Streamflow Prediction

Streamflow prediction aims to accurately forecast river discharge, crucial for water resource management and flood control. Recent research heavily emphasizes the use of machine learning, particularly deep learning architectures like recurrent neural networks (RNNs), transformers, and convolutional neural networks (CNNs), often combined with techniques like attention mechanisms and graph neural networks to capture complex spatiotemporal dynamics. These models are being improved through methods such as domain adaptation to address data scarcity in many regions and constrained reasoning and learning to incorporate physical constraints. The resulting improvements in accuracy and uncertainty quantification enhance the reliability of streamflow predictions, supporting more informed decision-making in water resource management.

Papers

November 14, 2024

Caravan MultiMet: Extending Caravan with Multiple Weather Nowcasts and Forecasts
Guy Shalev, Frederik Kratzert
Forecast Utterance Hydrological Model Streamflow Prediction Multi Commodity Pickup Convection Nowcasting

October 23, 2024

Evaluating Deep Learning Approaches for Predictions in Unmonitored Basins with Continental-scale Stream Temperature Models
Jared D. Willard, Fabio Ciulla, Helen Weierbach, Vipin Kumar, Charuleka Varadharajan
Deep Learning Deep Learning Model Machine Learning Model Human Prediction Unsupervised Setting Streamflow Prediction VVV Basin Curve

October 21, 2024

Hydra-LSTM: A semi-shared Machine Learning architecture for prediction across Watersheds
Karan Ruparell, Robert J. Marks, Andy Wood, Kieran M. R. Hunt, Hannah L. Cloke, Christel Prudhomme, Florian Pappenberger, Matthew Chantry
Human Prediction Long Short Term Memory Streamflow Prediction

October 18, 2024

Hierarchical Conditional Multi-Task Learning for Streamflow Modeling
Shaoming Xu, Arvind Renganathan, Ankush Khandelwal, Rahul Ghosh, Xiang Li, Licheng Liu, Kshitij Tayal, Peter Harrington, Xiaowei Jia, Zhenong Jin, Jonh Nieber, Vipin Kumar
Multi Task Streamflow Prediction

July 29, 2024

Hierarchically Disentangled Recurrent Network for Factorizing System Dynamics of Multi-scale Systems
Rahul Ghosh, Zac McEachran, Arvind Renganathan, Kelly Lindsay, Somya Sharma, Michael Steinbach, John Nieber, Christopher Duffy, Vipin Kumar
Multi Scale Data Assimilation Forward Model Multiscale System Disentangled Learning System Dynamic Streamflow Prediction

June 11, 2024

Towards Generalized Hydrological Forecasting using Transformer Models for 120-Hour Streamflow Prediction
Bekir Z. Demiray, Ibrahim Demir
Transformer Model LSTM Network Streamflow Prediction

May 31, 2024

Streamflow Prediction with Uncertainty Quantification for Water Management: A Constrained Reasoning and Learning Approach
Mohammed Amine Gharsallaoui, Bhupinderjeet Singh, Supriya Savalkar, Aryan Deshwal, Yan Yan, Ananth Kalyanaraman, Kirti Rajagopalan, Janardhan Rao Doppa
Gaussian Process Uncertainty Quantification Physic Based Model Learning Approach AI Reasoning Hydrological Model Streamflow Prediction Water Resource

April 22, 2024

Toward Routing River Water in Land Surface Models with Recurrent Neural Networks
Mauricio Lima, Katherine Deck, Oliver R. A. Dunbar, Tapio Schneider
Language Model Recurrent Neural Network Streamflow Prediction Land Surface Water Resource

April 20, 2024

Comparative Analysis on Snowmelt-Driven Streamflow Forecasting Using Machine Learning Techniques
Ukesh Thapa, Bipun Man Pati, Samit Thapa, Dhiraj Pyakurel, Anup Shrestha
Machine Learning Deep Learning Model Comparative Study Temporal Convolutional Network Streamflow Prediction

