About this Research Topic
Deep Learning (DL) is a rapidly evolving sub-field of Machine Learning (ML) which has been developed to achieve a sophisticated performance in complex-task solving that is akin to that of the human brain neural system. Deep Learning Models (DLMs) are powerful tools which have been used widely in a number of scientific fields and endeavours, among which is hydrological and environmental research. Typical examples of DLM application in the field of hydrology include the implementation of Feed Forward Neural Networks (FFNN), Gated Recurrent Unit (GRU), and Long Short-Term Memory (LSTM) models to perform complex tasks such as hydrological time series modelling, water quality modelling, water resources management, and more. With the development of Artificial Intelligence (AI), new techniques, such as attention mechanism, have been coupled with DLMs in the attempt to improve their performance; however, the outcome of such coupling in hydrological and environmental research remains relatively unexplored.
This Research Topic aims to address various issues associated with the usage of ‘enhanced’ DLMs in the field of hydrology and environmental modelling, such as, inter alia, uncertainty of hydrological time series modelling and accuracy of water quality modelling. This Research Topic, therefore, aims to accrue research aimed at testing the applicability and effectiveness of state-of-art DLMs in solving important and complex issues in water sciences.
Potential themes of interest include, but are not limited to:
(1) Hydrological time series modelling using advanced deep learning models, such as surface and groundwater water level forecasting and water temperature prediction;
(2) Coupling of deep learning and hydrological models for watershed runoff and nutrients modelling;
(3) Rainfall-runoff modelling using advanced deep learning models;
(4) Surface and groundwater quality modelling employing advanced deep learning models; and,
(5) Lake or reservoir eutrophication forecasting by coupling big-data and advanced deep learning models.
Keywords: Deep learning, LSTM, GRU, hydrology, environmental modelling
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.