Accurately estimating aboveground forest biomass is essential for understanding regional and global carbon cycles. In subalpine forest regions, complex topography and challenging forest inventories introduce significant uncertainties in estimating structural parameters and aboveground biomass. To generate continuous biomass maps over large-scale mountainous forests, it's necessary to extrapolate biomass from sample plots using appropriate models and remote sensing data. This study utilized ground survey data, UAV-LiDAR data, GEDI data, Sentinel-1, and Landsat 8 OLI imagery to estimate forest biomass in Qilian Mountain National Park. Key findings include: (1) UAV-LiDAR-derived parameters, when integrated with a random forest model, effectively predict forest biomass at the sample plot level; (2) combining GEDI data with UAV-LiDAR estimates provides accurate biomass predictions at footprint points; (3) by extrapolating biomass from discrete GEDI footprints and incorporating variables from Sentinel-1 and Landsat 8 OLI, a continuous, high-accuracy forest biomass map for the entire Qilian Mountain National Park was generated (R² = 0.66, RMSE = 19.08 Mg/ha, rRMSE = 11.04%). This study successfully scaled biomass estimates from plots to a regional level, enhancing biomass estimation accuracy in mountainous regions by leveraging complementary data sources.

Traditional GIS-based statistical models are intended to extrapolate patterns of settlements and their interactions with the environment. They contribute significantly to our knowledge of past human–land relationships. Yet, these models are often criticized for their empiricism, lopsided specific factors, and for overlooking the synergy between variables. Though largely untested, machine learning and artificial intelligence methods have the potential to overcome these shortcomings comprehensively and objectively. The northeastern Tibetan Plateau (NETP) is characterized by diverse environments and significant changes to the social system from the Neolithic to Bronze Age. In this study, this area serves as a representative case for assessing the complex relationships between settlement locations and geographic environments, taking full advantages of these new models. We have explored a novel modeling case by employing GIS and random forests to consider multiple factors, including terrain, vegetation, soil, climate, hydrology, and land suitability, to construct classification models identifying environmental variation across different cultural periods. The model exhibited strong performance and a high archaeological prediction value. Potential living maps were generated for each cultural stage, revealing distinct environmental selection strategies from the Neolithic to Bronze Age. The key environmental parameters of elevation, climate, soil erosion, and cultivated land suitability were calculated with high weights, influencing human environmental decisions synergistically. Furthermore, we conducted a quantitative analysis of temporal dynamics in climate and subsistence to understand driving mechanisms behind environmental strategies. These findings suggest that past human environmental strategies were based on the comprehensive consideration of various factors, coupled with their social economic scenario. Such subsistence-oriented activities supported human beings in overcoming elevation limitation, and thus allowed them to inhabit wider pastoral areas. This study showcases the potential of machine learning in predicting archaeological probabilities and in interpreting the environmental influence on settlement patterns.

Forests in alpine mountainous regions are sensitive to global climate change. Accurate measurement of tree height is essential for forest aboveground biomass estimation. Unmanned aerial vehicle light detection and ranging (UAV-LiDAR) in tree height estimation has been extensively used in forestry inventories. This study investigated the influence of varying flight heights and point cloud densities on the extraction of tree height, and four flight heights (i.e., 85, 115, 145, and 175 m) were set in three Picea crassifolia plots in the Qilian Mountains. After point cloud data were classified, tree height was extracted from a canopy height model (CHM) on the basis of the individual tree segmentation. Through comparison with ground measurements, the tree height estimations of different flight heights and point cloud densities were analyzed. The results indicated that (1) with a flight height of 85 m, the tree height estimation achieved the highest accuracy (R² = 0.75, RMSE = 2.65), and the lowest accuracy occurred at a height of 175 m (R² = 0.65, RMSE = 3.00). (2) The accuracy of the tree height estimation decreased as the point cloud density decreased. The accuracies of tree height estimation from low-point cloud density (R² = 0.70, RMSE = 2.75) and medium density (R² = 0.69, RMSE = 2.80) were comparable. (3) Tree height was slightly underestimated in most cases when CHM-based segmentation methods were used. Consequently, a flight height of 145 m was more applicable for maintaining tree height estimation accuracy and assuring the safety of UAVs flying in alpine mountain regions. A point cloud density of 125–185 pts/m² can guarantee tree height estimation accuracy. The results of this study could potentially improve tree height estimation and provide available UAV-LiDAR flight parameters in alpine mountainous regions in Northwest China.

Fine particulate matter (PM_2.5) plays a major role in haze, and studying its spatio-temporal dynamics and influencing factors is crucial for improving air quality. However, previous studies have often obscured the spatio-temporal interactions of PM_2.5 and neglected local spatio-temporal differences in influencing factors. To address these limitations, this research utilized PM_2.5 concentration data derived from satellite remote sensing and employed exploratory spatio-temporal data analysis (ESTDA) methods to investigate the spatio-temporal evolution patterns of PM_2.5 in Chinese cities from 2000 to 2021. Furthermore, the effects of natural environmental and socioeconomic factors on PM_2.5 were analyzed from both global and local perspectives using a spatial econometric model and the geographically and temporally weighted regression (GTWR) model. Key findings include (1) The annual value of PM_2.5 from 2000 to 2021 ranged between 27.4 and 42.6 µg/m³, exhibiting a “bimodal” variation trend and phased evolutionary characteristics. Spatially, higher concentrations were observed in the central and eastern regions, as well as along the northwestern border, while lower concentrations were prevalent in other areas. (2) The spatial–temporal distribution of PM_2.5 was generally stable, demonstrating a strong spatial dependence during its growth process, with significant path dependence characteristics in local spatial clusters of PM_2.5. (3) Precipitation, temperature, wind speed, and the Normalized Difference Vegetation Index (NDVI) significantly reduced PM_2.5 levels, whereas relative humidity, per capita Gross Domestic Product (GDP), industrialization level, and energy consumption exerted positive effects. These factors exhibited distinct local spatio-temporal variations. These findings aim to provide scientific evidence for the implementation of coordinated regional efforts to reduce air pollution across China.