Concerning the Issue of Classification of Hazardous Weather Events

Vasiliev, Oleg V.; Boyarenko, Elvira S.; Galaeva, Ksenia I.; Zyabkin, Sergey A.

doi:10.1109/tsczh55469.2022.9802491

Cited by 2 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…5. Далее был проведен анализ горизонтального разреза кучево-дождевых облаков, в результате которого для каждого разреза кучево-дождевых облаков было найдено распределение отражаемости (Z) и удельной скорости диссипации турбулентной энергии (EDR) [2].…”

Section: методика проведения экспериментальных исследований регистрац...unclassified

“…Аппроксимация экспериментальных данных параметров отражаемости и удельной скорости диссипации турбулентной энергии ливней, гроз и града была проведена с использованием критерия χ 2 [12] с уровнем значимости 0,01 для распределения Райса, имеющего плотностью распределения указанную ниже…”

Section: статистический анализ экспериментальных данных опасных метео...unclassified

“…Радиолокационный мониторинг погоды предполагает использование наземных метеорологических радиолокационных станций (РЛС) для анализа метеообстановки и классификации опасных явлений погоды в соответствии с принятыми критериями [1]. Как показано в [2,3], данные критерии имеют, по мнению авторов, ряд недостатков: они далеки от оптимальных с точки зрения теории принятия решений, не учитывают информацию о распределении ветровых характеристик, а также особенности кучево-грозовой активности в различных климатических зонах. Очевидно, что один из приоритетных путей повышения достоверности классификации опасных метеоявленийсовместный учет высотного распределения отражательных и турбулентных характеристик атмосферы для различных фаз развития кучево-грозовой облачности.…”

Section: Introductionunclassified

See 2 more Smart Citations

Experimental statistical analysis of radar signals reflected from weather hazards

Boyarenko,

Bolelov,

Vasiliev

et al. 2023

Naučn. vestn. MGTU GA

View full text Add to dashboard Cite

The nature of the causes of prerequisites for flight accidents due to meteorological conditions has remained unchanged for many years. For the effective operation of aviation, it is necessary to solve the issues of the timely detection of weather hazards and the identification of their intensity. This article discusses the research into the atmospheric reflectivity and turbulence in cumulonimbus clouds using a near-field meteorological radar system. Experimental studies are carried out with the aim of obtaining estimates of statistical characteristics of the reflectivity distribution and turbulence for weather hazards. The methodology for conducting an experimental study to obtain information about the weather hazards (rain shower, thunderstorm and hail), special features of the radar reflectivity propagation and the specific rate of turbulent energy dissipation in the considered conditions for the Tver region is presented. The analysis of the obtained results has been carried out: comparisons of meteorological data derived, using the meteorological radar complex of the near airfield zone (WR BZ), with the reliable sources of meteorological observation data obtained during experimental studies. Studies of horizontal sections and vertical profiles of the weather hazards parameters under consideration, associated with the cumulonimbus area, have been carried out. A data bank has been formed. Histograms of the information parameter distribution have been constructed. The article considers the results of experimental data approximation, using the χ2 criterion for various distribution laws. It is shown that the distributions of reflectivity and turbulence can be described by the generalized Rice’s law. The results obtained can be used to correct the classification criteria of weather hazards to subsequently increase the justification and reliability of the weather hazard classification. The further development of the method to process meteorological information is also of paramount importance to more correctly interpretate experimental data processing results of remote meteorological phenomena sensing.

show abstract

Section: методика проведения экспериментальных исследований регистрац...unclassified

Section: статистический анализ экспериментальных данных опасных метео...unclassified

Section: Introductionunclassified

See 1 more Smart Citation

Experimental statistical analysis of radar signals reflected from weather hazards

Boyarenko,

Bolelov,

Vasiliev

et al. 2023

Naučn. vestn. MGTU GA

View full text Add to dashboard Cite

show abstract

“…Hence, it is beneficial to agricultural planning if meteorological events are correctly differentiated [2]. In addition, weather phenomena dramatically affect car-assisted driving systems and our day-to-day lives, impacting things such as the technology we wear, use to travel, and rely on for energy [3][4][5]. Many visual designs, including outdoor video surveillance, are similarly vulnerable to the effects of weather on their functioning [6].…”

Section: Introductionmentioning

confidence: 99%

“…5 Li et al[22] Generative adversarial networks (GAN) 98.09 6Wang et al[24] ResNet and DenseNet 72.25 7 Bai et al[26] Multimodal Information Fusion 98.46 8 Proposed Model Yolo Model with LwF 99.19%…”

mentioning

confidence: 99%

Optimized Deep Learning with Learning without Forgetting (LwF) for Weather Classification for Sustainable Transportation and Traffic Safety

Dalal

Seth²,

Rădulescu

et al. 2023

Sustainability

View full text Add to dashboard Cite

Unfortunately, accidents caused by bad weather have regularly made headlines throughout history. Some of the more catastrophic events to recently make news include a plane crash, ship collision, railway derailment, and several vehicle accidents. The public’s attention has been directed to the severe issue of safety and security under extreme weather conditions, and many studies have been conducted to highlight the susceptibility of transportation services to environmental factors. An automated method of determining the weather’s state has gained importance with the development of new technologies and the rise of a new industry: intelligent transportation. Humans are well-suited for determining the temperature from a single photograph. Nevertheless, this is a more challenging problem for a fully autonomous system. The objective of this research is developing a good weather classifier that uses only a single image as input. To resolve quality-of-life challenges, we propose a modified deep-learning method to classify the weather condition. The proposed model is based on the Yolov5 model, which has been hyperparameter tuned with the Learning-without-Forgetting (LwF) approach. We took 1499 images from the Roboflow data repository and divided them into training, validation, and testing sets (70%, 20%, and 10%, respectively). The proposed model has gained 99.19% accuracy. The results demonstrated that the proposed model gained a much higher accuracy level in comparison with existing approaches. In the future, this proposed model may be implemented in real-time.

show abstract

Concerning the Issue of Classification of Hazardous Weather Events

Cited by 2 publications

References 9 publications

Experimental statistical analysis of radar signals reflected from weather hazards

Experimental statistical analysis of radar signals reflected from weather hazards

Optimized Deep Learning with Learning without Forgetting (LwF) for Weather Classification for Sustainable Transportation and Traffic Safety

Contact Info

Product

Resources

About