Review on environmental aspects in smart city concept: Water, waste, air pollution and transportation smart applications using IoT techniques

Sustainable Cities and Society, Год журнала: 2023, Номер 94, С. 104567 - 104567

Опубликована: Апрель 2, 2023

Язык: Английский

---

Machine learning and remote sensing integration for leveraging urban sustainability: A review and framework

Sustainable Cities and Society, Год журнала: 2023, Номер 96, С. 104653 - 104653

Опубликована: Май 15, 2023

Climate change and rapid urbanisation exacerbated multiple urban issues threatening sustainability. Numerous studies integrated machine learning remote sensing to monitor develop mitigation strategies for However, few comparatively analysed joint applications of This paper presents a systematic review formulates framework integrating in studies. The literature analysis reveals: Most occurred Asia, Europe, North America, driven by technical ethical factors, highlighting responsible approaches data-scarce regions; Reviewed prioritised physical spatial aspects over socioeconomic requiring multi-source data comprehensive analysis; Conventional satellite, aerial images, Lidar are prevalent due affordability, quality, accessibility; Although supervised dominates, unsupervised methods algorithm selection paradigms require exploration; Integration offers accurate results thorough image processing analytics, while acquisition decision-making necessitate human supervision. provides an integrative sensing, enriching insights into their potential analytics. study informs planning policymaking promoting efficient management via enhanced integration, bolstering data-driven decision-making.

Язык: Английский

---

U-net-based semantic classification for flood extent extraction using SAR imagery and GEE platform: A case study for 2019 central US flooding

The Science of The Total Environment, Год журнала: 2023, Номер 869, С. 161757 - 161757

Опубликована: Янв. 21, 2023

Язык: Английский

---

A systematic review of trustworthy artificial intelligence applications in natural disasters

Computers & Electrical Engineering, Год журнала: 2024, Номер 118, С. 109409 - 109409

Опубликована: Июнь 29, 2024

Artificial intelligence (AI) holds significant promise for advancing natural disaster management through the use of predictive models that analyze extensive datasets, identify patterns, and forecast potential disasters. These facilitate proactive measures such as early warning systems (EWSs), evacuation planning, resource allocation, addressing substantial challenges associated with This study offers a comprehensive exploration trustworthy AI applications in disasters, encompassing management, risk assessment, prediction. research is underpinned by an review reputable sources, including Science Direct (SD), Scopus, IEEE Xplore (IEEE), Web (WoS). Three queries were formulated to retrieve 981 papers from earliest documented scientific production until February 2024. After meticulous screening, deduplication, application inclusion exclusion criteria, 108 studies included quantitative synthesis. provides specific taxonomy disasters explores motivations, challenges, recommendations, limitations recent advancements. It also overview techniques developments using explainable artificial (XAI), data fusion, mining, machine learning (ML), deep (DL), fuzzy logic, multicriteria decision-making (MCDM). systematic contribution addresses seven open issues critical solutions essential insights, laying groundwork various future works trustworthiness AI-based management. Despite benefits, persist In these contexts, this identifies several unused used areas disaster-based theory, collects ML, DL techniques, valuable XAI approach unravel complex relationships dynamics involved utilization fusion processes related Finally, extensively analyzed ethical considerations, bias, consequences AI.

Язык: Английский

---

Urban Flood Hazard Assessment and Management Practices in South Asia: A Review

Land, Год журнала: 2023, Номер 12(3), С. 627 - 627

Опубликована: Март 6, 2023

Urban flooding is a frequent disaster in cities. With the increasing imperviousness caused by rapid urbanization and rising frequency severity of extreme events climate change, hydrological status urban area has changed, resulting floods. This study aims to identify trends gaps highlight potential research prospects field South Asia. Based on an extensive literature review, this paper reviewed flood hazard assessment methods using hydraulic/hydrological models management practices advancement technology high-resolution topographic data, hydrologic/hydraulic such as HEC-RAS/HMS, MIKE, SWMM, etc., are increasingly used for assessment. vary among countries based existing technologies infrastructures. In order control flooding, both conventional physical structures, including drainage embankments, well new innovative techniques, low-impact development, implemented. Non-structural mitigation measures, improved warning systems, have been developed implemented few The major challenge process-based hydraulic was lack DEM short-duration rainfall data region, significantly affecting model’s simulation results implementation measures. Risk-informed must be immediately reduce adverse effects change unplanned flooding. Therefore, it crucial encourage emergency managers local planning authorities consider nature-based solution integrated approach enhances resilience.

Язык: Английский

---

GIS-based flood risk assessment using multi-criteria decision analysis of Shebelle River Basin in southern Somalia

SN Applied Sciences, Год журнала: 2023, Номер 5(5)

Опубликована: Апрель 11, 2023

Abstract Floods are the most common and expensive natural calamity, affecting every country. Flooding in Shebelle River Basin (SRB) southern Somalia has posed a significant challenge to sustainable development. The main goal of this study was analyze flood hazard, vulnerability risk part SRB using GIS-based Multi-Criteria Decision Analysis (MCDA). hazard map constructed seven important causative factors: elevation, slope, drainage density, distance river, rainfall, soil geology. results demonstrate that very low, moderate, high, high zones correspond 10.92%, 24.97%, 29.13%, 21.93% 13.04% area SRB, respectively. created five spatial layers: land use/land cover, population road, Global man-made impervious surface (GMIS), Human built-up settlement extent (HBASE). In addition, susceptibility maps were used create map. for Basin, 27.6%, 30.9%, 23.6%, 12.1%, 5.7% zones, Receiver Operating Characteristics-Area Under Curve (ROC-AUC) model exhibited good prediction accuracy 0.781. majority basin is at flooding moderate ranges; however, some tiny areas ranges. Flood should be provided distributed authorities responsible protection so people aware locations.

Язык: Английский

---

Rapid urban flood risk mapping for data-scarce environments using social sensing and region-stable deep neural network

Journal of Hydrology, Год журнала: 2022, Номер 617, С. 128758 - 128758

Опубликована: Ноя. 24, 2022

Язык: Английский

---

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

Water, Год журнала: 2025, Номер 17(5), С. 707 - 707

Опубликована: Фев. 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.

Язык: Английский

---

SpaceNet 8 - The Detection of Flooded Roads and Buildings

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Год журнала: 2022, Номер unknown, С. 1471 - 1479

Опубликована: Июнь 1, 2022

The frequency and intensity of natural disasters (i.e. wildfires, storms, floods) has increased over recent decades. Extreme weather can often be linked to climate change, human population expansion urbanization have led a growing risk. In particular floods due large amounts rainfall are rising severity causing loss life, destruction buildings infrastructure, erosion arable land, environmental hazards around the world. Expanding along rivers creeks includes opening flood plains for building construction river straightening dredging speeding up flow water. event, rapid response is essential which requires knowledge susceptible flooding roads still accessible. To this aim, SpaceNet 8 first remote sensing machine learning training dataset combining footprint detection, road network extraction, detection covering 850km ² , including 32k 1,300km 13% 15% flooded, respectively.

Язык: Английский

---

MultiRS flood mapper: a google earth engine application for water extent mapping with multimodal remote sensing and quantile-based postprocessing

Environmental Modelling & Software, Год журнала: 2024, Номер 176, С. 106022 - 106022

Опубликована: Март 14, 2024

Язык: Английский

---