基于NGO-Attention-RF的森林树种多源遥感识别

doi:10.13474/j.cnki.11-2246.2026.1007

摘要/Abstract

摘要： [目的] 针对传统遥感方法在强背景干扰场景下的树种分类精度局限，本文提出一种融合北方苍鹰优化(NGO)算法与注意力机制的随机森林优化模型(NGO-Attention-RF)。[方法] 以辽宁省阜新市为研究区，融合多源遥感数据构建多维特征集，利用NGO算法优化随机森林超参数以避免局部最优，并在节点分裂中引入注意力机制动态调整特征权重，从而使模型聚焦于树种区分的关键特征。[结果] 试验结果表明，该模型总体精度为85.4%，在各类树种精度及总体分类指标上均优于MLP、CNN、RNN、Transformer及SVM方法，验证了NGO算法与注意力机制的有效性。[结论] 本文揭示了阜新市森林树种的空间分布格局，阐明了不同特征在树种区分中的作用机理，为类似生态区的森林监测提供了方法参考。

关键词: 森林树种分类, 多源遥感, 特征融合, 随机森林, 北方苍鹰优化算法, 注意力机制

Abstract: [Purposes] To address the limitations of traditional remote sensing methods in tree species classification accuracy under strong background interference,this study proposes an optimized random forest model integrating the northern goshawk optimization(NGO)algorithm and an attention mechanism (NGO-Attention-RF). [Methods] Taking Fuxin city,Liaoning province as the study area,multi-source remote sensing data were fused to construct a multi-dimensional feature set.The NGO algorithm was employed to optimize the hyperparameters of the random forest,thereby avoiding local optima.An attention mechanism was introduced during node splitting to dynamically adjust feature weights,enabling the model to focus on key features that distinguish tree species. [Findings] Experimental results show that the proposed model achieved an overall accuracy of 85.4%.It outperformed methods such as MLP,CNN,RNN,Transformer,and SVM in terms of accuracy for each tree species category and overall classification metrics,validating the effectiveness of the NGO algorithm and the attention mechanism. [Conclusions] The study reveals the spatial distribution patterns of forest tree species in Fuxin city,elucidates the role of different features in tree species discrimination,and provides a methodological reference for forest monitoring in similar ecological regions．

Key words: forest tree species classification, multi-source remote sensing, feature fusion, random forest, northern goshawk optimization algorithm, attention mechanism

中图分类号:

P237

张兵, 安高钱, 胡忠超, 张继超, 范强, 任东风. 基于NGO-Attention-RF的森林树种多源遥感识别[J]. 测绘通报, 2026, 0(10): 47-54.

Zhang Bing, An Gaoqian, Hu Zhongchao, Zhang Jichao, Fan Qiang, Ren Dongfeng. Multi-source remote sensing identification of forest tree species based on NGO-Attention-RF[J]. Bulletin of Surveying and Mapping, 2026, 0(10): 47-54.

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: http://tb.chinasmp.com/CN/10.13474/j.cnki.11-2246.2026.1007

http://tb.chinasmp.com/CN/Y2026/V0/I10/47

参考文献

[1] Jenkins J C,Chojnacky D C,Heath L S,et al.National-scale biomass estimators for United States tree species[J].Forest Science,2003,49(1):12-35.
[2] Domke G M,Woodall C W,Smith J E,et al.Consequences of alternative tree-level biomass estimation procedures on U.S.forest carbon stock estimates[J].Forest Ecology and Management,2012,270:108-116.
[3] Fassnacht F E,Latifi H,Stereńczak K,et al.Review of studies on tree species classification from remotely sensed data[J].Remote Sensing of Environment,2016,186:64-87.
[4] Li Hui,Hu Baoxin,Li Qian,et al.CNN-based tree species classification using airborne LiDAR data and high-resolution satellite image[C]//Proceedings of 2020 IEEE International Geoscience and Remote Sensing Symposium.Waikoloa:IEEE,2020:2679-2682.
[5] Zhang Bing,Zhu Hongbo,Song Weidong,et al.A multi-baseline forest height estimation method combining analytic and geometric expression of the RVoG model[J].Forests,2024,15(9):1496.
[6] Zhu Hongbo,Zhang Bing,Song Weidong,et al.Forest canopy height estimation by integrating structural equation modeling and multiple weighted regression[J].Forests,2024,15(2):369.
[7] Zhang Bing,Zhu Hongbo,Xu Wenxuan,et al.A Fourier-Legendre polynomial forest height inversion model based on a single-baseline configuration[J].Forests,2024,15(1):49.
[8] Xiao Yuelong,Wang Qunming,Zhang H K.Global natural and planted forests mapping at fine spatial resolution of 30 m[J].Journal of Remote Sensing,2024,4:204.
[9] Krishnan V,Asaithambi M.Semi-empirical SAR vegetation index for crop discrimination based on biomass in semi-arid region:a case study in Perambalur district,India[J].Remote Sensing Applications:Society and Environment,2023,32:101064.
[10] 张良培,何江,杨倩倩,等.数据驱动的多源遥感信息融合研究进展[J].测绘学报,2022,51(7):1317-1337．
[11] Wei Kan,Dai Jinkun,Hong Danfeng,et al.MGFNet:an MLP-dominated gated fusion network for semantic segmentation of high-resolution multi-modal remote sensing images[J].International Journal of Applied Earth Observation and Geoinformation,2024,135:104241.
[12] 龚健雅,宦麟茜,郑先伟.影像解译中的深度学习可解释性分析方法[J].测绘学报,2022,51(6):873-884．
[13] Poggio T,Banburski A,Liao Qianli.Theoretical issues in deep networks[J].Proceedings of the National Academy of Sciences of the United States of America,2020,117(48):30039-30045.
[14] Breiman L.Random forests[J].Machine Learning,2001,45(1):5-32.
[15] Rodriguez-Galiano V F,Ghimire B,Rogan J,et al.An assessment of the effectiveness of a random forest classifier for land-cover classification[J].ISPRS Journal of Photogrammetry and Remote Sensing,2012,67:93-104.
[16] 王耕,张红玉.辽西北地区防风固沙服务空间流动与辐射效应[J].生态与农村环境学报,2023,39(1):52-59．
[17] Montero D,Aybar C,Mahecha M D,et al.A standardized catalogue of spectral indices to advance the use of remote sensing in Earth system research[J].Scientific Data,2023,10:197.
[18] Zhang Xin,Cui Jintian,Wang Weisheng,et al.A study for texture feature extraction of high-resolution satellite images based on a direction measure and gray level co-occurrence matrix fusion algorithm[J].Sensors,2017,17(7):1474.
[19] Liu Huaipeng,Su Xiaoyan,An Huijun.Typical landscape tree species recognition based on RedEdge-MX:suitability analysis of two texture extraction forms under random forest supervision[J].Polish Journal of Environmental Studies,2022,31(2):1475-1484.
[20] Wang Mo,Wang Laigang,Guo Yan,et al.A comprehensive evaluation of dual-polarimetric Sentinel-1 SAR data for monitoring key phenological stages of winter wheat[J].Remote Sensing,2024,16(10):1659.
[21] Kalbi S,Fallah A,Shataee S.Forest stand types classification using tree-based algorithms and SPOT-HRG data[J].Environmental Resources Research,2014,2(1):31-46．
[22] Dehghani M,Hubálovský Š,Trojovský P.Northern goshawk optimization:a new swarm-based algorithm for solving optimization problems[J].IEEE Access,2021,9:162059-162080.
[23] Vaswani A,Shazeer N,Parmar N,et al.Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.[S.l.]:Curran Associates，Inc.,2017:5998-6008.