In order to locate forest fire smoke more precisely and expand existing forest fire monitoring methods, this research employed Himawari-8 data with a sub-pixel positioning concept in smoke detection. In this study, Himawari-8 data of forest fire smoke in Xichang and Linzhi were selected. An improved sub-pixel mapping method based on random forest results was proposed to realize the identification and sub-pixel positioning of smoke. More spatial details of forest fire smoke were restored in the final results. The continuous monitoring of smoke indicated the dynamic changes therein. The accuracy evaluation of smoke detection was realized using a confusion matrix. Based on the improved sub-pixel mapping method, the overall accuracies were 87.95% and 86.32%. Compared with the raw images, the smoke contours of the improved sub-pixel mapping results were clearer and smoother. The improved sub-pixel mapping method outperforms traditional classification methods in locating smoke range. Moreover, it especially made a breakthrough in the limitations of the pixel scale and in realizing sub-pixel positioning. Compared with the results of the classic PSA method, there were fewer “spots” and “holes” after correction. The final results of this study show higher accuracies of smoke discrimination, with it becoming the basis for another method of forest fire monitoring.

The accurate and effective estimation of forest carbon density is an essential basis for effectively responding to climate change and achieving the goal of carbon neutrality. Aiming at the problem of the significant differences in the forest carbon model parameters of different tree species, this study used the tree forest in Yueyang City, Hunan Province, China, as the study object and used the random forest classification algorithm through the Google Earth Engine platform to classify the dominant tree species within the forested range of the study area based on the image elements. The overall accuracy in the forest/non-forest classification (primary classification) was 93.79% with a Kappa of 0.9145. The overall accuracy in the dominant species classification (secondary classification) was 87.30% with a Kappa of 0.7747. Based on the classification, a multiple linear regression (MLR), support vector machine (SVM), and random forest (RF) were constructed for different dominant tree species by combining some Forest Resource Inventory data and remote sensing data. The results showed that the RF model had a significantly higher coefficient of determination (R2 = 0.4054–0.7602) than the MLR (R2 = 0.0900–0.4070) and SVM (R2 = 0.1650–0.4450) as well as a substantially lower RMSE and MAE; its spatial distribution of forest carbon density ranged from 3.06 to 62.80 t·hm−2. Compared with the spatial distribution of the forest carbon density (4.64 to 31.96 t·hm−2) without the classification of dominant species, the method eliminated the problems of severe overfitting and significant underestimation of peak values when estimating under unclassified conditions. The method provides a reference for the remote sensing inversion of forest carbon density on a large scale.

With the Lutou Forest Farm as the research area, the Lasso algorithm was used for characteristic selection, and the optimal combination of variables was input into the support vector regression (SVR) model. The most suitable SVR model was selected to estimate the aboveground biomass of the forest through the comparison of the kernel function and optimal parameters, and the spatial distribution map of the aboveground biomass in the study area was drawn. The significance analysis of special variables showed good correlations between forest aboveground biomass and each vegetation index. There was a more significant correlation with some remote sensing bands, a less significant correlation with some texture features, and a strong correlation with DEM in the terrain features. When the parameters C is 2 and g is 0.01, the SVR model has the highest precision, which can illustrate 73% of the forest aboveground biomass, with the validation set R2 being 0.62. The statistical analysis of the results shows that the total aboveground biomass of the Lutou Forest Farm is 4.82 × 105 t. The combination of Lasso with the SVR model can improve the estimation accuracy of forest aboveground biomass, and the model has a strong generalization ability.

Forest fires seriously jeopardize forestry resources and endanger people and property. The efficient identification of forest fire smoke, generated from inadequate combustion during the early stage of forest fires, is important for the rapid detection of early forest fires. By combining the Convolutional Neural Network (CNN) and the Lightweight Vision Transformer (Lightweight ViT), this paper proposes a novel forest fire smoke detection model: the SR-Net model that recognizes forest fire smoke from inadequate combustion with satellite remote sensing images. We collect 4,000 satellite remote sensing images, 2,000 each for clouds and forest fire smoke, from Himawari-8 satellite imagery located in forest areas of China and Australia, and the image data are used for training, testing, and validation of the model at a ratio of 3:1:1. Compared with existing models, the proposed SR-Net dominates in recognition accuracy (96.9%), strongly supporting its superiority over benchmark models: MobileNet (92.0%), GoogLeNet (92.0%), ResNet50 (84.0%), and AlexNet (76.0%). Model comparison results confirm the accuracy, computational efficiency, and generality of the SR-Net model in detecting forest fire smoke with high temporal resolution remote sensing images.