Impact of geophysical fields on Deep Learning-based Lagrangian drift simulations

Daria Botvynko; Carlos Granero-Belinchon; Simon Van Gennip; Abdesslam Benzinou; Ronan Fablet

physics.ao-phMar 27, 2026

Impact of geophysical fields on Deep Learning-based Lagrangian drift simulations

Authors: Daria Botvynko, Carlos Granero-Belinchon, Simon Van Gennip, Abdesslam Benzinou, Ronan Fablet

Organizations: Lab-STICC_OSE, IMT Atlantique - MEE, IMT Atlantique · Lab-STICC, UMR CNRS 6285, IMT Atlantique, Odyssey, INRIA, Brest, France · ODYSSEY, IMT Atlantique - MEE, Lab-STICC_OSE · MOi ·

Abstract

We assess the influence of different Eulerian geophysical input fields on Lagrangian drift simulations using DriftNet, a learning-based method designed to simulate Lagrangian drift on the sea surface. Two experiments are conducted: a fully numerical experiment (Benchmark B1) and a real-world drifters-based experiment (Benchmark B2). Both experiments are performed in two regions with different ocean dynamics: North East Pacific and Gulf Stream regions. The performance of DrifNet is evaluated with three different metrics: separation distance between simulated and ground-truth trajectories, the normalized cumulative Lagrangian separation and the autocorrelation of Lagrangian velocities. In both regions, results from B1 show that combining assimilated sea surface currents (SSC) with fully observed sea surface height (SSH) leads to greatest improvement in trajectory simulation. This configuration reduces separation distance by over 50% and significantly decreases normalized cumulative Lagrangian separation and metrics related to velocities autocorrelation functions compared to the baseline using SSC alone. On the other hand, the inclusion of sea surface temperature (SST) either alone or in combination with SSC generally degrades performance. In B2, using satellite-derived SSH, Ekman and winds velocities improves surface drifters trajectories simulation, particularly in the North East Pacific. While the satellite-derived SST in combination with reanalysis-based SSC configuration leads to better trajectories simulation in the Gulf Stream. Overall, we highlight the added value of combining multiple geophysical fields to improve Lagrangian drift simulation on both numerical and real-world experiments.

Figures & tables

Figure 1: Training and evaluation procedures of multivariate DriftNet’s extension: the input geophysical fields $\mathbf{g}$ over 9 days (here zonal $\mathbf{U}$ and meridional $\mathbf{V}$ components of the velocity field, SST and SSH) coupled to the intial spatio-temporal positional encoding $\mathbf{y_{0}}$ are fed to the DriftNet in order for it to generate the target trajectories to be compared to the ground-truth ones. Once DriftNet is trained, those geophysical fields are then used as input to it in order to simulate Lagrangian trajectories which are then evaluated on the set of test trajectories using evaluation metrics described in Section 3.4 .

Name	Source	Variable	Period	Spatial resolution	Temporal resolution
E1	Nature Run ( Le Traon et al.,, 2019 )	SSC, SSH, SST	2015	1/12 ∘	1 day
E2	OSSE-based assimilated free run ( Verrier et al.,, 2017 ; Verrier et al.,, 2018 )	SSC	2015	1/12 ∘	1 day
E3	GLORYS12 ( Lellouche et al.,, 2021 )	SSC	1992 - 2020	1/12 ∘	1 day
E3	DUACS ( Pujol et al.,, 2016 )	SSH	1992 - 2020	1/8 ∘	1 day
E3	OSTIA ( Good et al.,, 2020 )	SST	1992 - 2020	1/20 ∘	1 day
E3	GLOBCURRENT ( Rio et al.,, 2014 )	Ekman	1992 - 2020	1/4 ∘	1 day

Table 1: Summary description of Eulerian datasets used in the current study: Source makes reference to the used numerical or satellite product, Variable indicates the physical quantity of interest, Period the studied years. The spatial and temporal resolutions of each product are also indicated. SSC - Sea Surface Currents. SSH - Sea Surface Height. SST - Sea Surface Temperature.

