BALLAST: Bayesian Active Learning with Look-ahead Amendment for Sea-drifter Trajectories under Spatio-Temporal Vector Fields

Rui-Yang Zhang, Lachlan Astfalck, Edward Cripps, David S. Leslie, Henry Moss
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:154101-154124, 2026.

Abstract

We introduce a formal active learning methodology for guiding the placement of Lagrangian observers to infer time-dependent vector fields – a key task in oceanography, marine science, and ocean engineering – using a physics-informed spatio-temporal Gaussian process surrogate model. The majority of existing placement campaigns either follow standard ‘space-filling’ designs or relatively ad-hoc expert opinions. A key challenge to applying principled active learning in this setting is that Lagrangian observers are continuously advected through the vector field, so they make measurements at different locations and times. It is, therefore, important to consider the likely future trajectories of placed observers to account for the utility of candidate placement locations. To this end, we present BALLAST: Bayesian Active Learning with Look-ahead Amendment for Sea-drifter Trajectories. We observe noticeable benefits of BALLAST-aided sequential observer placement strategies on both synthetic and high-fidelity ocean current models. In addition, we developed a novel GP inference method – the Vanilla SPDE Exchange (VaSE) – to boost the GP posterior sampling efficiency, which is also of independent interest.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-zhang26b, title = {{BALLAST}: {B}ayesian Active Learning with Look-ahead Amendment for Sea-drifter Trajectories under Spatio-Temporal Vector Fields}, author = {Zhang, Rui-Yang and Astfalck, Lachlan and Cripps, Edward and Leslie, David S. and Moss, Henry}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {154101--154124}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/zhang26b/zhang26b.pdf}, url = {https://proceedings.mlr.press/v306/zhang26b.html}, abstract = {We introduce a formal active learning methodology for guiding the placement of Lagrangian observers to infer time-dependent vector fields – a key task in oceanography, marine science, and ocean engineering – using a physics-informed spatio-temporal Gaussian process surrogate model. The majority of existing placement campaigns either follow standard ‘space-filling’ designs or relatively ad-hoc expert opinions. A key challenge to applying principled active learning in this setting is that Lagrangian observers are continuously advected through the vector field, so they make measurements at different locations and times. It is, therefore, important to consider the likely future trajectories of placed observers to account for the utility of candidate placement locations. To this end, we present BALLAST: Bayesian Active Learning with Look-ahead Amendment for Sea-drifter Trajectories. We observe noticeable benefits of BALLAST-aided sequential observer placement strategies on both synthetic and high-fidelity ocean current models. In addition, we developed a novel GP inference method – the Vanilla SPDE Exchange (VaSE) – to boost the GP posterior sampling efficiency, which is also of independent interest.} }
Endnote
%0 Conference Paper %T BALLAST: Bayesian Active Learning with Look-ahead Amendment for Sea-drifter Trajectories under Spatio-Temporal Vector Fields %A Rui-Yang Zhang %A Lachlan Astfalck %A Edward Cripps %A David S. Leslie %A Henry Moss %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-zhang26b %I PMLR %P 154101--154124 %U https://proceedings.mlr.press/v306/zhang26b.html %V 306 %X We introduce a formal active learning methodology for guiding the placement of Lagrangian observers to infer time-dependent vector fields – a key task in oceanography, marine science, and ocean engineering – using a physics-informed spatio-temporal Gaussian process surrogate model. The majority of existing placement campaigns either follow standard ‘space-filling’ designs or relatively ad-hoc expert opinions. A key challenge to applying principled active learning in this setting is that Lagrangian observers are continuously advected through the vector field, so they make measurements at different locations and times. It is, therefore, important to consider the likely future trajectories of placed observers to account for the utility of candidate placement locations. To this end, we present BALLAST: Bayesian Active Learning with Look-ahead Amendment for Sea-drifter Trajectories. We observe noticeable benefits of BALLAST-aided sequential observer placement strategies on both synthetic and high-fidelity ocean current models. In addition, we developed a novel GP inference method – the Vanilla SPDE Exchange (VaSE) – to boost the GP posterior sampling efficiency, which is also of independent interest.
APA
Zhang, R., Astfalck, L., Cripps, E., Leslie, D.S. & Moss, H.. (2026). BALLAST: Bayesian Active Learning with Look-ahead Amendment for Sea-drifter Trajectories under Spatio-Temporal Vector Fields. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:154101-154124 Available from https://proceedings.mlr.press/v306/zhang26b.html.

Related Material