Sustainable flood risk assessment using deep learning-based algorithms with a blockchain technology

The couplings of convolutional neural networks (CNN) with random forest (RF), support vector machine (SVM), long short-term memory (LSTM), and extreme gradient boosting (XGBoost) ensemble algorithms were used to construct novel ensemble computational models (CNN-LSTM, CNN-XG, CNN-SVM, and CNN-RF) fo...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Geocarto international Ročník ahead-of-print; číslo ahead-of-print; s. 1 - 29
Hlavní autoři: Mia, Md. Uzzal, Rahman, Mahfuzur, Elbeltagi, Ahmed, Abdullah-Al-Mahbub, Md, Sharma, Gitika, Islam, H. M. Touhidul, Pal, Subodh Chandra, Costache, Romulus, Islam, Abu Reza Md. Towfiqul, Islam, Md Monirul, Chen, Ningsheng, Alam, Edris, Washakh, Rana Muhammad Ali
Médium: Journal Article
Jazyk:angličtina
Vydáno: Taylor & Francis 12.08.2022
Témata:
Blockchain
deep learning algorithm
flash floods
relief
sustainable development
ISSN:1010-6049, 1752-0762
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The couplings of convolutional neural networks (CNN) with random forest (RF), support vector machine (SVM), long short-term memory (LSTM), and extreme gradient boosting (XGBoost) ensemble algorithms were used to construct novel ensemble computational models (CNN-LSTM, CNN-XG, CNN-SVM, and CNN-RF) for flood hazard mapping in the monsoon-dominated catchment, Bangladesh. The results revealed that geology, elevation, the normalized difference vegetation index (NDVI), and rainfall are the most significant parameters in flash floods based on the Pearson correlation technique. Statistical method such as the area under the curve (AUC) was used to evaluate model performance. The CNN-RF model could be a promising tool for precisely predicting and mapping flash floods as it is outperformed the other models (AUC = 1.0). Furthermore, to meet sustainable development goals (SDGs), a blockchain-based technology is proposed to create a decentralized flood management tool for help seekers and help providers during and post floods. The suggested tool accelerates emergency rescue operations during flood events.
ISSN:1010-6049
1752-0762
DOI:10.1080/10106049.2022.2112982