A comparison of statistical and dynamical downscaling methods for short‐term weather forecasts in the <scp>US N</scp>ortheast

Alessi, Marc J.; DeGaetano, Arthur T.

doi:10.1002/met.1976

Cited by 3 publications

(2 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Still, reanalysis data frequently fail to simulate many of the processes that drive regional and local climate variability. Their limitations lie in their incapability of accurately depicting sub-km-scale climate variables at the needed timescales and do not allow for proper representations of the local topography and sub-grid-scale features that are essential in areas with complex terrain, microclimates or narrow mountain valleys, as highlighted by Holden et al [19], Zhang et al [20], Le Roux et al [21], Alessi and DeGaetano [22], and Zhang et al [23]. When evaluated in contrast to observational data, the raw output data are regularly found to have systematic biases [24,25], limiting their usefulness for local applications [26].…”

Section: Introductionmentioning

confidence: 99%

Machine-Learning-Based Downscaling of Hourly ERA5-Land Air Temperature over Mountainous Regions

et al. 2023

View full text Add to dashboard Cite

In mountainous regions, the scarcity of air temperature (Ta) measurements is a major limitation for hydrological and crop monitoring. An alternative to in situ measurements could be to downscale the reanalysis Ta data provided at high-temporal resolution. However, the relatively coarse spatial resolution of these products (i.e., 9 km for ERA5-Land) is unlikely to be directly representative of actual local Ta patterns. To address this issue, this study presents a new spatial downscaling strategy of hourly ERA5-Land Ta data with a three-step procedure. First, the 9 km resolution ERA5 Ta is corrected at its original resolution by using a reference Ta derived from the elevation of the 9 km resolution grid and an in situ estimate over the area of the hourly Environmental Lapse Rate (ELR). Such a correction of 9 km resolution ERA5 Ta is trained using several machine learning techniques, including Multiple Linear Regression (MLR), Support Vector Regression (SVR), and Extreme Gradient Boosting (Xgboost), as well as ancillary ERA5 data (daily mean, standard deviation, hourly ELR, and grid elevation). Next, the trained correction algorithms are run to correct 9 km resolution ERA5 Ta, and the corrected ERA5 Ta data are used to derive an updated ELR over the area (without using in situ Ta measurements). Third, the updated hourly ELR is used to disaggregate 9 km resolution corrected ERA5 Ta data at the 30-meter resolution of SRTM’s Digital Elevation Model (DEM). The effectiveness of this method is assessed across the northern part of the High Atlas Mountains in central Morocco through (1) k-fold cross-validation against five years (2016 to 2020) of in situ hourly temperature readings and (2) comparison with classical downscaling methods based on a constant ELR. Our results indicate a significant enhancement in the spatial distribution of hourly local Ta. By comparing our model, which included Xgboost, SVR, and MLR, with the constant ELR-based downscaling approach, we were able to decrease the regional root mean square error from approximately 3 ∘C to 1.61 ∘C, 1.75 ∘C, and 1.8 ∘C, reduce the mean bias error from −0.5 ∘C to null, and increase the coefficient of determination from 0.88 to 0.97, 0.96, and 0.96 for Xgboost, SVR, and MLR, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine-Learning-Based Downscaling of Hourly ERA5-Land Air Temperature over Mountainous Regions

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Moreover, due to their coarse spatial resolution, mostly lower than 1 km (Caldwell et al., 2009; Yan et al., 2020), NWP models have mainly been applied to develop climate change scenarios and perform large‐scale studies. These models suffer in their ability to resolve fine‐scale air temperature (sub‐km scale) at the timescales relevant to biota living in narrow mountain valleys (e.g., 10–30 m; Holden et al., 2011), in microclimates or in areas of complex terrain (Alessi & DeGaetano, 2021; Le Roux et al., 2018; Zhang et al., 2013).…”

