Arkansas’ subtropical climate nurtures extensive forested regions, particularly within the Ozark-St. Francis and Ouachita National Forests. Despite this, the state lacks an up-to-date high-resolution map detailing the distribution of tree species within its forests. This study harnesses the power of machine learning, specifically the Random Forest (RF), Gradient Tree Boosting (GTB), Support Vector Machine (SVM), and K-Nearest Neighbors (K-NN) classifiers, within the Google Earth Engine (GEE) framework. These classifiers are applied to classify tree species distribution in Arkansas’ forests by integrating data from various sources, including Sentinel-1/-2, Landsat-8, and the National Agriculture Imagery Program (NAIP). The study evaluates the classification accuracy of single-sensor images against fused composites, revealing that the fused Landsat-8 and Sentinel-1 data achieve the highest validation accuracy at 0.8875, followed by single-sensor Sentinel-1 and Landsat-8, which yield validation accuracies of 0.8863 and 0.8859, respectively. Among the classifiers, RF demonstrates the highest accuracy, followed by GTB, K-NN, and SVM when applied to fused Landsat-8 and Sentinel-1 images. This study incorporates the Shapley Additive Explanations (SHAP) to elucidate feature importance, and results show that elevation is the most influential variable across all forest classes, followed by vegetation indices. The study introduces a weighted ensemble method, resulting in a remarkably accurate tree species distribution map with an accuracy score of 0.9772. This research demonstrates the effectiveness of combining machine learning and satellite image fusion with explainable AI (XAI) and GEE to enhance tree species classification and produce a precise, high-resolution regional tree cover map.

Fire susceptibility modeling is crucial for sustaining and managing forests among many other valuable land resources. With 56% of its area covered by forests, Arkansas is known as the “natural state”. About 1000 wildfires occurred and burned more than 10,000 acres each year during 1981–2018. In this paper, we use remote-sensing-based machine learning methods to address the natural and anthropogenic factors influencing wildfires and model fire susceptibility in Arkansas. Among the 15 explored variables, potential evapotranspiration, soil moisture, Palmer drought severity index, and dry season precipitation were recognized as the most significant factors contributing to the fire density. The obtained R-squared values are significant, with 0.99 for training the model and 0.92 for the validation. The results show that the Ouachita National Forest and the Ozark Forest, in west-central and west Arkansas, respectively, have the highest susceptibility to wildfires. The southern part of Arkansas has low-to-moderate fire susceptibility, while the eastern part of the state has the lowest fire susceptibility. These new results for Arkansas demonstrate the potency of remote-sensing-based random forest in predicting fire susceptibility at the state level that can be adapted to study fires in other states and help with fire preparedness to reduce loss and save the precious environment.

Multi-source remote sensing fusion and machine learning are effective tools for forest monitoring. This study aimed to analyze various fusion techniques, their application with machine learning algorithms, and their assessment in estimating forest type and aboveground biomass (AGB). A keyword search across Web of Science, Science Direct, and Google Scholar yielded 920 articles. After rigorous screening, 72 relevant articles were analyzed. Results showed a growing trend in optical and radar fusion, with notable use of hyperspectral images, LiDAR, and field measurements in fusion-based forest monitoring. Machine learning algorithms, particularly Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbor (KNN), leverage features from fused sources, with proper variable selection enhancing accuracy. Standard evaluation metrics include Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Overall Accuracy (OA), User’s Accuracy (UA), Producer’s Accuracy (PA), confusion matrix, and Kappa coefficient. This review provides a comprehensive overview of prevalent techniques, data sources, and evaluation metrics by synthesizing current research and highlighting data fusion’s potential to improve forest monitoring accuracy. The study underscores the importance of spectral, topographic, textural, and environmental variables, sensor frequency, and key research gaps for standardized evaluation protocols and exploration of multi-temporal fusion for dynamic forest change monitoring.

Forests are essential for biodiversity conservation, climate change, natural education, scientific research, and carbon sequestration. This study uses machine learning-based Random Forest (RF) regression to estimate the Above Ground Biomass (AGB) of the Ozark and Ouachita forests at a 10-meter resolution by combining data from Sentinel-2, Sentinel-1, and GEDI (Global Ecosystem Dynamics Investigation) on Google Earth Engine. The RF model included 34 out of 154 variables representing topographical, spectral, and textural factors demonstrating strong correlations with measured biomass. The RF model showed strong performance with R-squared and RMSE values of 0.95 and 18.46 for the training dataset and 0.75 and 34.52 for the validation dataset, respectively. The primary predictors were elevation, vegetation indices such as Leaf Area Index (LAI), Normalized Vegetation Index (NDVI), and Enhanced Vegetation Index (EVI), as well as forest height measurements like RH100, RH98, and RH95. The study also extrapolates the historical biomass from 2015 to 2023 using Landsat 8 data using the image normalization technique. The model effectively identified spatial patterns in biomass, with mean extrapolated values ranging from approximately 100 Mg/ha to 200 Mg/ha from 2015 to 2023, underscoring the value of open-source cloud platforms and integrating topographical, spectral, and textural data for accurate regional AGB estimation. The results support precise estimation of fire-related emissions and strategic planning to improve forest health and sustainability, contributing significantly to biodiversity conservation and carbon sequestration efforts. Graphical Abstract This study explores an innovative workflow to estimate the Above Ground Biomass (AGB) of forests, focusing on the Ozark and Ouachita regions. This research utilizes open-source data and platforms like Google Earth Engine and integrates satellite-based radar, optical data, and GEDI lidar measurements to capture the diverse characteristics of forests. The process involves satellite data fusion and employing machine learning techniques to analyze various factors such as elevation, vegetation indices, and forest height metrics to capture the different dynamics of the forest to estimate AGB accurately. The study also applies an interpolation technique to reveal historical trends, offering insights into the spatial patterns of biomass distribution over time. The study provides a transferable framework that can be adapted to estimate biomass in other regions around the globe, empowering efforts toward sustainable forestry practices and environmental health. This approach combines advanced remote sensing technology with machine learning to support biodiversity, sustainable forest management, and carbon sequestration.