April 11, 2024

A Parsimonious Setup for Streamflow Forecasting using CNN-LSTM
Sudan Pokharel, Tirthankar Roy
Long Short Term Memory Parsimonious Machine Learning Streamflow Prediction

December 10, 2023

TransGlow: Attention-augmented Transduction model based on Graph Neural Networks for Water Flow Forecasting
Naghmeh Shafiee Roudbari, Charalambos Poullis, Zachary Patterson, Ursula Eicker
Graph Neural Network Spatiotemporal Forecasting Streamflow Prediction

October 3, 2023

Uncertainty Quantification in Inverse Models in Hydrology
Somya Sharma Chatterjee, Rahul Ghosh, Arvind Renganathan, Xiang Li, Snigdhansu Chatterjee, John Nieber, Christopher Duffy, Vipin Kumar
Uncertainty Quantification Inverse Problem Inverse Modeling Streamflow Prediction

May 21, 2023

Temporal Fusion Transformers for Streamflow Prediction: Value of Combining Attention with Recurrence
Sinan Rasiya Koya, Tirthankar Roy
Recurrent Neural Network Long Short Term Memory Human Attention Net Present Value Temporal Difference Type Recurrence Temporal Fusion Transformer Streamflow Prediction

April 4, 2023

Fully Convolutional Networks for Dense Water Flow Intensity Prediction in Swedish Catchment Areas
Aleksis Pirinen, Olof Mogren, Mårten Västerdal
Convolutional Neural Network Streamflow Prediction

February 10, 2023

Attention-based Domain Adaptation Forecasting of Streamflow in Data-Sparse Regions
Roland Oruche, Fearghal O'Donncha
Domain Adaptation Sparse Data Streamflow Prediction

October 12, 2022

Probabilistic Inverse Modeling: An Application in Hydrology
Somya Sharma, Rahul Ghosh, Arvind Renganathan, Xiang Li, Snigdhansu Chatterjee, John Nieber, Christopher Duffy, Vipin Kumar
Application Proficiency Inverse Problem Explainable Model Inverse Modeling Streamflow Prediction

December 6, 2021

Transfer learning to improve streamflow forecasts in data sparse regions
Roland Oruche, Lisa Egede, Tracy Baker, Fearghal O'Donncha
Transfer Learning Raw Data Long Short Term Memory Formality Transfer Sparse Data Hydrological Model Streamflow Prediction

Streamflow Prediction

Papers

Caravan MultiMet: Extending Caravan with Multiple Weather Nowcasts and Forecasts

Evaluating Deep Learning Approaches for Predictions in Unmonitored Basins with Continental-scale Stream Temperature Models

Hydra-LSTM: A semi-shared Machine Learning architecture for prediction across Watersheds

Hierarchical Conditional Multi-Task Learning for Streamflow Modeling

Hierarchically Disentangled Recurrent Network for Factorizing System Dynamics of Multi-scale Systems

Towards Generalized Hydrological Forecasting using Transformer Models for 120-Hour Streamflow Prediction

Streamflow Prediction with Uncertainty Quantification for Water Management: A Constrained Reasoning and Learning Approach

Toward Routing River Water in Land Surface Models with Recurrent Neural Networks

Comparative Analysis on Snowmelt-Driven Streamflow Forecasting Using Machine Learning Techniques

A Parsimonious Setup for Streamflow Forecasting using CNN-LSTM

TransGlow: Attention-augmented Transduction model based on Graph Neural Networks for Water Flow Forecasting

Uncertainty Quantification in Inverse Models in Hydrology

Temporal Fusion Transformers for Streamflow Prediction: Value of Combining Attention with Recurrence

Fully Convolutional Networks for Dense Water Flow Intensity Prediction in Swedish Catchment Areas

Attention-based Domain Adaptation Forecasting of Streamflow in Data-Sparse Regions

Probabilistic Inverse Modeling: An Application in Hydrology

Transfer learning to improve streamflow forecasts in data sparse regions