Pinliang Dong

Extreme heatwaves intensify urban heat islands and pose increasing risks to urban sustainability and human health. However, how urban morphology is associated with daytime and nighttime land surface temperature (LST) across urban functional zones (UFZs), particularly under heatwave conditions, remains insufficiently understood. To address this gap, this study integrates daytime and nighttime LST data derived from SDGSAT-1, multi-dimensional urban morphology indicators, and two interpretable ensemble models (XGBoost and GWRF) to investigate overall sample-level nonlinear model-based associations between urban morphology and LST and to explore spatial variation in local predictor importance within Beijing and Nanjing, China. Because the daytime and nighttime scenes were not always paired within the same heatwave episode, the analysis focuses on selected heatwave-condition observations. The results show marked contrasts between the selected daytime and nighttime observations in UFZ-level thermal patterns. Industrial zones generally exhibited the highest daytime LST, whereas residential zones showed the highest nighttime LST. Building density was identified as the primary model-based predictor of daytime LST in both cities, although its association with LST was nonlinear and varied across density ranges. In contrast, nighttime LST was characterized by more heterogeneous predictor associations, involving vegetation structure, sky openness, building form, anthropogenic indicators, and material-related variables, with their relative importance differing across cities and UFZ types. Local predictor-importance patterns also varied across neighborhoods, cities, and observation times, indicating that model-identified locally important predictors were not spatially uniform within each city. These findings highlight the potential of SDGSAT-1 daytime and nighttime thermal observations and interpretable machine learning for screening candidate local thermal priority areas and key morphology-related factors under heatwave conditions.

Climate change is amplifying heat-related health risks, making heat health risk assessment increasingly important for sustainable urban development. However, current studies still face three challenges: (1) macro-scale and fine-scale assessments remain weakly linked; (2) nighttime heat health risk has received limited attention; and (3) dominant factor identification remains insufficient, especially within the Local Climate Zone (LCZ) framework. To address these gaps, this study developed a hazard–exposure–vulnerability-based, multi-scale framework for assessing nighttime heat health risk in Shandong Province, China. At the macro scale, MODIS nighttime land surface temperature (1 km) was used to characterize heat hazard, and district-level risk was assessed by integrating socio-statistical data. Hotspot analysis was then applied to identify high-risk clusters and select cities for fine-scale assessment. At the fine scale, SDGSAT-1 thermal infrared data (30 m) were used to characterize intra-urban nighttime heat hazard, and block-level risk was assessed by integrating socioeconomic and urban infrastructure data. Dominant risk factors were further identified for each spatial unit. Results show that (1) at the macro scale, high nighttime heat health risk districts are concentrated mainly in southern Shandong and major urban cores; (2) at the fine scale, overall risk is higher in inland cities than in the coastal city, and the inland cities show similar spatial patterns; (3) at both district and block units, higher risk levels are associated with more complex dominant factor configurations; and (4) compact high- and mid-rise zones (LCZ 1–2) are mainly characterized by multiple dominant factors, whereas open low-rise/sparsely built zones (LCZ 6/9) are mainly characterized by no dominant factor. This study provides a multi-level perspective for heat-risk governance, offers a scientific basis for both macro-scale policy formulation and fine-scale intervention, and contributes to more sustainable and resilient cities.

