Disaster Management Systems: Utilizing YOLOv9 for Precise Monitoring of River Flood Flow Levels Using Video Surveillance

SN Computer Science, Journal Year: 2025, Volume and Issue: 6(3)

Published: March 14, 2025

Language: Английский

---

A Systematic Review of Urban Flood Susceptibility Mapping: Remote Sensing, Machine Learning, and Other Modeling Approaches

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(3), P. 524 - 524

Published: Feb. 3, 2025

Climate change has led to an increase in global temperature and frequent intense precipitation, resulting a rise severe urban flooding worldwide. This growing threat is exacerbated by rapid urbanization, impervious surface expansion, overwhelmed drainage systems, particularly regions. As becomes more catastrophic causes significant environmental property damage, there urgent need understand address flood susceptibility mitigate future damage. review aims evaluate remote sensing datasets key parameters influencing provide comprehensive overview of the causative factors utilized mapping. also highlights evolution traditional, data-driven, big data, GISs (geographic information systems), machine learning approaches discusses advantages limitations different mapping approaches. By evaluating challenges associated with current practices, this paper offers insights into directions for improving management strategies. Understanding identifying foundation developing effective resilient practices will be beneficial mitigating

Language: Английский

---

Urban Waterlogging Monitoring and Recognition in Low-Light Scenarios Using Surveillance Videos and Deep Learning

Water, Journal Year: 2025, Volume and Issue: 17(5), P. 707 - 707

Published: Feb. 28, 2025

With the intensification of global climate change, extreme precipitation events are occurring more frequently, making monitoring and management urban flooding a critical issue. Urban surveillance camera sensor networks, characterized by their large-scale deployment, rapid data transmission, low cost, have emerged as key complement to traditional remote sensing techniques. These networks offer new opportunities for high-spatiotemporal-resolution flood monitoring, enabling real-time, localized observations that satellite aerial systems may not capture. However, in low-light environments—such during nighttime or heavy rainfall—the image features flooded areas become complex variable, posing significant challenges accurate detection timely warnings. To address these challenges, this study develops an imaging model tailored under conditions proposes invariant feature extraction within videos. By using extracted (i.e., brightness areas) inputs, deep learning-based segmentation is built on U-Net architecture. A dataset, named UWs, constructed training testing model. The experimental results demonstrate efficacy proposed method, achieving mRecall 0.88, mF1_score 0.91, mIoU score 0.85. significantly outperform comparison algorithms, including LRASPP, DeepLabv3+ with MobileNet ResNet backbones, classic DeepLabv3+, improvements 4.9%, 3.0%, 4.4% mRecall, mF1_score, mIoU, respectively, compared Res-UNet. Additionally, method maintains its strong performance real-world tests, it also effective daytime showcasing robustness all-weather applications. findings provide solid support development network, practical value enhancing emergency disaster reduction efforts.

Language: Английский

---

Disaster Risk Reduction and Management With Emerging Technologies

IGI Global eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 71 - 110

Published: April 17, 2025

This chapter explores the role of emerging technologies in disaster risk reduction and management (DRRM), focusing on integration Internet Things (IoT), Artificial Intelligence (AI), Data Analytics to enhance urban resilience. IoT-enabled sensors smart infrastructure provide real-time data for early warning systems, monitoring, emergency response. AI-driven predictive analytics enhances assessment, resource allocation, post-disaster recovery, while enables integration, visualization, scenario planning. Despite their potential, challenges like quality, scalability, cybersecurity, ethical concerns must be addressed. The future Disaster Risk Reduction Management (DRRM) will depend incorporation modern technology, increased public involvement, global cooperation, allowing cities develop more intelligent, secure, sustainable settings.

Language: Английский

---

Experimental Study Unraveling Flow Allocation Patterns at Crossroad Intersections During Urban Flooding

Water, Journal Year: 2024, Volume and Issue: 16(22), P. 3314 - 3314

Published: Nov. 18, 2024

Urban roads can effectively handle peak flows during extreme storms by serving as surface flood passages, provided the flow remains within safety thresholds for vehicles and pedestrians. However, studies on allocation at crossroad intersections are limited. Previous research has overlooked important factors: road transverse slope turning radius. This study built a “two in, two out” laboratory intersection to examine patterns. Experiments explored effects of longitudinal slope, boundary conditions, combined influence radius side slope. The results indicated that flatter slopes, is more influenced while steeper inflow Froude number ratio becomes significant. effect in differs 44.3% compared rectangular orthogonal channel intersections. A straightforward formula proposed calculate based experimental power ratio. These findings could improve designs better mitigation, offering practical tool planning flood-resilient networks.

Language: Английский

---