시정계 자료와 기계학습 기법을 이용한 지역 안개예측 모형 개발

김대하 한국수자원학회 2021 한국수자원학회논문집 Vol.54 No.12

안개는 대체수자원이 될 수 있으나 교통사고 위험을 높이고 공항 운영에 제약을 가하는 사회적 영향이 큰 기상현상이다. 본 연구에서는 1 km 미만 가시거리(시정)로 정의되는 안개 발생을 기상자료로 예측하는 지역 기계학습모형을 개발하고 그 예측력을 평가하였다. 전라북도 지역의 10개 기상청 지상관측소의 2017-2019년 시정 및 기상관측자료로 앙상블 분류기법인 Extreme Gradient Boosting (XGB), Light Gradient Boosting (LGB), Random Forests (RF)를 학습시켜 지역 안개 모형을 개발하였고 독립적인 2020년 자료로 모형의 사용성을 평가하였다. 그 결과, 학습·검증기간(2017-2019)에는 True Skill Score를 기준으로 가장 높은 예측력을 보인 방법은 LGB 기법이었지만 다른 두 모형에 비해 False Alarm Ratio가 컸다. RF 모형과 XGB 방법 역시 기존 연구에 상응하는 예측성능을 보이는 것으로 확인되었다. 2020년 자료를 입력해 안개 발생을 모의했을 때 세 모형의 예측성능은 2017-2019년 기간보다 떨어졌지만 모두 관측 안개일수의 공간분포와 일관되는 안개 위험을 예측했다. 세 기계학습 모형은 안개위험이 상대적으로 높은 지역을 추출하는 기법으로 사용이 가능할 것으로 보인다. While it could become an alternative water resource, fog could undermine traffic safety and operational performance of infrastructures. To reduce such adverse impacts, it is necessary to have spatially continuous fog risk information. In this work, tree-based machine-learning models were developed in order to quantify fog risks with routine meteorological observations alone. The Extreme Gradient Boosting (XGB), Light Gradient Boosting (LGB), and Random Forests (RF) were chosen for the regional fog models using operational weather and visibility observations within the Jeollabuk-do province. Results showed that RF seemed to show the most robust performance to categorize between fog and non-fog situations during the training and evaluation period of 2017-2019. While the LGB performed better than in predicting fog occurrences than the others, its false alarm ratio was the highest (0.695) among the three models. The predictability of the three models considerably declined when applying them for an independent period of 2020, potentially due to the distinctively enhanced air quality in the year under the global lockdown. Nonetheless, even in 2020, the three models were all able to produce fog risk information consistent with the spatial variation of observed fog occurrences. This work suggests that the tree-based machine learning models could be used as tools to find locations with relatively high fog risks.

데이터마이닝 기법들을 통한 제주 안개 예측 방안 연구

이영미 ( Young Mi Lee ),배주현 ( Joo Hyun Bae ),박다빈 ( Da Bin Park ) 한국환경과학회 2016 한국환경과학회지 Vol.25 No.4

Fog may have a significant impact on road conditions. In an attempt to improve fog predictability in Jeju, we conducted machine learning with various data mining techniques such as tree models, conditional inference tree, random forest, multinomial logistic regression, neural network and support vector machine. To validate machine learning models, the results from the simulation was compared with the fog data observed over Jeju(184 ASOS site) and Gosan(185 ASOS site). Predictive rates proposed by six data mining methods are all above 92% at two regions. Additionally, we validated the performance of machine learning models with WRF (weather research and forecasting) model meteorological outputs. We found that it is still not good enough for operational fog forecast. According to the model assesment by metrics from confusion matrix, it can be seen that the fog prediction using neural network is the most effective method.

솔수염하늘소(Monochamus alternatus)에 대한 수종 살충제의 살충효과

이상명 ( I Sang Myeong ),문일성 ( Mun Il Seong ),정영진 ( Jeong Yeong Jin ),이상길 ( Lee Sang Gil ),이동운 ( Lee Dong Un ),추호열 ( Chu Ho Yeol ),박정규 ( Park Jeong Gyu ) 한국산림과학회 2003 한국산림과학회지 Vol.92 No.4

To develop efficient control program against Japanese pine sawyer (JPS). Monochamus alternatus Hope, laboratory bioassay using 7 insecticides, and the residual effects of fog-machine treatment and ultra-low-volume spray by helicopter of fenitrothion induced 100% mortality 4 days after exposure (DAE), and exposure for 4 minutes did that 2 DAE. Even the periods when they were alive, they did not feed on treated P. densiflora shoots. All the topical applications of the fenitrothion on elytra, head, mouth, tarsus, and ventral parts show 100% mortality. The residual effect of fog-machine treatment of fenitrothion was very effective against JPS adults. When the adults were inoculated on the treated shoots at the 1st day of treatment with 50,000 and 5,000 ppm solution of fenitrothion, the LT_(100) was only 1 day; even at the 11th day it was only 3 days. The residual efficacy of ultra-low-volume spray with helicopter lasted longer than that of fog-machine treatment. When the JPS adults were inoculated on the sprayed shoots even at the 10th day of the spray with 60,240, 5,000 and 1,000 ppm, the LT_(100) was only a day.

