channel data and the radiosonde data observed at Osan, Pohang, Kwangiu and Cheju staions for 4 months. The air temperature of 700 hPa from the Global Spectral Model of Korea Meteorological Administration (GSM/KMA) has been used as mean air temperature for single layer radiation model. The retrieved precipitable water for the period from August 1996 through December 1996 are compared to radiosonde data. It is shown that the root mean square differences between radiosonde observations and the GMS-5 retrievals range from 0.65 g/$cm^2$ to 1.09 g/$cm^2$ with correlation coefficient of 0.46 on hourly basis. The monthly distribution of precipitable water from GMS-5 shows almost good representation in large scale. Precipitable water is produced 4 times a day at Korea Meteorological Administration in the form of grid point data with 0.5 degree lat./lon. resolution. The data can be used in the objective analysis for numerical weather prediction and to increase the accuracy of humidity analysis especially under clear sky condition. And also, the data is a useful complement to existing data set for climatological research. But it is necessary to get higher correlation between radiosonde observations and the GMS-5 retrievals for operational applications.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.19 no.2
• /
• pp.43-53
• /
• 2017

This study aims to analyze the effect of typhoons on pear production. Pears are typical fruits that are vulnerable to typhoon damages, so typhoons are negatively associated with pear productivity. However, relatively less pear damages by typhoons in the main pear production area, comparing to the average in Korea, have been reported. The main production area seems to adopt better agricultural techniques or practices to cope with natural disasters such as typhoons. Thus, this study tests the hypothesis that there are differences of production losses due to typhoons between the main pear production area and the rest using the stochastic frontier analysis. The main production area is defined by Location Quotient Index (LQI), and we found that LQI had a significant effect to decrease the productivity losses in the main production areas, which shows that those production areas alleviated the pear production loss due to typhoons.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.31 no.1
• /
• pp.71-76
• /
• 1998

To know the antibiotic specificity of a Dinoflagellate, Cochlodinium polykrikoides, we investigated the survival time of C. polykrikoides against several concentrations of antibiotics and judged the selective specificity of antibiotics based on the $LT_50$ ($50\%$ of lethal time). The result showed that C. polykrikoides was sensitive to tetracycline and chloramphenicol, and resistant to polymixin-B, ampicillin, penicillin-G, dihydrostreptomycin, and neomycin. In the case of sensitive antibiotics to C. polykrikoides, tetracycline and chloramphenicol, the safety concentrations of both antibiotics were determined and the antibiotic specificity based or the plotted survival curve was analyzed. Before antibiotic treatment, we tested the antibiotic susceptibility of the contaminated bacterial population in tile culture of C. polykrikoides, and decided the proper kinds of antibiotics and concentrations before percoll-centrifugation. By percoll-centrifugation, we reduced bacteria, removed fungi, collected the algal pellet, and made axonic culture by antibiotic cascade procedure based on the result of antibiotic susceptibility test. We observed that axonic C. polykrikoides culture entered the logarthmic phase of growth when cell density was over 740 cells/ml and propagated to 5,800 cells/ml maximally. Divisions per day, k value of C. polykrikoides represented a good index for growth at the low density of cells. There was a highest k value shift before reaching to the logarithmic phase. We suggested that the preceeding highest k value shift stage is a good indicator for accurate broadcasting for red. tide blooming in the field, and the stage is also a good time for controlling red tide blooming in the filed, either.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.21 no.1
• /
• pp.55-64
• /
• 2019

The flowering seasons can be advanced due to climate change that would cause an abnormally warm winter. Such warm winter would increase the frequency of crop damages resulted from sudden occurrences of low temperature before and after the vegetative growth stages, e.g., the period from germination to flowering. The degree and pattern of freezing damage would differ by the development stage of each individual fruit tree even in an orchard. A critical temperature, e.g., killing temperature, has been used to predict freeze damage by low-temperature conditions under the assumption that such damage would be associated with the development stage of a fruit flower bud. However, it would be challenging to apply the critical temperature to a region where spatial variation in temperature would be considerably high. In the present study, a phenological model was used to estimate major bud development stages, which would be useful for prediction of regional risks for the freeze damages. We also derived a linear function to calculate a probabilistic freeze risk in spring, which can quantitatively evaluate the risk level based solely on forecasted weather data. We calculated the dates of freeze damage occurrences and spatial risk distribution according to main production areas by applying the spring freeze risk function to apple, peach, and pear crops in 2018. It was predicted that the most extensive low-temperature associated freeze damage could have occurred on April 8. It was also found that the risk function was useful to identify the main production areas where the greatest damage to a given crop could occur. These results suggest that the freezing damage associated with the occurrence of low-temperature events could decrease providing early warning for growers to respond abnormal weather conditions for their farm.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.3
• /
• pp.149-155
• /
• 2021

Early warning systems for weather risk management in the agricultural sector have been developed to predict potential wind damage to crops. These systems take into account the daily maximum wind speed to determine the critical wind speed that causes fruit drops and provide the weather risk information to farmers. In an effort to increase the accuracy of wind risk predictions, an artificial neural network for binary classification was implemented. In the present study, the daily wind speed and other weather data, which were measured at weather stations at sites of interest in Jeollabuk-do and Jeollanam-do as well as Gyeongsangbuk- do and part of Gyeongsangnam- do provinces in 2019, were used for training the neural network. These weather stations include 210 synoptic and automated weather stations operated by the Korean Meteorological Administration (KMA). The wind speed data collected at the same locations between January 1 and December 12, 2020 were used to validate the neural network model. The data collected from December 13, 2020 to February 18, 2021 were used to evaluate the wind risk prediction performance before and after the use of the artificial neural network. The critical wind speed of damage risk was determined to be 11 m/s, which is the wind speed reported to cause fruit drops and damages. Furthermore, the maximum wind speeds were expressed using Weibull distribution probability density function for warning of wind damage. It was found that the accuracy of wind damage risk prediction was improved from 65.36% to 93.62% after re-classification using the artificial neural network. Nevertheless, the error rate also increased from 13.46% to 37.64%, as well. It is likely that the machine learning approach used in the present study would benefit case studies where no prediction by risk warning systems becomes a relatively serious issue.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.33 no.6
• /
• pp.265-274
• /
• 2021

Outlier detection research in ocean data has traditionally been performed using statistical and distance-based machine learning algorithms. Recently, AI-based methods have received a lot of attention and so-called supervised learning methods that require classification information for data are mainly used. This supervised learning method requires a lot of time and costs because classification information (label) must be manually designated for all data required for learning. In this study, an autoencoder based on unsupervised learning was applied as an outlier detection to overcome this problem. For the experiment, two experiments were designed: one is univariate learning, in which only SST data was used among the observation data of Deokjeok Island and the other is multivariate learning, in which SST, air temperature, wind direction, wind speed, air pressure, and humidity were used. Period of data is 25 years from 1996 to 2020, and a pre-processing considering the characteristics of ocean data was applied to the data. An outlier detection of actual SST data was tried with a learned univariate and multivariate autoencoder. We tried to detect outliers in real SST data using trained univariate and multivariate autoencoders. To compare model performance, various outlier detection methods were applied to synthetic data with artificially inserted errors. As a result of quantitatively evaluating the performance of these methods, the multivariate/univariate accuracy was about 96%/91%, respectively, indicating that the multivariate autoencoder had better outlier detection performance. Outlier detection using an unsupervised learning-based autoencoder is expected to be used in various ways in that it can reduce subjective classification errors and cost and time required for data labeling.