Autonomous Seagrass Habitat Monitoring System (ASHMoS)
Autonomous Seagrass Habitat Monitoring System (ASHMoS)
批准号:
10053530
负责人:
金额:
$19.46万
依托单位国家:
英国
项目类别:
CR&D Bilateral
财政年份:
2023
资助国家:
英国
项目状态:
已结题
起止时间:
2023 至 --
中文摘要
合作伙伴HydroSurv无人调查(英国)有限公司和普利茅斯大学海洋研究所汇集了一个专家团队,将HydroSurv的机器人调查技术和快速开发能力与国际公认的海洋科学学术专业知识相结合,开发一个开创性的解决方案,用于水下水生植被的潮下调查,将一个新的端到端解决方案交到英国沿海从业者手中,用于自然资本评估和监测。在他们之前监测海草的声学地面识别技术项目的成功宣传的推动下,合作伙伴关系将提高这项新技术的准确性,汇集一系列新的数据集,以评估底栖生物栖息地的状况,并根据调查专员和公共数据用户的验证需求,提供沉积物特征和海草生物量估算。政府和地方当局组织。新方法的核心是使用具有电力推进的快速部署的HydroSurv无人水面船(USV)平台,结合先进的传感器阵列,从地面真实仪器阵列收集一系列水声和观测测量数据。深度学习算法的使用从表征海草的覆盖范围、密度和冠层高度扩展到进行沉积物分析,同时收集与主要数据集定位的互补环境数据集。数据交付建立在HydroSurv的企业级GIS云应用程序上,使用户无需专业数据查询技能即可监控时间变化。与现有的调查技术相比,该解决方案将大幅降低数据收集的成本和碳强度,同时将人员从危害中移除,并将灵活方便地进入市场,从而忠实于HydroSurv实现海洋数据民主化的目标。
英文摘要
Collaborators HydroSurv Unmanned Survey (UK) Ltd and University of Plymouth Marine Institute are bringing together an expert team to combine HydroSurv's robotic survey technology and rapid development capabilities with an internationally recognised academic expertise in marine science to develop a groundbreaking solution for subtidal survey of submerged aquatic vegetation, putting a new end-to-end solution into the hands of UK coastal practioners for natural capital assessment and monitoring.Driven by the well-publicised successes within their previous project for acoustic ground discrimination techniques for the monitoring of seagrass, the partnership will advance the accuracy of this novel technique bringing together a series of new datasets to assess the condition of benthic habitats and provide sediment characterisation alongside seagrass biomass estimation based on the validated needs of survey commissioners and data users within public, government and local authority organisations.Central to the new approach is use of rapidly-deployable HydroSurv Uncrewed Surface Vessel (USV) platforms with electric propulsion, combined with an advanced sensor array to collect a range of hydroacoustic and observational measurements from a ground truthing instrument array. The use of deep learning algorithms is expanded from characterising the coverage, density and canopy height of seagrass to carrying out sediment analysis, whilst collecting complementary environmental datasets geolocated to the primary datasets. The data delivery builds upon HydroSurv's enterprise-scale GIS cloud application to enable users to monitor temporal changes without specialist data interrogation skills.Staying true to HydroSurv's aim to democratise ocean data, the solution will slash the cost and carbon intensity of data collection relative to established survey techniques whilst removing personnel from harms way, and will be made flexibly and conveniently accessible to the market.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
海外基金