Towards an Integrated Performance Framework for Fire Science and Management Workflows
H. Ahmed, R. Shende, I. Perez, D. Crawl, S. Purawat, I. Altintas
TL;DR
This paper tackles the need for reliable, end-to-end performance metrics to enable use-inspired, real-time scientific workflows for wildfire management. It proposes an AI/ML–enabled framework that integrates AI-ready data preparation, predictive modeling, and user-centric interfaces within the BP3D platform as part of the WIFIRE and National Data Platform ecosystems. Early results from 900 BP3D runs show baseline predictive capability, with CPU and memory usage explained to a notable degree ($R^2$ values of $0.706$ and $0.922$, respectively), while acknowledging data limitations and future work to improve accuracy and uncertainty quantification. The work advances scalable, data-driven provisioning for high-performance wildfire modeling workflows, with potential impact on reliability and timeliness of decision support in urgent contexts.
Abstract
Reliable performance metrics are necessary prerequisites to building large-scale end-to-end integrated workflows for collaborative scientific research, particularly within context of use-inspired decision making platforms with many concurrent users and when computing real-time and urgent results using large data. This work is a building block for the National Data Platform, which leverages multiple use-cases including the WIFIRE Data and Model Commons for wildfire behavior modeling and the EarthScope Consortium for collaborative geophysical research. This paper presents an artificial intelligence and machine learning (AI/ML) approach to performance assessment and optimization of scientific workflows. An associated early AI/ML framework spanning performance data collection, prediction and optimization is applied to wildfire science applications within the WIFIRE BurnPro3D (BP3D) platform for proactive fire management and mitigation.