AI声纹监测与人工样线调查在鸟类多样性监测中的差异研究: 以西溪国家湿地公园为例

doi:10.17520/biods.2025239

生物多样性

AI声纹监测与人工样线调查在鸟类多样性监测中的差异研究: 以西溪国家湿地公园为例

姚可侃^1,2, 余卉^1,2, 张巧玲^1,2, 陈琳^1,2*

1. 杭州西溪国家湿地公园服务中心(杭州西溪国家湿地公园生态文化研究中心), 杭州 310030; 2. 浙江西溪湿地生态系统定位观测研究站, 杭州 310030

收稿日期:2025-06-22 修回日期:2025-09-18 接受日期:2026-01-06
通讯作者: 陈琳
基金资助:
声纹识别技术支持下自然保护地鸟类多样性节律特征及监测有效性研究——以黄龙自然保护区为例. 园林, 41,(11-18); 许晓青, 余楚萌, 徐荣林, 刘颂(2024)

A comparative study of AI voiceprint monitoring and manual transect surveys in avian diversity monitoring: A case study of Xixi National Wetland Park

Kekan Yao^1,2, Hui Yu^1,2, Qiaoling Zhang^1,2, Lin Chen^1,2*

1 Hangzhou Xixi National Wetland Park Service Center (Hangzhou Xixi National Wetland Park Ecological and Cultural Research Center, Hangzhou 310030, China

2 Zhejiang Xixi Wetland Ecosystem Observation and Research Station, Hangzhou 310030, China

Received:2025-06-22 Revised:2025-09-18 Accepted:2026-01-06
Contact: Lin Chen
Supported by:
A case study of Huanglong Nature Reserve. Landscape Architecture, 41, 11-18.(in Chinese with English abstract)

摘要/Abstract

摘要： 鸟类多样性特征是评价湿地生态系统质量的重要指标。传统鸟类多样性调查多限于人工观测, 而近年来声纹监测技术逐步应用, 为鸟类多样性研究提供了新途径。为对比AI声纹监测与人工样线调查差异, 本研究于2024年1月(冬)、4月(春)、8月(夏)和10月(秋), 在杭州西溪国家湿地公园选取5处人工样线调查与声纹监测设备重合的样区开展同步监测。声纹监测选取77.5%作为置信阈值输出数据, 基于Simpson优势度指数(C)、Shannon-Wiener多样性指数(H′)、Pielou均匀度指数(J)和Margalef丰富度指数(M)等指标, 评估两种方法的适用性与局限。结果表明: (1)四季累计, 声纹监测设备检测到鸟类105种, 人工样线记录鸟类89种; 声纹监测在物种丰富度(S)上表现更优。(2)按居留型看, 声纹监测对候鸟的检出更优, 人工样线则在留鸟的检出上更优; 声纹监测还贡献了区域新记录。(3)两种方法在各指数的季节变化不完全一致。(4)按区域看, 声纹监测下绿堤/水下长廊的H′、J、M最高, 人工样线下则以莲花滩最高。总体声纹监测适合长期、广时段的动态监测, 具有广阔前景; 可与人工样线互补, 建议建立识别置信度与质量控制阈值的评估体系, 提升方法准确性与可比性。

关键词: 鸟类多样性, 声纹监测, 人工样线, 湿地, 杭州西溪

Abstract

Aim: Traditional bird diversity surveys have largely relied on manual observations; however, in recent years, voiceprint monitoring technology has been gradually applied, providing a new approach for studying avian diversity. Avian diversity is a key indicator for assessing the quality of wetland ecosystems. This study aims to compare AI-based voiceprint monitoring with manual transect surveys, offering a case reference for the application of bird voiceprint monitoring devices in wetland parks nationwide.

Methods: In January (winter), April (spring), August (summer), and October (autumn) of 2024, this study conducted comprehensive and systematic bird diversity surveys at five sites within Xixi National Wetland Park in Hangzhou, Zhejiang, where manual transect surveys and voiceprint monitoring devices overlapped. The voiceprint monitoring uses a confidence threshold of 77.5% for output data. Based on Simpson dominance index (C), Shannon-Wiener diversity index (H′), Pielou evenness index (J), and Margalef richness index (M), the applicability and limitations of two methods were evaluated.

Results: (1) Across the four seasons, voiceprint monitoring detected 105 species, while manual transect surveys recorded 89 species; voiceprint monitoring showed better performance in species richness (S). (2) In terms of residency status, voiceprint monitoring showed higher detection efficiency for migratory and passage birds, whereas manual transect surveys performed better for resident birds; moreover, voiceprint monitoring contributed new regional records. (3) The seasonal variations of the indices obtained by the two methods were not entirely consistent. (4) By region, the highest H′, J, and M values under voiceprint monitoring were observed at Lüdi/Shuixiachanglang area, whereas under manual transect surveys, the highest values were recorded at Lianhuatan area.

