A Novel LSTM Approach for Reliable and Real-Time Flood Prediction in Complex Watersheds DOI Creative Commons
Wassima Moutaouakil, Soufiane Hamida,

Oussama ElGannour

и другие.

Research Square (Research Square), Год журнала: 2025, Номер unknown

Опубликована: Март 26, 2025

Abstract In the context of global climate change, world is increasingly experiencing abnormal phenomena, with natural disasters being among most critical challenges. Adapting to these changes and mitigating their risks has become imperative. Floods, as one devastating threats, are a crucial subject study, particularly in understanding predicting dynamic behavior. This research highlights importance flood mapping assessment using satellite imagery advanced technologies such Geographical Information System (GIS) Deep Learning (DL). The study focuses on Tetouan city, located northern Morocco, which provides ideal conditions for this research. Eleven conditioning factors were analyzed, including elevation, slope, aspect, Stream Power Index (SPI), Topographic Position (TPI), Wetness (TWI), curvature, drainage density (DD), distance rivers (DR), Normalized Difference Vegetation (NDVI), land use (LU). To identify relevant influencing occurrence, Gain Ratio (IGR) Frequency (FR) methods applied, allowing exclusion non-impactful factors. Long Short-Term Memory (LSTM) deep learning technique was utilized balanced dataset 1946 samples generated through data augmentation. Additional optimization techniques implemented enhance model’s performance. findings demonstrate high prediction accuracy 96.06%, underscoring model's effectiveness risk assessment.

Язык: Английский

Predicting flood risks using advanced machine learning algorithms with a focus on Bangladesh: influencing factors, gaps and future challenges DOI
Abu Reza Md. Towfiqul Islam,

Md. Jannatul Naeem Jibon,

Md. Abubakkor Siddik

и другие.

Earth Science Informatics, Год журнала: 2025, Номер 18(3)

Опубликована: Фев. 27, 2025

Язык: Английский

Процитировано

0
A Novel LSTM Approach for Reliable and Real-Time Flood Prediction in Complex Watersheds DOI Creative Commons
Wassima Moutaouakil, Soufiane Hamida,

Oussama ElGannour

и другие.

Research Square (Research Square), Год журнала: 2025, Номер unknown

Опубликована: Март 26, 2025

Abstract In the context of global climate change, world is increasingly experiencing abnormal phenomena, with natural disasters being among most critical challenges. Adapting to these changes and mitigating their risks has become imperative. Floods, as one devastating threats, are a crucial subject study, particularly in understanding predicting dynamic behavior. This research highlights importance flood mapping assessment using satellite imagery advanced technologies such Geographical Information System (GIS) Deep Learning (DL). The study focuses on Tetouan city, located northern Morocco, which provides ideal conditions for this research. Eleven conditioning factors were analyzed, including elevation, slope, aspect, Stream Power Index (SPI), Topographic Position (TPI), Wetness (TWI), curvature, drainage density (DD), distance rivers (DR), Normalized Difference Vegetation (NDVI), land use (LU). To identify relevant influencing occurrence, Gain Ratio (IGR) Frequency (FR) methods applied, allowing exclusion non-impactful factors. Long Short-Term Memory (LSTM) deep learning technique was utilized balanced dataset 1946 samples generated through data augmentation. Additional optimization techniques implemented enhance model’s performance. findings demonstrate high prediction accuracy 96.06%, underscoring model's effectiveness risk assessment.

Язык: Английский

Процитировано

0