Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Rapidly Varying Flow

Rapidly Varying Flow

Rapidly varying flow (RVF) in open channels is characterized by abrupt changes in flow depth over a short distance, with the rate of depth change relative to distance often approaching unity. These flows are inherently complex due to their transient and multi-dimensional nature, making exact analysis difficult. However, approximate solutions using simplified models provide valuable insights into their behavior.Key Features of Rapidly Varying FlowRVF is commonly observed in scenarios involving...

Streamlines, Streaklines, and Pathlines

Streamlines, Streaklines, and Pathlines

A streamline represents the trajectory that is always tangent to the fluid's velocity vector at any given point. The velocity of a fluid particle is always directed along the streamline, ensuring the particle continuously follows the streamline's path. Streamlines are particularly useful for visualizing the overall direction of flow in a fluid system, and they provide an instantaneous representation of the flow's velocity field. In steady flow, where conditions do not change over...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Assessing ChatGPT's Capability as a New Age Standardized Patient: Qualitative Study.

JMIR medical education·2025

Same author

Retraction notice to "Spatiotemporal convolutional long short-term memory for regional streamflow predictions" [J. Environ. Manag. 350 (2024) 119585].

Journal of environmental management·2024

Same author

Effect of the ethnic, profession, gender, and social background on the perception of upper dental midline deviations in smile esthetics by Chinese and Black raters.

BMC oral health·2023

Same author

A reduced latency regional gap-filling method for SMAP using random forest regression.

iScience·2023

Same author

An end-end deep learning framework for lesion segmentation on multi-contrast MR images-an exploratory study in a rat model of traumatic brain injury.

Medical & biological engineering & computing·2023

Same author

Hydroinformatic tools and their potential in the search for missing persons in rivers.

Forensic science international·2022

Search research articles

Related Experiment Video

Updated: Jul 9, 2025

Spatial Temporal Analysis of Fieldwise Flow in Microvasculature

Spatial Temporal Analysis of Fieldwise Flow in Microvasculature

Published on: November 18, 2019

Spatiotemporal convolutional long short-term memory for regional streamflow predictions.

Abdalla Mohammed¹, Gerald Corzo²

¹Hydroinformatics Department, IHE Delft Institute for Water Education, Westvest 7, 2611 AX, Delft, Netherlands; School of Geography and the Environment, University of Oxford, Oxford, UK.

Journal of Environmental Management

|November 28, 2023

Summary

A novel CNN-LSTM deep learning model effectively predicts daily streamflow across 86 US catchments by integrating spatial and temporal data. Fine-tuning enhanced performance, showing potential for regional rainfall-runoff (RR) modeling.

Keywords:

CAMELS CNN Deep learning LSTM Rainfall-runoff Regional modelling

More Related Videos

Watershed Planning within a Quantitative Scenario Analysis Framework

Watershed Planning within a Quantitative Scenario Analysis Framework

Published on: July 24, 2016

Capturing Flow-weighted Water and Suspended Particulates from Agricultural Canals During Drainage Events

Capturing Flow-weighted Water and Suspended Particulates from Agricultural Canals During Drainage Events

Published on: November 7, 2017

Related Experiment Videos

Last Updated: Jul 9, 2025

Spatial Temporal Analysis of Fieldwise Flow in Microvasculature

Spatial Temporal Analysis of Fieldwise Flow in Microvasculature

Published on: November 18, 2019

Watershed Planning within a Quantitative Scenario Analysis Framework

Watershed Planning within a Quantitative Scenario Analysis Framework

Published on: July 24, 2016

Capturing Flow-weighted Water and Suspended Particulates from Agricultural Canals During Drainage Events

Capturing Flow-weighted Water and Suspended Particulates from Agricultural Canals During Drainage Events

Published on: November 7, 2017

Area of Science:

Hydrology
Deep Learning
Geospatial Analysis

Background:

Rainfall-runoff (RR) modeling is crucial for water resource management but challenging at regional scales.
Existing methods often struggle to capture complex spatial and temporal dynamics inherent in hydrological processes.
Accurate streamflow prediction is vital for flood forecasting, drought management, and water infrastructure planning.

Purpose of the Study:

To develop and evaluate a deep learning approach for simultaneous regional daily streamflow prediction.
To assess the efficacy of a combined Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) architecture for capturing spatiotemporal patterns.
To investigate the impact of fine-tuning the regional model on local sub-clusters for improved predictive accuracy.

Main Methods:

A sequential CNN-LSTM deep learning architecture was employed to process spatially distributed daily meteorological data (precipitation, max/min temperature).
The model was trained regionally on 86 US catchments and subsequently fine-tuned on three local sub-clusters.
Performance was evaluated using Nash-Sutcliffe efficiency (NSE) and compared against standalone CNN, LSTM, and Artificial Neural Network (ANN) models.

Main Results:

The fine-tuned CNN-LSTM model achieved a median NSE of 0.62 across the 86 catchments.
65% of the stations reached an NSE greater than 0.6, indicating strong predictive performance.
The regional CNN-LSTM model outperformed other regional deep learning models and showed comparable results to a locally trained LSTM.

Conclusions:

The CNN-LSTM deep learning approach demonstrates significant potential for effective regional rainfall-runoff modeling.
Integrating spatial information (CNN) with temporal dependencies (LSTM) is key to capturing complex hydrological processes.
Fine-tuning regional models can further enhance streamflow prediction accuracy at local scales.