Application of hybrid model-based deep learning and swarm‐based optimizers for flood susceptibility prediction in Binh Dinh province, Vietnam

Nguyen, Huu Duy; Van, Chien Pham; Duc, Anh Nguyen

doi:10.1007/s12145-023-00954-4

Cited by 10 publications

(2 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SGD has the advantage of being simple in structure, easy to use and extremely stable during training. However, as the SGD algorithm needs to update all the parameters, it requires substantial computational resources (Nguyen et al, 2023).…”

Section: Stochastic Gradient Descentmentioning

confidence: 99%

Landslide susceptibility prediction using machine learning and remote sensing: Case study in Thua Thien Hue province, Vietnam

Nguyen,

et al. 2023

Geological Journal

Self Cite

View full text Add to dashboard Cite

Landslides lead to widespread devastation and significant loss of life in mountainous regions around the world. Susceptibility assessments can provide critical data to help decision‐makers, for example, local authorities and other organizations, mitigating the landslide risk, although the accuracy of existing studies needs to be improved. This study aims to assess landslide susceptibility in the Thua Thien Hue province of Vietnam using deep neural networks (DNNs) and swarm‐based optimization algorithms, namely Adam, stochastic gradient descent (SGD), Artificial Rabbits Optimization (ARO), Tuna Swarm Optimization (TSO), Sand Cat Swarm Optimization (SCSO), Honey Badger Algorithm (HBA), Marine Predators Algorithm (MPA) and Particle Swarm Optimization (PSO). The locations of 945 landslides occurring between 2012 and 2022, along with 14 conditioning factors, were used as input data to build the DNN and DNN‐hybrid models. The performance of the proposed models was evaluated using the statistical indices receiver operating characteristic curve, area under the curve (AUC), root mean square error, mean absolute error (MAE), R2 and accuracy. All proposed models had a high accuracy of prediction. The DNN‐MPA model had the highest AUC value (0.95), followed by DNN‐HBA (0.95), DNN‐ARO (0.95), DNN‐Adam (0.95), DNN‐SGD (0.95), DNN‐TSO (0.93), DNN‐PSO (0.9) and finally DNN‐SCSO (0.83). High‐precision models have identified that the majority of the western region of Thua Thien Hue province is very highly susceptible to landslides. Models like the aforementioned ones can support decision‐makers in updating large‐scale sustainable land‐use strategies.

show abstract

Section: Stochastic Gradient Descentmentioning

confidence: 99%

Landslide susceptibility prediction using machine learning and remote sensing: Case study in Thua Thien Hue province, Vietnam

Nguyen,

et al. 2023

Geological Journal

Self Cite

View full text Add to dashboard Cite

show abstract

“…In Vietnam, the adoption of mathematical simulation and surface water resource assessment models has also been popular, such as DPSIR, Quasi-2D, SWAT, and MIKE [6][7][8][9][10][11]. The combination of NAM and MIKE 11 models to simulate face flow matching high-slope terrain has been widely applied [12,13].…”

Section: Introductionmentioning

confidence: 99%

Evaluation of surface water quality and carrying capacity as planned by 2030 in the Lai Giang River basin, Binh Dinh Province, Vietnam

Nguyen,

2024

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

The quality of surface water in the river basin under the influence of industrial development and urbanization is one of the issues that need attention in the management of water resources in Binh Dinh province. The study assessed water quality in the Lai Giang river basin gives an overview of the surface water quality situation and predicts future changes in wastewater reception through the 2030 planning scenario. The study corrected the NAM model flow at An Hoa hydrological station with R2 = 0.777 and BIAS = 5%. The results of adjustment of water level and flow in 2016 for R2 are 0.893 and 0.731, respectively. The test of water level and flow in 2017 for R2 is 0.882 and 0.582 respectively, along with the test result of water level in 2021 is 0.689. The calculation of the current carrying capacity in 2021 and the planning scenario in 2030 shows that there is still capability to receive, but consideration should be given to rational use of water resources.

show abstract

Artificial Intelligence Algorithms in Flood Prediction: A General Overview

Pandey

2024

Geo-Information for Disaster Monitoring and Management

View full text Add to dashboard Cite

Application of hybrid model-based deep learning and swarm‐based optimizers for flood susceptibility prediction in Binh Dinh province, Vietnam

Cited by 10 publications

References 84 publications

Landslide susceptibility prediction using machine learning and remote sensing: Case study in Thua Thien Hue province, Vietnam

Landslide susceptibility prediction using machine learning and remote sensing: Case study in Thua Thien Hue province, Vietnam

Evaluation of surface water quality and carrying capacity as planned by 2030 in the Lai Giang River basin, Binh Dinh Province, Vietnam

Artificial Intelligence Algorithms in Flood Prediction: A General Overview

Contact Info

Product

Resources

About