Subgrid parameterizations, which represent physical processes occurring below the resolu- tion of current climate models, are an important component in producing accurate, long-term predictions for the climate. A variety of approaches have been tested to design these com- ponents, including deep learning methods. In this work, we evaluate a proof of concept illustrating a multiscale approach to this prediction problem. We train neural networks to predict subgrid forcing values on a testbed model and examine improvements in prediction accuracy that can be obtained by using additional information in both fine-to-coarse and coarse-to-fine directions.
more »
« less
The high-frequency and rare events barriers to neural closures of atmospheric dynamics
Recent years have seen a surge in interest for leveraging neural networks to parameterize small-scale or fast processes in climate and turbulence models. In this short paper, we point out two fundamental issues in this endeavor. The first concerns the difficulties neural networks may experience in capturing rare events due to limitations in how data is sampled. The second arises from the inherent multiscale nature of these systems. They combine high-frequency components (like inertia-gravity waves) with slower, evolving processes (geostrophic motion). This multiscale nature creates a significant hurdle for neural network closures. To illustrate these challenges, we focus on the atmospheric 1980 Lorenz model, a simplified version of the Primitive Equations that drive climate models. This model serves as a compelling example because it captures the essence of these difficulties.
more » « less- Award ID(s):
- 2108856
- NSF-PAR ID:
- 10501788
- Publisher / Repository:
- IOP Publishing
- Date Published:
- Journal Name:
- Journal of Physics: Complexity
- Volume:
- 5
- Issue:
- 2
- ISSN:
- 2632-072X
- Format(s):
- Medium: X Size: Article No. 025004
- Size(s):
- Article No. 025004
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
Abstract Climate models are essential to understand and project climate change, yet long‐standing biases and uncertainties in their projections remain. This is largely associated with the representation of subgrid‐scale processes, particularly clouds and convection. Deep learning can learn these subgrid‐scale processes from computationally expensive storm‐resolving models while retaining many features at a fraction of computational cost. Yet, climate simulations with embedded neural network parameterizations are still challenging and highly depend on the deep learning solution. This is likely associated with spurious non‐physical correlations learned by the neural networks due to the complexity of the physical dynamical system. Here, we show that the combination of causality with deep learning helps removing spurious correlations and optimizing the neural network algorithm. To resolve this, we apply a causal discovery method to unveil causal drivers in the set of input predictors of atmospheric subgrid‐scale processes of a superparameterized climate model in which deep convection is explicitly resolved. The resulting causally‐informed neural networks are coupled to the climate model, hence, replacing the superparameterization and radiation scheme. We show that the climate simulations with causally‐informed neural network parameterizations retain many convection‐related properties and accurately generate the climate of the original high‐resolution climate model, while retaining similar generalization capabilities to unseen climates compared to the non‐causal approach. The combination of causal discovery and deep learning is a new and promising approach that leads to stable and more trustworthy climate simulations and paves the way toward more physically‐based causal deep learning approaches also in other scientific disciplines.
-
more » « less
Abstract Assessing forced climate change requires the extraction of the forced signal from the background of climate noise. Traditionally, tools for extracting forced climate change signals have focused on one atmospheric variable at a time, however, using multiple variables can reduce noise and allow for easier detection of the forced response. Following previous work, we train artificial neural networks to predict the year of single‐ and multi‐variable maps from forced climate model simulations. To perform this task, the neural networks learn patterns that allow them to discriminate between maps from different years—that is, the neural networks learn the patterns of the forced signal amidst the shroud of internal variability and climate model disagreement. When presented with combined input fields (multiple seasons, variables, or both), the neural networks are able to detect the signal of forced change earlier than when given single fields alone by utilizing complex, nonlinear relationships between multiple variables and seasons. We use layer‐wise relevance propagation, a neural network explainability tool, to identify the multivariate patterns learned by the neural networks that serve as reliable indicators of the forced response. These “indicator patterns” vary in time and between climate models, providing a template for investigating inter‐model differences in the time evolution of the forced response. This work demonstrates how neural networks and their explainability tools can be harnessed to identify patterns of the forced signal within combined fields.
-
more » « less
Abstract Stochastic parameterizations account for uncertainty in the representation of unresolved subgrid processes by sampling from the distribution of possible subgrid forcings. Some existing stochastic parameterizations utilize data‐driven approaches to characterize uncertainty, but these approaches require significant structural assumptions that can limit their scalability. Machine learning models, including neural networks, are able to represent a wide range of distributions and build optimized mappings between a large number of inputs and subgrid forcings. Recent research on machine learning parameterizations has focused only on deterministic parameterizations. In this study, we develop a stochastic parameterization using the generative adversarial network (GAN) machine learning framework. The GAN stochastic parameterization is trained and evaluated on output from the Lorenz '96 model, which is a common baseline model for evaluating both parameterization and data assimilation techniques. We evaluate different ways of characterizing the input noise for the model and perform model runs with the GAN parameterization at weather and climate time scales. Some of the GAN configurations perform better than a baseline bespoke parameterization at both time scales, and the networks closely reproduce the spatiotemporal correlations and regimes of the Lorenz '96 system. We also find that, in general, those models which produce skillful forecasts are also associated with the best climate simulations.
-
more » « less
Summary Leaf vein network geometry can predict levels of resource transport, defence and mechanical support that operate at different spatial scales. However, it is challenging to quantify network architecture across scales due to the difficulties both in segmenting networks from images and in extracting multiscale statistics from subsequent network graph representations.
Here we developed deep learning algorithms using convolutional neural networks (CNNs) to automatically segment leaf vein networks. Thirty‐eight CNNs were trained on subsets of manually defined ground‐truth regions from >700 leaves representing 50 southeast Asian plant families. Ensembles of six independently trained CNNs were used to segment networks from larger leaf regions (
c . 100 mm2). Segmented networks were analysed using hierarchical loop decomposition to extract a range of statistics describing scale transitions in vein and areole geometry.The CNN approach gave a precision‐recall harmonic mean of 94.5% ± 6%, outperforming other current network extraction methods, and accurately described the widths, angles and connectivity of veins. Multiscale statistics then enabled the identification of previously undescribed variation in network architecture across species.
We provide a
LeafVeinCNN software package to enable multiscale quantification of leaf vein networks, facilitating the comparison across species and the exploration of the functional significance of different leaf vein architectures.
