GeoSim: Benchmarking Multi-Field Neural Operators for Geodynamics
physics.geo-ph
Submitted: 2026-11-03
Updated: 2026-11-03
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
The gist: Learning reliable surrogates for geodynamic models requires benchmarks that resolve coupled fields and temporal stability.
Terminology
Abstract
Learning reliable surrogates for geodynamic models requires benchmarks that resolve coupled fields and temporal stability. We present GeoSim, a benchmark of high-resolution two-dimensional mantle-plume simulations generated with I2VIS, comprising 237 trajectories across two parameter regimes, with six coupled fields, physical timestamps, and trajectory-level splits. GeoSim defines short-window prediction and autonomous rollout, and evaluates representative neural operators field by field. Across models, we observe a pronounced scalar--velocity gap: scalar fields are reconstructed accurately while velocity errors remain large, and short-window accuracy does not imply stable rollout. We also evaluate MFGNO (Multi-Field Graph Neural Operator), a joint multi-field graph baseline designed for this benchmark; on GeoSim-Plume1, under a fixed per-field objective, it reduces horizontal and vertical velocity errors by 58.4% and 38.5% relative to an independent-field graph baseline, while an explicit field-difference input shows no measurable benefit at this scale. GeoSim provides a reproducible benchmark for field-wise diagnosis and long-horizon evaluation of geodynamic surrogates.
Sources
- Message Passing Neural PDE Solvers
- Eagle: Large-Scale Learning of Turbulent Fluid Dynamics with Mesh Transformers
- Fourier Neural Operator for Parametric Partial Differential Equations
- WeatherBench: A benchmark dataset for data-driven weather forecasting
Related papers
- Geometry-Aware Transformer for Five-Dimensional Seismic Noise Attenuation and First-Arrival Picking
- Generative deep learning improves reconstruction of global historical climate records
- Field-Deployable Hybrid Gravimetry: Projecting Absolute Accuracy Across a Remote 24km squared Survey via Daily Quantum Calibration
- Parameter-Efficient Transfer Learning for Microseismic Phase Picking Using a Neural Operator
- Scaling-law-informed neural point processes for earthquake sequence forecasting
- Supershear Rupture Indicator in Near-fault Particle Motion