Figure 2: North East Pacific: SSC velocity in m/s, SST in ${}^{\circ}C$ , SSH in m, wind velocity in m/s, Ekman in m/s. Snapshot on 01/06/2015 12:00:00 UTC.

Figure 3: Gulf Stream: SSC velocity in m/s, SST in ${}^{\circ}C$ , SSH in m, wind velocity in m/s, Ekman component in m/s. Snapshot on 01/06/2015 12:00:00 UTC.

Name	Source	Variable	Period	Temporal
				resolution
L1	Ocean Parcels simulation using E1 SSC	Position	2015	6 hours
L2	Ocean Parcels simulation using E2 SSC	Position	2015	6 hours
L3	CMEMS drifters ( Etienne et al.,, 2023 )	Position	1992 - 2020	6 hours

Table 2: Summary description of Lagrangian datasets used in the current study: Source makes reference to the used numerical or satellite product, Variable indicates the physical quantity of interest, Period the studied years. The temporal resolution of each product is also indicated.

	North East Pacific				Gulf Stream
	$D$ , km	$\mathcal{L}_{Liu}$	$\Delta R_{\vec{u}}$	$\Delta R_{\vec{v}}$	$D$ , km	$\mathcal{L}_{Liu}$	$\Delta R_{\vec{u}}$	$\Delta R_{\vec{v}}$
L2	53.8	0.87	0.0086	0.016	168.3	0.75	0.01	0.02
SSC	45.4	0.70	0.12	0.12	154.6	0.63	0.16	0.14
SSH	31.2	0.32	0.06	0.07	160.3	0.70	0.07	0.06
SST	49.6	0.68	0.14	0.12	170.3	0.77	0.08	0.08
SSC, SSH	22.2	0.29	0.05	0.06	127.0	0.52	0.08	0.06

Table 3: Performance of DriftNet with different Eulerian geophysical input fields and Ocean Parcels (L2 dataset) in Benchmark B1 with respect to the reference trajectories (L1 dataset). We benchmark DriftNet scheme using as inputs data-assimilation-based SSC from dataset E2 and idealized ’fully observed’ SSH and SST fields from dataset E1. We illustrate performance in two study regions: North East Pacific and Gulf Stream. The evaluation metrics are the last time step mean separation distance (

D

), mean Liu index (

\mathcal{L}_{Liu}

) and error between autocorrelation functions of zonal and meridional components respectively (

\Delta R_{\vec{u}}

and

\Delta R_{\vec{v}}

). Bold indicates the best performance.

Panel of Figure 4 — Figure 4: Examples of simulated trajectories for Benchmark B1 : Panel (a) : North East Pacific, Panel (b) : Gulf Stream. The reference trajectories simulated with Ocean Parcels using Nature Run SSC L1, the baseline ones L2 simulated using SSC from OSSE. Eight randomly-selected trajectories are superimposed to the mean relative vorticity of the Nature Run SSC.

	North East Pacific				Gulf Stream
	$D$ , km	$\mathcal{L}_{Liu}$	$\Delta R_{\vec{u}}$	$\Delta R_{\vec{v}}$	$D$ , km	$\mathcal{L}_{Liu}$	$\Delta R_{\vec{u}}$	$\Delta R_{\vec{v}}$
SSC	62.4	0.55	0.05	0.03	118.4	0.6	0.08	0.08
SSC, SSH	60.2	0.52	0.03	0.03	122.4	0.61	0.03	0.03
SSC, SST	63.6	0.55	0.03	0.02	103.2	0.51	0.04	0.03
SSC, Wind	63.2	0.55	0.06	0.06	136.4	0.7	0.08	0.08
SSC, SSH, Winds	60.1	0.52	0.05	0.04	136.2	0.65	0.1	0.1

Table 4: Performance of DriftNet with different Eulerian geophysical input fields from remote sensing and reanalysis models with respect to the reference trajectories (L3 dataset) in Benchmark B2. We indicate the considered input data: SSC, namely the velocity fields U and V from the GLORYS12 reanalysis ( Lellouche et al.,, 2018 ) , complemented by satellite-derived optimally-interpolated SSH fields ( Pujol et al.,, 2016 ) , SST fields ( Good et al.,, 2020 ) , winds fields ( Dee et al.,, 2011 ) and Ekman ( Rio et al.,, 2014 ) . We report the performance metrics in the two study regions: North East Pacific and Gulf Stream. The evaluation metrics are the last time step mean separation distance (

D

), mean Liu index (

\mathcal{L}_{Liu}

) and mean absolute error between autocorrelation functions (

\Delta R_{\vec{u}}

and

\Delta R_{\vec{v}}

). Bold indicates the best performance.

