Stepwise extreme learning machine for statistical downscaling of daily maximum and minimum temperature

Abstract

Increasing temperature from climate change can bring a number of different risks such as more droughts and heat waves, and increasing sea level rise. Assessment of climate change with future scenarios is essential to adapt these impacts. To provide climate change information through the outputs of general circulation models at finer resolution, a reliable and accurate downscaling model has always been of great interest. Meeting this need, artificial neural network (ANN) has been commonly employed in downscaling for nonlinear models. Extreme learning machine (ELM), a recently developed ANN, is an efficient learning algorithm for generalized single hidden layer feedforward neural networks. In light of its simple learning algorithm, we introduced a useful approach to combine the stepwise feature selection method into ELM for temperature downscaling, as stepwise ELM (SWELM), since model complexity and computational time consumption of a traditional ANN impedes application of stepwise feature selection. This SWELM is able to identify the most influential predictors in a dataset and use them to train a nonlinear model while removing the irrelevant ones. The ELM and SWELM as well as regular ANN were tested in a simulation study. Results indicated that ELM even with randomness of weights and biases in the nodes of input and hidden layers better performed than did ANN. Also, SWELM presents a capability to select the influential predictors and remove the unrelated variables. A case study with downscaling temperature of Wisconsin, USA, showed that ELM was a comparable alternative to ANN. SWELM outperformed the ANN algorithm for temperature downscaling and sometimes predicted the temperature increase larger than did others for future scenarios. The current study of temperature downscaling with the statistical tool allows assessing the possible impacts of climate change in a local scale and some developing countries where sophisticate research cannot be eligible.