An Optimized Deep Transformer Framework Using Informer Architecture for Accurate Temperature Forecasting
Open Access
- 1 June 2026
- journal article
- research article
- Published by MDPI AG in Algorithms
- Vol. 19 (6) , 437
Abstract
Accurate temperature forecasting is essential for agriculture, disaster management, and infrastructure planning, yet numerical weather prediction models face increasing limitations under climate change. Deep learning architectures, particularly transformers, offer promising alternatives but suffer from quadratic complexity and limited ability to capture both long-range dependencies and local periodic patterns in volatile climate data. To address these challenges, this paper proposes the Hybrid Attention Informer (HA-Informer), a unified end-to-end framework that introduces three modifications to the standard Informer: a hybrid attention mechanism combining ProbSparse attention with depthwise separable convolutions to capture global and local patterns simultaneously, an adaptive distillation mechanism that dynamically adjusts compression based on attention entropy to preserve fine-grained information, and a residual refinement decoder that mitigates error accumulation in long-horizon forecasting. The proposed model is evaluated on hourly temperature data from three climatically diverse cities, Niamey (hot), Tehran (temperate), and Harbin (cold), against seven baselines, namely, LSTM, a CNN, ARIMA, XGBoost, DLinear, transformer, and the standard Informer. The experimental results demonstrate that HA-Informer consistently achieves the lowest forecasting errors across all three locations, with mean squared error reductions of approximately over Informer, over DLinear, and over LSTM in the Niamey dataset, supported by statistically significant Diebold–Mariano test statistics () confirming the superiority of the proposed approach.
Keywords
This publication has 38 references indexed in Scilit:
- Time series forecasting of train axle fatigue crack acoustic emission signals by integrating multi-head attention mechanism into DLinear modelApplied Acoustics, 2025
- Deep learning for time series forecasting: a surveyInternational Journal of Machine Learning and Cybernetics, 2025
- Forecasting Nordic electricity spot price using deep learning networksNeural Computing and Applications, 2023
- Exploring the potential of time-series transformers for process modeling and control in chemical systems: An inevitable paradigm shift?Chemical Engineering Research and Design, 2023
- Parameter estimation of uncertain differential equation by implementing an optimized artificial neural networkChaos, Solitons & Fractals, 2022
- Large-scale atmospheric circulation patterns associated with extreme monsoon precipitation in Pakistan during 1981–2018Atmospheric Research, 2021
- A microphysically based precipitation scheme for the UK meteorological office unified modelQuarterly Journal of the Royal Meteorological Society, 1999
- The ECMWF Ensemble Prediction System: Methodology and validationQuarterly Journal of the Royal Meteorological Society, 1996
- Analysis methods for numerical weather predictionQuarterly Journal of the Royal Meteorological Society, 1986
- A Mathematical Theory of CommunicationBell System Technical Journal, 1948