<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="Chaudhuri-2020-CliGAN:">
    <titleInfo>
        <title>CliGAN: A Structurally Sensitive Convolutional Neural Network Model for Statistical Downscaling of Precipitation from Multi-Model Ensembles</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chiranjib</namePart>
        <namePart type="family">Chaudhuri</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Colin</namePart>
        <namePart type="family">Robertson</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Water, Volume 12, Issue 12</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MDPI AG</publisher>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Despite numerous studies in statistical downscaling methodologies, there remains a lack of methods that can downscale from precipitation modeled in global climate models to regional level high resolution gridded precipitation. This paper reports a novel downscaling method using a Generative Adversarial Network (GAN), CliGAN, which can downscale large-scale annual maximum precipitation given by simulation of multiple atmosphere-ocean global climate models (AOGCM) from Coupled Model Inter-comparison Project 6 (CMIP6) to regional-level gridded annual maximum precipitation data. This framework utilizes a convolution encoder-dense decoder network to create a generative network and a similar network to create a critic network. The model is trained using an adversarial training approach. The critic uses the Wasserstein distance loss function and the generator is trained using a combination of adversarial loss Wasserstein distance, structural loss with the multi-scale structural similarity index (MSSIM), and content loss with the Nash-Sutcliff Model Efficiency (NS). The MSSIM index allowed us to gain insight into the model’s regional characteristics and shows that relying exclusively on point-based error functions, widely used in statistical downscaling, may not be enough to reliably simulate regional precipitation characteristics. Further use of structural loss functions within CNN-based downscaling methods may lead to higher quality downscaled climate model products.</abstract>
    <identifier type="citekey">Chaudhuri-2020-CliGAN:</identifier>
    <identifier type="doi">10.3390/w12123353</identifier>
    <location>
        <url>https://gwf-uwaterloo.github.io/gwf-publications/G20-87001</url>
    </location>
    <part>
        <date>2020</date>
        <detail type="volume"><number>12</number></detail>
        <detail type="issue"><number>12</number></detail>
        <detail type="page"><number>3353</number></detail>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T CliGAN: A Structurally Sensitive Convolutional Neural Network Model for Statistical Downscaling of Precipitation from Multi-Model Ensembles
%A Chaudhuri, Chiranjib
%A Robertson, Colin
%J Water, Volume 12, Issue 12
%D 2020
%V 12
%N 12
%I MDPI AG
%F Chaudhuri-2020-CliGAN:
%X Despite numerous studies in statistical downscaling methodologies, there remains a lack of methods that can downscale from precipitation modeled in global climate models to regional level high resolution gridded precipitation. This paper reports a novel downscaling method using a Generative Adversarial Network (GAN), CliGAN, which can downscale large-scale annual maximum precipitation given by simulation of multiple atmosphere-ocean global climate models (AOGCM) from Coupled Model Inter-comparison Project 6 (CMIP6) to regional-level gridded annual maximum precipitation data. This framework utilizes a convolution encoder-dense decoder network to create a generative network and a similar network to create a critic network. The model is trained using an adversarial training approach. The critic uses the Wasserstein distance loss function and the generator is trained using a combination of adversarial loss Wasserstein distance, structural loss with the multi-scale structural similarity index (MSSIM), and content loss with the Nash-Sutcliff Model Efficiency (NS). The MSSIM index allowed us to gain insight into the model’s regional characteristics and shows that relying exclusively on point-based error functions, widely used in statistical downscaling, may not be enough to reliably simulate regional precipitation characteristics. Further use of structural loss functions within CNN-based downscaling methods may lead to higher quality downscaled climate model products.
%R 10.3390/w12123353
%U https://gwf-uwaterloo.github.io/gwf-publications/G20-87001
%U https://doi.org/10.3390/w12123353
%P 3353

Markdown (Informal)

[CliGAN: A Structurally Sensitive Convolutional Neural Network Model for Statistical Downscaling of Precipitation from Multi-Model Ensembles](https://gwf-uwaterloo.github.io/gwf-publications/G20-87001) (Chaudhuri & Robertson, GWF 2020)

• CliGAN: A Structurally Sensitive Convolutional Neural Network Model for Statistical Downscaling of Precipitation from Multi-Model Ensembles (Chaudhuri & Robertson, GWF 2020)

ACL

• Chiranjib Chaudhuri and Colin Robertson. 2020. CliGAN: A Structurally Sensitive Convolutional Neural Network Model for Statistical Downscaling of Precipitation from Multi-Model Ensembles. Water, Volume 12, Issue 12, 12(12):3353.