ClimAlign: Unsupervised statistical downscaling of climate variables via normalizing flows

  title={ClimAlign: Unsupervised statistical downscaling of climate variables via normalizing flows},
  author={Brian Groenke and Luke E. Madaus and Claire Monteleoni},
  journal={Proceedings of the 10th International Conference on Climate Informatics},
Downscaling is a common task in climate science and meteorology in which the goal is to use coarse scale, spatio-temporal data to infer values at finer scales. Statistical downscaling aims to approximate this task using statistical patterns gleaned from an existing dataset of downscaled values, often obtained from observations or physical models. In this work, we investigate the application of domain alignment to the task of statistical downscaling. We present ClimAlign, a novel method for… 

Figures and Tables from this paper

Convolutional conditional neural processes for local climate downscaling
Abstract. A new model is presented for multisite statistical downscaling of temperature and precipitation using convolutional conditional neural processes (convCNPs). ConvCNPs are a recently
Convolutional conditional neural processes for local climate downscaling
The convCNP model is shown to outperform an ensemble of existing downscaling techniques over Europe for both temperature and precipitation taken from the VALUE intercomparison project, and substantial improvement is seen in the representation of extreme precipitation events.
RainNet: A Large-Scale Dataset for Spatial Precipitation Downscaling
This work presents the first \textbf{REAL} (non-simulated) Large-Scale Spatial Precipitation Downscaling Dataset, which contains 62,424 pairs of low-resolution and high-resolution precipitation maps for 17 years, and proposes an implicit physical estimation framework to learn the above characteristics.
DL4DS -- Deep Learning for empirical DownScaling
DL4DS has been designed with the goal of providing a general framework for training convolutional neural networks with configurable architectures and learning strategies to facilitate the conduction of comparative and ablation studies in a robust way and is presented as the first open-source library with state-of-the-art and novel deep learning algorithms for empirical downscaling.
Downscaled hyper-resolution (400 m) gridded datasets of daily precipitation and temperature (2008-2019) for East Taylor subbasin (western United States)
. High resolution gridded datasets of meteorological variables are needed in order to resolve fine-scale hydrological gradients in complex mountainous terrain. Across the United States, the highest
Increasing the accuracy and resolution of precipitation forecasts using deep generative models
Accurately forecasting extreme rainfall is notoriously difficult, but is also ever more crucial for society as climate change increases the frequency of such extremes. Global numerical weather
Deconditional Downscaling with Gaussian Processes
This work introduces conditional mean process (CMP), a new class of Gaussian Processes describing conditional means, and demonstrates its proficiency in a synthetic and a real-world atmospheric field downscaling problem, showing substantial improvements over existing methods.
Multivariate climate downscaling with latent neural processes
Statistical downscaling is a vital tool in generating high resolution projections for climate impact studies. This study applies convolutional latent neural processes to multivariate downscaling of
AtmoDist: Self-supervised Representation Learning for Atmospheric Dynamics
This work trains a neural network on the simple yet intricate task of predicting the temporal distance between atmospheric fields, e.g. the components of the wind field, from distinct but nearby times and introduces a data-driven distance metric for atmospheric states based on representations learned from ERA5 reanalysis.
Physics-informed machine learning: case studies for weather and climate modelling
This work surveys systematic approaches to incorporating physics and domain knowledge into ML models and distill these approaches into broad categories, and shows how these approaches have been used successfully for emulating, downscaling, and forecasting weather and climate processes.


DeepSD: Generating High Resolution Climate Change Projections through Single Image Super-Resolution
DeepSD is presented, a generalized stacked super resolution convolutional neural network (SRCNN) framework for statistical downscaling of climate variables and augments SRCNN with multi-scale input channels to maximize predictability in statisticalDownscaling.
Statistical downscaling of global climate models with image super-resolution and uncertainty quantification
High-resolution probabilistic projections of precipitation and temperature under climate change are crucial for stakeholders to make well-informed decisions in mitigating and adapting to more
Intercomparison of machine learning methods for statistical downscaling: the case of daily and extreme precipitation
The direct application of state-of-the-art machine learning methods to statistical downscaling does not provide direct improvements over simpler, longstanding approaches and results suggest that L1 sparsity constraints aid in reducing error through internal feature selection.
Downscaling Numerical Weather Models with GANs
This work uses ESRGAN to learn to downscale wind speeds by a factor of 4 from a coarse grid and finds that it can recover spatial details with higher fidelity than bicubic upsampling or SR-CNN, consistent with the observation that the generated images are of superior visual quality compared withSR-CNN.
Downscaling Extremes—An Intercomparison of Multiple Statistical Methods for Present Climate
AbstractFive statistical downscaling methods [automated regression-based statistical downscaling (ASD), bias correction spatial disaggregation (BCSD), quantile regression neural networks (QRNN),
Configuration and Intercomparison of Deep Learning Neural Models for Statistical Downscaling
A comprehensive assessment of deep learning techniques for continental-scale statistical downscaling, building on the VALUE validation framework, shows that, whilst the added value of CNNs is mostly limited to the reproduction of extremes for temperature, these techniques do outperform the classic ones for the case of precipitation for most aspects considered.
Statistical downscaling of precipitation using machine learning techniques
Statistical downscaling of general circulation model output: A comparison of methods
A range of different statistical downscaling models was calibrated using both observed and general circulation model (GCM) generated daily precipitation time series and intercompared. The GCM used
Towards a more reliable historical reanalysis: Improvements for version 3 of the Twentieth Century Reanalysis system
Historical reanalyses that span more than a century are needed for a wide range of studies, from understanding large‐scale climate trends to diagnosing the impacts of individual historical extreme
Long‐range experimental hydrologic forecasting for the eastern United States
[1] We explore a strategy for long-range hydrologic forecasting that uses ensemble climate model forecasts as input to a macroscale hydrologic model to produce runoff and streamflow forecasts at