NASA's (National Aeronautics and Space Administration) ICESat-2 with a Photon Counting LiDAR (Light Detection And Ranging) Sensor sensitively detects signal photons at high speed with an advanced detection system called the Advanced Topographic Laser Altimeter System (ATLAS). However, the sensor also extracts a large amount of background photon noise coming from the atmosphere, ground, sun, or other radiation. This condition is particularly evident in forest areas. This study proposes an automatic machine learning approach to utilize data for forestry applications to improve data availability compared to NASA's official product. Our method uses only a very limited number (10%) of sample points for training, ensuring operational efficiency and training accuracy. We conclude that the integrated learning performance generally outperforms single models, and the mean F1 score of all tests is approximately 0.9. The mean F1 score of the Stacked Ensembles model is 0.957 ahead of the other models. The top three variables used in training models are kNNdist5, kNNdist10, and h. These three variables could explain 51.6% of the components of the models. Over the regions tested, the proposed method could improve the proportion of signals correctly identified by 6.4%, 12.2%, 2.7%, 9.3%, and 1.4% in five datasets. The model performs better in low signal-to-noise (SNR) datasets less than 7.5. The method would be largely unaffected by differences in topography, noise distribution, and SNR. The classifiers could correct misclassified labels in ATL08 products and show good stability in different conditions.

Frequent forest fires cause air pollution, threaten biodiversity and spoil forest ecosystems. Forest fire vulnerability assessment is a potential way to improve the ability of forests to resist climate disasters and help formulate appropriate forest management countermeasures. Here, we developed an automated hybrid machine learning algorithm by selecting the optimal model from 24 models to map potential forest fire vulnerability over China during the period 2001–2020. The results showed forest aboveground biomass (AGB) had a vulnerability of 26%, indicating that approximately 2.32 Gt C/year of forest AGB could be affected by fire disturbances. The spatiotemporal patterns of forest fire vulnerability were dominated by both forest characteristics and climate conditions. Hotspot regions for vulnerability were mainly located in arid areas in western China, mountainous areas in southwestern China, and edges of vegetation zones. The overall forest fire vulnerability across China was insignificant. The forest fire vulnerability of boreal and temperate coniferous forests and mixed forests showed obviously decreasing trends, and cultivated forests showed an increasing trend. The results of this study are expected to provide important support for the forest ecosystem management in China.

Tropical forests are abundant in biodiversity and carbon stock, and the simulation of carbon flux in tropical forests is particularly challenged due to their immense biodiversity, complex and dynamic ecological processes, diverse soil and hydrological profiles, complex microclimate, and frequent human disturbance. Therefore, the process-based Biome-BGCMuSo model was applied in this study to obtain accurate regional forest carbon fluxes. The model was first calibrated using eddy covariance data and a Gaussian process regression algorithm by the most sensitivity parameters for natural forests and rubber plantations. The results from the calibrated Biome-BGCMuSo model were validated against observed carbon fluxes. Finally, the carbon sink differences between natural forests and plantations were deeply analyzed. The results showed the following: (1) Sensitivity parameters varied in natural and rubber plantations. The key parameters of carbon flux in natural forests were sensitive to specific leaf area (SLA) and light extinction coefficient (k); carbon fluxes of rubber plantations were mainly affected by maintenance respiration per nitrogen (MRpern). This difference played a role in calibrating the model parameters. (2) The simulation of carbon fluxes improved through the calibrated Biome-BGCMuSo model, with the average RMSE between simulated and observed carbon fluxes reduced by 60.23%. (3) The calibration effect of the model in natural forests is better than that in plantations with less standard deviation. In summary, this study developed a region-specific calibration of the Biome-BGCMuSo model designed to enhance the precision of carbon flux estimations within tropical forests. This advancement refines the understanding of carbon dynamics and lays a pivotal foundation for scaling up to regional modeling frameworks.

Mangrove ecosystems are important blue carbon systems and play a critical role in understanding carbon cycling and responses to climate change. However, accurate regional estimation of Net Ecosystem Exchange (NEE) remains challenging due to the environmental complexity and spatial heterogeneity. This study combined eddy covariance observations from four mangrove sites along China’s southeastern coast (natural and restored mangrove forests) with multi-source remote sensing and environmental reanalysis data to construct three variable schemes (site observations only, with added vegetation indices, and comprehensive multi-source variables). We compared three machine learning models for daily NEE prediction, including eXtreme Gradient Boosting (XGBoost), Random Forest (RF), and Support Vector Machine (SVM). The results showed that: (1) Restored and natural mangroves exhibited similar temporal NEE dynamics and consistently functioned as carbon sinks, restored mangrove sites showed greater cross-site variability. Among the study sites, CN-LZR exhibited the strongest cumulative carbon uptake. (2) Scheme 3 combined with the XGBoost algorithm achieved the highest predictive accuracy, reaching an R² of 0.73 across sites. Differences among machine learning models were primarily associated with their ability to capture nonlinear interactions between atmospheric and hydrological variables, with tree-based models outperforming SVM. (3) SHAP analysis indicated that radiation-related variables were the dominant drivers of NEE, while hydrological influences were site-dependent; and (4) Regional upscaling indicated that all sites consistently functioned as long-term carbon sinks, with CN-LZR exhibiting slightly higher daily mean carbon uptake than the other sites. This study presented the first machine learning framework for estimating daily-scale NEE in mangroves, providing methodological and data support for regional carbon flux assessment and blue carbon management.