NSF Convergence Accelerator – Track D: Artificial Intelligence and Community Driven Wildland Fire Innovation via a WIFIRE Commons Infrastructure for Data and Model Sharing

NSF 融合加速器 — 轨道 D：通过 WIFIRE 共享基础设施实现数据和模型共享，人工智能和社区驱动的野地火灾创新

• 批准号: 2134904
• 负责人: Ilkay Altintas
• 金额: $ 500万
• 依托单位: University of California-San Diego
• 依托单位国家: 美国
• 项目类别: Cooperative Agreement
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-10-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2134904&HistoricalAwards=false
• 关键词: NSF; Convergence; Accelerator; Track; Artificial

A century of suppressing wildfires has created a dangerous accumulation of flammable vegetation on landscapes, contributing to megafires that risk human life and property, and permanently destroy ecosystems. Small controllable fires can dramatically reduce the risk of large fires that are uncontrollable. BurnPro3D is a decision support platform to help the fire response and mitigation community understand risks and tradeoffs quickly and accurately to more effectively manage wildfires or conduct controlled burns. To achieve this vision, this project is developing specific AI innovations to: (i) Use knowledge management techniques to fuse data coming from diverse sources and prepare it for fire modeling; (ii) Conduct physics-based machine learning within next-generation fire models to use deep learning to understand complex processes that drive fire behavior; (iii) Apply constraint optimization methods to address complex tradeoffs in the decision process for the placement and timing of controlled burns; (iv) Employ explainable AI to increase the interpretability of data and models by diverse users all along the decision-making chain.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

世纪来对野火的压制造成了易燃植被在景观上的危险积累，助长了危及人类生命和财产的特大火灾，并永久破坏了生态系统。可控的小型火灾可以大大降低无法控制的大型火灾的风险。BurnPro 3D是一个决策支持平台，可帮助火灾响应和缓解社区快速准确地了解风险和权衡，以更有效地管理野火或进行受控燃烧。为了实现这一愿景，该项目正在开发具体的人工智能创新：（i）使用知识管理技术融合来自不同来源的数据，并为火灾建模做好准备;（ii）在下一代火灾模型中进行基于物理的机器学习，以使用深度学习来理解驱动火灾行为的复杂过程; ㈢采用约束最优化方法，以解决受控燃烧的位置和时间决定过程中的复杂权衡问题;（iv）采用可解释的人工智能，以增加数据和模型的可解释性，由不同的用户在整个决策过程中沿着-该奖项反映了NSF的法定使命，并被认为是值得通过使用基金会的知识价值和更广泛的影响审查标准进行评估的支持。

项目成果

Synthetic Forest Stands and Point Clouds for Model Selection and Feature Space Comparison

• DOI: 10.3390/rs15184407
• 发表时间: 2023-09
• 期刊: Remote. Sens.
• 作者: Michelle S. Bester;Aaron E. Maxwell;Isaac Nealey;Michael R. Gallagher;N. Skowronski;Brenden E. McNeil

TrueTrees: A Scalable Workflow for the Integration of Airborne LiDAR Scanning Data into Fuel Models for Prescribed Fire Simulations

TrueTrees：可扩展的工作流程，用于将机载 LiDAR 扫描数据集成到燃料模型中以进行规定的火灾模拟

• DOI: 10.1109/e-science58273.2023.10254923
• 发表时间: 2023
• 期刊: IEEE
• 作者: Roten, Daniel;Wells, Lucas;Crawl, Daniel;Parsons, Russell A.;Marcozzi, Anthony;Linn, Rodman R.;Hiers, Kevin;Altintas, Ilkay
• 通讯作者: Altintas, Ilkay

Automating the Evaluation of Datasets for FAIR and CARE Principles

自动评估数据集的公平和关怀原则

• DOI: 10.1109/e-science58273.2023.10254897
• 发表时间: 2023
• 期刊: IEEE
• 作者: Yete, Rujula;Purawat, Shweta;Perez, Ismael;Crawl, Daniel L.;Altintas, Ilkay
• 通讯作者: Altintas, Ilkay

Visualization and Labeling of Terrestrial LiDAR Data for Three-Dimensional Fuel Classification

用于三维燃料分类的地面激光雷达数据的可视化和标记

• DOI: 10.1109/e-science58273.2023.10254841
• 发表时间: 2023
• 期刊: IEEE
• 作者: Moreno, Ivannia Gomez;Nealey, Isaac;Roten, Daniel;Nguyen, Mai H.;Crawl, Daniel;O'Laughlin, Kate;Floca, Melissa;Pokswinski, Scott;Altintas, Ilkay
• 通讯作者: Altintas, Ilkay

Terrestrial Laser Scan Metrics Predict Surface Vegetation Biomass and Consumption in a Frequently Burned Southeastern U.S. Ecosystem

地面激光扫描指标可预测经常被烧毁的美国东南部生态系统的地表植被生物量和消耗

• DOI: 10.3390/fire6040151
• 发表时间: 2023
• 期刊: Fire
• 作者: Loudermilk, Eva Louise;Pokswinski, Scott;Hawley, Christie M.;Maxwell, Aaron;Gallagher, Michael R.;Skowronski, Nicholas S.;Hudak, Andrew T.;Hoffman, Chad;Hiers, John Kevin
• 通讯作者: Hiers, John Kevin