Treffer: TEXNOGEN HADİSƏLƏRİN ÖYRƏNİLMƏSİNDƏ PEYK MƏLUMATLARININ İSTİFADƏSİ: MÜASİR YANAŞMALAR.

In recent years, there has been a noticeable increase in the number of technogenic emergencies – industrial accidents, explosions, chemical spills, radiation incidents, and other anthropogenic disasters. Such events not only pose serious risks to human health but also cause significant damage to social infrastructure, economic activities, and natural ecosystems. The rapid and accurate assessment of technogenic events, the determination of their impact zones, and the implementation of safety measures have become among the most pressing scientific and practical challenges of our time. Traditional observation and analysis methods – such as ground-based monitoring, visual inspection, and laboratory analysis – have certain limitations in terms of responsiveness when dealing with large-scale incidents. These methods are time- and resource-intensive and can be risky to apply in hazardous zones. In this context, remote sensing (RS) technologies, particularly satellite observation systems, offer an effective, flexible, and safe means for monitoring and assessing the impacts of technogenic events over large areas. Remote sensing enables the acquisition of information from a distance based on the reflection or emission of electromagnetic radiation from surfaces. This method is widely used to detect changes in land surface elements such as soil, water, vegetation, and urban areas. Among the most commonly used satellite platforms are Sentinel-1 (radar), Sentinel-2 (optical multispectral), Landsat 8, and MODIS. Satellite data is mainly categorized into three groups: optical multispectral, radar (SAR), and thermal infrared imagery. Optical imagery enables the observation of changes in vegetation, water bodies, and built-up areas using spectral indices such as NDVI, NDBI, and NDWI. Radar images are particularly useful for detecting deformations in terrain (subsidence, underground movements) and can operate under all weather conditions. Thermal imagery is used to analyze events such as explosions, fires, and heat emissions. The identification of technogenic events using satellite data typically involves "before-and-after" (pre-event vs. post-event) analysis, evaluation of differences in spectral indices, generation of change detection maps, and application of radar interferometry methods. For example, the ammonium nitrate explosion in Beirut in 2020 was precisely assessed using satellite imagery, identifying the extent of destruction and pollution in the affected area. Recently, the automated analysis of satellite data has increasingly incorporated artificial intelligence and machine learning technologies. Techniques such as Random Forest, Support Vector Machines, Convolutional Neural Networks (CNN), and cluster analysis are used to classify damaged areas, define the boundaries of impact zones, and assess risk. These processes are effectively supported by cloud-based geoinformation platforms like Google Earth Engine, Sentinel Hub, and Amazon AWS. Research findings indicate that satellite-based analysis of technogenic events not only supports emergency response planning but also provides critical information for the safe operation of industrial facilities, environmental monitoring, and risk forecasting. With the help of these technologies, preliminary assessments of emergencies can be conducted within 24–72 hours, significantly accelerating the decision-making process for governmental and municipal authorities. In conclusion, the application of remote sensing methods in the study of technogenic disasters is not only a frontier of modern science but also holds strategic importance in the context of global security and sustainable development. Future research should focus on the integration of satellite and ground-based data, the use of hyperspectral analysis methods, and the enhancement of artificial intelligence models. [ABSTRACT FROM AUTHOR]

Рост интенсивности техногенных чрезвычайных ситуаций — промышленных аварий, химических утечек, взрывов и радиационных инцидентов — превращает их своевременное обнаружение и оценку в актуальную научно-практическую задачу стратегического значения в современных условиях. Традиционные методы мониторинга обладают ограниченными возможностями в плане оперативности и безопасности при наблюдении за изменениями большого масштаба, поэтому всё шире применяются технологии дистанционного зондирования (ДЗ), особенно спутниковые наблюдательные системы. Дистанционное зондирование, основанное на отражении электромагнитных сигналов от поверхности Земли, позволяет отслеживать изменения в растительности, водоёмах, почве и температурных условиях. Для этого широко используются спутниковые платформы Sentinel-1 (радар), Sentinel-2 (оптический спектр), Landsat 8 и MODIS. Спутниковые данные классифицируются на три основных типа — оптические, радиолокационные и тепловые инфракрасные изображения — и выбираются в зависимости от характера анализируемого события. Для выявления техногенных происшествий применяются спектральные индексы (NDVI, NDBI, NDWI), радиолокационная интерферометрия и тепловой анализ. Взрыв аммиачной селитры в Бейруте в 2020 году наглядно продемонстрировал эффективность таких подходов. В последние годы автоматизированный анализ спутниковых данных стал возможным благодаря применению технологий искусственного интеллекта и машинного обучения, а также платформ Google Earth Engine и Sentinel Hub, которые позволяют быстро идентифицировать пострадавшие территории. Исследования показывают, что спутниковые данные являются незаменимым источником информации не только при оценке последствий чрезвычайных ситуаций, но и для экологического мониторинга, обеспечения промышленной безопасности и прогнозирования рисков. [ABSTRACT FROM AUTHOR]

Copyright of IRETC - Proceedings of Azerbaijan High Technical Educational Institutions (PAHTEI) is the property of International Research, Education & Training Center. MTU and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)