Accurate estimation of fuels is essential for wildland fire simulations as well as decision-making related to land management. Numerous research efforts have leveraged remote sensing and machine learning for classifying land cover and mapping forest vegetation species. In most cases that focused on surface fuel mapping, the spatial scale of interest was smaller than a few hundred square kilometers; thus, many small-scale site-specific models had to be created to cover the landscape at the national scale. The present work aims to develop a large-scale surface fuel identification model using a custom deep learning framework that can ingest multimodal data. Specifically, we use deep learning to extract information from multispectral signatures, high-resolution imagery, and biophysical climate and terrain data in a way that facilitates their end-to-end training on labeled data. A multi-layer neural network is used with spectral and biophysical data, and a convolutional neural network backbone is used to extract the visual features from high-resolution imagery. A Monte Carlo dropout mechanism was also devised to create a stochastic ensemble of models that can capture classification uncertainties while boosting the prediction performance. To train the system as a proof-of-concept, fuel pseudo-labels were created by a random geospatial sampling of existing fuel maps across California. Application results on independent test sets showed promising fuel identification performance with an overall accuracy ranging from 55% to 75%, depending on the level of granularity of the included fuel types. As expected, including the rare—and possibly less consequential—fuel types reduced the accuracy. On the other hand, the addition of high-resolution imagery improved classification performance at all levels.

Airborne Laser Scanners (ALS) and Terrestrial Laser Scanners (TLS) are two lidar systems frequently used for remote sensing forested ecosystems. The aim of this study was to compare crown metrics derived from TLS, ALS, and a combination of both for describing the crown structure and fuel attributes of longleaf pine (Pinus palustris Mill.) dominated forest located at Eglin Air Force Base (AFB), Florida, USA. The study landscape was characterized by an ALS and TLS data collection along with field measurements within three large (1963 m² each) plots in total, each one representing a distinct stand condition at Eglin AFB. Tree-level measurements included bole diameter at breast height (DBH), total height (HT), crown base height (CBH), and crown width (CW). In addition, the crown structure and fuel metrics foliage biomass (FB), stem branches biomass (SB), crown biomass (CB), and crown bulk density (CBD) were calculated using allometric equations. Canopy Height Models (CHM) were created from ALS and TLS point clouds separately and by combining them (ALS + TLS). Individual trees were extracted, and crown-level metrics were computed from the three lidar-derived datasets and used to train random forest (RF) models. The results of the individual tree detection showed successful estimation of tree count from all lidar-derived datasets, with marginal errors ranging from −4 to 3%. For all three lidar-derived datasets, the RF models accurately predicted all tree-level attributes. Overall, we found strong positive correlations between model predictions and observed values (R² between 0.80 and 0.98), low to moderate errors (RMSE% between 4.56 and 50.99%), and low biases (between 0.03% and −2.86%). The highest R² using ALS data was achieved predicting CBH (R² = 0.98), while for TLS and ALS + TLS, the highest R² was observed predicting HT, CW, and CBD (R² = 0.94) and HT (R² = 0.98), respectively. Relative RMSE was lowest for HT using three lidar datasets (ALS = 4.83%, TLS = 7.22%, and ALS + TLS = 4.56%). All models and datasets had similar accuracies in terms of bias (<2.0%), except for CB in ALS (−2.53%) and ALS + TLS (−2.86%), and SB in ALS + TLS data (−2.22%). These results demonstrate the usefulness of all three lidar-related methodologies and lidar modeling overall, along with lidar applicability in the estimation of crown structure and fuel attributes of longleaf pine forest ecosystems. Given that TLS measurements are less practical and more expensive, our comparison suggests that ALS measurements are still reasonable for many applications, and its usefulness is justified. This novel tree-level analysis and its respective results contribute to lidar-based planning of forest structure and fuel management.

The rising severity and frequency of wildfires in recent years in the United States have raised numerous concerns regarding the improvement in wildfire emergency response management and decision-making systems, which require operational high temporal and spatial resolution monitoring capabilities. Satellites are one of the tools that can be used for wildfire monitoring. However, none of the currently available satellite systems provide both high temporal and spatial resolution. For example, GOES-17 geostationary satellite fire products have high temporal (1–5 min) but low spatial resolution (≥2 km), and VIIRS polar orbiter satellite fire products have low temporal (~12 h) but high spatial resolution (375 m). This work aims to leverage currently available satellite data sources, such as GOES and VIIRS, along with deep learning (DL) advances to achieve an operational high-resolution, both spatially and temporarily, wildfire monitoring tool. Specifically, this study considers the problem of increasing the spatial resolution of high temporal but low spatial resolution GOES-17 data products using low temporal but high spatial resolution VIIRS data products. The main idea is using an Autoencoder DL model to learn how to map GOES-17 geostationary low spatial resolution satellite images to VIIRS polar orbiter high spatial resolution satellite images. In this context, several loss functions and DL architectures are implemented and tested to predict both the fire area and the corresponding brightness temperature. These models are trained and tested on wildfire sites from 2019 to 2021 in the western U.S. The results indicate that DL models can improve the spatial resolution of GOES-17 images, leading to images that mimic the spatial resolution of VIIRS images. Combined with GOES-17 higher temporal resolution, the DL model can provide high-resolution near-real-time wildfire monitoring capability as well as semi-continuous wildfire progression maps.

