A Computationally Efficient Method for Updating Fuel Inputs for Wildfire Behavior Models Using Sentinel Imagery and Random Forest Classification

Application of the wildland fire emissions inventory system to estimate fire emissions on forest lands of the United States

BACKGROUND

Forests are significant terrestrial biomes for carbon storage, and annual carbon accumulation of forest biomass contributes offsets affecting net greenhouse gases in the atmosphere. The immediate loss of stored carbon through fire on forest lands reduces the annual offsets provided by forests. As such, the United States reporting includes annual estimates of direct fire emissions in conjunction with the overall forest stock and change estimates as a part of national greenhouse gas inventories within the United Nations Framework Convention on Climate Change. Forest fire emissions reported for the United States, such as the 129 Tg CO2 reported for 2022, are based on the Wildland Fire Emissions Inventory System (WFEIS). Current WFEIS estimates are included in the Inventory of U.S. Greenhouse Gas Emissions and Sinks: 1990-2022 published in 2024 by the United States Environmental Protection Agency. Here, we describe WFEIS the fire emissions inventory system we used to address current information needs, and an analysis to confirm compatibility of carbon mass between estimated forest fire emissions and carbon in forest stocks.

RESULTS

The summaries of emissions from forests are consistent with previous reports that show rates and interannual variability in emissions and forest land area burned are generally greater in recent years relative to the 1990s. Both emissions and interannual variability are greater in the western United States. The years with the highest CO2 emissions from forest fires on the 48 conterminous states plus Alaska were 2004, 2005, and 2015. In some years, Alaska emissions exceed those of the 48 conterminous states, such as in 2022, for example. Comparison of forest fire emission to forest carbon stocks indicate there is unlikely any serious disconnect between inventory and fire emissions estimates.

CONCLUSIONS

The WFEIS system is a user-driven approach made available via a web browser. Model results are compatible with the scope and reporting needs of the annual national greenhouse gas inventories.

Wildfire spreading prediction using multimodal data and deep neural network approach

Predicting wildfire spread behavior is an extremely important task for many countries. On a small scale, it is possible to ensure constant monitoring of the natural landscape through ground means. However, on the scale of large countries, this becomes practically impossible due to remote and vast forest territories. The most promising source of data in this case that can provide global monitoring is remote sensing data. Currently, the main challenge is the development of an effective pipeline that combines geospatial data collection and the application of advanced machine learning algorithms. Most approaches focus on short-term fire spreading prediction and utilize data from unmanned aerial vehicles (UAVs) for this purpose. In this study, we address the challenge of predicting fire spread on a large scale and consider a forecasting horizon ranging from 1 to 5 days. We train a neural network model based on the MA-Net architecture to predict wildfire spread based on environmental and climate data, taking into account spatial distribution features. Estimating the importance of features is another critical issue in fire behavior prediction, so we analyze their contribution to the model's results. According to the experimental results, the most significant features are wind direction and land cover parameters. The F1-score for the predicted burned area varies from 0.64 to 0.68 depending on the day of prediction (from 1 to 5 days). The study was conducted in northern Russian regions and shows promise for further transfer and adaptation to other regions. This geospatial data-based artificial intelligence (AI) approach can be beneficial for supporting emergency systems and facilitating rapid decision-making.