Hybrid Deep Learning and Stacking Ensemble Model for Time Series-Based Global Temperature Forecasting
Open Access
- 13 August 2025
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 14 (16) , 3213
Abstract
Variations in global surface temperatures serve as critical indicators of climate change, and making accurate predictions regarding these patterns is essential for designing effective mitigation strategies. This study utilized a time series prediction methodology, leveraging annual temperature anomaly records from 1880 to 2022 provided by NASA’s GISTEMP v4 dataset. Following an extensive preprocessing phase, multiple deep learning models, namely, LSTM, DNN, CNN, and Transformer, were trained and analyzed separately. The individual model outputs were subsequently combined using a weighted averaging strategy grounded in linear regression, forming a novel LSTM and Transformer-based hybrid forecasting model. Model performance was assessed through widely recognized metrics including MSE, MAE, RMSE, and R2. By integrating the distinct advantages of each model, the ensemble framework aimed to improve the overall predictive capability. The findings revealed that this hybrid design delivered more stable and accurate forecasts compared to any single model. The integration of diverse neural network structures proved effective in boosting predictive reliability and underscored the viability of deep learning-based hybrid modeling for climate trend forecasting.Keywords
This publication has 35 references indexed in Scilit:
- Forecasting air temperature and rainfall in Mymensingh, Bangladesh with ARIMA: Implications for aquaculture managementEgyptian Journal of Aquatic Research, 2025
- Enhancing temperature prediction in the UAE: a process-driven framework for adaptive learning with GRU-CNN hybrid modelsModeling Earth Systems and Environment, 2025
- Estimating and forecasting daily reference crop evapotranspiration in China with temperature-driven deep learning modelsAgricultural Water Management, 2024
- Global monthly sea surface temperature forecasting using the SARIMA, LSTM, and GRU modelsEarth Science Informatics, 2024
- Analysis of historical and future cooling degree days over Türkiye for facade design and energy efficiency in buildingsJournal of Thermal Analysis and Calorimetry, 2024
- Forecasting greenhouse air and soil temperatures: A multi-step time series approach employing attention-based LSTM networkComputers and Electronics in Agriculture, 2024
- A novel global average temperature prediction model——based on GM-ARIMA combination modelEarth Science Informatics, 2023
- Daily air temperature forecasting using LSTM-CNN and GRU-CNN modelsActa Geophysica, 2023
- Reference evapotranspiration estimation using long short‐term memory network and wavelet‐coupled long short‐term memory networkIrrigation and Drainage, 2022
- Forecasting across time series databases using recurrent neural networks on groups of similar series: A clustering approachExpert Systems with Applications, 2020