Prediction of Long-Term Near-Surface Temperature Based on NA-CORDEX Output

Abstract

Temperature is one of the most important parameters in climate modeling, as it has significant impacts on various geophysical processes such as evaporation and precipitation. Applying multiple climate models for prediction generally outperforms the use of individual climate models, and neural networks perform well at capturing nonlinear relationships, which can provide more reliable temperature projections. In this study, three neural network algorithms, including Multi-layer Perceptron (MLP), Time-lagged Feed-forward Neural Networks (TLFN) and Nonlinear Auto-Regressive Networks with exogenous inputs (NARX), were used to develop data-driven models for predicting daily mean near-surface temperature based on North American Coordinated Regional Downscaling Experiment (NA-CORDEX) output. A case study of Big Trout Lake in Ontario, Canada was carried out to demonstrate the applications and to evaluate the performance of the proposed neural network based models. The results showed that MLP, TLFN, and NARX performed well in generating accurate daily near-surface temperature predictions with the coefficient of determination (R 2) values above 0.84. The three neural network based models had similar performance with no significant difference in terms of root mean square error and R 2. Neural network based climate prediction models outperformed each of the individual regional climate models and generated smoother predicttions with less fluctuation. This study provides a technical basis for generating reliable predictions of daily temperature using neural networks based model.

An integrated multi‐GCMs Bayesian‐neural‐network hydrological analysis method for quantifying climate change impact on runoff of the Amu Darya River basin

“…However, climate change projections generated by different GCMs are uncertain, since each GCM has been developed based on its own assumptions and unique mathematical representations of physical climate system processes (Zhuang et al ., 2016). Due to the enormous uncertainty caused by the choice of a single GCM, the use of multi‐GCM ensembles has been widely used for a realistic assessment of climate change (Chilkoti et al ., 2017; Her et al ., 2019; Li et al ., 2019). Multi‐GCM ensembles are able to provide more comprehensive simulations of climate variables than the use of individual climate models (Li et al ., 2020).…”

Ensemble Drought Exposure Projection for Multifactorial Interactive Effects of Climate Change and Population Dynamics: Application to the Pearl River Basin

“…Ensemble modeling was a key technology to project drought population exposure (J. Li et al., 2020; X. Li et al., 2020). Many studies have indicated the advantages of ensemble modeling (Li et al., 2019). In recent years, economic construction and human production in the PRB have been affected dramatically by climate change, especially extreme climate events.…”