Revealing public attitudes toward mobile cabin hospitals during Covid-19 pandemic: Sentiment and topic analyses using social media data in China

Sustainable Cities and Society, Journal Year: 2024, Volume and Issue: 107, P. 105440 - 105440

Published: April 12, 2024

Language: Английский

---

Investigating disaster response for resilient communities through social media data and the Susceptible-Infected-Recovered (SIR) model: A case study of 2020 Western U.S. wildfire season

Sustainable Cities and Society, Journal Year: 2024, Volume and Issue: 106, P. 105362 - 105362

Published: March 20, 2024

Language: Английский

---

A novel framework for the spatiotemporal assessment of urban flood vulnerability

Sustainable Cities and Society, Journal Year: 2024, Volume and Issue: 109, P. 105523 - 105523

Published: May 13, 2024

Language: Английский

---

Artificial Intelligence Algorithms in Flood Prediction: A General Overview

Springer eBooks, Journal Year: 2024, Volume and Issue: unknown, P. 243 - 296

Published: Jan. 1, 2024

Language: Английский

---

Appraisal of Urban Waterlogging and Extent Damage Situation after the Devastating Flood

Water Resources Management, Journal Year: 2024, Volume and Issue: 38(12), P. 4911 - 4931

Published: June 8, 2024

Language: Английский

---

A Systematic Literature Review on Classification Machine Learning for Urban Flood Hazard Mapping

Water Resources Management, Journal Year: 2024, Volume and Issue: 38(15), P. 5823 - 5864

Published: Aug. 3, 2024

Language: Английский

---

Pluvial flood susceptibility mapping for data-scarce urban areas using graph attention network and basic flood conditioning factors

Geocarto International, Journal Year: 2023, Volume and Issue: 38(1)

Published: Oct. 27, 2023

Pluvial floods are destructive natural disasters in cities. With high computational efficiency, machine learning models increasingly used for flood susceptibility mapping. However, limited flooded or nonflooded samples constrain models' predictive capability and introduce uncertainty feature engineering. This study introduces a semi-supervised graph-structured model, Graph Attention Network (GAT), to address data scarcity enable the use of only basic conditioning factors as inputs. GAT uses nodes edges represent spatial units their relative relationships. Based on its graph structure attention mechanism, automatically extracts high-order features from inputs labeled unlabeled modeling. In metropolitan area Dalian, China, outperformed other flooded-nonflooded sample classification exhibited rational distribution pattern, with four less than 1.2% training. can be an effective tool practical urban management.

Language: Английский

---

Assessing urban drainage pressure and impacts of future climate change based on shared socioeconomic pathways

Journal of Hydrology Regional Studies, Journal Year: 2024, Volume and Issue: 53, P. 101760 - 101760

Published: April 5, 2024

The increasing frequency of urban flood disasters presents a significant obstacle to sustainability. Urban management aims reduce the occurrences, currently addressed through drainage systems. Previous studies have demonstrated future precipitation extremes will pose larger pressure on network, but when and where reach dangerous level never been assessed in any city China. This study establishes initial framework for identifying critical decades hot spots changes due climate change, case conducted southern China (Haining city). was by combination model known as Storm Water Management Model (SWMM) pipe statistics. Using projections from latest phase Coupled Intercomparison Project (CMIP6) under four typical SSP-RCP (shared socioeconomic pathway-representative concentration pathway) scenarios, we project 21st century, identify key high risk areas with occurrence levels. results indicate an overall upward trend Haining city, over 97% flooding nodes projected firstly 2030 s. Comparisons patterns different suggest that higher forcing pathway would expedite deterioration pressure, particularly lower DEM building intensity. has broad implications better informing disaster policy-making similar cities, especially those inadequate capacities.

Language: Английский

---

Classification machine learning models for urban flood hazard mapping: case study of Zaio, NE Morocco

Natural Hazards, Journal Year: 2024, Volume and Issue: 120(11), P. 10013 - 10041

Published: April 16, 2024

Language: Английский

---

Fine-grained flood disaster information extraction incorporating multiple semantic features

International Journal of Digital Earth, Journal Year: 2025, Volume and Issue: 18(1)

Published: Jan. 2, 2025

Flood disasters rank as the most prevalent natural calamities of twenty-first century, incurring extensive human and economic losses globally. As a crucial source for disaster monitoring, social media data exhibits high variability ambiguity, with current research lacking targeted multidimensional semantic analysis, resulting in coarse granularity limited accuracy. To address this problem, study proposes framework method synthesizing multiple features to extract fine-grained information. Static embeddings representing stable semantics dynamic changing are fused toponyms, depth-first search used generate addresses through toponym tree. Guiding prompts incorporating domain-specific knowledge designed large language model, an iterative feedback process refining location-based Finally, reliability media-sourced information is assessed by comparing extracted flooded locations actual monitoring data. The case on Zhengzhou '7·20' flood event demonstrates effectiveness our fusion approach, achieving F1 score 0.9384 extraction, accuracies 0.8485 0.8788 waterlogging depth trapped individuals, respectively. This offers practical nuanced perception timely rescue operations urban management.

Language: Английский

---