Scholarlink

<p>Rapid urbanization combined with the intensification of extreme rainfall under climate change has substantially increased flood risk in coastal megacities, particularly in data-scarce regions. Conventional flood risk assessments predominantly rely on hydrometeorological and physical indicators, often neglecting real-time societal response and infrastructure stress. This study develops an integrated framework for flood risk prediction by coupling social media intelligence with urban morphology to capture both physical vulnerability and dynamic public response during extreme rainfall events. The framework is applied to Karachi, Pakistan, using the 2022 monsoon floods as a representative climate extreme. A dataset of 8,732 flood-related georeferenced social media posts was analyzed using natural language processing, sentiment analysis, topic modeling, and machine learning techniques. Public Concern Index and Public Sentiment Index metrics were employed to quantify temporal variations in public response, revealing that flood-related discussions peaked during extreme rainfall days, with Public Concern Index values reaching 17.28%, nearly 3.6 times higher than during earlier rainfall events. Spatial integration with urban morphology indicators including land use, elevation, road density, and drainage structure demonstrated that low-lying and highly impervious areas consistently exhibited elevated flood risk and stronger negative sentiment polarity. Topic modeling results showed that disruptions to daily life, traffic, and infrastructure accounted for more than 65% of flood-related discourse, while sentiment analysis revealed a dominance of negative emotional responses exceeding 70% during peak flooding. Spatial interpolation and clustering analyses identified high-risk flood zones with strong spatial autocorrelation, and the proposed framework achieved a predictive accuracy of approximately 93%, outperforming conventional assessment approaches. The results demonstrate that social media-derived signals provide early, spatially granular insights into flood impacts and infrastructure failure, often preceding official damage reports. By integrating social sensing with urban morphology, this study offers a scalable and transferable approach for enhancing flood risk prediction, climate adaptation planning, and urban resilience under increasing climate extremes.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Integrating crowdsourced geospatial intelligence and urban morphology for urban waterlogging risk mapping in Karachi, Pakistan

  • 期刊论文

  • 发表日期：

    2026年5月18日

查看全文
  • Shan-e-hyder Soomro,
  • Huaibin Wei,
  • Muhammad Waseem Boota,
  • Mairaj Hyder Alias Aamir Soomro,
  • Caihong Hu,
  • Yinghai Li,
  • Chengshuai Liu,
  • Junaid Abdul Wahid,
  • Jiali Guo,
  • Xiaotao Shi,
  • Gul-e-Zehra Soomro

摘要

Rapid urbanization combined with the intensification of extreme rainfall under climate change has substantially increased flood risk in coastal megacities, particularly in data-scarce regions. Conventional flood risk assessments predominantly rely on hydrometeorological and physical indicators, often neglecting real-time societal response and infrastructure stress. This study develops an integrated framework for flood risk prediction by coupling social media intelligence with urban morphology to capture both physical vulnerability and dynamic public response during extreme rainfall events. The framework is applied to Karachi, Pakistan, using the 2022 monsoon floods as a representative climate extreme. A dataset of 8,732 flood-related georeferenced social media posts was analyzed using natural language processing, sentiment analysis, topic modeling, and machine learning techniques. Public Concern Index and Public Sentiment Index metrics were employed to quantify temporal variations in public response, revealing that flood-related discussions peaked during extreme rainfall days, with Public Concern Index values reaching 17.28%, nearly 3.6 times higher than during earlier rainfall events. Spatial integration with urban morphology indicators including land use, elevation, road density, and drainage structure demonstrated that low-lying and highly impervious areas consistently exhibited elevated flood risk and stronger negative sentiment polarity. Topic modeling results showed that disruptions to daily life, traffic, and infrastructure accounted for more than 65% of flood-related discourse, while sentiment analysis revealed a dominance of negative emotional responses exceeding 70% during peak flooding. Spatial interpolation and clustering analyses identified high-risk flood zones with strong spatial autocorrelation, and the proposed framework achieved a predictive accuracy of approximately 93%, outperforming conventional assessment approaches. The results demonstrate that social media-derived signals provide early, spatially granular insights into flood impacts and infrastructure failure, often preceding official damage reports. By integrating social sensing with urban morphology, this study offers a scalable and transferable approach for enhancing flood risk prediction, climate adaptation planning, and urban resilience under increasing climate extremes.