머신러닝을 이용한 안개 예측 시 목측과 시정계 계측 방법에 따른모델 성능 차이 비교

박창현,이순환 한국지구과학회 2023 한국지구과학회지 Vol.44 No.2

In this study, we predicted the presence of fog with a one-hour delay using the XGBoost DART machinelearning algorithm for Andong, which had the highest occurrence of fog among inland stations from 2016 to 2020. Weused six datasets: meteorological data, agricultural observation data, additional derived data, and their expanded data. Theweather phenomenon numbers obtained through naked-eye observations and the visibility distances measured by visibilitymeters were classified as fog [1] or no-fog [0]. We set up twelve machine learning modeling experiments and used datafrom 2021 for model validation. We mainly evaluated model performance using recall and AUC-ROC, considering theharmful effects of fog on society and local communities. The combination of oversampled meteorological data featuresand the target induced by weather phenomenon numbers showed the best performance. This result highlights theimportance of naked-eye observations in predicting fog using machine learning algorithms. 본 연구에서는 2016년부터 2020년까지 내륙 관측소 중 안개 최다발 지역인 안동을 대상으로 XGBoost-DART머신러닝 알고리즘을 이용하여 1 시간 후 안개 유무를 예측하였다 . 기상자료 , 농업관측자료 , 추가 파생자료와 각 자료를 오버 샘플링한 확장자료 , 총 6개의 데이터 세트를 사용하였다 . 목측으로 획득한 기상현상번호와 시정계 관측으로 측정된 시정거리 자료를 각각 안개 유[1]무[0]로 이진 범주화하였다 . 총 12개의 머신러닝 모델링 실험을 설계하였고 , 안개가 사회와 지역사회에 미치는 유해성을 고려하여 모델의 성능은 재현율과 AUC-ROC를 중심으로 평가하였다 . 전체적으로, 오버샘플링한 기상자료와 기상현상번호 기반의 예측 목표를 조합한 실험이 최고 성능을 보였다 . 이 연구 결과는 머신러닝 알고리즘을 활용한 안개 예측에 있어서 , 목측으로 획득한 기상현상번호의 중요성을 암시한다 .

GK2A/AMI와 GK2B/GOCI-II 자료를 융합 활용한주간 고해상도 안개 탐지 알고리즘 개발

유하영,서명석 대한원격탐사학회 2023 大韓遠隔探査學會誌 Vol.39 No.6

Satellite-based fog detection algorithms are being developed to detect fog in real-time overa wide area, with a focus on the Korean Peninsula (KorPen). The GEO-KOMPSAT-2A/AdvancedMeteorological Imager (GK2A/AMI, GK2A) satellite offers an excellent temporal resolution (10 min)and a spatial resolution (500 m), while GEO-KOMPSAT-2B/Geostationary Ocean Color Imager-II(GK2B/GOCI-II, GK2B) provides an excellent spatial resolution (250 m) but poor temporal resolution(1 h) with only visible channels. To enhance the fog detection level (10 min, 250 m), we developed afused GK2AB fog detection algorithm (FDA) of GK2A and GK2B. The GK2AB FDA comprises threemain steps. First, the Korea Meteorological Satellite Center’s GK2A daytime fog detection algorithm isutilized to detect fog, considering various optical and physical characteristics. In the second step, GK2Bdata is extrapolated to 10-min intervals by matching GK2A pixels based on the closest time and locationwhen GK2B observes the KorPen. For reflectance, GK2B normalized visible (NVIS) is corrected usingGK2A NVIS of the same time, considering the difference in wavelength range and observation geometry. GK2B NVIS is extrapolated at 10-min intervals using the 10-min changes in GK2A NVIS. In the finalstep, the extrapolated GK2B NVIS, solar zenith angle, and outputs of GK2A FDA are utilized as inputdata for machine learning (decision tree) to develop the GK2AB FDA, which detects fog at a resolutionof 250 m and a 10-min interval based on geographical locations. Six and four cases were used for thetraining and validation of GK2AB FDA, respectively. Quantitative verification of GK2AB FDA utilizedground observation data on visibility, wind speed, and relative humidity. Compared to GK2A FDA,GK2AB FDA exhibited a fourfold increase in spatial resolution, resulting in more detailed discriminationbetween fog and non-fog pixels. In general, irrespective of the validation method, the probability ofdetection (POD) and the Hanssen-Kuiper Skill score (KSS) are high or similar, indicating that it better detects previously undetected fog pixels. However, GK2AB FDA, compared to GK2A FDA, tends toover-detect fog with a higher false alarm ratio and bias.