Panel of Figure 5 — Figure 5: Examples of simulated trajectories for Benchmark B2 : Panel (a) : North East Pacific, Panel (b) : Gulf Stream. We depict real drifters trajectories in black (L3) and trajectories simulated with DriftNet using various input geophysical fields. Eight randomly-selected trajectories are superimposed to the mean relative vorticity of GLORYS12.

Trajectory Prediction

Trajectory prediction forecasts how people, vehicles, robots, and other dynamic systems will move from observed histories and context.

See all 187 papers

Drift Field Net: Learning Ocean Lagrangian advection fields from in-situ and satellite observations
Sep 14, 2026Théo Archambault, Pierre Garcia, Mattia Romero +2Physics-Informed ML Spatiotemporal Forecasting
Amphitrite, Paris, France · Sorbonne Université, LIP6, Pequan, Paris, France · The Ocean Cleanup, Rotterdam, Netherlands +1
Learning effective Sargassum transport dynamics from limited drifter observations
May 28, 2026F. J. Beron-VEra, M. J. Olascoaga, J. Morell +1Sparse Identification of Nonlinear Dynamics Nonlinear System Identification
Department of Atmospheric Sciences Rosenstiel School of Marine, Atmospheric, and Earth Science University of Miami Miami, Florida, USA · Department of Ocean Sciences Rosenstiel School of Marine, Atmospheric, and Earth Science University of Miami Miami, Florida, USA · Department of Marine Sciences University of Puerto Rico Mayagüez, Puerto Rico
Hybrid Lagrangian-Eulerian Model for Lagrangian Fluid Simulation
Aug 2, 2026Ruoyan Li, Wei Wang, Yizhou SunNeural PDE Solvers Computational Fluid Dynamics
University of California, Los Angeles

Sep 14, 2026J/K move · Enter open · S save

Drift Field Net: Learning Ocean Lagrangian advection fields from in-situ and satellite observations

Théo Archambault, Pierre Garcia, Mattia Romero, Anastase Charantonis+1

Amphitrite, Paris, France · Sorbonne Université, LIP6, Pequan, Paris, France · The Ocean Cleanup, Rotterdam, Netherlands+1

Physics-Informed ML Spatiotemporal Forecasting Trajectory Prediction

Open paper AskPDF arXiv

The North Pacific Subtropical Gyre (NPSG) is a major accumulation zone for floating plastic debris, resulting from basin-scale convergent ocean circulation. Effective cleanup strategies in this region rely on accurate forecasts of Lagrangian particle drift. Here, we introduce Drift Field Net (DFN), a deep neural network that predicts ocean surface flow fields from operational satellite observations. DFN is trained using a novel two-stage strategy that combines pretraining on simulated data with Lagrangian fine-tuning based on an advection-consistent loss function. This physics-informed optimization directly improves the accuracy of particle trajectory predictions. We evaluate DFN against an operational physics-based forecasting system and demonstrate the potential of deep learning for ocean surface flow prediction. On in situ drifter trajectories, DFN reduces the mean positioning error by 20 km after a 7-day forecast compared with the operational model. Furthermore, Lagrangian fine-tuning with the proposed advection loss further reduces the positioning error by 10 km, highlighting the benefits of incorporating Lagrangian constraints into the training process.

Abstract

Trajectory Prediction

Explore similar work

Drift Field Net: Learning Ocean Lagrangian advection fields from in-situ and satellite observations

Learning effective Sargassum transport dynamics from limited drifter observations

Hybrid Lagrangian-Eulerian Model for Lagrangian Fluid Simulation