Downscaling daily air-temperature measurements in the Netherlands

Marieke Dirksen,Gert-Jan Steeneveld,Albert M G Klein Tank,Wouter H Knap,Albert A M Holtslag

doi:10.1007/s00704-020-03313-1

Abstract

High-resolution, regularly gridded air-temperature maps are frequently used in climatology, hydrology, and ecology. Within the Netherlands, 34 official automatic weather stations (AWSs) are operated by the National Met Service according to World Meteorological Organization (WMO) standards. Although the measurements are of high quality, the spatial density of the AWSs is not sufficient to reconstruct the temperature on a 1-km-resolution grid. Therefore, a new methodology for daily temperature reconstruction from 1990 to 2017 is proposed, using linear regression and multiple adaptive regression splines. The daily 34 AWS measurements are interpolated using eight different predictors: diurnal temperature range, population density, elevation, albedo, solar irradiance, roughness, precipitation, and vegetation index. Results are cross-validated for the AWS locations and compared with independent citizen weather observations. The RMSE of the reference method ordinary kriging amounts to 2.6 °C whereas using the new methods the RMSE drops below 1.0 °C. Especially for cities, a substantial improvement of the predictions is found. Independent predictions are on average 0.3 °C less biased than ordinary kriging at 40 high-quality citizen measurement sites. With this new method, we have improved the representation of local temperature variations within the Netherlands. The temperature maps presented here can have applications in urban heat island studies, local trend analysis, and model evaluation.

Highlights

High-resolution, regularly gridded temperature maps are essential for the construction of climatologies (Newman et al 2015; Mohr and Tveito 2008; van den Hurk et al 2006)
The additional predictors used for the lm and multiple adaptive regression splines (MARS) resulted in a higher spatial variability which is reflected in the RMSE values of the automatic weather stations (AWSs) stations
The comparison with independent citizen weather observation has shown that both lm and MARS have a smaller bias compared with the ok method which does not use additional predictors

Summary

Introduction

High-resolution, regularly gridded temperature maps are essential for the construction of climatologies (Newman et al 2015; Mohr and Tveito 2008; van den Hurk et al 2006). On the larger scale, homogenized gridded time series have been constructed to study temperature changes (van der Schrier et al 2011). ◦C over the twentieth century (van Oldenborgh and Van Ulden 2003). These authors have used data from the automatic weather stations (AWSs) to estimate a regional representation of the warming trends. Western Europe has been warming much faster than climate models projected (van Oldenborgh et al 2009). The resolution of climate models is increasing and there is a need for high resolution temperature products for their evaluation

Objectives

Methods

Results

Discussion

Conclusion