Geochemical equilibrium determination using an artificial neural network in compositional reservoir flow simulation

Guérillot, Dominique; Bruyelle, Jérémie

doi:10.1007/s10596-019-09861-4

Cited by 25 publications

(13 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this current era, various AI methods covered both artificial neural network (ANN) [31], and genetic algorithm because it is the dominant source for building an intelligent system to extract hidden cues from data and show their importance and effectiveness [32,33]. In [34] the authors developed an ANN model for energy forecasting using multi-layer perceptron (MLP) technique with different factors and the results were encouraging than the simple ML technique.…”

Section: Literature Reviewmentioning

confidence: 99%

Short-Term Energy Forecasting Framework Using an Ensemble Deep Learning Approach

2021

View full text Add to dashboard Cite

Industrial and building sectors demand efficient smart energy strategies, techniques of optimization, and efficient management for reducing global energy consumption due to the increasing world population. Nowadays, various artificial intelligence (AI) based methods are utilized to perform optimal energy forecasting, different simulation tools, and engineering methods to predict future demand based on historical data. Nevertheless, nonlinear energy demand modeling is still unfledged for a better solution to handle short-term and long-term dependencies and avoid static nature because it is purely on historical datadriven. In this paper, we propose an ensemble deep learning-based approach to predict and forecast energy demand and consumption by using chronological dependencies. Our system initially processes the data, cleaning, normalization, and transformation to ensure the model performance. Furthermore, the preprocess data is fed to propose the ensemble model to extract hybrid discriminative features by using convolution neural network (CNN), stacked, and bi-directional long-short term memory (LSTM) architectures. We trained our proposed system on the historical data to forecast the energy demand and consumption with a different time interval. In the proposed technique, we utilized the concept of active learning based on moving windows to ensure and improve the prediction performance of the system. The proposed system could be applicable to employ energy consumption in industrial and building sectors to demonstrate their significance and effectiveness. We evaluated the proposed system by using benchmark, residential UCI, and local Korean commercial building datasets. We conducted different extensive experimentation to show the error rate and used various kinds of evaluation matrices, which indicate the lower error rate of the proposed system.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Short-Term Energy Forecasting Framework Using an Ensemble Deep Learning Approach

2021

View full text Add to dashboard Cite

show abstract

“…This largely depends on the problem at hand and on the skills of the modeller. While we rather focused on gradient boosting decision-tree regressors for the reasons briefly discussed in section 3, a consistent number of authors successfully applied artificial neural networks to a variety of geochemical problems and coupled simulations (Laloy and Jacques, 2019;Guérillot and Bruyelle, 2020;Prasianakis et al, 2020). We would like to point out that transforming geochemistry -as any other process -in a pure machine learning problem requires on one hand skills that are usually difficult for the geoscientists to acquire, and on the other it fatally overlooks domain knowledge that can be used to improve at least the learning task, which will directly result in accurate and robust predictions, as we demonstrated in section 4.…”

Section: Discussion and Future Workmentioning

confidence: 99%

DecTree v1.0 – Chemistry speedup in reactive transport simulations: purely data-driven and physics-based surrogates

Lucia¹,

Kühn²

2021

Preprint

View full text Add to dashboard Cite

Abstract. The computational costs associated with coupled reactive transport simulations are mostly due to the chemical subsystem: replacing it with a pre-trained statistical surrogate is a promising strategy to achieve decisive speedups at the price of small accuracy losses and thus to extend the scale of problems which can be handled. We introduce a hierarchical coupling scheme in which full physics, equation-based geochemical simulations are partially replaced by surrogates. Errors on mass balance resulting from multivariate surrogate predictions effectively assess the accuracy of multivariate regressions at runtime: inaccurate surrogate predictions are rejected and the more expensive equation-based simulations are run instead. Gradient boosting regressors such as xgboost, not requiring data standardization and being able to handle Tweedie distributions, proved to be a suitable emulator. Finally, we devise a surrogate approach based on geochemical knowledge, which overcomes the issue of robustness when encountering previously unseen data, and which can serve as basis for further development of hybrid physics-AI modelling.

show abstract

Section: Discussion and Future Workmentioning

confidence: 99%

“…We found out that the Tweedie distribution is suited to reproduce many of the variables in the training dataset. The Tweedie distribution is a special case of exponential dispersion models introduced by Tweedie (1984) and toroughly described by Jørgensen (1987), which finds application in many actuarial and signal processing processes (Hassine et al, 2017). A Random Variable Y is a Tweedie distribution of parameter p if Y ≥ 0, E[Y ] = µ and V ar(Y ) = σ 2 µ p .…”

Section: Fully Data-driven Approachmentioning

confidence: 99%

“…A surrogate is a statistical multivariate regressors which has to be trained in advance on a set of precalculated "full physics" solutions of the geochemical model at hand, spanning the whole parameter range expected for the simulations. Since the regressors are much quicker to compute than the setup and integration of a DAE system of equations, this promises a significant speedup and has thus found resonance in the scientific community (e.g., De Lucia et al, 2017;Laloy and Jacques, 2019;Guérillot and Bruyelle, 2020). However, all approximations and especially purely data-driven surrogates introduce accuracy losses into the coupled simulations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Chemistry speedup in reactive transport simulations: purely data-driven and physics-based surrogates

Lucia¹,

Kühn²

2020

Preprint

View full text Add to dashboard Cite

show abstract

Geochemical equilibrium determination using an artificial neural network in compositional reservoir flow simulation

Cited by 25 publications

References 33 publications

Short-Term Energy Forecasting Framework Using an Ensemble Deep Learning Approach

Short-Term Energy Forecasting Framework Using an Ensemble Deep Learning Approach

DecTree v1.0 – Chemistry speedup in reactive transport simulations: purely data-driven and physics-based surrogates

Chemistry speedup in reactive transport simulations: purely data-driven and physics-based surrogates

Contact Info

Product

Resources

About