Using Machine Learning to Cut the Cost of Dynamical Downscaling

Hobeichi, Sanaa; Nishant, Nidhi; Shao, Yawen; Abramowitz, Gab; Pitman, A. J.; Sherwood, Steven C.; Bishop, Craig H.; Green, Samuel

doi:10.1029/2022ef003291

Cited by 7 publications

(4 citation statements)

References 79 publications

(93 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In dynamic downscaling, physics‐based regional climate models, which incorporate topography, and land‐surface characteristics, are used to simulate data (Feser et al, 2011). Statistical downscaling approaches involve establishing a statistical relationship between variables simulated by the ESMs (predictors) and local‐scale observations or reanalysis (predictands) to correct ESM errors (Hobeichi et al, 2023). Compared with dynamic downscaling, statistical downscaling is more efficient and has proven to be effective in topographically complex terrain (Hanssen‐Bauer et al, 2005).…”

Section: Introductionmentioning

confidence: 99%

Triple coupling random forest approach for bias correction of ensemble precipitation data derived from Earth system models for Divandareh‐Bijar Basin (Western Iran)

Zebarjadian,

Dolatabadi,

Zahraie

et al. 2024

Intl Journal of Climatology

View full text Add to dashboard Cite

Climate change is expected to change the frequency, duration, intensity, and pattern of precipitation, underscoring the need for accurate predictive tools. Earth system models (ESMs) serve as invaluable instruments in this endeavour, simulating climate variable variations across temporal and spatial dimensions. This study aims to develop a methodology for generating precise daily precipitation maps by rectifying biases inherent in ESM outputs. The proposed methodology includes downscaling ESM outputs to simulate historical daily grid‐based precipitation, thereby enhancing the fidelity of daily precipitation representation. For this purpose, 14 models from the Coupled Model Intercomparison Project Phase 6 (CMIP6) were employed. Random forest (RF) machine learning method was used to correct biases in these ESM outputs. This study's novelty lies in integrating results of a grid‐based RF classification model, employed to distinguish between rainy and non‐rainy days, with those obtained by two RF regression models, to estimate precipitation amounts for grid cells receiving extreme and non‐extreme precipitation, to generate an ensemble of ESM outputs. The resulting method, termed the triple coupling method (EN‐RF), was validated using precipitation data from the Divandareh‐Bijar Basin in western Iran to simulate historical climate conditions. Furthermore, the accuracy of the developed triple coupling approach was compared with that of a commonly used single machine learning‐based downscaling model (EN‐Single‐RF). Comparative analysis against a commonly used single machine learning‐based downscaling model (EN‐Single‐RF) revealed the superior performance of the EN‐RF approach in replicating the intensity and distribution of daily precipitation. Furthermore, within the triple coupling framework, support vector machine (SVM) was utilized to simulate daily historical precipitation (EN‐SVM), while the quantile mapping (QM) method served as a benchmark. Comparison of the results showed superiority of the EN‐RF to other methods (EN‐Single‐RF, EN‐SVM, and QM) in terms of various accuracy metrics (Kling‐Gupta Efficiency = 0.95, mean square error = 0.22). The findings indicated the capability of the proposed triple coupling framework using the RF algorithm to simulate the spatio‐temporal distribution of precipitation using the ESM precipitation outputs. The developed framework can be used to produce reliable projections to gain deeper insights into the potential impacts of climate change on regional precipitation patterns.

show abstract

Section: Introductionmentioning

confidence: 99%

Triple coupling random forest approach for bias correction of ensemble precipitation data derived from Earth system models for Divandareh‐Bijar Basin (Western Iran)

Zebarjadian,

Dolatabadi,

Zahraie

et al. 2024

Intl Journal of Climatology

View full text Add to dashboard Cite

show abstract

“…The main drawbacks of dynamical downscaling are the high complexity and computational cost [18]. Lately, some studies have combined the traditional downscaling approach with machine learning so that a collection of statistical models can emulate the downscaling [19].…”

Section: Introductionmentioning

confidence: 99%

Downscaling Climatic Variables at a River Basin Scale: Statistical Validation and Ensemble Projection under Climate Change Scenarios

