All-hazards dataset mined from the US National Incident Management System 1999–2020

Abstract

This paper describes a dataset mined from the public archive (1999–2020) of the US National Incident Management System Incident Status Summary (ICS-209) forms (a total of 187,160 reports for 35,170 incidents, including 34,478 wildland fires). This system captures detailed daily/regular information on incident development and response, including social and economic impacts. Most (98.4%) reports are wildland fire-related, with other incident types including hurricane, hazardous materials, flood, tornado, search and rescue, civil unrest, and winter storms. The archive, although publicly available, has been difficult to use for research due to multiple record formats, inconsistent data entry, and no clean pathway from individual reports to high-level incident analysis. Here, we describe the open-source, reproducible methods used to produce a science-grade version of the data, including formal connections made to other published wildland fire data products. Among other applications, this integrated and spatially augmented dataset enables exploration of the daily progression of the most costly, damaging, and deadly environmental-hazard events in recent US history.

Dataset of United States Incident Management Situation Reports from 2007 to 2021

“…We are unaware of any effort or intention to publish a research-ready version of the ROSS/IROC data, as they have restricted access. However, there are research-ready versions of the Incident Status Summary (ICS-209) portion of the SIT-209 data archive 22 , 23 spanning 1999–2020, including linkages to agency fire reports 24 . Here, we describe a complimentary effort to generate a processed and quality-checked version of the Incident Management Situation Report (IMSR) component of the SIT-209 application.…”

Fire suppression makes wildfires more severe and accentuates impacts of climate change and fuel accumulation

“…Furthermore, it is difficult to measure the magnitude of suppression efforts because even relatively direct proxies such as suppression cost are confounded by other factors, including terrain accessibility, human infrastructure at risk, and availability of suppression resources 41 . Finally, data on suppression efforts are generally only available for larger fires 42 , obscuring the many ignitions that are quickly and easily suppressed during initial attack 20 , 21 . To overcome these constraints, we used a simulation approach to assess and quantify the magnitude of the fire suppression bias on fire behavior and ecological impacts, relative to the influence of climate change and fuel accumulation.…”

Revealing the Potential of Deep Learning for Detecting Submarine Pipelines in Side-Scan Sonar Images: An Investigation of Pre-Training Datasets

“…In recent years, artificial intelligence methods have made significant strides in geological fields, including remote sensing [5][6][7][8], geological hazard prediction [9][10][11][12][13][14][15][16], geological exploration [17][18][19][20][21][22], and energy development [23]. However, the applicability and effectiveness of these methods in the specialized field of pipeline or cable (POC) detection remain inadequately explored.…”