Skip to main content Skip to secondary navigation
Main content start
Ph.D. Student

Daniel Neamati

Ph.D. Student in Aeronautics and Astronautics, admitted Autumn 2021

TomKat Graduate Fellow for Translational Research

Research Lab: Grace Gao

Year Awarded: 2024

Daniel is a Ph.D. candidate in the Department of Aeronautics and Astronautics, advised by Professor Grace Gao. His current research in the Navigation and Autonomous Vehicles Lab (NAV Lab, https://navlab.stanford.edu/) focuses on neural digital twins of the wildland-urban interface with an emphasis on forest management in wildfire-prone areas. Daniel recently completed his M.S. in Aeronautics and Astronautics at Stanford University. He graduated from the California Institute of Technology in 2021 with a bachelor's degree in Mechanical Engineering and a minor in Planetary Science.

Daniel's Webpage

Google Scholar page

Neural Digital Twins to Enable Large-Scale Fire Management at the Wildland-Urban Interface

Prescribed burns are critical to sustainable forest management, preventing uncontrolled fires, and maintaining ecosystem health. Implementing prescribed burns requires significant planning, operations, and review, limiting operations to small regions. When burns occur at the wildland-urban interface (WUI), care must be taken to account for potential property damage, power grid collapse, emergency evacuations, and human health impacts due to detrimental air quality. The difficulty in using prescribed burns to mitigate uncontrolled fire risks at the WUI has led to rapidly rising insurance costs and insurance companies rejecting new customers, leaving people, property, and ecosystems stranded. To improve decision-making surrounding prescribed burns and provide accurate historical reviews, agencies like NASA and CALFire have considered using aerial systems to reconstruct active fires into near real-time digital twins. However, agencies are far from implementing detailed digital twins at scale due to the difficulty in reconstructing the fire scenes, integrating data from multiple sources at different wavelengths, and obtaining aerial imagery near the fires. This project leverages our recent work on neural models of complex outdoor environments to address the gap in translating digital twins to prescribed burn planning at the WUI.