데이터셋 상세
미국
Burn probability predictions for the state of California, USA using an optimal set of spatio-temporal features.
Burn probability (BP) models the likelihood that a location could burn. However, predicting BP is extremely challenging, because fire behavior varies strongly among landscapes and with changing weather conditions and wildfire spread simulations are computationally intensive and require integration of data with large spatial and temporal variability. In this data release we include the monthly BP estimation for the state of California, USA for the 2015-2019 period produced using a machine learning model and two different sets of input features. For the first case, the baseline, the model used all available input features to predict BP. The second output set corresponds to the BP predictions when the model used only the set of optimal features as determined in the cited paper.
데이터 정보
연관 데이터
Evaluations of FSim burn probability maps for pyromes of the conterminous United States based on observed wildfire perimeters
공공데이터포털
The FSim wildfire simulation model is widely used to generate estimates of burn probability (BP). However, few studies have compared BP models to subsequent wildfires to assess their suitability for estimating near-future wildfire risk. Here, we compared the U.S.D.A. Forest Service’s publicly available BP map for the conterminous U.S. (Short et al., 2020; Dillon et al., 2023) to observed wildfire perimeters. Our main focus was to evaluate the BP map version based on 2014 LANDFIRE fuels data and calibrated to historical wildfires from 1992-2015, allowing us to compare BP to observed wildfires from 2016-2022. We also compared evaluations using a newer version of the BP map based on 2020 LANDFIRE fuels and 1992-2020 historical wildfires, and additionally performed evaluations for the western U.S. based on differing wildfire size classes. This dataset includes CSV tables summarizing burned area proportions by BP classes for individual pyromes, or regions with similar wildfire regimes, as well as processing code used to summarize burned area by BP classes.
Probabilistic Wildfire Risk Flame Length Probability 1 Hawaii (Image Service)
공공데이터포털
,
Probabilistic Wildfire Risk Flame Length Probability 6 Hawaii (Image Service)
공공데이터포털
,
Probabilistic Wildfire Risk Flame Length Probability 3 Hawaii (Image Service)
공공데이터포털
,
Probabilistic Wildfire Risk Flame Length Probability 5 Hawaii (Image Service)
공공데이터포털
,
Probabilistic Wildfire Risk Burn Probability Hawaii (Image Service)
공공데이터포털
,
Probabilistic Wildfire Risk Flame Length Probability 2 Hawaii (Image Service)
공공데이터포털
,
Probabilistic Wildfire Risk Flame Length Probability 4 Hawaii (Image Service)
공공데이터포털
,
Spatial dataset of probabilistic wildfire risk components for the conterminous United States
공공데이터포털
National burn probability (BP) and conditional fire intensity level (FIL) data were generated for the conterminous United States (US) using a geospatial Fire Simulation (FSim) system developed by the US Forest Service Missoula Fire Sciences Laboratory to estimate probabilistic components of wildfire risk (Finney et al. [2011]). The FSim system includes modules for weather generation, wildfire occurrence, fire growth, and fire suppression. FSim is designed to simulate the occurrence and growth of wildfires under tens of thousands of hypothetical contemporary fire seasons in order to estimate the probability of a given area (i.e., pixel) burning under current landscape conditions and fire management practices. The data presented here represent modeled BP and FIL for the conterminous US at a 270-meter grid spatial resolution. The six FILs correspond to flame-length classes as follows: FIL1 = < 2 feet (ft); FIL2 = 2 < 4 ft.; FIL3 = 4 < 6 ft.; FIL4 = 6 < 8 ft.; FIL5 = 8 < 12 ft.; FIL6 = 12+ ft. Because they indicate conditional probabilities (i.e., representing the likelihood of burning at a certain intensity level, given that a fire occurs), the FIL*_20160830 data must be used in conjunction with the BP_20160830 data for risk assessment.
Probabilistic Wildfire Risk Flame Length Probability 1 Alaska (Image Service)
공공데이터포털
,
목록