aiqbench analysis
The PyroStack dataset represents a significant advancement in environmental AI by harmonizing high-resolution satellite, meteorological, and topographic data across the US to support machine learning models for wildfire prediction. This resource directly addresses critical gaps in spatial and temporal coverage, enabling robust benchmarking for physics-informed and data-driven approaches to fire spread dynamics. By facilitating systematic evaluation of predictive algorithms under diverse climate conditions, it lays essential groundwork for improving next-generation disaster response systems.
PyroStack: A Multi-Band Spatio-Temporal Sub-Daily Dataset for Wildfires in the United States
arXiv:2609.36315v1 Announce Type: new Abstract: Wildfires are an increasing hazard to ecosystems, air quality, and human systems, creating a growing need for datasets that support systematic development and evaluation of models for predicting fire spread across diverse landscapes. Effective prediction requires integrating meteorological conditions, fuels, vegetation, and topography at spatial and temporal resolutions suitable for both physical simulation and data-driven approaches. However, existing datasets often lack the resolution and coverage needed to capture these interacting controls. The PyroStack dataset addresses this gap by providing a harmonized, event-based collection of wildfire and environmental data across the contiguous United States and Alaska. It integrates satellite-derived fire observations with atmospheric reanalysis, vegetation, fuel characteristics, and topographic information into a unified framework spanning 6994 wildfires that occurred between 2012 and 2024 across a wide range of ecosystems and climate conditions. PyroStack offers spatial resolutions ranging from 30 m to 9 km and hourly temporal resolution, along with fire progression data at 12-hour intervals to support model initialization and evaluation. By combining broad spatial coverage with fine spatial and temporal detail, the dataset enables systematic analysis of wildfire dynamics and supports both physics-based and machine learning approaches, providing a foundation for benchmarking and improving fire spread models, with future extensions aimed at incorporating additional regions and fire suppression data streams to further advance wildfire prediction.
Authors:Arya Kondur, Giosue Migliorini, Cameron Schmitt, Francesco Immorlano, Tairan Wang, Rebecca C. Scholten, Efi Foufoula-Georgiou, Gary Johnson, Chris Lautenberger, Valentin Waeselynck, J. Shane Romsos, Kasra Shamsaei, Alejandro Tejedor, Tianjia Liu, Yang Chen, Padhraic Smyth, James T. Randerson
Abstract:Wildfires are an increasing hazard to ecosystems, air quality, and human systems, creating a growing need for datasets that support systematic development and evaluation of models for predicting fire spread across diverse landscapes. Effective prediction requires integrating meteorological conditions, fuels, vegetation, and topography at spatial and temporal resolutions suitable for both physical simulation and data-driven approaches. However, existing datasets often lack the resolution and coverage needed to capture these interacting controls. The PyroStack dataset addresses this gap by providing a harmonized, event-based collection of wildfire and environmental data across the contiguous United States and Alaska. It integrates satellite-derived fire observations with atmospheric reanalysis, vegetation, fuel characteristics, and topographic information into a unified framework spanning 6994 wildfires that occurred between 2012 and 2024 across a wide range of ecosystems and climate conditions. PyroStack offers spatial resolutions ranging from 30 m to 9 km and hourly temporal resolution, along with fire progression data at 12-hour intervals to support model initialization and evaluation. By combining broad spatial coverage with fine spatial and temporal detail, the dataset enables systematic analysis of wildfire dynamics and supports both physics-based and machine learning approaches, providing a foundation for benchmarking and improving fire spread models, with future extensions aimed at incorporating additional regions and fire suppression data streams to further advance wildfire prediction.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2609.36315 [cs.LG]
(or arXiv:2609.36315v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.36315 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 279 words
Related coverage
MP3: Multi-Period Pattern Pre-training for Spatio-Temporal Forecasting
arXiv · Jun 15, 2026
MP3: Multi-Period Pattern Pre-training forSpatio-Temporal Forecasting
arXiv · Jun 12, 2026
DSFNet: Learning Dual-Domain Spectral Operators for Multi-Modality Spatio-Temporal Forecasting in Urban Transportation Systems
arXiv · Jun 9, 2026
A Modular Multitask Reasoning Framework Integrating Spatio-temporal Models and LLMs
arXiv · Aug 25, 2026