. Climate, land use, and other anthropogenic and natural drivers have the potential to influence fire dynamics in many regions. To develop a mechanistic understanding of the changing role of these drivers and their impact on atmospheric composition, long-term fire records are needed that fuse information from different satellite and in situ data streams. Here we describe the fourth version of the Global Fire Emissions Database (GFED) and quantify global fire emissions patterns during 1997–2016. The modeling system, based on the Carnegie–Ames–Stanford Approach (CASA) biogeochemical model, has several modifications from the previous version and uses higher quality input datasets. Significant upgrades include (1) new burned area estimates with contributions from small fires, (2) a revised fuel consumption parameterization optimized using field observations, (3) modifications that improve the representation of fuel consumption in frequently burning landscapes, and (4) fire severity estimates that better represent continental differences in burning processes across boreal regions of North America and Eurasia. The new version has a higher spatial resolution (0.25°) and uses a different set of emission factors that separately resolves trace gas and aerosol emissions from temperate and boreal forest ecosystems. Global mean carbon emissions using the burned area dataset with small fires (GFED4s) were 2.2  ×  1015 grams of carbon per year (Pg C yr−1) during 1997–2016, with a maximum in 1997 (3.0 Pg C yr−1) and minimum in 2013 (1.8 Pg C yr−1). These estimates were 11 % higher than our previous estimates (GFED3) during 1997–2011, when the two datasets overlapped. This net increase was the result of a substantial increase in burned area (37 %), mostly due to the inclusion of small fires, and a modest decrease in mean fuel consumption (−19 %) to better match estimates from field studies, primarily in savannas and grasslands. For trace gas and aerosol emissions, differences between GFED4s and GFED3 were often larger due to the use of revised emission factors. If small fire burned area was excluded (GFED4 without the s for small fires), average emissions were 1.5 Pg C yr−1. The addition of small fires had the largest impact on emissions in temperate North America, Central America, Europe, and temperate Asia. This small fire layer carries substantial uncertainties; improving these estimates will require use of new burned area products derived from high-resolution satellite imagery. Our revised dataset provides an internally consistent set of burned area and emissions that may contribute to a better understanding of multi-decadal changes in fire dynamics and their impact on the Earth system. GFED data are available from http://www.globalfiredata.org .

/pdf/global-fire-emissions-estimates-during-1997-2016-lq51nvtc0m.pdf

Global fire emissions estimates during 1997–2016

For more information on the USGS—the Federal source for science about the Earth, its natural and living resources, natural hazards, and the environment, visit http://www.usgs.gov or call 1–888–ASK–USGS. For an overview of USGS information products, including maps, imagery, and publications, Any use of trade, product, or firm names is for descriptive purposes only and does not imply endorsement by the U.S. Government. Although this report is in the public domain, permission must be secured from the individual copyright owners to reproduce any copyrighted materials contained within this report. 10. Diagram showing the GMTED2010 layer extents (minimum and maximum latitude and longitude) are a result of the coordinate system inherited from the 1-arc-second SRTM

Global Multi-resolution Terrain Elevation Data 2010 (GMTED2010)

The Collection 6 MODIS burned area mapping algorithm and product

Several machine-learning algorithms have been proposed for remote sensing image classification during the past two decades. Among these machine learning algorithms, Random Forest (RF) and Support Vector Machines (SVM) have drawn attention to image classification in several remote sensing applications. This article reviews RF and SVM concepts relevant to remote sensing image classification and applies a meta-analysis of 251 peer-reviewed journal papers. A database with more than 40 quantitative and qualitative fields was constructed from these reviewed papers. The meta-analysis mainly focuses on 1) the analysis regarding the general characteristics of the studies, such as geographical distribution, frequency of the papers considering time, journals, application domains, and remote sensing software packages used in the case studies, and 2) a comparative analysis regarding the performances of RF and SVM classification against various parameters, such as data type, RS applications, spatial resolution, and the number of extracted features in the feature engineering step. The challenges, recommendations, and potential directions for future research are also discussed in detail. Moreover, a summary of the results is provided to aid researchers to customize their efforts in order to achieve the most accurate results based on their thematic applications.

/pdf/support-vector-machine-versus-random-forest-for-remote-2imvn9our6.pdf

Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review

Biomass burning impacts vegetation dynamics, biogeochemical cycling, atmospheric chemistry, and climate, with sometimes deleterious socio-economic impacts. Under future climate projections it is often expected that the risk of wildfires will increase. Our ability to predict the magnitude and geographic pattern of future fire impacts rests on our ability to model fire regimes, using either well-founded empirical relationships or process-based models with good predictive skill. While a large variety of models exist today, it is still unclear which type of model or degree of complexity is required to model fire adequately at regional to global scales. This is the central question underpinning the creation of the Fire Model Intercomparison Project (FireMIP), an international initiative to compare and evaluate existing global fire models against benchmark data sets for present-day and historical conditions. In this paper we review how fires have been represented in fire-enabled dynamic global vegetation models (DGVMs) and give an overview of the current state of the art in fire-regime modelling. We indicate which challenges still remain in global fire modelling and stress the need for a comprehensive model evaluation and outline what lessons may be learned from FireMIP.

