Multimodal deep learning for estimating mean precipitable water vapor
| dc.authorid | Mowla, Najmul/0000-0003-0613-9858 | |
| dc.contributor.author | Mowla, Md. Najmul | |
| dc.contributor.author | Aksoy, Muhammed M. | |
| dc.contributor.author | Pinar, Engin | |
| dc.contributor.author | Bilgili, Mehmet | |
| dc.contributor.author | Durhasan, Tahir | |
| dc.date.accessioned | 2026-02-27T07:33:40Z | |
| dc.date.available | 2026-02-27T07:33:40Z | |
| dc.date.issued | 2026 | |
| dc.description.abstract | Precipitable water vapor (PWV) is a crucial atmospheric variable that influences weather systems, climate variability, and hydrological processes. Accurate PWV estimation is essential for improving numerical weather prediction, climate modeling, and remote-sensing applications. However, existing methods often rely on extensive meteorological inputs or computationally intensive architectures, limiting their applicability in data-sparse regions. This study introduces a novel hybrid framework, EMMA-NN-BiGRU-XGBoost, designed to forecast monthly mean PWV across Turkey using only four physically meaningful inputs: latitude, longitude, altitude, and seasonal indicators. The framework integrates an enhanced multimodal attention (EMMA) mechanism that disentangles spatial, altitudinal, and seasonal influences, improving interpretability and physical consistency. Bidirectional gated recurrent units (BiGRU) capture temporal dependencies, and XGBoost models nonlinear feature interactions within a weighted stacking ensemble. Hyperparameters are optimized via particle swarm optimization and Bayesian optimization, with particle swarm optimization demonstrating superior tuning efficiency. Extensive benchmarking against traditional machine-learning models, using grid search and random search with fivefold cross-validation, as well as deep-learning baselines, demonstrates significant improvements in predictive accuracy, achieving an root-mean-square error of and an of 0.92, representing a 15%-20% reduction in error compared with state-of-the-art methods. The model also exhibits robustness across diverse climatic zones in Turkey. Shapley additive explanations further elucidate feature importance, aligning model outputs with climatological principles. Beyond methodological advances, this work provides a scalable, interpretable, and data-efficient baseline for PWV forecasting, thereby facilitating enhanced climate diagnostics, hydrological risk assessments, and early warning systems, particularly in regions with limited meteorological observations. | |
| dc.identifier.doi | 10.1002/qj.70089 | |
| dc.identifier.issn | 0035-9009 | |
| dc.identifier.issn | 1477-870X | |
| dc.identifier.uri | http://dx.doi.org/10.1002/qj.70089 | |
| dc.identifier.uri | https://hdl.handle.net/20.500.14669/4661 | |
| dc.identifier.wos | WOS:001656467600001 | |
| dc.indekslendigikaynak | Web of Science | |
| dc.language.iso | en | |
| dc.publisher | Wiley | |
| dc.relation.ispartof | Quarterly Journal of The Royal Meteorological Society | |
| dc.relation.publicationcategory | Makale - Uluslararas� Hakemli Dergi - Kurum ��retim Eleman� | |
| dc.rights | info:eu-repo/semantics/closedAccess | |
| dc.snmz | KA_20260302 | |
| dc.subject | climate modeling | |
| dc.subject | deep learning | |
| dc.subject | multimodal attention | |
| dc.subject | precipitable water vapor | |
| dc.subject | SearchOptimizer | |
| dc.subject | SHAP | |
| dc.title | Multimodal deep learning for estimating mean precipitable water vapor | |
| dc.type | Article; Early Access |