El-Samra,

Haddad,

Alameddine

et al. 2024

Climate

View full text Add to dashboard Cite

Climatic statistical downscaling in arid and topographically complex river basins remains relatively lacking. To address this gap, climatic variables derived from a global climate model (GCM) ensemble were downscaled from a grid resolution of 2.5° × 2.5° down to the station level. For this purpose, a combination of multiple linear and logistic regressions was developed, calibrated and validated with regard to their predictions of monthly precipitation and daily temperature in the Jordan River Basin. Seasonal standardized predictors were selected using a backward stepwise regression. The validated models were used to examine future scenarios based on GCM simulations under two Representative Concentration Pathways (RCP4.5 and RCP8.5) for the period 2006–2050. The results showed a cumulative near-surface air temperature increase of 1.54 °C and 2.11 °C and a cumulative precipitation decrease of 100 mm and 135 mm under the RCP4.5 and RCP8.5, respectively, by 2050. This pattern will inevitably add stress to water resources, increasing management challenges in the semi-arid to arid regions of the basin. Moreover, the current application highlights the potential of adopting regression-based models to downscale GCM predictions and inform future water resources management in poorly monitored arid regions at the river basin scale.

show abstract

“…Recently, computationally efficient statistical/empirical algorithms have been explored for RCM emulation, including simple multiple linear regression (Holden et al, 2015), multilayer perceptron (Chadwick et al, 2011;Hobeichi et al, 2023;Nishant et al, 2023), statistical analogues (Boé et al, 2023), and normalizing flows (Groenke et al, 2020). In both RCM emulation and other downscaling applications, there has been a shift towards regression-based deep learning computer vision algorithms such as CNNs (Babaousmail et al, 2021;Bano-Medina et al, 2023;Doury et al, 2022;van der Meer et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

A Robust Generative Adversarial Network Approach for Climate Downscaling and Weather Generation

Rampal,

Gibson,

Sherwood

et al. 2024

Preprint

View full text Add to dashboard Cite

Anticipating climate impacts and risks in present or future climates requires predicting the statistics of high-impact weather events at fine-scales. Direct numerical simulations of fine-scale weather are computationally too expensive for many uses. While regression-based (deep-learning or statistical) downscaling of low-resolution climate simulations is several orders of magnitude faster than direct numerical simulations, it suffers from several limitations. These limitations include the tendency to regress to the mean, which produces excessively smooth predictions and underestimates the magnitude of extreme events. Additionally, they also fail to preserve statistical measures that are key for climate research. We use a conditional GAN (c-GAN) architecture to downscale daily precipitation as a Regional Climate Model (RCM) emulator. The c-GAN generates plausible residuals on top of the predictable expectation state produced by a regression-based DL algorithm. The skill of c-GANs is highly sensitive to a hyperparameter known as the weight of the adversarial loss (λadv), and the value of λadv required for accurate results varies with season and performance metric, casting doubt on the robustness of c-GANs as usually implemented. But, by applying a simple intensity constraint to the loss function, it is possible to obtain robust performance results across λadv spanning two orders of magnitude. C-GANs are considerably more skillful in capturing climatological statistics including the distribution and spatial characteristics of extreme events. We expect c-GANs with this modification to be readily transferable to other problems and time periods, making them a useful weather generator for representing extreme event statistics in present and future climates.

show abstract

Using Machine Learning to Cut the Cost of Dynamical Downscaling

Cited by 7 publications

References 79 publications

Triple coupling random forest approach for bias correction of ensemble precipitation data derived from Earth system models for Divandareh‐Bijar Basin (Western Iran)

Triple coupling random forest approach for bias correction of ensemble precipitation data derived from Earth system models for Divandareh‐Bijar Basin (Western Iran)

Downscaling Climatic Variables at a River Basin Scale: Statistical Validation and Ensemble Projection under Climate Change Scenarios

A Robust Generative Adversarial Network Approach for Climate Downscaling and Weather Generation

Contact Info

Product

Resources

About