Fine scale surface climate in complex terrain using machine learning
Accurate and high spatial resolution (<100 m) surface climate information is crucial for process‐based modelling in hydrology, ecology, agriculture, urban studies etc, especially in complex terrain landscapes where coarse grid resolution information (∼10 km) is inadequate to represent pronounced...
Saved in:
Published in | International journal of climatology Vol. 41; no. 1; pp. 233 - 250 |
---|---|
Main Authors | , , |
Format | Journal Article |
Language | English |
Published |
Chichester, UK
John Wiley & Sons, Ltd
01.01.2021
Wiley Subscription Services, Inc |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Accurate and high spatial resolution (<100 m) surface climate information is crucial for process‐based modelling in hydrology, ecology, agriculture, urban studies etc, especially in complex terrain landscapes where coarse grid resolution information (∼10 km) is inadequate to represent pronounced local variability. We used a machine learning‐based workflow to predict high resolution (30 m) and sub‐daily atmospheric variables fields of near‐surface air temperature and humidity, and wind speed. The method used the Principal Component Analysis (PCA) decomposition applied on ground stations observations or Global Climate Model (GCM) residual error, in a sequence with bias correction and statistical models (Linear Regression‐LR, Artificial Neural Network model‐ANN and Empirical Quantile Mapping‐EQM) to provide downscaling from large scale atmospheric conditions to complex terrain variability. The predictions described relationships of Principal Component (PC) scores dependent on GCM temporal variability on 6‐hourly basis (with LR or ANN or EQM), and PC loadings dependent on topographic indexes to help providing horizontal sub‐grid extrapolation. The methods were validated with a 1‐year dataset from a dense weather stations network deployed in a complex terrain basin in tropical climate of Southeast Brazil. We present an exhaustive description of the PC modes daily/seasonal variability for each variable, and their spatial variability associated to the topography and thermal driven circulations. The predictions in general substantially improved accuracy when compared to GCM outputs, especially near the valley and in sheltered area where local effects are mandatories. Specially, ANN and EQM significantly improved the predictions at the variability of extreme events, such as the formation of strong cold air pooling or wetting in the valley.
This article describes a machine learning based method to obtain high‐resolution fields of near‐surface air temperature, humidity and wind speed in complex terrain. The predictions incorporated the influence of the topography and lead to substantial improvement when compared to GCM output, especially near the valley and in sheltered area where local effect are mandatories. The use of Neural Network models in the method significantly improve prediction of extreme events, such as the formation of strong cold air pooling or wetting. |
---|---|
Bibliography: | Funding information Fundação de Amparo à Pesquisa do Estado de São Paulo, Grant/Award Numbers: 2012/50343‐9, 2012/51872‐5, 2015/50682‐6 |
ISSN: | 0899-8418 1097-0088 |
DOI: | 10.1002/joc.6617 |