Accurate classification of wetland vegetation is essential for biodiversity conservation and carbon cycle monitoring, yet traditional methods face significant limitations in complex ecosystems like karst wetlands. A new study published in the Journal of Remote Sensing on October 16, 2025, introduces an adaptive ensemble learning stacking (AEL-Stacking) framework that combines hyperspectral imagery and light detection and ranging data captured by unmanned aerial vehicles to precisely identify vegetation species with up to 92.77% accuracy.
Karst wetlands are globally significant ecosystems that regulate water, store carbon, and harbor rich biodiversity, but their intricate vegetation composition and similar canopy spectra among species have hindered accurate remote sensing classification. Traditional field surveys are costly and spatially limited, while multispectral imaging lacks sufficient spectral resolution for species-level mapping. LiDAR provides 3D structural data but struggles with water-surface reflectance and weak signals. The integration of complementary optical and structural data through this new approach addresses these persistent challenges.
The research, conducted by scientists from Guilin University of Technology and collaborators, demonstrated that combining hyperspectral and LiDAR data achieved the highest overall accuracy (87.91%–92.77%), surpassing single-data approaches by up to 9.5%. The AEL-Stacking model, which integrates Random Forest, LightGBM, and CatBoost classifiers, outperformed both conventional ensemble and deep-learning algorithms by 0.96%–7.58%. The full study is available at https://spj.science.org/doi/10.34133/remotesensing.0452 with DOI 10.34133/remotesensing.0452.
Field surveys were conducted in the Huixian Karst Wetland of Guilin, China, one of the country's largest karst wetlands. UAV flights equipped with Headwall Nano-Hyperspec and DJI Zenmuse L1 LiDAR sensors collected over 4,500 hyperspectral images and dense point clouds. The integrated dataset covered 13 vegetation types, including lotus, miscanthus, and camphor trees. Through recursive feature elimination and correlation analysis, 40 optimal features were selected from more than 600 variables.
The LiDAR features—especially digital surface model variables—were pivotal for distinguishing species with distinct vertical structures, while hyperspectral vegetation indices such as NDVI and blue-edge parameters enhanced recognition of herbaceous species. These results highlight the synergy between optical and structural data in resolving species with overlapping spectral signatures. The model significantly reduced misclassification between morphologically similar species, offering detailed vegetation maps critical for ecosystem monitoring.
"Our approach bridges the gap between spectral and structural sensing," said Dr. Bolin Fu, corresponding author. "By combining UAV hyperspectral and LiDAR data through adaptive ensemble learning, we achieved both precision and interpretability in vegetation mapping. The framework not only improves species recognition in complex karst environments but also provides a generalizable tool for ecological monitoring and habitat restoration worldwide."
The framework uses local interpretable model-agnostic explanations to visualize how each feature contributes to the decision-making process, offering both high precision and interpretability in mapping complex wetland vegetation structures. This integrative approach demonstrates a scalable and explainable method for high-resolution wetland mapping, potentially applicable to forest, grassland, and coastal ecosystems.
Future work will focus on integrating multi-temporal UAV observations and satellite data fusion to monitor seasonal vegetation dynamics and climate-driven changes in wetland health. By enhancing the transparency and accuracy of AI-driven ecological models, this research supports the global agenda for biodiversity conservation and carbon neutrality while providing a practical tool for environmental managers and conservationists working in complex ecosystems worldwide.
