文献类型：期刊文献

英文题名：Cognition-inspired multimodal attention fusion of close-range laser scanning data for globally representative tree species classification

作者：Luo, Xin[1] Tian, Xin[1] Liang, Xinlian[2] Mokros, Martin[3] Chai, GuoQi[1] Li, Zengyuan[1] Guo, Ying[1] Yang, Yudi[1] Pang, Yong[1] Wang, Yunsheng[4] Guo, Keruo[5] Zhang, Xiaoli[6] Chen, Xinjing[1] Chen, Shuxin[1] Wang, Haiyi[1]

通信作者：Tian, X[1]

机构：[1]Chinese Acad Forestry, Inst Forest Resource Informat Tech, Beijing 100091, Peoples R China;[2]Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & Re, Wuhan 430070, Peoples R China;[3]UCL, Fac Social & Hist Sci, Geog Dept, London, England;[4]Nat Land Survey Finland, Dept Remote Sensing & Photogrammetry, Finnish Geospatial Res Inst, Vuorimiehentie 5, Espoo 02150, Finland;[5]Chinese Acad Sci, LREIS, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China;[6]Beijing Forestry Univ, Key Lab Forest Cultivat & Protect, Minist Educ, Beijing 100083, Peoples R China

年份：2026

卷号：335

外文期刊名：REMOTE SENSING OF ENVIRONMENT

收录：;WOS:【SCI-EXPANDED(收录号:WOS:001685420900001)】；

基金：This work was supported by the National Key Research and Devel-opment Program of China (No. 2023YFD2201705) . We also extend our gratitude to the 3DForEcoTech COST-Action, supported by the European Cooperation in Science and Technology (COST) , for its foundational contributions and conceptual inspiration to this research.

语种：英文

外文关键词：Tree species classification; Close-range sensing; Multimodal fusion; Deep learning; Attention mechanism; Forest remote sensing

摘要：Species-level tree identification is a fundamental task in forest monitoring, biodiversity assessment, and climate-smart ecosystem modeling. Close-range laser scanning technologies have become indispensable tools for forest mapping because they provide high-resolution, three-dimensional structural data at the individual-tree level. However, species-level identification remains a major challenge in global environmental monitoring and AI-driven ecological assessment owing to high species diversity, structural plasticity, and variability across sensing platforms. Here, we propose the cognition-inspired multimodal attention fusion network (CI-MAFusion), a dual-branch deep learning framework that integrates point cloud data with multi-view imagery. Guided by expert dendrological reasoning and cognitive neuroscience principles, CI-MAFusion incorporates a structural branch based on an improved graph attention-based point network for encoding 3D morphological patterns and a visual branch that processes standardized multi-view projections to extract textural features. A cross-gate attention mechanism adaptively fuses structural and visual features. Each branch uses an enhanced convolutional block attention module to highlight salient features, analogous to selective attention in the human visual system. We tested CI-MAFusion using Global LiDAR TreeBank, which contains 12,057 trees from 36 species across four continents and six K & ouml;ppen climate zones. The model achieved 87.50% overall accuracy at the genus level and 86.12% at the species level, outperforming unimodal and existing fusion approaches by up to 8.1%. Additionally, it further achieved > 90% overall accuracy across regions and > 80% across climate zones, with attention visualizations highlighting biologically diagnostic features such as crown contours, bark textures, and branch junctions. This cognitively inspired architecture improves generalization and advances AI-based systems toward robust recognition of biological structures in complex environments.