发表机构
Helmholtz-Zentrum Hereon; Institute of Coastal Systems - Analysis and Modeling（亥姆霍兹中心黑尔戈兰研究所; 海岸系统分析与建模研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ADDA是基于PyTorch实现的模块化端到端可微数据同化框架，支持多种网格、并行计算与自动微分，兼容JAX，含10种动力学系统实现，用于解决DA跨算法与系统比较的挑战。
AI 中文摘要
数据同化（DA）是地球科学中用于预测和理解的重要工具，它将代表科学知识的模拟程序与约束系统动力学的观测结果相结合，生成融合了知识与数据的分析结果和预报。DA任务可通过多样的工具集解决，包括变分法、集合法和基于学习的方法，尤其近年来许多研究提出使用自动微分工具实现变分、基于学习或混合方法。然而，由于模拟与同化代码不兼容、时空离散化处理不灵活、DA方法针对特定模拟的专业化，以及模拟中自动微分和并行计算支持有限，跨算法和动力学系统的全面比较仍具挑战性。为应对该挑战，我们引入Automatic Differentiation for Data Assimilation（ADDA，即数据同化自动微分框架），这是一个用于定义和处理系统状态、模拟、观测方案及DA方法的软件框架。ADDA提供强大且灵活的基类集合，用于表示动力学系统和观测算子，支持共置与交错网格、非结构化网格、拉格朗日状态变量，以及不规则或连续时间观测。并行处理和可微性是其一级特性，全程支持批次轴和自动微分。ADDA基于PyTorch库实现，但支持对基于JAX的动力学及其梯度的DA计算。为展示其特性，我们还提供10种不同维度和规模的动力学系统的可微、ADDA兼容实现，基于这些系统设计了多个说明性DA示例，所有代码已公开于此httpsURL。
英文摘要
Data assimilation (DA) is an essential tool for prediction and understanding in the geosciences. DA combines simulation programs representing scientific knowledge with observations that constrain system dynamics, resulting in analyses and forecasts that incorporate both knowledge and data. DA tasks can be addressed with a diverse toolset, including variational, ensemble and learning-based methods. In particular, many recent works have proposed using automatic differentiation tools for variational, learning-based or hybrid methods. However, comprehensive comparisons across algorithms and dynamical systems remain challenging, due to the incompatibility of simulation and assimilation codes, inflexible handling of spatial and temporal discretizations, specialization of DA methods to specific simulations, and limited support for automatic differentiation and parallel computation in simulations. To address this challenge, we introduce Automatic Differentiation for Data Assimilation (ADDA), a software framework for defining and working with system states, simulations, observation schemes and DA methods. ADDA provides a powerful and flexible set of base classes for representing dynamical systems and observation operators, with support for collocated and staggered grids, unstructured meshes, Lagrangian state variables and irregular or continuous-time observations. Parallel processing and differentiability are first-class features, with support for batch axes and automatic differentiation throughout. ADDA is implemented in PyTorch library, but supports DA for JAX-based computation of dynamics and their gradients. To demonstrate its features, we further provide differentiable, ADDA-compatible implementations of 10 dynamical systems of various dimensionalities and scales, from which we design multiple illustrative DA examples. All of our code is publicly available at https://github.com/m-dml/ADDA.
