Recurrent Neural Network Architecture Search for Geophysical Emulation

Maulik, Romit; Égelé, Romain; Lusch, Bethany; Balaprakash, Prasanna

doi:10.48550/arxiv.2004.10928

Cited by 9 publications

(11 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The three gates are called: forget gate f g , input gate i g and output gate o g , which operate the information flow by erasing, writing and reading, respectively. Therefore, LSTM models memorize information at different intervals and are suitable to predict time series with a certain duration interval [30,31].…”

Section: Long Short Term Memorymentioning

confidence: 99%

Water Flow Forecasting Based on River Tributaries Using Long Short-Term Memory Ensemble Model

et al. 2021

View full text Add to dashboard Cite

Water flow forecasts are an essential information for energy production, management and hydropower control. Advanced actions to optimize electricity production can be taken based on predicted information. This work proposes an ensemble strategy using recurrent neural networks to generate a forecast of water flow at Jirau Hydroelectric Power Plant (HPP), installed on the Madeira River in Brazil. The ensemble strategy consists of combining three long short-term memory (LSTM) networks that model the Madeira River and two of its tributaries: Mamoré and Abunã rivers. The historical data from streamflow of the Madeira river and its tributaries are used to validate the ensemble LSTM model, where each time series of river tributaries are modeled separated by LSTM models and the result used as input for another LSTM model in order to forecast the streamflow of the main river. The experimental results present low errors for training and test sets for individual LSTM networks and ensemble model. In addition, these results were compared with the operational forecasts performed by Jirau HPP. The proposed model showed better accuracy in four of the five scenarios tested, which indicates a promising approach to be explored in water flow forecasting based on river tributaries.

show abstract

Section: Long Short Term Memorymentioning

confidence: 99%

Water Flow Forecasting Based on River Tributaries Using Long Short-Term Memory Ensemble Model

et al. 2021

View full text Add to dashboard Cite

show abstract

“…This is because solving PDE forward-models for such systems may require very fine spatiotemporal numerical discretizations which cause a significant bottleneck in design and forecast tasks [44]. The prospect of bypassing traditional numerical methods and building surrogates from data alone [26,36,37,41] is attractive for multiple applications ranging from engineering design [4,38] and control [35,23] to climate modeling [8,9,28]. This is because data-driven ROMs allow for rapid predictions of nonlinear dynamics unencumbered by the stability-based arXiv:2007.12167v1 [physics.comp-ph] 23 Jul 2020 limitations of numerical discretizations.…”

Section: Introductionmentioning

confidence: 99%

Latent-space time evolution of non-intrusive reduced-order models using Gaussian process emulation

Maulik

Botsas

Ramachandra

et al. 2021

Physica D: Nonlinear Phenomena

Self Cite

View full text Add to dashboard Cite

“…[33] introduced a multi-agent reinforcement learning framework as an automated discovery tool for turbulence models and applied it to forced homogeneous isotropic turbulence. Besides turbulence closure modeling, deep learning has been proved to be very successful for challenging problems such as super-resolution of turbulent flows [34][35][36], data-driven modeling of chaotic systems [37][38][39], reduced order modeling of high-dimensional multiphysics systems [40][41][42][43], and developing forecast models for complex physical systems [44][45][46][47].…”

Section: Introductionmentioning

confidence: 99%

Data assimilation empowered neural network parametrizations for subgrid processes in geophysical flows

Pawar

San

2021

Phys. Rev. Fluids

View full text Add to dashboard Cite

In the past couple of years, there is a proliferation in the use of machine learning approaches to represent subgrid scale processes in geophysical flows with an aim to improve the forecasting capability and to accelerate numerical simulations of these flows. Despite its success for different types of flow, the online deployment of a data-driven closure model can cause instabilities and biases in modeling the overall effect of subgrid scale processes, which in turn leads to inaccurate prediction. To tackle this issue, we exploit the data assimilation technique to correct the physics-based model coupled with the neural network as a surrogate for unresolved flow dynamics in multiscale systems. In particular, we use a set of neural network architectures to learn the correlation between resolved flow variables and the parameterizations of unresolved flow dynamics and formulate a data assimilation approach to correct the hybrid model during their online deployment. We illustrate our framework in a application of the multiscale Lorenz 96 system for which the parameterization model for unresolved scales is exactly known. Our analysis, therefore, comprises a predictive dynamical core empowered by (i) a data-driven closure model for subgrid scale processes, (ii) a data assimilation approach for forecast error correction, and (iii) both data-driven closure and data assimilation procedures. We show significant improvement in the long-term perdition of the underlying chaotic dynamics with our framework compared to using only neural network parameterizations for future prediction. Moreover, we demonstrate that these data-driven parameterization models can handle the non-Gaussian statistics of subgrid scale processes, and effectively improve the accuracy of outer data assimilation workflow loops in a modular non-intrusive way.

show abstract

Recurrent Neural Network Architecture Search for Geophysical Emulation

Cited by 9 publications

References 0 publications

Water Flow Forecasting Based on River Tributaries Using Long Short-Term Memory Ensemble Model

Water Flow Forecasting Based on River Tributaries Using Long Short-Term Memory Ensemble Model

Latent-space time evolution of non-intrusive reduced-order models using Gaussian process emulation

Data assimilation empowered neural network parametrizations for subgrid processes in geophysical flows

Contact Info

Product

Resources

About