Understory biomass plays an important role in forests, and explicit characterizations of live and dead understory vegetation are critical for wildland fuel characterization and to link understory vegetation to ecosystem processes. Current methods to accurately model understory fuel complexity in 3D rely on expensive and often inaccessible technologies. Structure-from-motion close-range photogrammetry, in which ordinary photographs or video stills are overlaid to generate point clouds, is promising as an alternative method to generate 3D models of fuels at a fraction of the cost of more traditional field surveys. In this study, we compared the performance of close-range photogrammetry with field sampling surveys to assess the utility of this alternative technique for quantifying understory fuel structure. Using a commercially available GoPro camera, we generated 3D point cloud models from video-derived image stills of 138 sampling plots across two western ponderosa pine and two southeastern slash pine sites. We directly compared structural metrics derived from the photogrammetry to those derived from field sampling, then evaluated predictive models of biomass calibrated by means of destructive sampling. Photogrammetry-derived measures of occupied volume and fuel height showed strong agreements with field sampling (Pearson’s R = 0.81 and 0.86, respectively). While we found weak relationships between photogrammetry metrics and biomass 0 to 10 cm in height, occupied volume and a novel metric to characterize the vertical profile of vegetation produced the strongest relationships with biomass above the litter layer (i.e., >10 cm) across different fuel types (R² = 0.55–0.76). The application of this technique has the potential to provide managers with an accessible option for inexpensive data collection and can lay the groundwork for the rapid collection of input datasets to train landscape-scale fuel models.

Effective estimation of fuel load is critical for mitigating wildfire risks. Here, we evaluate the performance of mobile laser scanning (MLS) and terrestrial laser scanning (TLS) to estimate fuel loads across multiple vegetation layers. Data were collected in two forest regions: the North Kaibab (NK) Plateau in Arizona and Monroe Mountain (MM) in Utah. We used random forest models to predict vegetation attributes, evaluating the performance of full models and transferred models using R², RMSE, and bias. The MLS consistently outperformed the TLS system, particularly for canopy-related attributes and woody biomass components. However, the TLS system showed potential for capturing canopy structure attributes, while offering advantages like operational simplicity, low equipment demands, and ease of deployment in the field, making it a cost-effective alternative for managers without access to more complex and expensive mobile or airborne systems. Our results show that model transferability between NK and MM is highly variable depending on the fuel attributes. Attributes related to canopy biomass showed better transferability, with small losses in predictive accuracy when models were transferred between the two sites. Conversely, surface fuel attributes showed more significant challenges for model transferability, given the difficulty of laser penetration in the lower vegetation layers. In general, models trained in NK and validated in MM consistently outperformed those trained in MM and transferred to NK. This may suggest that the NK plots captured a broader complexity of vegetation structure and environmental conditions from which models learned better and were able to generalize to MM. This study highlights the potential of ground-based LiDAR technologies in providing detailed information and important insights into fire risk and forest structure.

Electromagnetic radiation at 1550 nm is highly absorbed by water and offers a novel way to collect fuel moisture data, along with 3D structures of wildland fuels/vegetation, using lidar. Two terrestrial laser scanning (TLS) units (FARO s350 (phase shift, PS) and RIEGL vz-2000 (time of flight, TOF)) were assessed in a series of laboratory experiments to determine if lidar can be used to estimate the moisture content of dead forest litter. Samples consisted of two control materials, the angle and position of which could be manipulated (pine boards and cheesecloth), and four single-species forest litter types (Douglas-fir needles, ponderosa pine needles, longleaf pine needles, and southern red oak leaves). Sixteen sample trays of each material were soaked overnight, then allowed to air dry with scanning taking place at 1 h, 2 h, 4 h, 8 h, 12 h, and then in 12 h increments until the samples reached equilibrium moisture content with the ambient relative humidity. The samples were then oven-dried for a final scanning and weighing. The spectral reflectance values of each material were also recorded over the same drying intervals using a field spectrometer. There was a strong correlation between the intensity and standard deviation of intensity per sample tray and the moisture content of the dead leaf litter. A multiple linear regression model with a break at 100% gravimetric moisture content produced the best model with R2 values as high as 0.97. This strong relationship was observed with both the TOF and PS lidar units. At fuel moisture contents greater than 100% gravimetric water content, the correlation between the pulse intensity values recorded by both scanners and the fuel moisture content was the strongest. The relationship deteriorated with distance, with the TOF scanner maintaining a stronger relationship at distance than the PS scanner. Our results demonstrate that lidar can be used to detect and quantify fuel moisture across a range of forest litter types. Based on our findings, lidar may be used to quantify fuel moisture levels in near real-time and could be used to create spatial maps of wildland fuel moisture content.