Analysis of spatial and temporal characteristics of major natural disasters in China from 2008 to 2021 based on mining news database

Yang, Chenchen; Zhang, Han; Li, Xunhua; He, Zhongshi; Jun-li, LI

doi:10.1007/s11069-023-06097-5

Cited by 4 publications

(2 citation statements)

References 80 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some studies about natural hazards have revealed the power of media data to supplement the shortcomings of traditional natural science data sources (Avellaneda et al, 2020;Lai et al, 2022). For instance, Yang et al (2023) analyzed the clustering of multiple natural disasters including earthquakes, floods, droughts, etc. in China based on news data.…”

Section: Introductionmentioning

confidence: 99%

Extracting Spatiotemporal Flood Information from News Texts Using Machine Learning for a National Dataset in China

Fu,

Schultz,

Lyu

et al. 2024

Preprint

View full text Add to dashboard Cite

Abstract. Urban floods present a threat in China, demanding an understanding of their spatiotemporal distribution. Current flood datasets primarily offer provincial-scale insights and lack temporal continuity, which leads to a challenge in detailed analysis. To create a consistent national dataset of flood events, this study introduces a machine learning framework by applying online news media as a primary data source to construct a county-level dataset of urban flood events from 2000 to 2022. Using the Bidirectional Encoder Representations from Transformers (BERT) model, we achieved robust performance in information extraction, with an F1 score of 0.86 and an exact match score of 0.82. Further, a combined model of Bidirectional Long Short-term Memory (BiLSTM) networks with a Conditional Random Field (CRF) layer effectively identified flood locations. Our analysis reveals that the temporal trend of flooded cities in the news-based dataset is similar to the China Flood and Drought Bulletin. Furthermore, the consistency of flood events in the news with the typhoon trajectory in two cases, and the connection between flood occurrences and flood conditioning factors, confirm the accuracy of spatial distribution. The validated news-based dataset analyzes urban floods in China from both temporal and spatial perspectives. First, this dataset shows the seasonal characteristics of flood events, which are concentrated in the summer. From 2000 to 2022, the peak year for floods was 2010, and excluding the influence of peak year, the overall temporal trend of total flood occurrence shows an increase. Spatially, the distribution of floods decreases from southeast to northwest, with Guangxi Province having the highest number of floods. Additionally, the Yangtze and Pearl River basins are most frequently affected by urban floods. The subtropical climate zone is the most susceptible to flooding. This study provides an automated and effective method for constructing a national flood event dataset and reveals the spatiotemporal characteristics of urban flooding in China.

show abstract

Section: Introductionmentioning

confidence: 99%

Extracting Spatiotemporal Flood Information from News Texts Using Machine Learning for a National Dataset in China

Fu,

Schultz,

Lyu

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The total length of national highways has grown from 1.6 million kilometers in 1978 to 5.16 million kilometers in 2022, with expressways reaching 177,300 km, making China the world leader in terms of expressway infrastructure [2]. China stands as one of the nations most significantly impacted by geomorphological disasters, with losses attributed to these events representing more than 35% of the overall losses incurred from various natural calamities [3][4][5]. In geomorphological incidents, collapses, landslides, debris flows, and engineering incidents induced by human activities account for more than half of the losses, amounting to approximately 20 billion yuan annually [6].…”

Section: Introductionmentioning

confidence: 99%

Exploring the Spatio-Temporal Trends of Geomorphological Incidents Induced by Precipitation on Chinese Highways

Zhang,

Tian,

Song

2024

Atmosphere

View full text Add to dashboard Cite

The spatiotemporal distribution of geomorphological incidents was examined in the present study, including the characteristics of obstruction distances and durations, by utilizing nationwide incident mitigation data and precipitation observation records from the period spanning 2019 to 2022. By comparing rainfall features over different temporal scales across various regions, the aim of the present study was to enhance the current comprehension of the patterns through which regional precipitation initiates incidents on highways by comparing rainfall characteristics over distinct temporal scales across diverse geographical areas. The findings indicate that: (1) The spatial distribution of highway incidents in China is significantly correlated with regional natural environments, predominantly concentrated in the southern parts of the country’s second and third topographical terraces. The temporal distribution closely aligns with annual and monthly precipitation patterns, with the majority of occurrences taking place from June to September. Further, notable disparities in the distribution of highway-related incidents were observed among counties across most provinces; (2) National highways experience a notably higher frequency of incidents than expressways and provincial roads, with most obstruction lengths concentrated within 1 km and durations predominantly under 3 days; (3) The probability of daily rainfall inducing highway incidents is distinctly higher than that of short-duration rainfall, with eastern and southern China experiencing significantly greater inducing precipitation volumes than other regions. The majority of areas are susceptible to incidents within a 3-day window following heavy rainfall or within 24 h after intense short-duration rainfall. Moreover, it is observed that incidents are more closely associated with extreme precipitation occurring within a single day; (4) There is a certain lag between the timing of incidents and the occurrence of extreme short-duration heavy rainfall, with the highest frequency of incidents coinciding with continuous rainfall periods of 3 to 6 days.

show abstract

Exploring and analyzing disaster coupling characteristics at the regional scale: evidence from Hubei Province

Wang,

Hou,

Guo

2024

Geomatics, Natural Hazards and Risk

View full text Add to dashboard Cite

Analysis of spatial and temporal characteristics of major natural disasters in China from 2008 to 2021 based on mining news database

Cited by 4 publications

References 80 publications

Extracting Spatiotemporal Flood Information from News Texts Using Machine Learning for a National Dataset in China

Extracting Spatiotemporal Flood Information from News Texts Using Machine Learning for a National Dataset in China

Exploring the Spatio-Temporal Trends of Geomorphological Incidents Induced by Precipitation on Chinese Highways

Exploring and analyzing disaster coupling characteristics at the regional scale: evidence from Hubei Province

Contact Info

Product

Resources

About