Using all data to improve seasonal sea surface temperature predictions: A combination‐based model forecast with unequal observation lengths

Abstract

One way to reduce model uncertainty in climate predictions is to combine forecasts from several models. Recent multi‐model combination approaches combine model forecasts by pooling data for a time period, common across all the models, thus ignoring the additional data available or discarding altogether the models with the shorter time period. This results in the loss of some information which could otherwise be used while combining the models to possibly improve forecast skill. Our research explores this issue in the context of multi‐model sea surface temperature (SST) models predictions and proposes a novel concept that allows a framework for combining models with unequal time period. Here, the unequal time periods imply different range of start and end dates of available model forecasts. A qualitative standpoint of our multi‐model forecasting strategy is to reduce the uncertainty and improve the forecast skill. The utility of the approach is demonstrated by combining the global seasonal NDJ (November–January) SST predictions of two models and also as many as eight models, obtained using both equal and unequal time periods. The proposed approach shows improvement over 62–69% grid cells around the entire globe over the case when the common period of data length across the models is considered.

A Novel Hybrid Data-Driven Model for Daily Land Surface Temperature Forecasting Using Long Short-Term Memory Neural Network Based on Ensemble Empirical Mode Decomposition

“…In industry, accurate forecasts of temperature are part of an energy-management strategy to reduce energy consumption while maintaining an internal temperature within a specified comfort range [ 14 , 15 ]. As the dramatic and continuous increase of rapid socio-economic development, population growth, and industrial, commercial and residential emissions of large amounts of heat have led to local temperature increases, they have in turn attracted attention from national governments and scientists [ 16 , 17 , 18 , 19 , 20 ]. However, daily LST variations are extremely nonstationary and nonlinear in nature, because the meteorological processes have been heavily impacted by global and local warming and climate change, as well as human activities [ 21 ].…”

Long-Term Prediction of Hydrometeorological Time Series Using a PSO-Based Combined Model Composed of EEMD and LSTM

“…Due to the non-stationary and nonlinear nature of hydrometeorological elements, the task of improving the prediction accuracy faces significant challenges. Therefore, the prediction of hydrometeorological elements has received significant attention [10][11][12][13]. Researchers have developed a variety of forecasting models for hydrometeorological elements, which can generally be divided into two categories: physical models and data-driven models.…”