DeepSD: Generating High Resolution Climate Change Projections through Single Image Super-Resolution

@article{Vandal2017DeepSDGH,
  title={DeepSD: Generating High Resolution Climate Change Projections through Single Image Super-Resolution},
  author={Thomas J. Vandal and Evan Kodra and Sangram Ganguly and Andrew R. Michaelis and Ramakrishna R. Nemani and Auroop Ratan Ganguly},
  journal={Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
  year={2017}
}
  • T. Vandal, E. Kodra, A. Ganguly
  • Published 9 March 2017
  • Environmental Science
  • Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
The impacts of climate change are felt by most critical systems, such as infrastructure, ecological systems, and power-plants. However, contemporary Earth System Models (ESM) are run at spatial resolutions too coarse for assessing effects this localized. Local scale projections can be obtained using statistical downscaling, a technique which uses historical climate observations to learn a low-resolution to high-resolution mapping. Depending on statistical modeling choices, downscaled… 

Figures and Tables from this paper

Augmented Convolutional LSTMs for Generation of High-Resolution Climate Change Projections
TLDR
This work presents auxiliary variables informed spatio-temporal neural architecture for statistical downscaling of precipitation variable over one of the most climatically diversified countries, India and showcases significant improvement gain against two popular state-of-the-art baselines with better ability to predict statistics of extreme events.
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
ClimAlign: Unsupervised statistical downscaling of climate variables via normalizing flows
TLDR
ClimAlign is presented, a novel method for unsupervised, generative downscaling using adaptations of recent work in normalizing flows for variational inference, and one of very few proposed methods that allows for efficient sampling of synthetic data.
Convolutional conditional neural processes for local climate downscaling
TLDR
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.
Deep learning–based downscaling of summer monsoon rainfall data over Indian region
Downscaling is necessary to generate high-resolution observation data to validate the climate model forecast or monitor rainfall at the micro-regional level operationally. Available observations
Deep Neural Networks for Statistical Downscaling of Climate Change Projections 1
Global Climate Models (GCMs) are the main tool to predict the future evolution of the atmosphere at different time scales, from weather forecast (for the next few days) to climate change projections
Deep Learning Approaches to Spatial Downscaling of GRACE Terrestrial Water Storage Products Using EALCO Model Over Canada
Abstract Estimating terrestrial water storage (TWS) with high spatial resolution is crucial for hydrological and water resource management. Comparing to traditional in-situ data measurement,
ResLap: Generating High-Resolution Climate Prediction Through Image Super-Resolution
TLDR
ResLap is a spatial downscaling method that converts low spatial resolution climate data into high-resolution regional climate forecasts and introduces a novel residual dense block (RDB) into the Laplacian pyramid super-resolution network (LapSRN).
Downscaling Numerical Weather Models with GANs
TLDR
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.
TRU-NET: A Deep Learning Approach to High Resolution Prediction of Rainfall
TLDR
TRU-NET (Temporal Recurrent U-Net), an encoder-decoder model featuring a novel 2D cross attention mechanism between contiguous convolutional-recurrent layers to effectively model multi-scale spatio-temporal weather processes and shows that there is enough data for the deep learning approach to output robust, high-quality results across seasons and varying regions.
...
...

References

SHOWING 1-10 OF 58 REFERENCES
Comparison of SDSM and LARS-WG for simulation and downscaling of extreme precipitation events in a watershed
Future climate projections of Global Climate Models (GCMs) under different emission scenarios are usually used for developing climate change mitigation and adaptation strategies. However, the
Utility of daily vs. monthly large-scale climate data: an intercomparison of two statistical downscaling methods
Downscaling of climate model data is essential to local and regional impact analysis. We compare two meth- ods of statistical downscaling to produce continuous, grid- ded time series of precipitation
Automated regression-based statistical downscaling tool
Expanded downscaling for generating local weather scenarios
In an attempt to reconcile the capabilities of statistical downscaling and the demands of ecosystem modeling, the technique of expanded downscaling is introduced. Aimed at use in ecosystem models,
Statistical Downscaling Using Localized Constructed Analogs (LOCA)
AbstractA new technique for statistically downscaling climate model simulations of daily temperature and precipitation is introduced and demonstrated over the western United States. The localized
An asynchronous regional regression model for statistical downscaling of daily climate variables
The asynchronous regional regression model (ARRM) is a flexible and computationally efficient statistical model that can downscale station‐based or gridded daily values of any variable that can be
Credibility of statistical downscaling under nonstationary climate
Statistical downscaling (SD) establishes empirical relationships between coarse-resolution climate model simulations with higher-resolution climate variables of interest to stakeholders. These
Fast and accurate image upscaling with super-resolution forests
TLDR
This paper shows the close relation of previous work on single image super-resolution to locally linear regression and demonstrates how random forests nicely fit into this framework, and proposes to directly map from low to high-resolution patches using random forests.
SVM-PGSL coupled approach for statistical downscaling to predict rainfall from GCM output
TLDR
The results obtained from the proposed model are compared with earlier developed SVM-based downscaling models, and improved performance is observed.
Physiographically sensitive mapping of climatological temperature and precipitation across the conterminous United States
Spatial climate data sets of 1971–2000 mean monthly precipitation and minimum and maximum temperature were developed for the conterminous United States. These 30‐arcsec (∼800‐m) grids are the
...
...