Publications

Oskouei, EA; Pakdaman, M; Falamarzi, Y; Javanshiri, Z (2024). A hybrid approach for generating daily 2m temperature of 1km spatial resolution over Iran. THEORETICAL AND APPLIED CLIMATOLOGY, 155(8), 7109-7119.

Abstract
Access to high-resolution historical climate data is vital for both theoretical and applied climatology. The aim of this paper is to propose a hybrid algorithm, which consists of two main steps. At the first step, using temperature lapse rate, the temperature data of ERA5, MERRA2 and CFS were downscaled. The temperature lapse rate was calculated using MODIS temperature data. Then, at the second step, the ability of machine learning algorithms was examined in generating daily 2m temperature data with spatial resolution of 1km for Iran during 1980-2021. The inputs of the machine learning algorithms include the downscaled outputs of ERA5, MERRA2 and CFS data (which were calculated at the first step), elevation, aspect and Julian day. Several machine learning algorithms were examined including multi-layered perceptron neural networks (MLPNN), Random Forest (RF), Gradient Boosting (GB), Adaptive Boosting (AB) and Cubist Regression (CB). The results indicated that the MLPNN outperforms other techniques. Also, the final temperature map was depicted for Feb and Jul and also the MLPNN output predictions were evaluated for six different climate regions in the country. Evaluation results in regional section indicated that the MLPNN best performance was in very warm region with low rainfall while its worst performance was in mountainous and cold region.

DOI:
10.1007/s00704-024-05042-1

ISSN:
1434-4483