Geographically Weighted Machine Learning and Downscaling for High-Resolution Spatiotemporal Estimations of Wind Speed

High-resolution spatiotemporal wind speed mapping is useful for atmospheric environmental monitoring, air quality evaluation and wind power siting. Although modern reanalysis techniques can obtain reliable interpolated surfaces of meteorology at a high temporal resolution, their spatial resolutions are coarse. Local variability of wind speed is difficult to capture due to its volatility. Here, a two-stage approach was developed for robust spatiotemporal estimations of wind speed at a high resolution. The proposed approach consists of geographically weighted ensemble machine learning (Stage 1) and downscaling based on meteorological reanalysis data (Stage 2). The geographically weighted machine learning method is based on three base learners, which are an autoencoder-based deep residual network, XGBoost and random forest, and it incorporates spatial autocorrelation and heterogeneity to boost the ensemble predictions. With reanalysis data, downscaling was introduced in Stage 2 to reduce bias and spatial abrupt (non-natural) variation in the predictions inferred from Stage 1. The autoencoder-based residual network was used in Stage 2 to adjust the difference between the averages of the fine-resolution predicted values and the coarse-resolution reanalysis data to ensure consistency. Using mainland China as a case study, the geographically weighted regression (GWR) ensemble predictions were shown to perform better than individual learners’ predictions (with an approximately 12–16% improvement in R2 and a decrease of 0.14–0.19 m/s in root mean square error). Downscaling further improved the predictions by reducing inconsistency and obtaining better spatial variation (smoothing). The proposed approach can also be applied for the high-resolution spatiotemporal estimation of other meteorological parameters or surface variables involving remote sensing images (i.e. reliable coarsely resolved data), ground monitoring data and other relevant factors.

[1]  Zhang Yan,et al.  A review on the forecasting of wind speed and generated power , 2009 .

[2]  Peter M. Atkinson,et al.  Downscaling in remote sensing , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[3]  Jürgen Schmidhuber,et al.  Highway Networks , 2015, ArXiv.

[4]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[5]  Nicola Jones,et al.  How machine learning could help to improve climate forecasts , 2017, Nature.

[6]  Yuhang Wang,et al.  Arctic sea ice, Eurasia snow, and extreme winter haze in China , 2017, Science Advances.

[7]  Mario Chica-Olmo,et al.  Image fusion by spatially adaptive filtering using downscaling cokriging , 2011 .

[8]  Manolis A. Christodoulou,et al.  Adaptive control of unknown plants using dynamical neural networks , 1994, IEEE Trans. Syst. Man Cybern..

[9]  Catherine A. Calder,et al.  Beyond Moran's I: Testing for Spatial Dependence Based on the Spatial Autoregressive Model , 2007 .

[10]  Despina Deligiorgi,et al.  Artificial Neural Network Modeling of Relative Humidity and Air Temperature Spatial and Temporal Distributions Over Complex Terrains , 2013, ICPRAM.

[11]  Somnath Baidya Roy,et al.  A Short-Term Ensemble Wind Speed Forecasting System for Wind Power Applications , 2011 .

[12]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[13]  P. Goovaerts Combining Areal and Point Data in Geostatistical Interpolation: Applications to Soil Science and Medical Geography , 2010, Mathematical geosciences.

[14]  Martin Charlton,et al.  Geographically weighted regression with a non-Euclidean distance metric: a case study using hedonic house price data , 2014, Int. J. Geogr. Inf. Sci..

[15]  Teri A. Crosby,et al.  How to Detect and Handle Outliers , 1993 .

[16]  W. Tobler A Computer Movie Simulating Urban Growth in the Detroit Region , 1970 .

[17]  Jun Wu,et al.  Autoencoder Based Residual Deep Networks for Robust Regression Prediction and Spatiotemporal Estimation , 2018, ArXiv.

[18]  E. Wendell Hewson Meteorological Factors Affecting Causes and Controls of Air Pollution , 1956 .

[19]  Effects of Meteorological Factors and Air Pollution on Urban Pollen Concentrations , 2011 .

[20]  M. Charlton,et al.  Geographically Weighted Regression: A Natural Evolution of the Expansion Method for Spatial Data Analysis , 1998 .

[21]  S. Schubert,et al.  MERRA: NASA’s Modern-Era Retrospective Analysis for Research and Applications , 2011 .

[22]  J. Thepaut,et al.  The ERA‐Interim reanalysis: configuration and performance of the data assimilation system , 2011 .

[23]  Jian Sun,et al.  Convolutional neural networks at constrained time cost , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Christos H. Halios,et al.  Meteorology, air quality, and health in London: the ClearfLo project , 2015 .

[25]  Joel Schwartz,et al.  The impact of weather changes on air quality and health in the United States in 1994–2012 , 2015, Environmental research letters : ERL [Web site].

[26]  Enrico Zio,et al.  Two Machine Learning Approaches for Short-Term Wind Speed Time-Series Prediction , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[27]  Martin Kappas,et al.  Application of Geographically Weighted Regression to Investigate the Impact of Scale on Prediction Uncertainty by Modelling Relationship between Vegetation and Climate , 2007, Int. J. Spatial Data Infrastructures Res..

[28]  Mohamed Mohandes,et al.  Support vector machines for wind speed prediction , 2004 .

[29]  Tin Kam Ho,et al.  The Random Subspace Method for Constructing Decision Forests , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[30]  Wendy S. Parker,et al.  Reanalyses and observations : what's the difference? , 2016 .

[31]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[32]  C. Gotway,et al.  Combining Incompatible Spatial Data , 2002 .

[33]  Uang,et al.  The NCEP Climate Forecast System Reanalysis , 2010 .

[34]  X. Jie,et al.  A time series analysis of meteorological factors and hospital outpatient admissions for cardiovascular disease in the Northern district of Guizhou Province, China , 2014, Brazilian journal of medical and biological research = Revista brasileira de pesquisas medicas e biologicas.

[35]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.