The accuracy of forest canopy height estimation is crucial for forest resource management and ecosystem carbon sequestration. However, existing approaches often face limitations in effectively integrating multisource remote sensing data, feature representation, and model learning strategies. To enhance the prediction performance of the model in complex terrain and multisource data environments, this study comprehensively used ICESat-2/ATLAS photon point clouds, Sentinel-2/MSI multispectral imagery, and SRTM-DEM to construct a remote sensing-driven multisource feature system, which eliminated redundant interference using permutation feature importance analysis. Additionally, a self-attention (SA) mechanism was introduced to strengthen high-dimensional feature representation. Three heterogeneous models, incorporating deep neural network (DNN), extreme gradient boosting (XGBoost), and residual network (ResNet), were independently applied for forest canopy height estimation and were further used as base learners, with a random forest as the meta-learner, and an SA-Blending heterogeneous ensemble model that combines a blending technique with an SA mechanism was proposed to enhance the accuracy of forest canopy height estimation. To evaluate the SA optimization strategy and the role of multisource fusion, this study used the original features, SA-optimized features, and multisource fusion features (i.e., the concatenation and fusion of original features and self-attention mechanism features) as inputs to comprehensively compare the performance of each single model and the integrated model. The results show that: (1) The self-attention mechanism significantly improves the prediction performance of heterogeneous models. Compared with original features inputs, the R² of DNN (SA-Only) and XGBoost (SA-Only) increased to 0.706 and 0.708, respectively, and the RMSE decreased to 1.691 m and 1.613 m. Although the R² for ResNet (SA-Only) decreased slightly to 0.699 and the RMSE increased to 1.712 m, the overall impact was not significant. (2) Under the condition of multisource fusion feature input, DNN+SA, XGBoost+SA, and ResNet+SA all demonstrated higher fitting accuracy and stability, verifying the enhancing effect of the SA mechanism on the association expression of multisource information. (3) The SA-Blending model achieved the best overall performance, with R² of 0.766 and RMSE of 1.510 m. It outperformed individual models and the SA-optimized model in terms of overall accuracy, stability, and robustness. The results can provide technical support for high-precision forest canopy height mapping and are of great significance for ecological monitoring applications.

Canopy gaps are vital microhabitats for forest carbon cycling and species regeneration, whose accurate extraction is crucial for ecological modeling and smart forestry. However, traditional monitoring methods have notable limitations: ground-based measurements are inefficient; remote-sensing interpretation is susceptible to terrain and spectral interference; and traditional algorithms exhibit an insufficient feature representation capability. Aiming at overcoming the bottleneck issues of canopy gap identification in mountainous forest regions, we constructed a multi-task deep learning model (ES-Net) integrating an edge–semantic collaborative perception mechanism. First, a refined sample library containing multi-scale interference features was constructed, which included 2808 annotated UAV images. Based on this, a dual-branch feature interaction architecture was designed. A cross-layer attention mechanism was embedded in the semantic segmentation module (SSM) to enhance the discriminative ability for heterogeneous features. Meanwhile, an edge detection module (EDM) was built to strengthen geometric constraints. Results from selected areas in Yunnan Province (China) demonstrate that ES-Net outperforms U-Net, boosting the Intersection over Union (IoU) by 0.86% (95.41% vs. 94.55%), improving the edge coverage rate by 3.14% (85.32% vs. 82.18%), and reducing the Hausdorff Distance by 38.6% (28.26 pixels vs. 46.02 pixels). Ablation studies further verify that the synergy between SSM and EDM yields a 13.0% IoU gain over the baseline, highlighting the effectiveness of joint semantic–edge optimization. This study provides a terrain-adaptive intelligent interpretation method for forest disturbance monitoring and holds significant practical value for advancing smart forestry construction and ecosystem sustainable management.

Scanning forests with LiDAR is an efficient method for conducting forest resource surveys, including estimating tree diameter at breast height (DBH), canopy height, and segmenting individual trees. This study uses three-dimensional (3D) forest test data and point cloud data simulated by the Helios++ V1.3.0 software, and proposes a voxelized trunk extraction algorithm to determine the trunk location and the vertical structure of single tree trunks in forest areas. Firstly, the voxel-based shape recognition algorithm is used to extract the trunk structure of tree point clouds, then the random sample consensus (RANSAC) algorithm is used to solve the vertical structure connectivity problem of tree trunks generated by the above method, and the Alpha Shapes algorithm is selected among various point cloud surface reconstruction algorithms to reconstruct the surface of tree point clouds. Then, building on the tree surface model, a light projection scene is introduced to locate the tree trunk coordinates at different heights. Finally, the convex hull of the trunk bottom is solved by the Graham scanning method. Accuracy assessments show that the proposed single-tree extraction algorithm and the forest vertical structure recognition algorithm, when applied within the light projection scene, effectively delineate the regions where the vertical structure distribution of single tree trunks is inconsistent.

