Publications & Patents
Paper: "A Review of Technologies for the Early Detection of Wildfires"
Published in the American Society of Mechanical Engineers peer-reviewed Open Journal of Engineering in January 2025
In this paper we review the various architectures and approaches adopted for wildfire detection, including spaceborne, airborne, fixed cameras, and sensor networks. The paper further analyzes the pros and cons of each approach and reviews recent deployments and published research. In particular, it focuses on the growing and significant role that Artificial Intelligence (AI) and Deep Learning (DL) play in improving the effectiveness of the aforementioned architectures.
​
Ryan was lead author on the paper along with UCLA Professor Kavehpour and OCFA Fire Captain Jeff Shelton as co-authors. Published in the peer-reviewed ASME Open Journal of Engineering in January 2025, the paper has consistently been in the top 3 Most Read papers in the journal with over 2700 page reviews, over 600 pdf downloads, and 8 citations as of October 2025.
Issued Patent: "Distributed Implementation of Random Forest in a Network"
Patent no. 12373740 issued by US Patent & Trademark Office, filed as a non-provisional application in August 2024 and issued on July 29, 2025.
Ryan is the sole inventor on this patent which outlines a distributed implementation of a well known Machine Learning model across a network of processors/sensors. This approach is relevant in natural disaster environments where some of the sensors might be destroyed by fire, flood... this patented approach can continue to operate and provide graceful performance drop even while parts of network have become inoperable.
Paper: "An Artificial Intelligence Driven Thermodynamics Based IOT Sensor Network for the Ultra-Early Detection of Wildfire"
Presented in-person at the 2025 IEEE World AI IOT Congress in Seattle May 2025, and published in the IEEE Conference Proceedings August 2025
In this work we have developed a new detection technique focused on leveraging the laws of heat transfer and fluid dynamics to detect the “heat” signature of a small fire from a distance. We were able to detect small fires with flames lengths of less than 1ft from around 600ft away without line of sight. This work represents a significant advancement in AI-enabled wildfire detection and offers promising opportunities for improving early response times and mitigating the devastating impacts of wildfires.
​
Ryan was lead author on the paper and UCLA Professor Kavehpour was co-author. Ryan conducted much of the original research under guidance of Prof. Kavehpour at the Complex Fluids and Interfacial Physics Lab at the Mechanical and Aerospace Engineering Dept. of UCLA between March 2025 - March 2026.
