Cited by Assessment of urban flood susceptibility based on a novel integrated machine learning method

Geo-environmental GIS modeling to predict flood hazard in heavy rainfall eastern Himalaya region: a precautionary measure towards disaster risk reduction DOI

Pradeep Kumar Rawat, Khrieketouno Belho,

Mohan Singh Maniyari Rawat

et al.

Environmental Monitoring and Assessment, Journal Year: 2025, Volume and Issue: 197(2)

Published: Feb. 1, 2025

Language: Английский

Citations

Flood resilience through hybrid deep learning: Advanced forecasting for Taipei's urban drainage system DOI

Li‐Chiu Chang,

Ming-Ting Yang,

Fi‐John Chang

et al.

Journal of Environmental Management, Journal Year: 2025, Volume and Issue: 379, P. 124835 - 124835

Published: March 7, 2025

Language: Английский

Citations

Remote sensing-based flash flood mapping and damage assessment in Dera Ismail Khan, Khyber Pakhtunkhwa, Pakistan DOI

Asif Sajjad, Muhammad Ahmad, Rana Waqar Aslam

et al.

Environmental Monitoring and Assessment, Journal Year: 2025, Volume and Issue: 197(4)

Published: March 21, 2025

Language: Английский

Citations

Integrating Remote Sensing and Machine Learning for Actionable Flood Risk Assessment: Multi-Scenario Projection in the Ili River Basin in China Under Climate Change DOI

Minjie Zhang,

Xiang Fu,

Shuangjun Liu

et al.

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(7), P. 1189 - 1189

Published: March 27, 2025

Climate change is leading to an increase in the frequency and intensity of flooding, making it necessary consider future changes flood risk management. In regions where ground-based observations are significantly restricted, implementation conventional assessment methodologies always challenging. This study proposes integrated remote sensing machine learning approach for data-scarce regions. We extracted historical inundation using Sentinel-1 SAR Landsat imagery from 2001 2023 predicted susceptibility XGBoost, Random Forest (RF), LightGBM models. The framework systematically integrates hazard components (flood frequency) with vulnerability factors (population, GDP, land use) two SSP-RCP scenarios. results indicate that SSP2-RCP4.5 SSP5-RCP8.5 scenarios, combined high- very-high-flood-risk areas Ili River Basin China (IRBC) projected reach 29.1% 29.7% basin by 2050, respectively. short term, contribution predominant, while factors, particularly population, contribute increasingly long term. demonstrates integrating open geospatial data enables actionable assessment, quantitatively supporting climate-resilient planning.

Language: Английский

Citations

Fine-Scale Identification of Agricultural Flooding Disaster Areas Based on Sentinel-1/2: A Case Study of Shengzhou, Zhejiang Province, China DOI

Jiayun Li, Jiaqi Gao, Haiyan Chen

et al.

Atmosphere, Journal Year: 2025, Volume and Issue: 16(4), P. 420 - 420

Published: April 4, 2025

Flood disasters are one of the major natural hazards threatening agricultural production. To reduce disaster losses, accurately identifying flood-affected areas is crucial. Taking Shengzhou City as a case study, we proposed refined method for by integrating microwave and optical remote sensing data with deep learning techniques, GIS, pixel-based direct differencing method. Complementary advantages can effectively solve problem difficulty in detecting floods due to thick clouds before after flood disasters. Deep technology identify farmland areas, pixel difference analyze Analyzing three typical rainfall events along topographical geomorphological characteristics City, results indicate that exhibit significant spatial heterogeneity. The primary influencing factors include intensity, topography, drainage infrastructure. northern, eastern, southwestern regions particularly peripheral adjacent mountainous hilly terrains, contain most farmland. These characterized low-lying highly susceptible Therefore, optimizing systems near essential enhance resilience.

Language: Английский

Citations

Urban Flood Risk Analysis Using the SWAGU-Coupled Model and a Cloud-Enhanced Fuzzy Comprehensive Evaluation Method DOI

Jinhui Hu,

Chunyuan Deng,

Xinyu Chang

et al.

Environmental Modelling & Software, Journal Year: 2025, Volume and Issue: unknown, P. 106461 - 106461

Published: April 1, 2025

Language: Английский

Citations

Estimation of Flood Inundation Area Using Soil Moisture Active Passive Fractional Water Data with an LSTM Model DOI

Rekzi D. Febrian,

Wanyub Kim,

Yangwon Lee

et al.

Sensors, Journal Year: 2025, Volume and Issue: 25(8), P. 2503 - 2503

Published: April 16, 2025

Accurate flood monitoring and forecasting techniques are important continue to be developed for improved disaster preparedness mitigation. Flood estimation using satellite observations with deep learning algorithms is effective in detecting patterns environmental relationships that may overlooked by conventional methods. Soil Moisture Active Passive (SMAP) fractional water (FW) was used as a reference estimate areas long short-term memory (LSTM) model combination of soil moisture information, rainfall forecasts, floodplain topography. To perform modeling LSTM, datasets different spatial resolutions were resampled 30 m resolution bicubic interpolation. The model’s efficacy quantified validating the LSTM-based inundation area mask from Senti-nel-1 SAR images regions topographic characteristics. average under curve (AUC) value LSTM 0.93, indicating high accuracy FW. confusion matrix-derived metrics validate had high-performance ~0.9. SMAP FW showed optimal performance low-covered vegetation, seasonal variations flat regions. estimates show methodological promise proposed framework resilience.

Language: Английский

Citations

A Deep Learning Framework for Flash-Flood-Runoff Prediction: Integrating CNN-RNN with Neural Ordinary Differential Equations (ODEs) DOI

Khaula Alkaabi,

Uzma Sarfraz,

Saif Bin Hdhaiba

et al.

Water, Journal Year: 2025, Volume and Issue: 17(9), P. 1283 - 1283

Published: April 25, 2025

Flash floods pose serious risks to human life and infrastructure, leading significant economic losses. While traditional conceptual models have long been used for runoff estimation, recent advancements in artificial intelligence introduced machine learning deep more accurate predictions. This study presents a framework that integrates Convolutional Neural Networks (CNNs), Recurrent (RNNs), Ordinary Differential Equations (Neural ODEs) enhance precipitation-induced forecasting. A six-year dataset (2016–2022) from Al Ain, United Arab Emirates (UAE), was employed model training, with validation conducted using data severe April 2024 flash flood. The proposed compared against standalone CNN, RNN, ODE evaluate its predictive performance. Results show the combination of CNN’s feature extraction, RNN’s temporal analysis, ODE’s continuous-time modeling achieves superior accuracy, an R2 value 0.98, RMSE = 2.87 × 106, MAE 1.13 PBIAS −8.38. These findings highlight model’s ability effectively capture complex hydrological dynamics. provides valuable tool improving flash-flood forecasting water resource management, especially arid regions like UAE. Future work may explore application different climates integration real-time monitoring systems.

Language: Английский

Citations

Assessment of urban flood susceptibility based on a novel integrated machine learning method DOI

Haidong Yang, Ting Zou, Biyu Liu

et al.

Environmental Monitoring and Assessment, Journal Year: 2024, Volume and Issue: 197(1)

Published: Dec. 5, 2024

Language: Английский

Citations