Deep learning to assess the effects of land use/land cover and climate change on landslide susceptibility in the Tra Khuc river basin of Vietnam

Du, Quan Vu Viet; Nguyen, Huu Duy; Pham, Viet–Thanh; Chau, N.; Nguyen, Quoc Hung; Bui, Quang‐Thanh; Doan, Thanh Thuy; Tran, Anh; Petrişor, Alexandru-Ionuţ

doi:10.1080/10106049.2023.2172218

Cited by 9 publications

(6 citation statements)

References 127 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results support the first hypothesis in the introduction section that the inundation susceptibility exhibits strong relationships with natural and human factors as the slope, elevation, TWI and rainfall. For inundation susceptibility model development, studies have indicated that low quality of data has a negative effect on the quality of inundation susceptibility models and that, therefore, pre-processing of the data is critical (Du et al 2023). In this study, random forest was used to assess the importance of each of 11 conditioning factors.…”

Section: Inner Validation Of the Resultsmentioning

confidence: 99%

Assessment of Inundation Susceptibility in the Context of Climate Change, Based on Machine Learning and Remote Sensing: Case Study in Vinh Phuc Province of Vietnam

HUNG¹,

NGUYEN²,

Van³

2023

View full text Add to dashboard Cite

Accurate prediction of streamflow plays an important role in water resource management and the continuous assessment of inundation susceptibility in the context of climate change plays a key role in facilitating the construction of appropriate strategies for sustainable development. So far, few studies into inundation susceptibility have explicitly incorporated the effects of climate change into their methodologies. This study aimed to assess inundation susceptibility for Vinh Phuc province in Vietnam, from 2000 to 2020, using machine learning and remote sensing. The algorithms used were support vector machine, catboost, and extratrees. A geo-spatial database of 206 inundation points and 11 conditioning factors (namely elevation, slope, curvature, aspect, distance to river, distance to road, NDVI, NDBI, rainfall, soil type, and TWI) from 2000 to 2020 was developed to be used as the input data. RMSE, MAE, AUC, and R² were used to assess the fit of the models. The results showed that all the proposed models were a good fit, with AUC values of 0.95 and over. In general, the total area marked as very low risk or low risk has increased, with the high risk and very high-risk areas having decreased over the period studied. This change was mainly concentrated in the city of Vinh Yen where there has been strong urban growth. The models proposed in this study are a promising toolkit to assess inundation susceptibility continuously and can support decision makers involved in sustainable development. Our results highlight the benefits and consequences of planned and unplanned development. Properly planned can reduce the flood risk, while unplanned development can increase the risk. Therefore, by applying the theoretical framework in this study, decision makers or planners can build the most appropriate strategies for flood control in the context of climate change. Our approach in this study represents a theoretical framework for future research not only on inundation management but also natural hazard management, in regions around the world.

show abstract

Section: Inner Validation Of the Resultsmentioning

confidence: 99%

Assessment of Inundation Susceptibility in the Context of Climate Change, Based on Machine Learning and Remote Sensing: Case Study in Vinh Phuc Province of Vietnam

HUNG¹,

NGUYEN²,

Van³

2023

View full text Add to dashboard Cite

show abstract

“…The selection of factors that affect landslides is an important consideration in modelling landslides, as they can significantly affect model performance. There is no standard guide or universal agreement on the exact selection of landslide conditioning factors and the optimal number of factors for any landslide susceptibility model (Ado et al, 2022; Du et al, 2023; Zhang, Fu, et al, 2022). In many cases, authors select all factors available in the study area, and then use algorithms to assess the importance of each element, as well as their permutability.…”

Section: Discussionmentioning

confidence: 99%

“…With a third of its land area consisting of hills and mountains, Vietnam is one of the countries most affected. According to data from the General Department of Disaster Reduction (Ministry of Agriculture and Rural Development), between 2000 and 2015, Vietnam was affected by 250 flash floods and landslides, causing 779 deaths (Du et al, 2023; Nguyen et al, 2020).…”

Section: Introductionmentioning

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

“…Therefore, non-landslide points must be collected. Several studies have pointed out that several non-landslides similar to the landslide points can increase the accuracy of models Viet Du et al, 2023). Therefore, 252 non-landslide points were selected randomly from regions never affected by the landslide, such as the low slope and elevation region.…”

Section: Landslide Inventorymentioning

confidence: 99%

Assessing the relationship between landslide susceptibility and land cover change using machine learning

Nguyen Huu,

Vu Cong,

Bretcan

et al. 2024

Vietnam J. Earth Sci.

View full text Add to dashboard Cite

Landslides are natural disasters most frequent in the mountain region of Vietnam, producing critical damage to human lives and assets. Therefore, precisely identifying the landslide occurrence probability within the region is essential in supporting decision-makers or developers in establishing effective strategies for reducing the damage. This study is aimed at developing a methodology based on machine learning, namely Xgboost (XGB), lightGBM, K-Nearest Neighbors (KNN), and Bagging (BA) for assessing the connection of land cover change to landslide susceptibility in Da Lat City, Vietnam. 202 landslide locations and 13 potential drivers became input data for the model. Various statistical indices, namely the root mean square error (RMSE), the area under the curve (AUC), and mean absolute error (MAE), were used to evaluate the proposed models. Our findings indicate that the Xgboost model was better than other models, as shown by the AUC value of 0.94, followed by LightGBM (AUC=0.91), KNN (AUC=0.87), and Bagging (AUC=0.81). In addition, urban areas increased during 2017-2023 from 25 km² to 30 km² in very high landslide susceptibility areas. Our approach can be applied to test the other regions in Vietnam. Our findings might represent a necessary tool for land use planning strategies to reduce damage from natural disasters and landslides.

show abstract

Deep learning to assess the effects of land use/land cover and climate change on landslide susceptibility in the Tra Khuc river basin of Vietnam

Cited by 9 publications

References 127 publications

Assessment of Inundation Susceptibility in the Context of Climate Change, Based on Machine Learning and Remote Sensing: Case Study in Vinh Phuc Province of Vietnam

Assessment of Inundation Susceptibility in the Context of Climate Change, Based on Machine Learning and Remote Sensing: Case Study in Vinh Phuc Province of Vietnam

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

Assessing the relationship between landslide susceptibility and land cover change using machine learning

Contact Info

Product

Resources

About