A novel data source for human-caused wildfires in China: extracting information from judgment documents
GEOMATICS NATURAL HAZARDS & RISK(2024)
Abstract
Information on the spatiotemporal distribution of human-caused wildfires on a national scale is crucial for developing susceptibility map and facilitating decision-making in fire risk management. In China, it is difficult to access a national dataset of wildfires based on ground records at a fine spatiotemporal scale for understanding fire regimes. This study explores the use of judgment documents as a potential alternative long-term key data source, considering human-caused wildfire events as criminal offense in certain cases. Judgment documents are readily accessible, regularly updated, and provide a diverse range of reliable information. To extract information on human-caused wildfires, we develop a rule-based approach for judgment documents. The results indicate the feasibility of the method, allowing for the effective extraction of specific information of event such as the start date and time, location, burn area, and ignition cause. A comparison reveals limited consistency in the spatiotemporal distributions between the novel data and conventional datasets. Notably, judgment documents provide richer attribute information and identify additional human-caused wildfires challenging to capture using conventional datasets. Despite inherent limitations, information sourced from judgment documents proves valuable data for characterizing national patterns of wildfire occurrence at a fine scale.
MoreTranslated text
Key words
Judgment documents,human-caused wildfire,information extraction,rule-based approach,spatiotemporal distribution
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined