基于多源感知的输电线路鸟类活动监测与生态友好型防治数据集

本数据集是面向能源电力行业鸟害防治与生态保护双重需求，构建的国内首个融合鸟类学、电力工程、生态学多学科交叉的特色数据集。数据集涵盖2022年1月至2024年12月期间，陕西省境内220kV及以上电压等级输电线路沿线鸟类活动监测数据、涉鸟物种特征知识库、空间风险评估数据及防治措施效果评估数据四大核心模块。通过高清摄像头、红外热像仪、无人机巡检、智能识别终端等多源感知设备采集，结合人工核验与AI算法识别，形成包含鸟类活动时空分布规律、电网安全风险预警、生态友好型防治策略等关键信息的知识密集型数据资产。数据集总记录数超过6000条，涉及10种典型涉鸟物种、50个监测区段、8类防治措施，为电网鸟害精准防治、生物多样性保护、电力设施安全运行提供科学决策支持，具有显著的工程应用价值和生态保护价值。

This is the first interdisciplinary specialized dataset in China integrating ornithology, electrical engineering, and ecology, developed to meet the dual needs of bird damage prevention and ecological protection for the energy and power industry. Covering the period from January 2022 to December 2024 within the territory of Shaanxi Province, it includes four core modules: bird activity monitoring data along transmission lines with a voltage grade of 220 kV and above, knowledge base of bird-related species' characteristics, spatial risk assessment data, and effect evaluation data of prevention and control measures. Collected via multi-source sensing equipment including high-definition cameras, infrared thermal imagers, unmanned aerial vehicle (UAV) inspections, and intelligent recognition terminals, and processed through manual verification combined with AI algorithm recognition, it forms a knowledge-intensive data asset containing key information such as spatiotemporal distribution patterns of bird activities, power grid safety risk early warnings, and eco-friendly prevention and control strategies. The dataset has over 6,000 total records, involving 10 typical bird-related species, 50 monitoring sections, and 8 types of prevention and control measures. It provides scientific decision-making support for precise bird damage prevention and control of power grids, biodiversity conservation, and safe operation of power facilities, and holds remarkable engineering application value and ecological conservation value.

搜集汇总

背景与挑战

背景概述

该数据集专注于输电线路鸟类活动的监测与防治，通过多源感知技术收集数据，旨在实现生态友好的防治策略。数据集由西安创奕信息科技有限公司提供，目前处于公示阶段，预计在2026年3月27日前完成公示，适用于电力行业生态保护与故障预防场景。