/pdf/the-status-and-challenge-of-global-fire-modelling-59kqtguydq.pdf

The status and challenge of global fire modelling

This paper aims to develop a global burned area (BA) algorithm for MODIS BRDF-corrected images based on the Random Forest (RF) classifier. Two RF models were generated, including: (1) all MODIS reflective bands; and (2) only the red (R) and near infrared (NIR) bands. Active fire information, vegetation indices and auxiliary variables were taken into account as well. Both RF models were trained using a statistically designed sample of 130 reference sites, which took into account the global diversity of fire conditions. For each site, fire perimeters were obtained from multitemporal pairs of Landsat TM/ETM+ images acquired in 2008. Those fire perimeters were used to extract burned and unburned areas to train the RF models. Using the standard MD43A4 resolution (500 × 500 m), the training dataset included 48,365 burned pixels and 6,293,205 unburned pixels. Different combinations of number of trees and number of parameters were tested. The final RF models included 600 trees and 5 attributes. The RF full model (considering all bands) provided a balanced accuracy of 0.94, while the RF RNIR model had 0.93. As a first assessment of these RF models, they were used to classify daily MCD43A4 images in three test sites for three consecutive years (2006–2008). The selected sites included different ecosystems: Australia (Tropical), Boreal (Canada) and Temperate (California), and extended coverage (totaling more than 2,500,000 km2). Results from both RF models for those sites were compared with national fire perimeters, as well as with two existing BA MODIS products; the MCD45 and MCD64. Considering all three years and three sites, commission error for the RF Full model was 0.16, with an omission error of 0.23. For the RF RNIR model, these errors were 0.19 and 0.21, respectively. The existing MODIS BA products had lower commission errors, but higher omission errors (0.09 and 0.33 for the MCD45 and 0.10 and 0.29 for the MCD64) than those obtained with the RF models, and therefore they showed less balanced accuracies. The RF models developed here should be applicable to other biomes and years, as they were trained with a global set of reference BA sites.

Developing a Random Forest Algorithm for MODIS Global Burned Area Classification

A data mining approach for global burned area mapping

This paper presents the first global burned area (BA) product derived from the land long term data record (LTDR), a long-term 0.05-degree resolution dataset generated from advanced very high resolution radiometer (AVHRR) images. Daily images were combined in monthly composites using the maximum temperature criterion to enhance the burned signal and eliminate clouds and artifacts. A synthetic BA index was created to improve the detection of the BA signal. This index included red and near infrared reflectance, surface temperature, two spectral indices, and their temporal differences. Monthly models were generated using the random forest classifier, using the twelve monthly composites of each year as the predictors. Training data were obtained from the NASA MCD64A1 collection 6 product (500 m spatial resolution) for eight years of the overlapping period (2001–2017). This included some years with low and high fire occurrence. Results were tested with the remaining eight years. Pixels classified as burned were converted to burned proportions using the MCD64A1 product. The final product (named FireCCILT10) estimated BA in 0.05-degree cells for the 1982 to 2017 period (excluding 1994, due to input data gaps). This product is the longest global BA currently available, extending almost 20 years back from the existing NASA and ESA BA products. BA estimations from the FireCCILT10 product were compared with those from the MCD64A1 product for continental regions, obtaining high correlation values (r2 > 0.9), with better agreement in tropical regions rather than boreal regions. The annual average of BA of the time series was 3.12 Mkm2. Tropical Africa had the highest proportion of burnings, accounting for 74.37% of global BA. Spatial trends were found to be similar to existing global BA products, but temporal trends showed unstable annual variations, most likely linked to the changes in the AVHRR sensor and orbital decays of the NOAA satellites.

https://www.mdpi.com/2072-4292/11/18/2079/pdf

Global Detection of Long-Term (1982-2017) Burned Area with AVHRR-LTDR Data

This paper proposes a validation-comparison method for burned area (BA) products. The technique considers: (1) bootstrapping of scenes for validation-comparison and (2) permutation tests for validation. The research focuses on the tropical regions of Northern Hemisphere South America and Northern Hemisphere Africa and studies the accuracy of the BA products: MCD45, MCD64C5.1, MCD64C6, Fire CCI C4.1, and Fire CCI C5.0. The first and second parts consider methods based on random matrix theory for zone differentiation and multiple ancillary variables such as BA, the number of burned fragments, ecosystem type, land cover, and burned biomass. The first method studies the zone effect using bootstrapping of Riemannian, full Procrustes, and partial Procrustes distances. The second method explores the validation by using distance permutation tests under uncertainty. The results refer to Fire CCI 5.0 with the best BA description, followed by MCD64C6, MCD64C5.1, MCD45, and Fire CCI 4.1. It was also found that biomass, total BA, and the number of fragments affect the BA product accuracy.

About Validation-Comparison of Burned Area Products

The authors wish to make the following corrections to this paper [...]

Rubén Ramo

Papers

Developing a Random Forest Algorithm for MODIS Global Burned Area Classification

A data mining approach for global burned area mapping

Global Detection of Long-Term (1982-2017) Burned Area with AVHRR-LTDR Data

About Validation-Comparison of Burned Area Products

Correction: Otón, G., et al. Global Detection of Long-Term (1982─2017) Burned Area with AVHRR-LTDR Data. Remote Sensing 2019, 11, 2079