Conclusion: Overall, voiceprint monitoring is suitable for long-term and wide time-scale dynamic monitoring, with broad application prospects, and can serve as a complement to manual transect surveys. An evaluation system incorporating recognition confidence and quality control thresholds is recommended to enhance the accuracy and comparability of the method.

Key words: avian diversity, voiceprint monitoring, manual transect, wetland, Hangzhou Xixi

姚可侃, 余卉, 张巧玲, 陈琳. AI声纹监测与人工样线调查在鸟类多样性监测中的差异研究: 以西溪国家湿地公园为例. 生物多样性, DOI: 10.17520/biods.2025239.

Kekan Yao, Hui Yu, Qiaoling Zhang, Lin Chen. A comparative study of AI voiceprint monitoring and manual transect surveys in avian diversity monitoring: A case study of Xixi National Wetland Park. Biodiversity Science, DOI: 10.17520/biods.2025239.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.biodiversity-science.net/CN/10.17520/biods.2025239

[1]	洪欣艺, 蔡易朗, 方嘉乐, 姚可侃, 李佳乐, 王懿祥, 白尚斌, 王楠, 周秀梅. 西溪湿地土壤病毒多样性及其碳代谢基因解析[J]. 生物多样性, 2025, 33(9): 25190-.
[2]	孙济伦, 谢将剑, 张长春, 张军国. 基于YOLO-DAS模型的湿地水鸟检测方法: 以内蒙古南海子湿地为例[J]. 生物多样性, 2025, 33(9): 25237-.
[3]	王欣, 鲍风宇. 基于鸟类多样性提升的南滇池国家湿地公园生态修复效果[J]. 生物多样性, 2025, 33(5): 24531-.
[4]	徐欢, 辛凤飞, 施宏亮, 袁琳, 薄顺奇, 赵欣怡, 邓帅涛, 潘婷婷, 余婧, 孙赛赛, 薛程. 生态修复技术集成应用对长江口北支生境与鸟类多样性提升效果评估[J]. 生物多样性, 2025, 33(5): 24478-.
[5]	宋远昊, 龚吕, 李贲, 胡阳, 李秀珍. 辽河口不同退塘还湿方式对大型底栖动物的影响[J]. 生物多样性, 2025, 33(2): 24316-.
[6]	刘源, 杜剑卿, 马丽媛, 杨刚, 田建卿. 纳木措流域岸边带湿地产甲烷古菌群落多样性与分布特征[J]. 生物多样性, 2025, 33(1): 24247-.
[7]	段菲, 刘鸣章, 卜红亮, 俞乐, 李晟. 城市化对鸟类群落组成及功能特征的影响——以京津冀地区为例[J]. 生物多样性, 2024, 32(8): 23473-.
[8]	王秦韵, 张玉泉, 刘浩, 李明, 刘菲, 赵宁, 陈鹏, 齐敦武, 阙品甲. 成都大熊猫繁育研究基地鸟类多样性[J]. 生物多样性, 2024, 32(8): 24066-.
[9]	白皓天, 余上, 潘新园, 凌嘉乐, 吴娟, 谢恺琪, 刘阳, 陈学业. AI辅助识别的鸟类被动声学监测在城市湿地公园中的应用[J]. 生物多样性, 2024, 32(8): 24188-.
[10]	张乃鹏, 梁洪儒, 张焱, 孙超, 陈勇, 王路路, 夏江宝, 高芳磊. 土壤类型和地下水埋深对黄河三角洲典型盐沼植物群落空间分异的影响[J]. 生物多样性, 2024, 32(2): 23370-.
[11]	胡婉君, 郝泽周, 夏灿玮, 谢将剑. 湿地声景录音策略及面向声景分类的特征选择[J]. 生物多样性, 2024, 32(10): 24121-.
[12]	郝泽周, 张承云, 李乐, 高丙涛, 曾伟, 王淳, 王梓炫, 黄万涛, 张悦, 裴男才, 肖治术. 城市鸟类多样性被动声学监测与评价技术应用[J]. 生物多样性, 2024, 32(10): 24123-.
[13]	李乐, 张承云, 裴男才, 高丙涛, 王娜, 李嘉睿, 武瑞琛, 郝泽周. 基于被动声学监测技术的城市绿地景观格局与鸟类多样性关联分析[J]. 生物多样性, 2024, 32(10): 24296-.
[14]	殷鲁秦, 王成, 韩文静. 基于取食行为探究北京居民区鸟类的食源特征及多样性[J]. 生物多样性, 2023, 31(5): 22473-.
[15]	吴浩, 余玉蓉, 王佳钰, 赵媛博, 高娅菲, 李小玲, 卜贵军, 薛丹, 吴林. 低水位增加灌木多样性和生物量但降低土壤有机碳含量: 以鄂西南贫营养泥炭地为例[J]. 生物多样性, 2023, 31(3): 22600-.