Fine assessment of tropical cyclone disasters based on GIS and SVM in Zhejiang Province, China

Lou, Weiping; Chen, Haiyan; Shen, Xiaoling; Sun, Ke Qin; Deng, Shengrong

doi:10.1007/s11069-012-0254-x

Cited by 17 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, this study extensively collects open-source data and develops a relatively comprehensive indicator system covering three aspects of TCDL: the hazard of disaster-causing factors (maximum daily rainfall, maximum wind speed, etc.) [34], the vulnerability of the disaster-bearing body (provincial GDP, population, etc.) [35], and the resilience (beds of medical institutions, telephones, etc.)…”

Section: Data Sourcesmentioning

confidence: 99%

Evaluation of Tropical Cyclone Disaster Loss Using Machine Learning Algorithms with an eXplainable Artificial Intelligence Approach

Liu

Chu

et al. 2023

Sustainability

View full text Add to dashboard Cite

In the context of global warming, tropical cyclones (TCs) have garnered significant attention as one of the most severe natural disasters in China, particularly in terms of assessing the disaster losses. This study aims to evaluate the TC disaster loss (TCDL) using machine learning (ML) algorithms and identify the impact of specific feature factors on the prediction of model with an eXplainable Artificial Intelligence (XAI) approach, SHapley Additive exPlanations (SHAP). The results show that LightGBM outperforms Random Forest (RF), Support Vector Machine (SVM), and Naive Bayes (NB) for estimating the TCDL grades, achieving the highest accuracy value of 0.86. According to the SHAP values, the three most important factors in the LightGBM classifier model are proportion of stations with rainfall exceeding 50 mm (ProRain), maximum wind speed (MaxWind), and maximum daily rainfall (MaxRain). Specifically, in the estimation of high TCDL grade, events characterized with MaxWind exceeding 30 m/s, MaxRain exceeding 200 mm, and ProRain exceeding 30% tend to exhibit a higher susceptibility to TC disaster due to positive SHAP values. This study offers a valuable tool for decision-makers to develop scientific strategies in the risk management of TC disaster.

show abstract

Section: Data Sourcesmentioning

confidence: 99%

Evaluation of Tropical Cyclone Disaster Loss Using Machine Learning Algorithms with an eXplainable Artificial Intelligence Approach

Liu

Chu

et al. 2023

Sustainability

View full text Add to dashboard Cite

show abstract

“…Most data augmentation algorithms focus on image data classification problems, but there is a data augmentation technique, noise injection [67], that can be applied to non-image data. It is used in the following way (refer to Equations (7) and (8)).…”

Section: Noise Injectionmentioning

confidence: 99%

“…Hence, more and more scholars have tried to apply machine learning algorithms to the typhoon storm surge’s economic loss assessment. Lou et al [ 8 ] selected 23 disaster-causing factors from four dimensions as input data to construct a loss assessment model of tropical cyclone disasters based on support vector regression (SVR). Wang et al [ 9 ] and Yuan et al [ 10 ] built an evaluation index system and utilized the backpropagation neural network (BPNN) model to forecast the storm surge’s economic damage.…”

Section: Introductionmentioning

confidence: 99%

A Data Augmentation-Based Evaluation System for Regional Direct Economic Losses of Storm Surge Disasters

Sun

Wang

2021

IJERPH

View full text Add to dashboard Cite

The accurate prediction of storm surge disasters’ direct economic losses plays a positive role in providing critical support for disaster prevention decision-making and management. Previous researches on storm surge disaster loss assessment did not pay much attention to the overfitting phenomenon caused by the data scarcity and the excessive model complexity. To solve these problems, this paper puts forward a new evaluation system for forecasting the regional direct economic loss of storm surge disasters, consisting of three parts. First of all, a comprehensive assessment index system was established by considering the storm surge disasters’ formation mechanism and the corresponding risk management theory. Secondly, a novel data augmentation technique, k-nearest neighbor-Gaussian noise (KNN-GN), was presented to overcome data scarcity. Thirdly, an ensemble learning algorithm XGBoost as a regression model was utilized to optimize the results and produce the final forecasting results. To verify the best-combined model, KNN-GN-based XGBoost, we conducted cross-contrast experiments with several data augmentation techniques and some widely-used ensemble learning models. Meanwhile, the traditional prediction models are used as baselines to the optimized forecasting system. The experimental results show that the KNN-GN-based XGBoost model provides more precise predictions than the traditional models, with a 64.1% average improvement in the mean absolute percentage error (MAPE) measurement. It could be noted that the proposed evaluation system can be extended and applied to the geography-related field as well.

show abstract

“…Studies of the mechanisms of disasters and analysis of disaster risk require an appropriate typhoon disaster database. The establishment of statistical models relies on reliable and abundant typhoon disaster data (Lou et al, 2012;Kim et al, 2016). In addition, the historical data form an important basis for a typhoon pre-assessment model that depend on analysis of historically similar typhoons (Zhang et al, 2012;Lai, 2020).…”

Section: Introductionmentioning

confidence: 99%

Reconstruction of a county-level resolution typhoon disaster database from 1980 to 2018 for China’s coastal area

Ren²,

Zhu³

et al. 2023

Front. Earth Sci.

View full text Add to dashboard Cite

This study develops a reconstructed typhoon disaster database over a longer period 1980–2018 and at higher spatial resolution by using the county-level resolution disaster records for the eight coastal provinces of China during the shorter period 2004–2013. Typhoon precipitation and wind data over the shorter period are matched to disaster data and a functional relationship is derived between typhoon meteorological impact and typhoon disaster (direct economic loss). This relationship is used to construct a disaster data set for a longer period. The basic characteristics of the reconstructed database are documented and analyzed. The above analyses show that, firstly, the reconstructed disaster data are consistent with the recorded data due to the highly significant correlation. Secondly, an appropriate reconstruction method is developed, involving three main phases: disaster data expansion for individual stations, establishment of relationships between disaster and typhoon precipitation and wind, and disaster database reconstruction. Thirdly, the annual cumulative damage shows an insignificant downward trend over time. Typhoon damage mainly occurred between July and September each year. Landfalling typhoons that moved northwestward and then turned northward always caused more severe damage in China. In general, the reconstructed disaster database can provides a data basis to typhoon risk and disaster mechanism researches.

show abstract

Fine assessment of tropical cyclone disasters based on GIS and SVM in Zhejiang Province, China

Cited by 17 publications

References 10 publications

Evaluation of Tropical Cyclone Disaster Loss Using Machine Learning Algorithms with an eXplainable Artificial Intelligence Approach

Evaluation of Tropical Cyclone Disaster Loss Using Machine Learning Algorithms with an eXplainable Artificial Intelligence Approach

A Data Augmentation-Based Evaluation System for Regional Direct Economic Losses of Storm Surge Disasters

Reconstruction of a county-level resolution typhoon disaster database from 1980 to 2018 for China’s coastal area

Contact Info

Product

Resources

About