Mangrove ecosystems play an irreplaceable role in coastal environments by providing essential ecosystem services. Diverse mangrove species have different functions due to their morphological and physiological characteristics. A precise spatial distribution map of mangrove species is therefore crucial for biodiversity maintenance and environmental conservation of coastal ecosystems. Traditional satellite data are limited in fine-scale mangrove species classification due to low spatial resolution and less spectral information. This study employed unmanned aerial vehicle (UAV) technology to acquire high-resolution multispectral and hyperspectral mangrove forest imagery in Guangxi, China. We leveraged advanced algorithms, including RFE-RF for feature selection and machine learning models (Adaptive Boosting (AdaBoost), eXtreme Gradient Boosting (XGBoost), Random Forest (RF), and Light Gradient Boosting Machine (LightGBM)), to achieve mangrove species mapping with high classification accuracy. The study assessed the classification performance of these four machine learning models for two types of image data (UAV multispectral and hyperspectral imagery), respectively. The results demonstrated that hyperspectral imagery had superiority over multispectral data by offering enhanced noise reduction and classification performance. Hyperspectral imagery produced mangrove species classification with overall accuracy (OA) higher than 91% across the four machine learning models. LightGBM achieved the highest OA of 97.15% and kappa coefficient (Kappa) of 0.97 based on hyperspectral imagery. Dimensionality reduction and feature extraction techniques were effectively applied to the UAV data, with vegetation indices proving to be particularly valuable for species classification. The present research underscored the effectiveness of UAV hyperspectral images using machine learning models for fine-scale mangrove species classification. This approach has the potential to significantly improve ecological management and conservation strategies, providing a robust framework for monitoring and safeguarding these essential coastal habitats.

Precise and timely leaf area index (LAI) estimation for winter wheat is crucial for precision agriculture. The emergence of high-resolution unmanned aerial vehicle (UAV) data and machine learning techniques offers a revolutionary approach for fine-scale estimation of wheat LAI at the low cost. While machine learning has proven valuable for LAI estimation, there are still model limitations and variations that impede accurate and efficient LAI inversion. This study explores the potential of classical machine learning models and deep learning model for estimating winter wheat LAI using multispectral images acquired by drones. Initially, the texture features and vegetation indices served as inputs for the partial least squares regression (PLSR) model and random forest (RF) model. Then, the ground-measured LAI data were combined to invert winter wheat LAI. In contrast, this study also employed a convolutional neural network (CNN) model that solely utilizes the cropped original image for LAI estimation. The results show that vegetation indices outperform the texture features in terms of correlation analysis with LAI and estimation accuracy. However, the highest accuracy is achieved by combining both vegetation indices and texture features to invert LAI in both conventional machine learning methods. Among the three models, the CNN approach yielded the highest LAI estimation accuracy (R² = 0.83), followed by the RF model (R² = 0.82), with the PLSR model exhibited the lowest accuracy (R² = 0.78). The spatial distribution and values of the estimated results for the RF and CNN models are similar, whereas the PLSR model differs significantly from the first two models. This study achieves rapid and accurate winter wheat LAI estimation using classical machine learning and deep learning methods. The findings can serve as a reference for real-time wheat growth monitoring and field management practices.

Phenology and photosynthetic capacity both regulate carbon uptake by vegetation. Previous research investigating the impact of phenology on vegetation productivity has focused predominantly on the start and end of growing seasons (SOS and EOS), leaving the influence of peak phenology metrics—particularly in typical climatic transition zones—relatively unexplored. Using a 24-year (2000–2023) enhanced vegetation index (EVI) dataset from the Moderate Resolution Imaging Spectroradiometer (MODIS), we extracted and examined the spatiotemporal variation for peak of season (POS) and peak growth (defined as EVI_max) of forest vegetation in the Funiu Mountain region, China. In addition to quantifying the factors influencing the peak phenology metrics, the relationship between vegetation productivity and peak phenological metrics (POS and EVI_max) was investigated. Our findings reveal that POS and EVI_max showed advancement and increase, respectively, negatively and positively correlated with vegetation productivity. This suggested that variations in EVI_max and peak phenology both increase vegetation productivity. Our analysis also showed that EVI_max was heavily impacted by precipitation, whereas SOS had the greatest effect on POS variation. Our findings highlighted the significance of considering climate variables as well as biological rhythms when examining the global carbon cycle and phenological shifts in response to climate change.

Eucalyptus, valued for its rapid growth and economic potential, has been widely introduced in China to address timber demands while conserving natural forests. Precisely estimating the spatiotemporal expansion of short-rotation eucalyptus plantations is crucial for evaluating their ecological and social value and formulating effective sustainable forestry policies. Medium-resolution satellite images, such as Landsat data, offer a cost-effective tool for large-scale forest mapping compared to traditional forest inventories. This study used pixel-level time series analysis to identify annual eucalyptus plantation distributions across Guangxi, China, from 2004 to 2019, based on the standard temporal vegetation index curves derived from the characteristics of short-rotation and fast-growing eucalyptus. Furthermore, an image segmentation method, coupled with an empirical relationship linking patch-level landscape indices to optimal thresholds, was employed to eliminate isolated pixels and reduce omission errors arising from above time series analysis. The established thresholds increased accurate identification of eucalyptus patches within segments. Our proposed eucalyptus detection algorithm achieved an overall accuracy exceeding 80%, demonstrating its effectiveness. The analysis revealed eucalyptus plantations increased from 0.42 × 10 ⁶ ha in 200 ⁴ to 2.47 × 10 ⁶ ha in 2019, exhibiting a pronounced northward expansion. Initially concentrated in upland areas, plantations subsequently expanded into flatter terrains, raising concerns about potential agricultural conflicts. Annual eucalyptus plantation maps offer critical information for sustainable forest management and policymaking. This study highlights the potential of medium-resolution satellite data and time series analysis for robust and cost-effective monitoring of annual short-rotation timber forest expansion dynamics over large scales.

Vegetation phenology derived from satellite vegetation indices is sensitive to spatial scale, yet how spatial aggregation affects phenological timing and temporal dynamics across broad geographical extents remains insufficiently understood. In this study, the 250 m MOD13Q1 Enhanced Vegetation Index (EVI) time series from 2000 to 2024 was used as a common data source, and 1 km and 5 km datasets were generated directly through spatial aggregation. By maintaining the same sensor, vegetation index, temporal sampling, and phenology retrieval method across scales, this controlled within-source framework minimizes confounding effects associated with cross-sensor differences. The start of the growing season (SOS) and end of the growing season (EOS) were retrieved using asymmetric Gaussian fitting combined with a dynamic threshold method. Their spatiotemporal patterns, aggregation-induced cross-scale consistency, and bias were systematically analyzed. The broad spatial patterns of multi-year mean SOS and EOS remained generally consistent across the three scales. SOS showed an overall advancing tendency and EOS an overall delaying tendency, while the proportion of pixels with relatively large trend magnitudes decreased at coarser spatial scales. Cross-scale correlations remained high across all scale pairs and generally increased with latitude, with SOS exhibiting higher cross-scale consistency than EOS. Annual SOS correlations declined during 2000–2024, whereas EOS correlations increased during the early part of the record and declined thereafter, with a breakpoint around 2010. The bias showed clear differences in direction and magnitude between SOS and EOS and among vegetation types, and its absolute magnitude generally increased with increasing scale disparity. These results indicate that aggregation-induced phenological responses are not spatially uniform but vary systematically with geographical context, vegetation type, and phenological phase. These findings provide a scientific reference for the cross-scale comparison and scale transformation of multi-source remotely sensed phenology products, as well as for studies of regional ecological processes.