Modeling Global Surface Dust Deposition Using Physics-Informed Neural Networks

Abstract

Paleoclimatic measurements serve to understand Earth System processes and evaluate climate model performances. However, their spatial coverage is generally sparse and unevenly distributed across the globe. Statistical interpolation methods are the prevalent techniques to grid such data, but these purely data-driven approaches sometimes produce results that are incoherent with our knowledge of the physical world. Physics-Informed Neural Networks (PINNs) follow an innovative approach to data analysis and physical modeling through machine learning, as they incorporate physical principles into the data-driven learning process. Here, we develop PINNs to reconstruct global maps of atmospheric dust surface deposition fluxes from measurement data in paleoclimatic archives for the Holocene and Last Glacial Maximum periods. We design an advection-diffusion equation to consider dominant wind directions at various latitudes, which prevents dust particles from flowing upwind. Our PINN improves on standard kriging interpolation by allowing variable asymmetry around data points. The reconstructions display realistic dust plumes from continental sources towards ocean basins following prevailing winds.

References in corpus (12)

• NSFnets (Navier-Stokes Flow nets): Physics-informed neural networks for the incompressible Navier-Stokes equations
• B-PINNs: Bayesian Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Noisy Data
• Machine learning in cardiovascular flows modeling: Predicting arterial blood pressure from non-invasive 4D flow MRI data using physics-informed neural networks
• Physics-informed Neural Networks (PINNs) for Wave Propagation and Full Waveform Inversions
• Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
• Flow over an espresso cup: Inferring 3D velocity and pressure fields from tomographic background oriented schlieren videos via physics-informed neural networks
• Physics-informed graph neural Galerkin networks: A unified framework for solving PDE-governed forward and inverse problems
• Bayesian Physics-Informed Neural Networks for real-world nonlinear dynamical systems
• Physics-Informed Neural Network Method for Forward and Backward Advection-Dispersion Equations
• HypoSVI: Hypocenter inversion with Stein variational inference and Physics Informed Neural Networks
• Towards a Collective Agenda on AI for Earth Science Data Analysis
• Digital Twin Earth -- Coasts: Developing a fast and physics-informed surrogate model for coastal floods via neural operators