Long-term stability and generalization of observationally-constrained stochastic data-driven models for geophysical turbulence
Long-term stability and generalization of observationally-constrained stochastic data-driven models for geophysical turbulence
复制标题
DOI：
10.1017/eds.2022.30
复制
发表时间：
2022-05
期刊：
影响因子：
--
通讯作者：
A. Chattopadhyay;Jaideep Pathak;Ebrahim Nabizadeh;W. Bhimji;P. Hassanzadeh
中科院分区：
文献类型：
--
作者：
A. Chattopadhyay;Jaideep Pathak;Ebrahim Nabizadeh;W. Bhimji;P. Hassanzadeh
近年来，人们对构建基于深度学习的完全数据驱动的天气预测模型的兴趣激增。这种深度学习模型，如果在观测数据上进行训练，可以减轻当前最先进的天气模型中的某些偏差，其中一些偏差源于亚网格尺度过程的不准确表示。然而，这些数据驱动的模型过于参数化，需要大量的训练数据，而这些数据可能无法从再分析（观测数据）产品中获得。此外，在现实场景中，使用数据驱动的天气模型开始预测的准确、无噪声的初始条件是不可用的。最后，确定性数据驱动的预测模型存在长期稳定性和非物理气候漂移的问题，这使得这些数据驱动的模型不适合计算气候统计数据。鉴于这些挑战，以前的研究试图在大量不完善的长期气候模型模拟上对基于深度学习的天气预报模型进行预训练，然后根据可用的观测数据对其进行重新训练。在这篇文章中，我们提出了一个基于卷积变分自编码器（VAE）的随机数据驱动模型，该模型在两层准地转流的不完美气候模型模拟上进行了预训练，并使用迁移学习在来自完美模拟的少量噪声观测上进行了重新训练。然后，这个重新训练的模型使用从完美模拟中采样的噪声初始条件进行随机预测。我们表明，我们基于集合的随机数据驱动模型在短期技能方面优于基于基线确定性编码器-解码器的卷积模型，同时在长期气候模拟中保持稳定，从而产生准确的气候学。
Abstract Recent years have seen a surge in interest in building deep learning-based fully data-driven models for weather prediction. Such deep learning models, if trained on observations can mitigate certain biases in current state-of-the-art weather models, some of which stem from inaccurate representation of subgrid-scale processes. However, these data-driven models, being over-parameterized, require a lot of training data which may not be available from reanalysis (observational data) products. Moreover, an accurate, noise-free, initial condition to start forecasting with a data-driven weather model is not available in realistic scenarios. Finally, deterministic data-driven forecasting models suffer from issues with long-term stability and unphysical climate drift, which makes these data-driven models unsuitable for computing climate statistics. Given these challenges, previous studies have tried to pre-train deep learning-based weather forecasting models on a large amount of imperfect long-term climate model simulations and then re-train them on available observational data. In this article, we propose a convolutional variational autoencoder (VAE)-based stochastic data-driven model that is pre-trained on an imperfect climate model simulation from a two-layer quasi-geostrophic flow and re-trained, using transfer learning, on a small number of noisy observations from a perfect simulation. This re-trained model then performs stochastic forecasting with a noisy initial condition sampled from the perfect simulation. We show that our ensemble-based stochastic data-driven model outperforms a baseline deterministic encoder–decoder-based convolutional model in terms of short-term skills, while remaining stable for long-term climate simulations yielding accurate climatology.