Deadwood is a critical component of forest ecosystems, storing nutrients for plants and serving as a carbon store and emission source. Climate change influences forest ecosystem dynamics with the potential for deadwood to emit carbon more rapidly due to accelerated decay and increased wildfires and increased inputs via mass forest mortality and disturbance events. To objectively inform our understanding of wildfires and associated carbon emissions, this study estimates the carbon content of dead fine woody debris (FWD) using multimodal data, such as Landsat-8 multispectral imagery, Sentinel-1 (C-band) and PALSAR (L-band) synthetic aperture radar (SAR) imagery, and terrain features to estimate the FWD of less than 0.25 in (1 h), 0.25–1 in (10 h), and 1–3 in (100 h). This data fusion provides spectral information to assess vegetation health that correlates with deadwood, as well as penetrability from SAR, resulting in structural information and biomass sensitivity. An ensemble machine learning (ML) model was trained using measurements from the Forest Inventory and Analysis (FIA) Database. A feature importance analysis was also performed to investigate the importance of input features to the model’s performance. A super learner regression (SLR) model composed of 9 base learners, including an ElasticNet model as meta-learner, was proposed and achieved the$R^{2}$values of 0.75, 0.72, and 0.62 to estimate 1-, 10-, and 100-h FWD, respectively. The validated model was then used to estimate deadwood carbon in the 2021 Dixie Fire region of California, demonstrating the effectiveness of our approach, emphasizing the value of multimodal data for real-time FWD carbon stock estimation.

Accurate fuel condition assessment is crucial for predicting fire behavior, enhancing operational decision support, and improving overall fire management. Our approach utilizes diverse data sources, such as Landsat-8 optical imagery, Sentinel-1 (C-band) SAR imagery, PALSAR (L-band) SAR imagery, and terrain features, to estimate time-lag fuel loadings (1 hour, 10 hours, and 100 hours). Optical data mainly captures the characteristics of leaf and forest canopy, while SAR data is more sensitive to forest vertical structures due to its strong penetrability. An ensemble model was trained on the Forest Inventory and Analysis (FIA) plots and spectral indices. Followed by, feature importance analysis and the inclusion of polynomial features were undertaken. The ensemble strategy, involving neural networks, decision trees, gradient boosting, and ensemble methods, achieved R2values of 0.72, 0.70, and 0.60 for 1-hour, 10-hour, and 100-hour fuel loads. Extensive experimentation in the 2021 Dixie Fire incident validates the effectiveness of our approach, emphasizing the value of leveraging multimodal data and ensemble machine learning models for real-time fuel load estimation.

Wildfire fuel mapping plays a vital role in understanding and mitigating the risks associated with wildfires. This study conducts a comprehensive analysis of existing literature to investigate the prevailing trends in wildfire fuel mapping, including an analysis of the satellite sensors commonly used for fuel mapping, the predominant types of fuels mapped, the resolution of fuel maps to assess accuracy and detail, and the publication trends over the years to understand the growth and interest in the field. By leveraging AI techniques including machine learning, we review solutions to overcome challenges such as data scarcity, modalities, mapping understory vegetation, model explainability, and lack of uncertainty-aware models. This manuscript aims to serve as a reference for researchers and practitioners seeking to advance the field of wildfire fuel mapping through data-driven and AI-powered approaches.

The unique spectral content provided by PRISMA's hyperspectral sensor gives the possibility to study the Earth's surface and environment from space in unprecedented detail. In this respect, our work presents the results of an Italian Space Agency-funded project aiming to develop eight prototypes for providing Value Added products based on such data. Prototypes focus on vegetation, urban areas, water quality, material detection, and natural hazards, combining multiple state-of-the-art techniques based on Machine Learning, physical models, and index-based algorithms. This is particularly relevant given the increasing demand for accurate information to address sustainable policies and support decision-making processes. Through a series of case studies, we highlight the versatility and utility of PRISMA's hyperspectral data for various scientific and operational applications.

City based pollution monitoring is essential for overall health and sustainability of the concerned city. PM2.5is one of the most hazardous pollutants whose excessive presence in the urban air makes it unfit to breathe. A study is conducted to estimate PM2.5(particulate matter with diameter ≤$2.5\ \mu\mathrm{m}$) using PRISMA (hyperspectral imagery based satellite) hyperspectral bands for the Delhi region in India. By using ground station measurements and simulated PM2.5concentrations (using Sequential Gaussian Simulation) as a reference, estimates of PM2.5are created from the PRISMA imagery. Various regression models are developed for PM2.5estimation from hyperspectral data and deployed for spatial estimation. This study provides a comparative demonstration of ground level PM2.5prediction for urban areas using various machine learning models from hyperspectral imagery and indicates the importance of it.

Italy has witnessed a significant increase in wildfires in recent decades. Forest fire fuel maps play a vital role in the prevention, management and risk assessment of wildfires, and this paper presents the procedure implemented to develop a dynamic wildfire fuel map using PRISMA hyperspectral data and Sentinel-2 multispectral data. Freely available multispectral datasets are widely used for land cover and land use mapping, but they have limited utility for fuel mapping due to their coarse spectral resolution. So, in this study, hyperspectral imagery (HSI) from PRISMA has been used for fuel types classification. The feed-forward neural network showed an overall accuracy of 79% by validation. To convert the classification map into a dynamic fuel map, the knowledge of the proportion of live/dead herbaceous loads available in that area is essential. The Relative Greenness approach, which places the Normalized Difference Vegetation Index (NDVI) in the time series of measurements, was implemented using Sentinel - 2 multispectral data. By fusing the fuel types classification, relative greenness map and iso-bioclimatic map, a dynamic fuel map for the west of Latium in Italy was developed with reference to Scott/Burgan fuel models.

Hyperspectral images have its applications in various fields. Here, hyperspectral image from PRISMA which is a fundamental satellite of Italian Space Agency is being used for discriminating the wildfire fuel types on Sardinian Island of Italy. PRISMA is an on-demand mission and the available data in the archive are limited. There is no literature available on land use/vegetation classification using PRISMA data. In this paper, a new approach for generating samples to form a dataset for classifying the wildfire fuels and for classifying mixed pixels using iso-bioclimatic conditions are proposed. The classified map created using the dataset and using the iso-bioclimatic conditions is been validated. From the accuracy assessment, SVM classifier showed an overall accuracy of 86% and kappa coefficient of 0.79. Then, the classified map is converted into fuel map. This study suggests that the proposed approach can be used to generate samples for land use/vegetation classification and to assign vegetation types to mixed pixels depending upon the iso-bioclimatic conditions.