Reservoir risk modelling using a hybrid approach based on the feature selection technique and ensemble methods

Xiong, Junnan; Quan, Pang; Cheng, Weiming; Wang, Nan; Yong, Zhiwei

doi:10.1080/10106049.2020.1852615

Cited by 5 publications

(4 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, we accessed the digital collection of HMP records put together thanks to the China National Flash Flood Disasters Prevention and Control Project (see, Liu et al, 2018bLiu et al, , 2021Xiong et al, 2019Xiong et al, , 2020. This project is a large-scale national initiative that has involved many administrations and research centers across China, to collect, standardize and digitize HMP occurrence data in the last fifty years.…”

Section: Hmp Inventorymentioning

confidence: 99%

On the use of explainable AI for susceptibility modeling: examining the spatial pattern of SHAP values

Wang¹,

Zhang²,

Dahal³

et al. 2023

Preprint

View full text Add to dashboard Cite

Hydro-morphological processes (HMP, any natural phenomenon contained within the spectrum defined between debris flows and flash floods) are globally occurring natural hazards which pose great threats to our society, leading to fatalities and economical losses. For this reason, understanding the dynamics behind HMPs is needed to aid in hazard and risk assessment. In this work, we take advantage of an explainable deep learning model to extract global and local interpretations of the HMP occurrences across the whole Chinese territory. We use a neural network architecture and interpret the model results through the spatial pattern of SHAP values.In doing so, we can understand the model prediction on a hierarchical basis, looking at how the predictor set controls the overall susceptibility as well as doing the same at the level of the single mapping unit.Traditional statistical tools usually lead to a clear interpretation at the expense of large performance, which is otherwise reached via machine/deep learning solutions, though at the expense of interpretation. Explainable AI is the key to combine both strengths and in this work, we explore this combination in the context of HMP susceptibility modeling. Specifically, we demonstrate the extent to which one can enter a new level of data-driven interpretation, supporting the decision-making process behind disaster risk mitigation and prevention actions.

show abstract

Section: Hmp Inventorymentioning

confidence: 99%

On the use of explainable AI for susceptibility modeling: examining the spatial pattern of SHAP values

Wang¹,

Zhang²,

Dahal³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The data we used in this study is extracted from the digital collection of Chinese HMP records (Liu et al, 2018(Liu et al, , 2021Xiong et al, 2019Xiong et al, , 2020, each one characterized by geographic coordinates, time information and albeit partially, by a summary of sustained live and financial losses. From these records, we extracted all the HMPs for which a loss estimate was recorded between 1985 and 2015.…”

Section: Hmp Inventorymentioning

confidence: 99%

Impact-based probabilistic modeling of hydro-morphological processes in China (1985-2015)

Wang¹,

Cheng²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Hydro-morphological processes (HMP, any natural phenomenon contained within the spectrum defined between debris flows and flash floods) pose a relevant threat to infrastructure, urban and rural settlements and to lives in general. This has been widely observed in recent years and will likely become worse as climate change will influence the spatio-temporal pattern of precipitation events. The modelling of where HMP-driven hazards may occur can help define the appropriate course of actions before and during a crisis, reducing the potential losses that HMPs cause in their wake. However, the probabilistic information on locations prone to experience a given hazard is not sufficient to depict the risk our society may incur. To cover this aspect, modeling the loss information could open up to better territorial management strategies.In this work, we made use of the HMP catalogue of China. This catalogue reports reliable records from 1985 to 2015 across the whole Chinese territory. Specifically, we implemented the Light Gradient Boosting (LGB) classifier to model the impact level that locations across China have suffered from HMPs over the thirty-year record. In doing so, we estimated spatial probabilities of certain HMP impact, something that has yet to be tested in the natural hazard community, especially over such a large spatio-temporal domain.This experiment follows a project launched by the Chinese government with the aim of improving national efforts against climate change and improving societal resilience to disastrous events. In this context, the good predictive performance our model produced suggest that the cartographic output could be useful to inform authorities of locations prone to human and infrastructural losses of specific magnitudes.

show abstract

“…More importantly, the reliability and attributes of these flash floods were strictly inspected by the experts and scholars of the China Institute of Water Resources and Hydropower [32]. Since the establishment of this database, it has successfully served a large number of studies [4,33,34].…”

Section: Flash Flood Inventory Mapmentioning

confidence: 99%

Hybrid Models Incorporating Bivariate Statistics and Machine Learning Methods for Flash Flood Susceptibility Assessment Based on Remote Sensing Datasets

et al. 2021

Self Cite

View full text Add to dashboard Cite

Flash floods are considered to be one of the most destructive natural hazards, and they are difficult to accurately model and predict. In this study, three hybrid models were proposed, evaluated, and used for flood susceptibility prediction in the Dadu River Basin. These three hybrid models integrate a bivariate statistical method of the fuzzy membership value (FMV) and three machine learning methods of support vector machine (SVM), classification and regression trees (CART), and convolutional neural network (CNN). Firstly, a geospatial database was prepared comprising nine flood conditioning factors, 485 flood locations, and 485 non-flood locations. Then, the database was used to train and test the three hybrid models. Subsequently, the receiver operating characteristic (ROC) curve, seed cell area index (SCAI), and classification accuracy were used to evaluate the performances of the models. The results reveal the following: (1) The ROC curve highlights the fact that the CNN-FMV hybrid model had the best fitting and prediction performance, and the area under the curve (AUC) values of the success rate and the prediction rate were 0.935 and 0.912, respectively. (2) Based on the results of the three model performance evaluation methods, all three hybrid models had better prediction capabilities than their respective single machine learning models. Compared with their single machine learning models, the AUC values of the SVM-FMV, CART-FMV, and CNN-FMV were 0.032, 0.005, and 0.055 higher; their SCAI values were 0.05, 0.03, and 0.02 lower; and their classification accuracies were 4.48%, 1.38%, and 5.86% higher, respectively. (3) Based on the results of the flood susceptibility indices, between 13.21% and 22.03% of the study area was characterized by high and very high flood susceptibilities. The three hybrid models proposed in this study, especially CNN-FMV, have a high potential for application in flood susceptibility assessment in specific areas in future studies.

show abstract

Reservoir risk modelling using a hybrid approach based on the feature selection technique and ensemble methods

Cited by 5 publications

References 79 publications

On the use of explainable AI for susceptibility modeling: examining the spatial pattern of SHAP values

On the use of explainable AI for susceptibility modeling: examining the spatial pattern of SHAP values

Impact-based probabilistic modeling of hydro-morphological processes in China (1985-2015)

Hybrid Models Incorporating Bivariate Statistics and Machine Learning Methods for Flash Flood Susceptibility Assessment Based on Remote Sensing Datasets

Contact Info

Product

Resources

About