Transformer based models with hierarchical graph representations for enhanced climate forecasting

Accurate climate predictions are essential for agriculture, urban planning, and disaster management. Traditional forecasting methods often struggle with regional accuracy, computational demands, and scalability. This study proposes a Transformer-based deep learning model for daily temperature foreca...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Scientific reports Ročník 15; číslo 1; s. 23464 - 22
Hlavní autoři:	Ramu, T. Bhargava, Kocherla, Raviteja, Sirisha, G. N. V. G., Chetana, V. Lakshmi, Sagar, P. Vidya, Balamurali, R., Boddu, Nanditha
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	London Nature Publishing Group UK 02.07.2025 Nature Publishing Group Nature Portfolio
Témata:	639/166 639/705 Accuracy Algorithms Case studies Climate change Climate prediction Climatic data Computer applications Decision making Deep learning Disaster management Emergency preparedness Feature optimization Feature selection Forecasting Graph representations Hierarchical graph modeling Humanities and Social Sciences Machine learning multidisciplinary Neural networks Permafrost Precipitation Rain Science Science (multidisciplinary) Storms Temperature Transformer-based forecasting Urban agriculture Urban planning Variables Weather forecasting Pacific Northwest Deep learning Transformer-based forecasting Feature optimization Hierarchical graph modeling Climate prediction
ISSN:	2045-2322, 2045-2322
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Accurate climate predictions are essential for agriculture, urban planning, and disaster management. Traditional forecasting methods often struggle with regional accuracy, computational demands, and scalability. This study proposes a Transformer-based deep learning model for daily temperature forecasting, utilizing historical climate data from Delhi (2013–2017, consisting of 1,500 daily records). The model integrates three key components: Spatial-Temporal Fusion Module (STFM) to capture spatiotemporal dependencies, Hierarchical Graph Representation and Analysis (HGRA) to model structured climate relationships, and Dynamic Temporal Graph Attention Mechanism (DT-GAM) to enhance temporal feature extraction. To improve computational efficiency and feature selection, we introduce a hybrid optimization approach (HWOA-TTA) that combines the Whale Optimization Algorithm (WOA) and Tiki-Taka Algorithm (TTA). Experimental results demonstrate that the proposed model outperforms baseline models (RF-LSTM-XGBoost, cGAN, CNN + LSTM, and MC-LSTM) by achieving 7.8% higher accuracy, 6.3% improvement in recall, and 8.1% enhancement in F1-score. Additionally, training time is reduced by 22.4% compared to conventional deep learning models, demonstrating improved computational efficiency. These findings highlight the effectiveness of hierarchical graph-based deep learning models for scalable and accurate climate forecasting. Future work will focus on validating the model across diverse climatic regions and enhancing real-time deployment feasibility.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ISSN:	2045-2322 2045-2322
DOI:	10.1038/s41598-025-07897-4