The use of imagery from small unmanned aircraft systems (sUAS) has enabled the production of more accurate data about the effects of wildland fire, enabling land managers to make more informed decisions. The ability to detect trees in hyperspatial imagery enables the calculation of canopy cover. A comparison of hyperspatial post-fire canopy cover and pre-fire canopy cover from sources such as the LANDFIRE project enables the calculation of tree mortality, which is a major indicator of burn severity. A mask region-based convolutional neural network was trained to classify trees as groups of pixels from a hyperspatial orthomosaic acquired with a small unmanned aircraft system. The tree classification is summarized at 30 m, resulting in a canopy cover raster. A post-fire canopy cover is then compared to LANDFIRE canopy cover preceding the fire, calculating how much the canopy was reduced due to the fire. Canopy reduction allows the mapping of burn severity while also identifying where surface, passive crown, and active crown fire occurred within the burn perimeter. Canopy cover mapped through this effort was lower than the LANDFIRE Canopy Cover product, which literature indicated is typically over reported. Assessment of canopy reduction mapping on a wildland fire reflects observations made both from ground truthing efforts as well as observations made of the associated hyperspatial sUAS orthomosaic.
providing an affordable, safe, and responsive on-demand tool for monitoring fire effects 5 at a much finer spatial resolution than is possible with current technology. Using 6 spectroscopic analysis of a variety of live as well as combusted vegetation samples to 7 identify the spectral separability of vegetation classes, an optimal set of spectra was 8 selected to be utilized by machine learning classifiers. This approach allows high 9 resolution mapping of wildland fire severity and extent. 10
Support vector machines are shown to be highly effective in mapping burn extent from hyperspatial imagery in grasslands. Unfortunately, this pixel-based method is hampered in forested environments that have experienced low-intensity fires because unburned tree crowns obstruct the view of the surface vegetation. This obstruction causes surface fires to be misclassified as unburned. To account for misclassifying areas under tree crowns, trees surrounded by surface burn can be assumed to have been burned underneath. This effort used a mask region-based convolutional neural network (MR-CNN) and support vector machine (SVM) to determine trees and burned pixels in a post-fire forest. The output classifications of the MR-CNN and SVM were used to identify tree crowns in the image surrounded by burned surface vegetation pixels. These classifications were also used to label the pixels under the tree as being within the fire’s extent. This approach results in higher burn extent mapping accuracy by eliminating burn extent false negatives from surface burns obscured by unburned tree crowns, achieving a nine percentage point increase in burn extent mapping accuracy.
The use of fire as a land management tool is well recognized for its ecological benefits in many natural systems. To continue to use fire while complying with air quality regulations, land managers are often tasked with modeling emissions from fire during the planning process. To populate such models, the Landscape Fire and Resource Management Planning Tools (LANDFIRE) program has developed raster layers representing vegetation and fuels throughout the United States; however, there are limited studies available comparing LANDFIRE spatially distributed fuel loading data with measured fuel loading data. This study helps address that knowledge gap by evaluating two LANDFIRE fuel loading raster options—Fuels Characteristic Classification System (LANDFIRE-FCCS) and Fuel Loading Model (LANDFIRE-FLM) layers—with measured fuel loadings for a 20 000 ha mixed conifer study area in northern Idaho, USA. Fuel loadings are compared, and then placed into two emissions models—the First Order Fire Effects Model (FOFEM) and Consume—for a subsequent comparison of consumption and emissions results. The LANDFIRE-FCCS layer showed 200%* higher duff loadings relative to measured loadings. These led to 23% higher total mean total fuel consumption and emissions when modeled in FOFEM. The LANDFIRE-FLM layer showed lower loadings for total surface fuels relative to measured data, especially in the case of coarse woody debris, which in turn led to 51% lower mean total consumption and emissions when modeled in FOFEM. When the comparison was repeated using Consume model outputs, LANDFIRE-FLM consumption was 59% lower relative to that on the measured plots, with 58% lower modeled emissions. Although both LANDFIRE and measured fuel loadings fell within the ranges observed by other researchers in US mixed conifer ecosystems, variation within the fuel loadings for all sources was high, and the differences in fuel loadings led to significant differences in consumption and emissions depending upon the data and model chosen. The results of this case study are consistent with those of other researchers, and indicate that supplementing LANDFIRE-represented data with locally measured data, especially for duff and coarse woody debris, will produce more accurate emissions results relative to using unaltered LANDFIRE-FCCS or LANDFIRE-FLM fuel loadings. Accurate emissions models will aid in representing emissions and complying with air quality regulations, thus ensuring the continued use of fire in wildland management.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.