Section: Introductionmentioning

confidence: 99%

Downscaling Hourly Air Temperature of WRF Simulations Over Complex Topography: A Case Study of Chongli District in Hebei Province, China

et al. 2022

View full text Add to dashboard Cite

The air temperature is one of the most frequently measured meteorological parameters. Air temperature forecasting is a crucial climatic factor-related task required in many different applications in areas such as agriculture, industry, energy, the environment, and tourism (Abdel-Aal, 2004;Cifuentes et al., 2020). Certain applications include short-term load forecasting for power utilities (Li et al., 2016), protection against freezing injury of various fruits (Chung et al., 2006), adaptive temperature control in greenhouses (Dombaycı & Gölcü, 2009), prediction of cooling and energy consumption in residential buildings (Ben-Nakhi & Mahmoud, 2004), and establishment of a planning horizon for infrastructure upgrades, insurance, energy policy, and business development purposes (Smith et al., 2007). Therefore, accurate forecasting of the air temperature with high spatiotemporal resolution has always been an important goal for meteorologists and weather forecasters.Mountainous areas also represent important areas of human activities, such as fruit cultivation, tourism, and skiing in the winter season. Therefore, hourly air temperature forecasting and high-resolution prediction in mountainous areas is necessary and important for human activities. In contrast to plain areas, the topography of a mountainous area is very complex, which can cause the air temperature to vary within small terrain units. For example, in a 1-km grid, the difference in altitude between the slope top and foot can reach as much as 500 m, and the temperature difference as high as 3°C, assuming that the slope of the grid is 0.5. It is a difficult task for air temperature forecasting and modeling in complex geographical zones because the temperature is influenced by several nonlinear processes, such as the interaction between large-scale air mass circulation and local airflow, airflow-topography interactions, and the interplay between radiation and topographic shading.Currently, many numerical weather prediction (NWP) models are available for air temperature prediction, for example, the European Centre for Medium-Range Weather Forecasts (ECMWF) model, the fifth-generation mesoscale model (MM5), and the Weather Research and Forecasting (WRF) model. All these NWP models allow day-ahead air temperature prediction, which is usually adopted in practice. However, uncertainties in model

show abstract

Comparison of a novel machine learning approach with dynamical downscaling for Australian precipitation

Nishant

Hobeichi

Sherwood

et al. 2023

Environ. Res. Lett.

View full text Add to dashboard Cite

Dynamical downscaling, and machine learning (ML) based techniques have been widely applied to downscale global climate models and reanalyses to a finer spatiotemporal scale, but the relative performance of these two methods remains unclear. We implement an ML regression approach using a multi-layer perceptron (MLP) with a novel loss function to downscale coarse-resolution precipitation from the Bureau of Meteorology Atmospheric high-resolution Regional Reanalysis for Australia from grids of 12-48 km to 5 km, using the Australia Gridded Climate Data observations as the target. A separate MLP is developed for each coarse grid to predict the fine grid values within it, by combining coarse-scale time-varying meteorological variables with fine-scale static surface properties as predictors. The resulting predictions (on out-of-sample test periods) are more accurate than dynamical downscaling in capturing the rainfall climatology, as well as the frequency distribution and spatiotemporal variability of daily precipitation, reducing biases in daily extremes by 15-85% with 12-km prediction fields. When prediction fields are coarsened, the skill of the MLP decreases—at 24 km relative bias increases by ~ 10%, and at 48 km it increases by another ~ 4%—but skill remains comparable to or, for some metrics, much better than dynamical downscaling. These results show that ML-based downscaling benefits from higher-resolution driving data but can still improve on dynamical downscaling (and at far less computational cost) when downscaling from a global climate model grid of ~50 km.

show abstract

A comparison of statistical and dynamical downscaling methods for short‐term weather forecasts in the US Northeast

Cited by 3 publications

References 48 publications

Machine-Learning-Based Downscaling of Hourly ERA5-Land Air Temperature over Mountainous Regions

Machine-Learning-Based Downscaling of Hourly ERA5-Land Air Temperature over Mountainous Regions

Downscaling Hourly Air Temperature of WRF Simulations Over Complex Topography: A Case Study of Chongli District in Hebei Province, China

Comparison of a novel machine learning approach with dynamical downscaling for Australian precipitation

Contact Info

Product

Resources

About