Application of a Combination of Machine Learning and Reservoir Physics to Increase Production in a Mature Waterflood Field in the San Jorge Basin in Argentina

2021 ◽  
Author(s):  
Javier Eusebio Gomez ◽  
Marcelo Robles ◽  
Cristian Di Giuseppe ◽  
Federico Galliano ◽  
Jeronimo Centineo ◽  
...  
Keyword(s):  
Machine Learning ◽  
Ensemble Kalman Filter ◽  
Pareto Front ◽  
Closed Loop ◽  
Optimization Techniques ◽  
Large Field ◽  
Initial Model ◽  
Initial Field ◽  
Loop Optimization ◽  
Novel Technology

Abstract This paper presents the process and results of the application of Data Physics to optimize production of a mature field in the Gulf of San Jorge Basin in Argentina. Data Physics is a novel technology that blends the reservoir physics (black oil) used in traditional numerical simulation with machine learning and advanced optimization techniques. Data Physics was described in detail in a prior paper (Sarma, et al SPE-185507-MS) as a physics-based modeling approach augmented by machine learning. In essence, historical production and injection data are assimilated using an Ensemble Kalman Filter (EnKF) to infer the petrophysical parameters and create a predictive model of the field. This model is then used with Evolutionary Algorithms (EA) to find the pareto front for multiple optimization objectives like production, injection and NPV. Ultimately, the main objective of Data Physics is to enable Closed Loop Optimization. The technology was applied on a small section of a very large field in the Gulf of San Jorge comprised of 134 wells including 83 active producers and 27 active water injectors; up to 12 mandrels per well are used to provide with selective injection, while production is carried out in a comingled manner. Production zonal allocation is calculated using an in-house process based on swabbing tests and recovery factors and is used as input to the Data Physics application, while injection allocation is based on tracer logs performed in each injection well twice a year. This paper describes the modeling and optimization phases as well as the implementation in the field and the results obtained after performing two close loop optimization cycles. The initial model was developed between October and December 2018 and initial field implementation took place between January to March 2019. A second optimization cycle was then executed in January 2020 and results observed for several months.

scholarly journals Realization of closed-loop optimization of epitaxial titanium nitride thin-film growth via machine learning

2021 ◽  
Vol 16 ◽  
pp. 100296
Author(s):  
I. Ohkubo ◽  
Z. Hou ◽  
J.N. Lee ◽  
T. Aizawa ◽  
M. Lippmaa ◽  
...  
Keyword(s):  
Thin Film ◽  
Machine Learning ◽  
Titanium Nitride ◽  
Closed Loop ◽  
Film Growth ◽  
Thin Film Growth ◽  
Loop Optimization

The Effect of Chemical Representation on Active Machine Learning Towards Closed-Loop Optimization

2022 ◽  
Author(s):  
Alexander Pomberger ◽  
Antonio Pedrina McCarthy ◽  
Ahmad Khan ◽  
Simon Sung ◽  
Connor Taylor ◽  
...  
Keyword(s):  
Machine Learning ◽  
Chemical Reaction ◽  
Closed Loop ◽  
Reaction Yield ◽  
Catalytic Systems ◽  
Loop Optimization ◽  
Reaction Optimization ◽  
Initial Dataset ◽  
Dataset Size ◽  
The Impact

Multivariate chemical reaction optimization involving catalytic systems is a non-trivial task due to the high number of tuneable parameters and discrete choices. Closed-loop optimization featuring active Machine Learning (ML) represents a powerful strategy for automating reaction optimization. However, the translation of chemical reaction conditions into a machine-readable format comes with the challenge of finding highly informative features which accurately capture the factors for reaction success and allow the model to learn efficiently. Herein, we compare the efficacy of different calculated chemical descriptors for a high throughput generated dataset to determine the impact on a supervised ML model when predicting reaction yield. Then, the effect of featurization and size of the initial dataset within a closed-loop reaction optimization was examined. Finally, the balance between descriptor complexity and dataset size was considered. Ultimately, tailored descriptors did not outperform simple generic representations, however, a larger initial dataset accelerated reaction optimization.

scholarly journals Closed-loop optimization of fast-charging protocols for batteries with machine learning

Nature ◽  
2020 ◽  
Vol 578 (7795) ◽  
pp. 397-402 ◽  
Author(s):  
Peter M. Attia ◽  
Aditya Grover ◽  
Norman Jin ◽  
Kristen A. Severson ◽  
Todor M. Markov ◽  
...  
Keyword(s):  
Machine Learning ◽  
Closed Loop ◽  
Loop Optimization ◽  
Fast Charging

Structural Analysis and Optimal Design of Lightweight Skate for Loading and Unloading

2013 ◽  
Vol 785-786 ◽  
pp. 1258-1261
Author(s):  
In Pyo Cha ◽  
Hee Jae Shin ◽  
Neung Gu Lee ◽  
Lee Ku Kwac ◽  
Hong Gun Kim
Keyword(s):  
Topology Optimization ◽  
Structural Analysis ◽  
Optimal Design ◽  
Optimization Techniques ◽  
Normal Operation ◽  
Stress And Strain ◽  
Initial Model ◽  
Design Variables ◽  
Model Set ◽  
Main Frame

Topology optimization and shape optimization of structural optimization techniques are applied to transport skate the lightweight. Skate properties by varying the design variables and minimize the maximum stress and strain in the normal operation, while reducing the volume of the objective function of optimal design and Skate the static strength of the constraints that should not degrade compared to the performance of the initial model. The skates were used in this study consists of the main frame, sub frame, roll, pin main frame only structural analysis and optimal design was performed using the finite element method. Simplified initial model set design area and it compared to SM45C, AA7075, CFRP, GFRP was using the topology optimization. Strength does not degrade compared to the initial model, decreased volume while minimizing the stress and strain results, the optimum design was achieved efficient lightweight.

scholarly journals Efficient hyperparameter-tuned machine learning approach for estimation of supercapacitor performance attributes

2021 ◽  
Author(s):  
Syed Ishtiyaq Ahmed ◽  
Sreevatsan Radhakrishnan ◽  
Binoy B Nair ◽  
Rajagopalan Thiruvengadathan
Keyword(s):  
Machine Learning ◽  
Surface Area ◽  
Computational Models ◽  
Performance Metrics ◽  
Structural Features ◽  
Optimization Techniques ◽  
Storage Device ◽  
Micropore Surface Area ◽  
Supercapacitor Performance ◽  
Carbon Based

Abstract Recent years have witnessed the rise of supercapacitor as effective energy storage device. Specifically, carbon-based electrodes have been experimentally well studied and used in the fabrication of supercapacitors due to their excellent electrochemical properties. This work reports the development and utilization of highly tuned and efficient Machine Learning (ML) models that give insights into correlation between structural features of electrodes and supercapacitor performance metrics namely specific capacitance, power density and energy density. Artificial Neural Networks (ANN) and Random Forest (RF) models have been employed to predict the various in-operando performance metrics of carbon-based supercapacitors based on three input features such as mesopore surface area, micropore surface area and scan rate. Experimentally measured values of these parameters used for training and testing these two models have been extracted from a set of research papers reported in literature. The optimization techniques and various tuning methodologies adopted for identifying model hyperparameters are discussed in this paper. The authors demonstrate the importance of hyperparameter tuning and optimization in building accurate and reliable computational models.

Sign in / Sign up

Export Citation Format

Share Document