Statistical downscaling of precipitation and temperature using sparse Bayesian learning, multiple linear regression and genetic programming frameworks

Joshi, Deepti; St‐Hilaire, André; Ouarda, Taha B. M. J.; Daigle, Anik

doi:10.1080/07011784.2015.1089191

Cited by 20 publications

(8 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, with advancement of computational facilities, robust neural network-based techniques are gaining popularity for developing complex relationships between high-dimensional predictor and predictand data sets. The relevance vector machine (RVM)based downscaling approach has been considered in a few studies (Ghosh and Mujumdar 2008;Okkan and Inan 2015;Joshi et al 2015;Deo et al 2016) to downscale different hydroclimatological variables. The statistical framework of RVM is the same as that of the support vector machine algorithm; however, RVM considers an alternative functional algorithm that develops a probabilistic regression between the predictors and predictant.…”

Section: Resultsmentioning

confidence: 99%

New Approach to Multisite Downscaling of Precipitation by Identifying Different Set of Atmospheric Predictor Variables

2020

View full text Add to dashboard Cite

Estimating reliable projections of precipitation considering climate change scenarios is important for hydrological studies. General circulation models provide future climate simulations at large scale in terms of large-scale atmospheric variables (LSAVs). Those LSAVs can be downscaled to finer special resolution using several downscaling approaches. This paper presents a support vector regression (SVR)-based downscaling approach to downscale rainfall at several locations in a study area. Because the rainfall generation mechanisms cannot be the same for all the sites in a study area, conventional multisite downscaling approaches that assume the same rainfall generation mechanism should not be used. Therefore, a new downscaling approach is proposed that (1) divides the study area in several climatological regions, and (2) develops different downscaling models for each of the climatological regions to obtain future projections of rainfall. The new approach was implemented on rainfall data obtained for Republic of Ireland to demonstrate the effectiveness of the approach compared with existing approaches. Future projections of rainfall were obtained for the period 2012-2050 corresponding to four Representative Concentration Pathway climate change scenarios. The performance of the SVR approach was compared with that of relevance vector machine-and deep learning-based downscaling approaches.

show abstract

Section: Resultsmentioning

confidence: 99%

New Approach to Multisite Downscaling of Precipitation by Identifying Different Set of Atmospheric Predictor Variables

2020

View full text Add to dashboard Cite

show abstract

“…Many regression-based approaches have been widely used in statistical downscaling which includes Automated regression-based statistical downscaling (which classify the wet and nonwet days first and later apply regression techniques) [20][21][22][23][24], Linear regression and stepwise regression model ( they will estimate predictand by using an optimized linear combination of predictors) [25][26][27], Support vector machines and Relevance Vector Machine (In the SVM and RVM algorithms, I use kernel functions to map non-linear problems into linear problems in high dimensional space) [28][29][30][31][32][33][34][35], Bayesian model averaging [36][37][38][39][40][41][42], LSTM [70,71], DeepSD [tj's pap] (which tries to captures spatial correlations by using convolution neural network and elevation as bias. But in his study, he has taken input as downscaled observation instead of a GCM output.…”

Section: Related Workmentioning

confidence: 99%

Regional analysis of climate projections using Bias Corrected spatial disaggregated super-resolution convolutional neural networks

AWASTHI¹

2023

Preprint

View full text Add to dashboard Cite

Climate change is very crucial for ecological systems and society. But Global climate models run at coarse spatial resolution which is difficult to do regional analysis. Regional-scale projections can be obtained by a technique called statistical downscaling which uses past data to find out the high resolution and low-resolution mapping. There are many methods for statistical downscaling of climate data: 1) Conventional methods 2) Deep learning architecture. Some of the existing works like DeepSd downscaled High-resolution climate projections but in such cases, Global climate model (GCM) data suffers from concept drift, change of mapping between input and label over time. So applying these deep learning models is not a good idea for statistical downscaling. In my study, I have developed new approach of downscaling which outperforms other deep learning architectures like super-resolution convolutional neural network (SRCNN), Long short term memory network (LSTM) in terms of accuracy and reliability. These existing models focus on minimizing the root mean square error (RMSE ) and do not take care of the tails or extremes. Therefore the objective function of these models should be changed other than root mean square error (RMSE). My proposed model focuses on both means and extremes. I provide a comparison between proposed and other existing deep learning models in downscaling daily precipitation and temperature from 1.25 to 0.25 resolution over India. I have downscaled 6 Global climate model (GCM) models in our comparative study.

show abstract

“…These NCEP/NCAR data are the outputs of a GCM . In different studies, NCEP/NCAR reanalysis data were utilized for the calibration and validation of the downscaling models . These data represent the predictor set of some grid boxes close to the study region that contain the large‐scale input variable data.…”

Section: Introductionmentioning

confidence: 99%

Statistical downscaling of global climate model outputs to monthly precipitation via extreme learning machine: A case study

Alizamir

Moghadam

Monfared

et al. 2018

Env Prog and Sustain Energy

View full text Add to dashboard Cite

The present article explores the impacts of climate change on precipitation at station scale in the Minab basin, Iran. The data used for evaluation were large‐scale input (predictor) parameters extracted from the reanalysis data set of the National Center for Environmental Prediction and National Center for Atmospheric Research to downscale monthly precipitation. In this research, four approaches were applied to downscale precipitation, including an implementation on extreme learning machine (ELM) for single‐hidden layer feedforward neural network, artificial neural network, genetic programming, and quantile mapping. The results indicated that the ELM approach outperformed all other approaches in downscaling the large‐scale global climate model atmospheric variables to monthly precipitation at station scale. © 2018 American Institute of Chemical Engineers Environ Prog, 37: 1853–1862, 2018

show abstract

Statistical downscaling of precipitation and temperature using sparse Bayesian learning, multiple linear regression and genetic programming frameworks

Cited by 20 publications

References 42 publications

New Approach to Multisite Downscaling of Precipitation by Identifying Different Set of Atmospheric Predictor Variables

New Approach to Multisite Downscaling of Precipitation by Identifying Different Set of Atmospheric Predictor Variables

Regional analysis of climate projections using Bias Corrected spatial disaggregated super-resolution convolutional neural networks

Statistical downscaling of global climate model outputs to monthly precipitation via extreme learning machine: A case study

Contact Info

Product

Resources

About