기계학습 기반의 클라우드를 위한 센서 데이터 수집 및 정제 시스템

황치곤,윤창표 한국정보통신학회 2021 한국정보통신학회논문지 Vol.25 No.2

Machine learning has recently been applied to research in most areas. This is because the results of machine learning are not determined, but the learning of input data creates the objective function, which enables the determination of new data. In addition, the increase in accumulated data affects the accuracy of machine learning results. The data collected here is an important factor in machine learning. The proposed system is a convergence system of cloud systems and local fog systems for service delivery. Thus, the cloud system provides machine learning and infrastructure for services, while the fog system is located in the middle of the cloud and the user to collect and refine data. The data for this application shall be based on the Sensitive data generated by smart devices. The machine learning technique applied to this system uses SVM algorithm for classification and RNN algorithm for status recognition. 기계학습은 최근 대부분의 분야에서 적용하여 연구를 하고 있다. 이것은 기계학습의 결과가 결정된 것이 아니라 입력데이터의 학습으로 목적함수를 생성하고, 이를 통해 통하여 새로운 데이터에 대한 판단이 가능하기 때문이다. 또한, 축적된 데이터의 증가는 기계학습 결과의 정확도에 영향을 미친다. 이에 수집된 데이터는 기계학습에 중요한 요인이다. 제안하는 본 시스템은 서비스 제공을 위한 클라우드 시스템과 지역의 포그 시스템의 융합 시스템이다. 이에 클라우드 시스템은 서비스를 위한 머신러닝과 기반 구조를 제공하고, 포그 시스템은 클라우드와 사용자의 중간에 위치하여 데이터 수집 및 정제를 수행한다. 이를 적용하기 위한 데이터는 스마트기기에서 발생하는 센세 데이터로 한다. 이에 적용된 기계학습 기법은 분류를 위한 SVM알고리즘, 상태 인지를 위한 RNN 알고리즘을 이용한다.

Reinforcement Learning based Resource Management for Fog Computing Environment: Literature Review, Challenges, and Open Issues

Hoa Tran-Dang,Sanjay Bhardwaj,Tariq Rahim,Arslan Musaddiq,Dong-Seong Kim 한국통신학회 2022 Journal of communications and networks Vol.24 No.1

In the IoT-based systems, the fog computing allowsthe fog nodes to offload and process tasks requested from IoTenableddevices in a distributed manner instead of the centralizedcloud servers to reduce the response delay. However, achievingsuch a benefit is still challenging in the systems with high rate ofrequests, which imply long queues of tasks in the fog nodes, thusexposing probably an inefficiency in terms of latency to offloadthe tasks. In addition, a complicated heterogeneous degree inthe fog environment introduces an additional issue that many ofsingle fogs can not process heavy tasks due to lack of availableresources or limited computing capabilities. Reinforcement learningis a rising component of machine learning, which providesintelligent decision making for agents to response effectively tothe dynamics of environment. This vision implies a great potentialof application of RL in the concept of fog computing regardingresource allocation for task offloading and execution to achievethe improved performance. This work presents an overview of RLapplications to solve the resource allocation related problems inthe fog computing environment. The open issues and challengesare explored and discussed for further study.

Research study on cognitive IoT platform for fog computing in industrial Internet of Things

홍성혁 한국사물인터넷학회 2024 한국사물인터넷학회 논문지 Vol.10 No.1

This paper proposes an innovative cognitive IoT framework specifically designed for fog computing (FC) in the context of industrial Internet of Things (IIoT). The discourse in this paper is centered on the intricate design and functional architecture of the Cognitive IoT platform. A crucial feature of this platform is the integration of machine learning (ML) and artificial intelligence (AI), which enhances its operational flexibility and compatibility with a wide range of industrial applications. An exemplary application of this platform is highlighted through the Predictive Maintenance-as-a-Service (PdM-as-a-Service) model, which focuses on real-time monitoring of machine conditions. This model transcends traditional maintenance approaches by leveraging real-time data analytics for maintenance and management operations. Empirical results substantiate the platform’s effectiveness within a fog computing milieu, thereby illustrating its transformative potential in the domain of industrial IoT applications. Furthermore, the paper delineates the inherent challenges and prospective research trajectories in the spheres of Cognitive IoT and Fog Computing within the ambit of Industrial Internet of Things (IIoT).

A Machine Learning Approach for Fog Detection in Areas with No Visibility Sensors

Jieun Cha,Yun Am Seo,Hye Sook Lee 한국기상학회 2023 한국기상학회 학술대회 논문집 Vol.2023 No.10

A Machine Learning Approach for Fog Detection in Areas with No Visibility Sensors

Jieun Cha,Yun Am Seo,Hye Sook Lee 한국기상학회 2023 한국기상학회 학술대회 논문집 Vol.2023 No.11