Water Stress on U.S. Power Production at Decadal Time Horizons

Ganguli, Poulomi; Kumar, Dheeraj; Yun, Ji Hyun; Short, Geoffrey; Klausner, James F.; Ganguly, Arnab

doi:10.2172/1339441

Cited by 2 publications

(2 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Key infrastructure allowing society to function, including power plants and transportation systems, are built to sustain specific levels of climate extremes and perform optimally in it's expected climate. Studies have shown that the changing climate has had, and will continue to have, significant impacts on critical infrastructure [13,31]. Furthermore, climate change is having dramatic negative effects to ecosystems, from aquatic species to forests ecosystems, caused by increases in greenhouse gases and temperatures [43,32,20].…”

Section: Introductionmentioning

confidence: 99%

Intercomparison of machine learning methods for statistical downscaling: the case of daily and extreme precipitation

Vandal

Kodra²,

Ganguly

2018

Theor Appl Climatol

Self Cite

137

102

View full text Add to dashboard Cite

Statistical downscaling of global climate models (GCMs) allows researchers to study local climate change effects decades into the future. A wide range of statistical models have been applied to downscaling GCMs but recent advances in machine learning have not been explored. In this paper, we compare four fundamental statistical methods, Bias Correction Spatial Disaggregation (BCSD), Ordinary Least Squares, Elastic-Net, and Support Vector Machine, with three more advanced machine learning methods, Multi-task Sparse Structure Learning (MSSL), BCSD coupled with MSSL, and Convolutional Neural Networks to downscale daily precipitation in the Northeast United States. Metrics to evaluate of each method's ability to capture daily anomalies, large scale climate shifts, and extremes are analyzed. We find that linear methods, led by BCSD, consistently outperform non-linear approaches. The direct application of stateof-the-art machine learning methods to statistical downscaling does not provide improvements over simpler, longstanding approaches. * vandal.t@husky.neu.edu † evan.kodra@risq.io ‡ a.ganguly@neu.edu limiting models to coarse spatial and temporal scale projections. While the coarse scale projections are useful in understanding climate change at a global and continental level, regional and local understanding is limited. Most often, the critical systems society depends on exist at the regional and local scale, where projections are most limited. Downscaling techniques are applied to provide climate projections at finer spatial scales, exploiting GCMs to build higher resolution outputs. Statistical and dynamical are the two classes of techniques used for downscaling. The statistical downscaling (SD) approach aims to learn a statistical relationship between coarse scale climate variables (ie. GCMs) and high resolution observations. The other approach, dynamical downscaling, joins the coarse grid GCM projections with known local and regional processes to build Regional Climate Models (RCMs). RCMs are unable to generalize from one region to another as the parameters and physical processes are tuned to specific regions. Though RCMs are useful for hypothesis testing, their lack of generality across regions and extensive computational resources required are strong disadvantages.

show abstract

Section: Introductionmentioning

confidence: 99%

Intercomparison of machine learning methods for statistical downscaling: the case of daily and extreme precipitation

Vandal

Kodra²,

Ganguly

2018

Theor Appl Climatol

Self Cite

137

102

View full text Add to dashboard Cite

show abstract

“…Key infrastructure allowing society to function, including power plants and transportation systems, are built to sustain specific levels of climate extremes and perform optimally in it's expected climate. Studies have shown that the changing climate has had, and will continue to have, significant impacts on critical infrastructure [35,87]. Furthermore, climate change is having dramatic negative effects to ecosystems, from aquatic species to forests ecosystems, caused by increases in greenhouse gases and temperatures [118,88,44].…”

Section: Introductionmentioning

confidence: 99%

Statistical downscaling of global climate models with image super-resolution and uncertainty quantification

Vandal¹

View full text Add to dashboard Cite

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 intense, longer duration, and more frequent extreme weather events. General circulation models (GCMs) provide us with the data to study climate change at the continental spatial scales, but are too coarse for local adaption. Furthermore, ensembles of multiple models, initial conditions, and emission trajectories must be harnessed for well quantified probabilistic estimates. Statistical downscaling, an approach that learns a functional mapping between low-and high-resolution GCMs, can be used to generate high-resolution ensemble projections in a computationally efficient manner. However, this process exacerbates, at a local scale, uncertainties inherently found in GCMs. Hence, it is crucial for our statistical downscaling methods to incorporate and quantify uncertainties, including both epistemic, or parameter misunderstanding, and aleatoric, or observational, uncertainties. In this work, we present a Bayesian deep learning and image super-resolution approach for statistical downscaling using discrete-continuous and non-normal likelihoods. Promising results for downscaling daily precipitation in the contiguous United States measured on predictive accuracy and uncertainty quantification are presented. Future work on stacking Bayesian deep learning networks and harnessing ensembles of high-resolution GCMs is discussed.iii ACKNOWLEDGMENTS It is my pleasure to thank the many people who have guided and helped me through the PhD process. Firstly, I'd like to thank my wife Amanda Mercer for being my rock as well as my parents Ann and James Vandal and sister Jessica Vandal for their continued support.

show abstract

Water Stress on U.S. Power Production at Decadal Time Horizons

Cited by 2 publications

References 64 publications

Intercomparison of machine learning methods for statistical downscaling: the case of daily and extreme precipitation

Intercomparison of machine learning methods for statistical downscaling: the case of daily and extreme precipitation

Statistical downscaling of global climate models with image super-resolution and uncertainty quantification

Contact Info

Product

Resources

About