UAV LiDAR and digital aerial photogrammetry (DAP) have shown great performance in forest inventory due to their advantage in three-dimensional information extraction. Many studies have compared their performance in individual tree segmentation and structural parameters extraction (e.g. tree height). However, few studies have compared their performance in tree species classification. Therefore, we have compared the performance of UAV LiDAR and DAP-based point clouds in individual tree species classification with the following steps: (1) Point cloud data processing: Denoising, smoothing, and normalization were conducted on LiDAR and DAP-based point cloud data separately. (2) Feature extraction: Spectral, structural, and texture features were extracted from the pre-processed LiDAR and DAP-based point cloud data. (3) Individual tree segmentation: The marked watershed algorithm was used to segment individual trees on canopy height models (CHM) derived from LiDAR and DAP data, respectively. (4) Pixel-based tree species classification: The random forest classifier (RF) was used to classify urban tree species with features derived from LiDAR and DAP data separately. (5) Individual tree species classification: Based on the segmented individual tree boundaries and pixel-based classification results, the majority filtering method was implemented to obtain the final individual tree species classification results. (6) Fused with hyperspectral data: LiDAR-hyperspectral and DAP-hyperspectral fused data were used to conduct individual tree species classification. (7) Accuracy assessment and comparison: The accuracy of the above results were assessed and compared. The results indicate that LiDAR outperformed DAP in individual tree segmentation (F-score 0.83 vs. 0.79), while DAP achieved higher pixel-level classification accuracy (73.83% vs. 57.32%) due to spectral-textural features. Fusion with hyperspectral data narrowed the gap, with LiDAR reaching 95.98% accuracy in individual tree classification. Our findings suggest that DAP offers a cost-effective alternative for urban forest management, balancing accuracy and operational costs.

Understanding global patterns of tree canopy height and density is essential for effective forest management and conservation planning. This study examines how these attributes vary along latitudinal gradients and identifies key climatic drivers influencing them. We utilized high-resolution remote sensing datasets, including a 10 m resolution canopy height dataset aggregated to 1 km for computational efficiency, and a 1 km resolution tree density dataset derived from ground-based measurements. To quantify the relationships between forest structure and environmental factors, we applied nonlinear regression models and climate dependency analyses, incorporating bioclimatic variables from the WorldClim dataset. Our key finding is that latitude exerts a dominant but asymmetric control on tree height and density, with tropical regions exhibiting the strongest correlations. Tree height follows a quadratic latitudinal pattern, explaining 29.3% of global variation, but this relationship is most pronounced in the tropics (−10° to 10° latitude, R² = 91.3%), where warm and humid conditions promote taller forests. Importantly, this effect differs by hemisphere, with the Southern Hemisphere (R² = 67.1%) showing stronger latitudinal dependence than the Northern Hemisphere (R² = 35.3%), indicating climatic asymmetry in forest growth dynamics. Tree density exhibits a similar quadratic trend but with weaker global predictive power (R² = 7%); however, within the tropics, latitude explains 90.6% of tree density variation, underscoring strong environmental constraints in biodiverse ecosystems. Among climatic factors, isothermality (Bio 3) is identified as the strongest determinant of tree height (R² = 50.8%), suggesting that regions with stable temperature fluctuations foster taller forests. Tree density is most strongly influenced by the mean diurnal temperature range (Bio 2, R² = 36.3%), emphasizing the role of daily thermal variability in tree distribution. Precipitation-related factors (Bio 14 and Bio 19) moderately explain tree height (~33%) and tree density (~25%), reinforcing the role of moisture availability in structuring forests. This study advances forest ecology research by integrating high-resolution canopy structure data with robust climate-driven modeling, revealing previously undocumented hemispheric asymmetries and biome-specific climate dependencies. These findings improve global forest predictive models and offer new insights for conservation strategies, particularly in tropical regions vulnerable to climate change.

