Torney Colin J, Morales Juan M, Husmeier Dirk
School of Mathematics and Statistics, University of Glasgow, Glasgow, G12 8SQ, UK.
Grupo de Ecología Cuantitativa, INIBIOMA, Universidad Nacional del Comahue, CONICET, Düsternbrooker Weg 20, Bariloche, S4140, Argentina.
Mov Ecol. 2021 Feb 18;9(1):6. doi: 10.1186/s40462-021-00242-0.
In recent years the field of movement ecology has been revolutionized by our ability to collect high-accuracy, fine scale telemetry data from individual animals and groups. This growth in our data collection capacity has led to the development of statistical techniques that integrate telemetry data with random walk models to infer key parameters of the movement dynamics. While much progress has been made in the use of these models, several challenges remain. Notably robust and scalable methods are required for quantifying parameter uncertainty, coping with intermittent location fixes, and analysing the very large volumes of data being generated.
In this work we implement a novel approach to movement modelling through the use of multilevel Gaussian processes. The hierarchical structure of the method enables the inference of continuous latent behavioural states underlying movement processes. For efficient inference on large data sets, we approximate the full likelihood using trajectory segmentation and sample from posterior distributions using gradient-based Markov chain Monte Carlo methods.
While formally equivalent to many continuous-time movement models, our Gaussian process approach provides flexible, powerful models that can detect multiscale patterns and trends in movement trajectory data. We illustrate a further advantage to our approach in that inference can be performed using highly efficient, GPU-accelerated machine learning libraries.
Multilevel Gaussian process models offer efficient inference for large-volume movement data sets, along with the fitting of complex flexible models. Applications of this approach include inferring the mean location of a migration route and quantifying significant changes, detecting diurnal activity patterns, or identifying the onset of directed persistent movements.
近年来，运动生态学领域因我们能够从个体动物和群体中收集高精度、细粒度的遥测数据而发生了变革。我们数据收集能力的这种提升促使了统计技术的发展，这些技术将遥测数据与随机游走模型相结合，以推断运动动态的关键参数。虽然在使用这些模型方面已经取得了很大进展，但仍存在一些挑战。特别是，需要强大且可扩展的方法来量化参数不确定性、应对间歇性定位以及分析生成的大量数据。
在这项工作中，我们通过使用多级高斯过程实现了一种新颖的运动建模方法。该方法的层次结构能够推断运动过程背后的连续潜在行为状态。为了对大数据集进行高效推断，我们使用轨迹分割近似全似然，并使用基于梯度的马尔可夫链蒙特卡罗方法从后验分布中采样。
虽然在形式上等同于许多连续时间运动模型，但我们的高斯过程方法提供了灵活、强大的模型，能够检测运动轨迹数据中的多尺度模式和趋势。我们说明了我们方法的另一个优势，即可以使用高效的、GPU加速的机器学习库进行推断。
多级高斯过程模型为大量运动数据集提供了高效推断，同时能够拟合复杂灵活的模型。这种方法的应用包括推断迁徙路线的平均位置并量化显著变化、检测昼夜活动模式或识别定向持续运动的开始。
