Environmental sensor placement with convolutional Gaussian neural processes

Andersson, Tom R. ORCID: https://orcid.org/0000-0002-1556-9932; Bruinsma, Wessel P.; Markou, Stratis; Requeima, James; Coca-Castro, Alejandro; Vaughan, Anna; Ellis, Anna-Louise; Lazzara, Matthew A.; Jones, Dani ORCID: https://orcid.org/0000-0002-8701-4506; Hosking, Scott ORCID: https://orcid.org/0000-0002-3646-3504; Turner, Richard E.. 2023 Environmental sensor placement with convolutional Gaussian neural processes. Environmental Data Science, 2, e32. 16, pp. https://doi.org/10.1017/eds.2023.22

Before downloading, please read NORA policies.

Preview

Text (Open Access) © The Author(s), 2023. Published by Cambridge University Press. environmental-sensor-placement-with-convolutional-gaussian-neural-processes.pdf - Published Version Available under License Creative Commons Attribution 4.0. Download (3MB) | Preview

Abstract/Summary

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.

Item Type:	Publication - Article
Digital Object Identifier (DOI):	https://doi.org/10.1017/eds.2023.22
ISSN:	2634-4602
Additional Keywords:	active learning; meta-learning; neural processes; sensor placement
Date made live:	19 Feb 2024 09:43 +0 (UTC)
URI:	https://nora.nerc.ac.uk/id/eprint/536929

Actions (login required)

View Item

Document Downloads

More statistics for this item...