Comprehensive Assessment of Flood Risk and Vulnerability for Essential Facilities: Iowa Case Study DOI Creative Commons

Cori Grant,

Yazeed Alabbad, Enes Yıldırım

и другие.

Urban Science, Год журнала: 2024, Номер 8(3), С. 145 - 145

Опубликована: Сен. 18, 2024

In this study, nine different types of essential facilities in the state Iowa (such as hospitals, fire stations, schools, etc.) were analyzed on a county level terms flood depth, functionality and restoration time after flooding, damage sustained during flooding. These also their location relative to 100 y 500 zones. Results show that number within extent reached up 39%, scenario all but one six chosen counties lost 100% facilities. Most found have depth 1 4 ft deep 480 days. The purpose study is bring awareness decisionmakers regarding risk flooding events pose highlight increasing dangers broader scale. This will be beneficial improve mitigation strategies, emergency response plans, ensuring services are available event future floods for affected areas.

Язык: Английский

The Implementation of Multimodal Large Language Models for Hydrological Applications: A Comparative Study of GPT-4 Vision, Gemini, LLaVa, and Multimodal-GPT DOI Creative Commons

Likith Kadiyala,

Omer Mermer, R. Dinesh Jackson Samuel

и другие.

Hydrology, Год журнала: 2024, Номер 11(9), С. 148 - 148

Опубликована: Сен. 11, 2024

Large Language Models (LLMs) combined with visual foundation models have demonstrated significant advancements, achieving intelligence levels comparable to human capabilities. This study analyzes the latest Multimodal LLMs (MLLMs), including Multimodal-GPT, GPT-4 Vision, Gemini, and LLaVa, a focus on hydrological applications such as flood management, water level monitoring, agricultural discharge, pollution management. We evaluated these MLLMs hydrology-specific tasks, testing their response generation real-time suitability in complex real-world scenarios. Prompts were designed enhance models’ inference capabilities contextual comprehension from images. Our findings reveal that Vision exceptional proficiency interpreting data, providing accurate assessments of severity quality. Additionally, showed potential various applications, drought prediction, streamflow forecasting, groundwater wetland conservation. These can optimize resource management by predicting rainfall, evaporation rates, soil moisture levels, thereby promoting sustainable practices. research provides valuable insights into advanced AI addressing challenges improving decision-making

Язык: Английский

Процитировано

5
Urban flood risk assessment and evacuation planning: a bi-level optimization model for sustainable high-density coastal areas DOI Creative Commons
Xinyue Gu, Yan Mao, Xintao Liu

и другие.

Annals of GIS, Год журнала: 2025, Номер unknown, С. 1 - 13

Опубликована: Янв. 13, 2025

Flooding caused by extreme climate change is becoming increasingly severe, especially in high-density coastal areas worldwide. Although many studies have conducted risk assessments of urban floods, most not formed a comprehensive evacuation plan considering population distribution and flood disaster risk. To further enhance planning emergency management for areas, this study uses Victoria Harbor Hong Kong, typical flood-prone region, as research area. The first conducts exposure assessment classifies different regions according to levels. Then, combining ability with the changing road flows, novel bi-level optimization model proposed allocate zones citizens day night. With upper level using genetic algorithm minimize total system time lower applying user equilibrium evacuee allocation, forms an that considers hotspots impact risks on network. findings show functional high pedestrian flow, tourist spots, commercial centres, schools are exposed higher Besides, simulation matches zoning results actual activities can effectively achieve goal evacuating 480,000 people within 12–18 minutes. This innovatively proposes effective reference government's work.

Язык: Английский

Процитировано

0
Geo-WC: Custom Web Components for Earth Science Organizations and Agencies DOI
Sümeyye Kaynak, Baran Kaynak, Carlos Erazo Ramirez

и другие.

Environmental Modelling & Software, Год журнала: 2025, Номер unknown, С. 106328 - 106328

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
A community-centric intelligent cyberinfrastructure for addressing nitrogen pollution using web systems and conversational AI DOI

Samrat Shrestha,

Jerry Mount,

Gabriel Vald

и другие.

Environmental Science & Policy, Год журнала: 2025, Номер 167, С. 104055 - 104055

Опубликована: Апрель 4, 2025

Язык: Английский

Процитировано

0
Understanding Flood Risk in Public Transit Systems: Insights from Accessibility and Vulnerability Analysis in Iowa DOI
Yazeed Alabbad, İbrahim Demir

International Journal of Disaster Risk Reduction, Год журнала: 2025, Номер unknown, С. 105615 - 105615

Опубликована: Май 1, 2025

Язык: Английский

Процитировано

0
Toward HydroLLM: a benchmark dataset for hydrology-specific knowledge assessment for large language models DOI Creative Commons

Dilara Kizilkaya,

Ramteja Sajja, Yusuf Sermet

и другие.

Environmental Data Science, Год журнала: 2025, Номер 4

Опубликована: Янв. 1, 2025

Abstract The rapid advancement of large language models (LLMs) has enabled their integration into a wide range scientific disciplines. This article introduces comprehensive benchmark dataset specifically designed for testing recent LLMs in the hydrology domain. Leveraging collection research articles and textbooks, we generated array hydrology-specific questions various formats, including true/false, multiple-choice, open-ended, fill-in-the-blank. These serve as robust foundation evaluating performance state-of-the-art LLMs, GPT-4o-mini, Llama3:8B, Llama3.1:70B, addressing domain-specific queries. Our evaluation framework employs accuracy metrics objective question types cosine similarity measures subjective responses, ensuring thorough assessment models’ proficiency understanding responding to hydrological content. results underscore both capabilities limitations artificial intelligence (AI)-driven tools within this specialized field, providing valuable insights future development educational resources. By introducing HydroLLM-Benchmark, study contributes vital resource growing body work on AI applications, demonstrating potential support complex, field-specific tasks hydrology.

Язык: Английский

Процитировано

0
Effectiveness of regional risk mitigation policies in equitably improving connectivity to essential service during hurricane-induced floods DOI

Naqib Mashrur,

Sabarethinam Kameshwar

International Journal of Disaster Risk Reduction, Год журнала: 2024, Номер 112, С. 104775 - 104775

Опубликована: Авг. 23, 2024

Язык: Английский

Процитировано

2
A Positional Knowledge-Guided Multiscale Gaussian Detail Enhancement Deep Learning Network for Ground Fissure Extraction DOI Creative Commons
Weiqiang Luo, Ming Hao, Shilin Chen

и другие.

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Год журнала: 2024, Номер 17, С. 13881 - 13892

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

1
Comprehensive Assessment of Flood Risk and Vulnerability for Essential Facilities: Iowa Case Study DOI Creative Commons

Cori Grant,

Yazeed Alabbad, Enes Yıldırım

и другие.

Urban Science, Год журнала: 2024, Номер 8(3), С. 145 - 145

Опубликована: Сен. 18, 2024

In this study, nine different types of essential facilities in the state Iowa (such as hospitals, fire stations, schools, etc.) were analyzed on a county level terms flood depth, functionality and restoration time after flooding, damage sustained during flooding. These also their location relative to 100 y 500 zones. Results show that number within extent reached up 39%, scenario all but one six chosen counties lost 100% facilities. Most found have depth 1 4 ft deep 480 days. The purpose study is bring awareness decisionmakers regarding risk flooding events pose highlight increasing dangers broader scale. This will be beneficial improve mitigation strategies, emergency response plans, ensuring services are available event future floods for affected areas.

Язык: Английский

Процитировано

1