Environmental Sensor Placement with Convolutional Gaussian Neural Processes
This work addresses the challenge of efficient sensor deployment for climate monitoring, offering a machine learning-based solution that could enhance environmental digital twins, though it is incremental as it builds on existing probabilistic models with neural network enhancements.
The paper tackled the problem of optimizing environmental sensor placement in remote regions like Antarctica by using a convolutional Gaussian neural process (ConvGNP) to capture complex non-stationary behavior and scale to large datasets, resulting in more informative sensor placements that outperformed Gaussian process baselines in simulated experiments.
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.