Downscaling Daily Temperature with Evolutionary Artificial Neural Networks

Min Shi

2015

Abstract

The spatial resolution of climate data generated by general circulation models (GCMs) is usually too coarse to present regional or local features and dynamics. State of the art research with Artificial Neural Networks (ANNs) for the downscaling of GCMs mainly uses back-propagation algorithm as a training approach. This paper applies another training approach of ANNs, Evolutionary Algorithm. The combined algorithm names neuroevolutionary (NE) algorithm. We investigate and evaluate the use of the NE algorithms in statistical downscaling by generating temperature estimates at interior points given information from a lattice of surrounding locations. The results of our experiments indicate that NE algorithms can be efficient alternative downscaling methods for daily temperatures.

Paper Citation

in Harvard Style

Shi M. (2015). Downscaling Daily Temperature with Evolutionary Artificial Neural Networks . In Proceedings of the 5th International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: SIMULTECH, ISBN 978-989-758-120-5, pages 237-243. DOI: 10.5220/0005507002370243

in Bibtex Style

@conference{simultech15,
author={Min Shi},
title={Downscaling Daily Temperature with Evolutionary Artificial Neural Networks},
booktitle={Proceedings of the 5th International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: SIMULTECH,},
year={2015},
pages={237-243},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005507002370243},
isbn={978-989-758-120-5},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: SIMULTECH,
TI - Downscaling Daily Temperature with Evolutionary Artificial Neural Networks
SN - 978-989-758-120-5
AU - Shi M.
PY - 2015
SP - 237
EP - 243
DO - 10.5220/0005507002370243