Differentiable modelling to unify machine learning and physical models for geosciences

Nature Reviews Earth & Environment, Год журнала: 2023, Номер 4(8), С. 552 - 567

Опубликована: Июль 11, 2023

Язык: Английский

---

An ensemble CNN-LSTM and GRU adaptive weighting model based improved sparrow search algorithm for predicting runoff using historical meteorological and runoff data as input

Journal of Hydrology, Год журнала: 2023, Номер 625, С. 129977 - 129977

Опубликована: Июль 22, 2023

Язык: Английский

---

Deep transfer learning based on transformer for flood forecasting in data-sparse basins

Journal of Hydrology, Год журнала: 2023, Номер 625, С. 129956 - 129956

Опубликована: Июль 19, 2023

Язык: Английский

---

A Novel Runoff Prediction Model Based on Support Vector Machine and Gate Recurrent unit with Secondary Mode Decomposition

Water Resources Management, Год журнала: 2024, Номер 38(5), С. 1655 - 1674

Опубликована: Фев. 6, 2024

Язык: Английский

---

Deep learning for cross-region streamflow and flood forecasting at a global scale

The Innovation, Год журнала: 2024, Номер 5(3), С. 100617 - 100617

Опубликована: Март 26, 2024

Язык: Английский

---

An interpretable hybrid deep learning model for flood forecasting based on Transformer and LSTM

Journal of Hydrology Regional Studies, Год журнала: 2024, Номер 54, С. 101873 - 101873

Опубликована: Июнь 27, 2024

Язык: Английский

---

Ensemble learning using multivariate variational mode decomposition based on the Transformer for multi-step-ahead streamflow forecasting

Journal of Hydrology, Год журнала: 2024, Номер 636, С. 131275 - 131275

Опубликована: Май 7, 2024

Язык: Английский

---

TLT: Recurrent fine-tuning transfer learning for water quality long-term prediction

Water Research, Год журнала: 2022, Номер 225, С. 119171 - 119171

Опубликована: Сен. 29, 2022

Язык: Английский

---

Runoff predictions in new-gauged basins using two transformer-based models

Journal of Hydrology, Год журнала: 2023, Номер 622, С. 129684 - 129684

Опубликована: Май 18, 2023

Язык: Английский

---

Transformer Based Water Level Prediction in Poyang Lake, China

Water, Год журнала: 2023, Номер 15(3), С. 576 - 576

Опубликована: Фев. 1, 2023

Water level is an important indicator of lake hydrology characteristics, and its fluctuation significantly affects ecosystems. In recent years, deep learning models have shown their superiority in the long-time range prediction processes, while application with attention mechanism for water very rare. this paper, taking Poyang Lake as a case study, transformer neural network model applied to examine performance prediction, explore effects Yangtze River on fluctuations, analyze influence hyper-parameters (window size layers) lead time accuracy. The result indicated that performs well simulating variations can reflect temporal variation characteristics Lake. testing stage, RMSE values were recorded 0.26–0.70 m, NSE are higher than 0.94. Moreover, inflow has great Lake, especially flood receding periods. contribution rate 80% 270%, respectively. Additionally, hyper-parameters, such window layers, simulation 90 d layer 6 most suitable may affect accuracy prediction. With varied from one seven days, was high 0.46–0.73 value increased 1.37 m 1.82 15 30 constructed paper first be forecasting showed efficiency However, few studies tried use coupling hydrological processes. It suggested used long sequence time-series processes other lakes test performance, providing further scientific evidence control floods management resources.

Язык: Английский

---