The stationarity of two statistical downscaling methods for precipitation under different choices of cross‐validation periods

Wang, Yaoping; Sivandran, G.; Bielicki, Jeffrey M.

doi:10.1002/joc.5375

Cited by 17 publications

(12 citation statements)

References 88 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ASDM/ASDMTE suffers from the same assumption of stationarity as other downscaling methods, that is it assumes the statistical association between coarse-and fine-scale data does not change outside of the model training time [51,52]. In addition, we may need to further assume stationary of within-scale temporal associations (i.e., temporal lags) used in the model.…”

Section: Discussionmentioning

confidence: 99%

Generating Fine-Scale Aerosol Data through Downscaling with an Artificial Neural Network Enhanced with Transfer Learning

Wang

Franklin

2022

Atmosphere

View full text Add to dashboard Cite

Spatially and temporally resolved aerosol data are essential for conducting air quality studies and assessing the health effects associated with exposure to air pollution. As these data are often expensive to acquire and time consuming to estimate, computationally efficient methods are desirable. When coarse-scale data or imagery are available, fine-scale data can be generated through downscaling methods. We developed an Artificial Neural Network Sequential Downscaling Method (ASDM) with Transfer Learning Enhancement (ASDMTE) to translate time-series data from coarse- to fine-scale while maintaining between-scale empirical associations as well as inherent within-scale correlations. Using assimilated aerosol optical depth (AOD) from the GEOS-5 Nature Run (G5NR) (2 years, daily, 7 km resolution) and Modern-Era Retrospective analysis for Research and Applications, Version 2 (MERRA-2) (20 years, daily, 50 km resolution), coupled with elevation (1 km resolution), we demonstrate the downscaling capability of ASDM and ASDMTE and compare their performances against a deep learning downscaling method, Super Resolution Deep Residual Network (SRDRN), and a traditional statistical downscaling framework called dissever ASDM/ASDMTE utilizes empirical between-scale associations, and accounts for within-scale temporal associations in the fine-scale data. In addition, within-scale temporal associations in the coarse-scale data are integrated into the ASDMTE model through the use of transfer learning to enhance downscaling performance. These features enable ASDM/ASDMTE to be trained on short periods of data yet achieve a good downscaling performance on a longer time-series. Among all the test sets, ASDM and ASDMTE had mean maximum image-wise R2 of 0.735 and 0.758, respectively, while SRDRN, dissever GAM and dissever LM had mean maximum image-wise R2 of 0.313, 0.106 and 0.095, respectively.

show abstract

Section: Discussionmentioning

confidence: 99%

Generating Fine-Scale Aerosol Data through Downscaling with an Artificial Neural Network Enhanced with Transfer Learning

Wang

Franklin

2022

Atmosphere

View full text Add to dashboard Cite

show abstract

“…The black lines show the magnification of the 90th, 95th, 99th and 99.9th percentile precipitation amount for increasing temperatures. mate the increases in the atmospheric moisture capacity and, thus, the precipitation changes (Van de Vyver et al, 2019;Wasko et al, 2018). Figure 5 compares the WT occurrences for the historical climate model outputs with those for the reanalysis data sets.…”

Section: The Informative Assumptionmentioning

confidence: 99%

Uncovering the shortcomings of a weather typing method

Uytven

Niel

Willems

2020

Hydrol. Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. In recent years many methods for statistical downscaling of the precipitation climate model outputs have been developed. Statistical downscaling is performed under general and method-specific (structural) assumptions but those are rarely evaluated simultaneously. This paper illustrates the verification and evaluation of the downscaling assumptions for a weather typing method. Using the observations and outputs of a global climate model ensemble, the skill of the method is evaluated for precipitation downscaling in central Belgium during the winter season (December to February). Shortcomings of the studied method have been uncovered and are identified as biases and a time-variant predictor–predictand relationship. The predictor–predictand relationship is found to be informative for historical observations but becomes inaccurate for the projected climate model output. The latter inaccuracy is explained by the increased importance of the thermodynamic processes in the precipitation changes. The results therefore question the applicability of the weather typing method for the case study location. Besides the shortcomings, the results also demonstrate the added value of the Clausius–Clapeyron relationship for precipitation amount scaling. The verification and evaluation of the downscaling assumptions are a tool to design a statistical downscaling ensemble tailored to end-user needs.

show abstract

“…In general, the model which captures best the relationships between predictors and predictand in calibration and validation within the observational period is used for projections. However, with closer examination of calibration and validation periods a temporal variation of the model skill can often be observed (Wang et al ., ). Wilby () attributes this variability to three different factors, but only one is related to changes within the atmospheric system through time.…”

Section: Introductionmentioning

confidence: 97%

A circulation‐based approach considering non‐stationarities within the scope of statistical downscaling: An example of seasonal daily precipitation extremes in the Mediterranean area

Merkenschlager

Hertig

2018

Intl Journal of Climatology

View full text Add to dashboard Cite

Non-stationarities within the predictor-predictand relationships can substantially affect model skill of statistical downscaling approaches. For this reason, an approach is presented which takes varying predictor-predictand relationships explicitly into account. Seasonal aggregated daily precipitation extremes (90th, 95th and 99th quantiles) were assessed by means of 31-year running contiguous calibration periods. Here, when the end of the time series was reached years from the beginning were attached. Thus, a regression model ensemble (RME) becomes available, with the number of established statistical models corresponding to the number of years within the time series. With respect to non-stationarities in the projection periods, a novel approach is presented. A single model of the RME is determined for each sub-period which seems to be the most suitable model (MSM) for assessing precipitation extremes within the respective period. In order to define the MSM weighted correlations of atmospheric circulation composites, represented by the geopotential heights, between reanalysis and model runs were calculated for all significant predictors. The reanalysis period which exhibits the highest mean correlation coefficient is then considered for the projections of the respective period of the model runs. Subsequently, a second selection process was performed in order to determine whether the regression model (RM) established within this period or the model with the highest skill within this period is used for assessing future precipitation extremes. Results have shown that projections can significantly differ depending on whether a non-stationary or a stationary downscaling setup is used for the assessments.

show abstract

The stationarity of two statistical downscaling methods for precipitation under different choices of cross‐validation periods

Cited by 17 publications

References 88 publications

Generating Fine-Scale Aerosol Data through Downscaling with an Artificial Neural Network Enhanced with Transfer Learning

Generating Fine-Scale Aerosol Data through Downscaling with an Artificial Neural Network Enhanced with Transfer Learning

Uncovering the shortcomings of a weather typing method

A circulation‐based approach considering non‐stationarities within the scope of statistical downscaling: An example of seasonal daily precipitation extremes in the Mediterranean area

Contact Info

Product

Resources

About