Estimating marine mammal abundance and distribution from passive acoustic and biotelemetry data

由于顶级捕食者数量减少而导致的生态系统功能弱化是一个一阶全球性问题。在海洋中，人类活动对海洋哺乳动物产生不利影响，25%的物种受到威胁。确定其时空分布和丰度是了解生态系统健康的核心。该研究金的目的是将联合收割机被动声学监测和卫星跟踪（生物遥测）结合起来，以确定海洋哺乳动物的丰度和分布。从这两种对比技术中确定可靠的动物分布将需要仔细的比较，数据整合和洞察力，因为PAM技术需要从它们的呼叫类型中识别单个物种，而在生物遥测中则跟踪特定的动物。海洋自动驾驶车辆可以有效地感知和理解海洋，并可以配备PAM设备，该设备可以记录大频率带宽，从而促进高保真和完整的海洋声景记录。询问由自主数据舰队记录的大量数据集是当前的挑战。首先，学生将应用并进一步开发机器学习技术来识别单个物种。其次，学生将利用大型海洋哺乳动物跟踪数据集以及丰度和分布预测，将跟踪，分布和丰度数据与PAM数据进行比较和整合。

Ecosystem function weakening due to reduction in top predator numbers is a first order global problem. In the oceans anthropogenic activities adversely affect marine mammals, with 25% of species being threatened. Determining their spatiotemporal distribution and abundance is central to understanding ecosystem health. The aim of this studentship is to combine Passive Acoustic Monitoring (PAM) and satellite-linked tracking (biotelemetry) to determine marine mammal abundance and distribution. Determining a reliable distribution of animals from these two contrasting techniques will require careful comparison, data integration and insight, as PAM techniques require identification of individual species from their call types, while in biotelemetry specific animals are tracked. Marine autonomous vehicles are effective in sensing and understanding the oceans and can be equipped with PAM devices that can record a large frequency bandwidth facilitating a high-fidelity and complete record of the marine soundscape. Interrogating the vast datasets that are recorded by fleets of autonomous data is a current challenge. The student will, firstly, apply and further develop machine-learning techniques to identify individual species. Secondly, the student will leverage large marine mammal tracking datasets, as well as abundance and distribution predictions, to compare and integrate tracking, distribution and abundance data with PAM data.