Recent advancements in texture-based metrics have improved the representation of landscape heterogeneity, yet global-scale analyses of the relationship between vegetation homogeneity and land surface temperature (LST) remain limited. This study addresses this gap by examining the correlation between Enhanced Vegetation Index (EVI)-derived texture metrics and LST worldwide. We used texture-based metrics from the EVI to assess landscape homogeneity, with LST data from the 2015 MODIS MOD11A1 V6.1 product at a 1 km spatial resolution. Correlation analyses and nonlinear regression models were applied to explore how EVI homogeneity relates to LST across latitudes. Our findings reveal a significant positive correlation between EVI homogeneity and LST, with the strongest association in the Northern Hemisphere (R² = 49.3%), followed by a moderate relationship in the Southern Hemisphere (R² = 21.1%). In tropical regions (−10° to 10° latitudes), the association is weaker but still significant (R² = 15.1%). The distribution of EVI homogeneity follows a Gaussian curve, peaking in mid-latitudes (from −35° to −15° in the Southern Hemisphere and from 15° to 35° in the Northern Hemisphere), while tropical regions exhibit consistently low homogeneity with minimal variation. Our results indicate that regions with higher EVI homogeneity, representing less fragmented vegetation, tend to experience higher LST, whereas areas with more fragmented vegetation (lower homogeneity) exhibit cooler temperatures. Our findings offer valuable insights into the role of vegetation structure in regulating surface temperature across diverse ecosystems. The study highlights the potential for texture-based metrics to enhance environmental monitoring, contributing to improved climate adaptation strategies and sustainable land management practices globally.

While numerous studies have investigated the NDVI-LST relationship at local or regional scales, existing global analyses are outdated and fail to incorporate recent environmental changes driven by climate change and human activity. This study aims to address this gap by conducting an extensive global analysis of NDVI-LST correlations from 2000 to 2024, utilizing multi-source satellite data to assess latitudinal and ecosystem-specific variability. The MODIS dataset, which provides global daily LST data at a 1 km resolution from 2000 to 2024, was used alongside MODIS-derived NDVI data, which offers global vegetation indices at a 1 km resolution and 16-day temporal intervals. A correlation analysis was performed by extracting NDVI and LST values for each raster cell. The analysis revealed significant negative correlations in regions such as the western United States, Brazil, southern Africa, and northern Australia, where increased temperatures suppress vegetation activity. A total of 38,281,647 pixels, or 20% of the global map, exhibited statistically significant correlations, with 80.4% showing negative correlations, indicating a reduction in vegetation activity as temperatures rise. The latitudinal distribution of significant correlations revealed two prominent peaks: one in the tropical and subtropical regions of the Southern Hemisphere and another in the temperate zones of the Northern Hemisphere. This study uncovers notable spatial and latitudinal patterns in the LST-NDVI relationship, with most regions exhibiting negative correlations, underscoring the cooling effects of vegetation. These findings emphasize the crucial role of vegetation in regulating surface temperatures, providing valuable insights into ecosystem health, and informing conservation strategies in response to climate change.

Previous studies have shown instances where aquatic ecosystems in Iran have experienced water loss even in the absence of upstream dams, while other ecosystems with upstream dams did not show significant declines in water levels. Thus, attributing the drying of these ecosystems solely to climate change in the watershed is not definitive, especially when water levels behind dams have increased while wetlands’ water volumes decreased due to water diversion. This complexity underscores the challenge of linking the decline of aquatic ecosystems exclusively to climate change, as reduced rainfall would naturally lead to decreased water levels behind dams as well. This study addresses this complex issue by analyzing 60 water bodies behind dams across various regions of Iran from 2013 to 2023, using Landsat 8 satellite images and the AWEIsh water index. We employed linear regression to detect surface change trends during this period. Our findings revealed statistically significant (P-value < 0.05) trends in 13 out of the 60 water bodies, with four showing an increasing trend in water levels, indicating diverse precipitation patterns across Iran rather than a uniform decline. Among these, nine dams with significant trends experienced decreased water levels, reflecting reduced upstream rainfall in their watersheds over the past decade. This supports existing research highlighting climate change’s impact on Iran’s water resources. Despite highlighting the impact of declining precipitation and increasing temperatures in certain regions, our study also reveals that certain areas in Iran have not faced such severe conditions. In fact, some regions have seen a notable increase in dam water levels over the past decade. This study emphasizes the importance of an impartial assessment of Iran’s water reserves, free from preconceived notions from previous studies. Such an objective evaluation is crucial for effective management of Iran’s water resources.