A novel approach for statistical downscaling of future precipitation over the Indo-Gangetic Basin

Chaudhuri, Chiranjib; Srivastava, Rajesh

doi:10.1016/j.jhydrol.2017.01.024

Cited by 12 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the 1st alternative network traditional mean absolute error has been used to train the generator instead of a combination of loss applied in the CliGAN. We also trained a second alternative model inspired by [2]. In this model, the first 10 principal components with the largest eigenvalues from each of the nine climate models are mapped to the 20 principal components (~99% variance explained) of the observation using a single layer neural network.…”

Section: Training Detailsmentioning

confidence: 99%

“…Despite over twenty years of studies developing statistical downscaling methodologies, there remains a lack of methods that can downscale from AOGCM precipitation to regional level high resolution gridded precipitation [1,2]. Compared to other climate variables, such as temperature or barometric pressure, precipitation is more fragmented in space, and interactions of different atmospheric scales (local, meso, synoptic) and terrestrial features are more apparent in observed precipitation patterns.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

CliGAN: A Structurally Sensitive Convolutional Neural Network Model for Statistical Downscaling of Precipitation from Multi-Model Ensembles

Chaudhuri

Robertson

2020

Water

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Training Detailsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

CliGAN: A Structurally Sensitive Convolutional Neural Network Model for Statistical Downscaling of Precipitation from Multi-Model Ensembles

Chaudhuri

Robertson

2020

Water

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the 1 st alternative network traditional mean absolute error has been used to train the generator instead of combination of loss applied in the CliGAN. We also trained a 2 nd alternative model inspired from the Chaudhuri et. al.…”

Section: Training Detailsmentioning

confidence: 99%

CliGAN: A Structurally Sensitive Convolutional Neural Network Model for Statistical Downscaling of Precipitation from Multi-Model Ensembles

Chaudhuri¹,

Robertson²

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Despite numerous studies in statistical downscaling methodology, 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.

show abstract

“…Thereafter, Lloyd et al [10], Duan et al [11], Park et al [12], and Fang et al [13] established a linear or exponential regression model between precipitation, NDVI, and digital elevation model (DEM) to achieve the spatial downscaling of TRMM. Later, the wavelet [14], multifractal [15], Bayesian model [16], area-to-point kriging (ATPK) [17][18][19][20][21], geographic weight regression methods (GWR) [18,[22][23][24][25][26], random forests (RF) method [5,27,28], support vector machine (SVM) [29], and artificial neural network method [30] were also introduced into the spatial downscaling of TRMM data by establishing a statistical relationship between TRMM data and environmental parameters, such as NDVI, DEM, latitude, longitude, slope, aspect, land surface temperature, and so on [31][32][33][34]. However, these spatial downscaling methods are only available on an annual scale, because environmental variables, such as vegetation and DEM, usually show a long-term distribution of precipitation.…”

Section: Introductionmentioning

confidence: 99%

A Temporal Disaggregation Approach for TRMM Monthly Precipitation Products Using AMSR2 Soil Moisture Data

Fan

Dong³

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

Accurate and spatially-distributed precipitation information is vital to the study of the regional hydrological cycle and water resources, as well as for environmental management. To provide high spatio-temporal resolution precipitation estimates over insufficient rain-gauge areas, great efforts have been taken in using the Normalized Difference Vegetation Index (NDVI) and other land surface variables to improve the spatial resolution of satellite precipitation datasets. However, the strong spatio-temporal heterogeneity of precipitation and the "hysteresis phenomenon" of the relationship between precipitation and vegetation has limited the application of these downscaling methods to high temporal resolutions. To overcome this limitation, a new temporal downscaling method was proposed in this study by introducing daily soil moisture data to explore the relationship between precipitation and the soil moisture increment index. The performance of this proposed temporal downscaling was assessed by downscaling the Tropical Rainfall Measuring Mission (TRMM) precipitation data from a monthly scale to a daily scale over the Hekouzhen to Tongguan of the Yellow River in 2013, and the downscaled daily precipitation datasets were validated with in-situ measurement from 23 rainfall observation stations. The validation results indicate that the downscaled daily precipitation agrees with the rain gauge observations, with a correlation coefficient of 0.59, a mean error range of 1.70 mm, and a root mean square error of 5.93 mm. In general, the monthly precipitation decomposition method proposed in this paper has combined the advantage of both microwave remote sensing products. It has acceptable precision and can generate precipitation on a diurnal scale. It is an important development in the field of using auxiliary data to perform temporal downscaling. Furthermore, this method also provides a reference example for the temporal downscaling of other low temporal resolution datasets.

show abstract

A novel approach for statistical downscaling of future precipitation over the Indo-Gangetic Basin

Cited by 12 publications

References 22 publications

CliGAN: A Structurally Sensitive Convolutional Neural Network Model for Statistical Downscaling of Precipitation from Multi-Model Ensembles

CliGAN: A Structurally Sensitive Convolutional Neural Network Model for Statistical Downscaling of Precipitation from Multi-Model Ensembles

CliGAN: A Structurally Sensitive Convolutional Neural Network Model for Statistical Downscaling of Precipitation from Multi-Model Ensembles

A Temporal Disaggregation Approach for TRMM Monthly Precipitation Products Using AMSR2 Soil Moisture Data

Contact Info

Product

Resources

About