Environmental sensor placement with convolutional Gaussian neural processes
Environmental sensor placement with convolutional Gaussian neural processes
复制标题
DOI：
10.1017/eds.2023.22
复制
发表时间：
2022-11
期刊：
影响因子：
--
通讯作者：
Tom R. Andersson;W. Bruinsma;Stratis Markou;James Requeima;Alejandro Coca-Castro;Anna Vaughan;A. Ellis;M. Lazzara;Daniel P. Jones;Scott Hosking;Richard E. Turner
中科院分区：
文献类型：
--
作者：
Tom R. Andersson;W. Bruinsma;Stratis Markou;James Requeima;Alejandro Coca-Castro;Anna Vaughan;A. Ellis;M. Lazzara;Daniel P. Jones;Scott Hosking;Richard E. Turner
摘要
环境传感器对于监测天气状况和气候变化的影响至关重要。然而，以一种能使测量信息最大化的方式放置传感器是具有挑战性的，特别是在像南极洲这样的偏远地区。概率机器学习模型可以通过找到能最大程度降低预测不确定性的地点来建议信息丰富的传感器放置位置。高斯过程（GP）模型广泛用于此目的，但它们难以捕捉复杂的非平稳行为以及扩展到大型数据集。本文提出使用卷积高斯神经过程（ConvGNP）来解决这些问题。ConvGNP使用神经网络在任意目标位置对联合高斯分布进行参数化，从而实现灵活性和可扩展性。利用南极洲模拟的地表气温异常作为训练数据，ConvGNP学习到空间和季节的非平稳性，性能优于非平稳GP基线。在一个模拟的传感器放置实验中，ConvGNP比GP基线更好地预测了从新观测中获得的性能提升，从而实现更具信息性的传感器放置。我们将我们的方法与基于物理的传感器放置方法进行了对比，并提出了朝着一个可操作的传感器放置推荐系统迈进的未来步骤。我们的工作可能有助于实现环境数字孪生，它能积极引导测量采样以改善对现实的数字表征。
Abstract Environmental sensors are crucial for monitoring weather conditions and the impacts of climate change. However, it is challenging to place sensors in a way that maximises the informativeness of their measurements, particularly in remote regions like Antarctica. Probabilistic machine learning models can suggest informative sensor placements by finding sites that maximally reduce prediction uncertainty. Gaussian process (GP) models are widely used for this purpose, but they struggle with capturing complex non-stationary behaviour and scaling to large datasets. This paper proposes using a convolutional Gaussian neural process (ConvGNP) to address these issues. A ConvGNP uses neural networks to parameterise a joint Gaussian distribution at arbitrary target locations, enabling flexibility and scalability. Using simulated surface air temperature anomaly over Antarctica as training data, the ConvGNP learns spatial and seasonal non-stationarities, outperforming a non-stationary GP baseline. In a simulated sensor placement experiment, the ConvGNP better predicts the performance boost obtained from new observations than GP baselines, leading to more informative sensor placements. We contrast our approach with physics-based sensor placement methods and propose future steps towards an operational sensor placement recommendation system. Our work could help to realise environmental digital twins that actively direct measurement sampling to improve the digital representation of reality.