An enhanced global oil spill dataset from 1967 to 2023 based on text-form incident information

<p dir="ltr">This project presents an enhanced version of the oil spill database, originally based on <a href="https://incidentnews.noaa.gov/raw/index" rel="noreferrer" target="_blank">IncidentNews</a> maintained by NOAA's Office of Resp...

Full description

Saved in:
Bibliographic Details
Main Author: Yiming Liu (18823387) (author)
Other Authors: Zhuoli Yin (10890792) (author), Hua Cai (18934195) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:<p dir="ltr">This project presents an enhanced version of the oil spill database, originally based on <a href="https://incidentnews.noaa.gov/raw/index" rel="noreferrer" target="_blank">IncidentNews</a> maintained by NOAA's Office of Response and Restoration (ORR). The primary limitation of the original dataset is the absence of actual release amounts (RA), only providing potential maximum estimates, which might not reflect real situations. Our enhanced database addresses this gap by adding structured data regarding the actual RA extracted using NLP tools from incident descriptions and related posts.</p><p dir="ltr">We added three new columns: "actual RA,", "RA source", and "update label" to the original dataset. </p><ul><li>The "actual RA" column lists the final incident-level RA determined from processing the textual description and post information. </li><li>The "RA source" column specifies whether the final RA value was determined based on “description”, “posts”, or “description and posts”. </li><li>The "update label" column notes the relationship between the actual RA and the original potential maximum release value.</li></ul><p dir="ltr">The code and raw data used to generate this dataset can be found in a separate <a href="https://figshare.com/articles/software/Code_and_data_for_evaluating_oil_spill_amount_from_text-form_incident_information/26130892" rel="noreferrer" target="_blank">project</a>.</p>