Forecasting Daily Wildfire Activity Using Poisson Regression

Abstract

Wildfires and their emissions reduce air quality in many regions of the world, contributing to thousands of premature deaths each year. Smoke forecasting systems have the potential to improve health outcomes by providing future estimates of surface aerosol concentrations (and health hazards) over a period of several days. In most operational smoke forecasting systems, fire emissions are assumed to remain constant during the duration of the weather forecast and are initialized using satellite observations. Recent work suggests that it may be possible to improve these models by predicting the temporal evolution of emissions. Here, we develop statistical models to predict fire activity one to five days into the future using Moderate Resolution Imaging Spectroradiometer (MODIS) satellite fire counts and weather data from ERA-interim reanalysis. Our predictive framework consists of two-Poisson regression models that separately represent new ignitions and the dynamics of existing fires on a coarse resolution spatial grid. We use ten years of active fire detections in Alaska to develop the model and use a cross-validation approach to evaluate model performance. Our results show that regression methods are significantly more accurate in predicting daily fire activity than persistence-based models (which suffer from an overestimation of fire counts by not accounting for fire extinction), with vapor pressure deficit being particularly effective as a single weather-based predictor in the regression approach.

A Poisson-Regression, Support Vector Machine and Grey Prediction Based Combined Forecasting Model Proposal: A Case Study in Distribution Business

“…The outcome is an %31 improvement above climatology. Graff et al [10] used PR to forecast daily wildfire activities. The results show that regression models significantly outperform traditional persistencebased models used in operational smoke forecasting applications at both the cell and regional levels.…”

BDANet: Multiscale Convolutional Neural Network With Cross-Directional Attention for Building Damage Assessment From Satellite Images

“…N ATURAL disasters, such as earthquakes, floods and tsunami, can cause serious social and economic devastation. When a natural disaster strikes, accurate and immediate responses are required in Humanitarian Assistance and Disaster Response (HADR) for saving thousands of lives [1], [2], [3], [4]. Before these responses, rescue planning and preparations are conducted based on damage analysis.…”

Integration of a Coupled Fire-Atmosphere Model Into a Regional Air Quality Forecasting System for Wildfire Events

“…While this approach is widely accepted by the modeling community, it has limitations for cases where fires exhibit significant day-to-day variations in the burned area or when the fire emissions do not conform to a typical diel pattern. Recent work by Graff et al (2020) highlighted the limitations of assuming unchanged diurnal patterns and showed that regression models accounting for weather-driven changes in fire activity often perform better. For plume rises, most AQ models parameterize the smoldering fraction and calculate plume-top height using methods developed for point-source modeling (e.g., industrial facilities).…”