On application of machine learning method for history matching and forecasting of times series data from hydrocarbon recovery process using water flooding

Pal, Mayur

doi:10.1080/10916466.2021.1918712

Cited by 17 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning, being an iterative process utilizing data to unveil underlying patterns, is well suited for solving inverse problems related to geothermal reservoir modeling. AI and ML technologies can also help in developing data-oriented history matching models, like the AI-and ML-based history matching approach proposed in [31]; additionally, AI and ML methods can also be used to quantify porosity and permeability trends, which can be used for THMC modeling, as proposed in [32]. Numerical simulations in geothermal reservoir modeling provide valuable insights into the behavior and characteristics of subsurface formations.…”

Section: Application Of New Technologymentioning

confidence: 99%

Unlocking Geothermal Energy: A Thorough Literature Review of Lithuanian Geothermal Complexes and Their Production Potential

Memon,

Makauskas,

Kaminskaite-Baranauskiene

et al. 2024

Energies

Self Cite

View full text Add to dashboard Cite

Lithuania is located on the East of Baltic sedimentary basin and has a geothermal anomaly situated in the southwestern region of the country. There are two primary geothermal complexes within the anomaly, composed of Cambrian and Devonian aquifers. The Cambrian formation is composed of sandstones that have a reservoir temperature reaching up to 96 °C (depth > 2000 m). The Devonian aquifer is composed of unconsolidated sands of Parnu–Kemeri and has a reservoir temperature of up to 46 °C (depth > 1000 m). Historically, both formations have been investigated for geothermal energy production. In this article, we present a detailed literature review of the geothermal work carried out on both formations, including past, present, and some possible future studies. The study presented in this paper highlights the key findings of previous research work, summarizes the research gaps, and then elaborates on the possible applications of emerging technologies to bridge the research gaps and improve our understanding of geothermal complexes in Lithuania. Although it is not the main aim of this article, this article also touches upon the important need to develop 2D/3D numerical models, to quantify uncertainties, in the evaluation of the geothermal potential in Lithuania for commercial development. This study also highlights possibilities of extending geothermal development to depleted hydrocarbon reservoirs through repurposing the high-water-production wells. Moreover, from the literature review, it can be concluded that the Lithuanian geothermal aquifers are hyper-saline in nature and temperature changes lead to the deposition of salts both upstream and downstream of the reservoir. Therefore, there is a need for developing multiphysics thermo-mechanical–chemical (THMC) models for evaluation of reservoir behavior. The literature also describes the potential use and development of the THMC model as a part of future work that must be carried out.

show abstract

Section: Application Of New Technologymentioning

confidence: 99%

Unlocking Geothermal Energy: A Thorough Literature Review of Lithuanian Geothermal Complexes and Their Production Potential

Memon,

Makauskas,

Kaminskaite-Baranauskiene

et al. 2024

Energies

Self Cite

View full text Add to dashboard Cite

show abstract

“…Those cases can be related to having few training samples due to unavailable field data, not taking into consideration the fracture geometry, etc. [106]. Pal M. [106] was the first to develop a DL-RNN-LSTM model to predict future oil and water production rates in a time series way for a tight carbonate reservoir under water-flooding with long horizontal wells, using a limited amount of real injection and production data as inputs.…”

Section: Dynamic Machine Learning Modelsmentioning

confidence: 99%

“…[106]. Pal M. [106] was the first to develop a DL-RNN-LSTM model to predict future oil and water production rates in a time series way for a tight carbonate reservoir under water-flooding with long horizontal wells, using a limited amount of real injection and production data as inputs. Due to data collection issues, such as challenges in injection/production measurements, in the collection of highfrequency injection/production data and in variations of injection/production data, data quality issues emerged; thus, simple manual data pre-processing procedures (e.g., checks for data formatting errors, missing values, repeated rows, spelling inconsistencies, etc.)…”

Section: Dynamic Machine Learning Modelsmentioning

confidence: 99%

Applications of Machine Learning in Subsurface Reservoir Simulation—A Review—Part II

Samnioti,

Gaganis

2023

Energies

View full text Add to dashboard Cite

In recent years, Machine Learning (ML) has become a buzzword in the petroleum industry, with numerous applications which guide engineers in better decision making. The most powerful tool that most production development decisions rely on is reservoir simulation with applications in multiple modeling procedures, such as individual simulation runs, history matching and production forecast and optimization. However, all of these applications lead to considerable computational time and computer resource-associated costs, rendering reservoir simulators as not fast and robust enough, and thus introducing the need for more time-efficient and intelligent tools, such as ML models which are able to adapt and provide fast and competent results that mimic the simulator’s performance within an acceptable error margin. In a recent paper, the developed ML applications in a subsurface reservoir simulation were reviewed, focusing on improving the speed and accuracy of individual reservoir simulation runs and history matching. This paper consists of the second part of that study, offering a detailed review of ML-based Production Forecast Optimization (PFO). This review can assist engineers as a complete source for applied ML techniques in reservoir simulation since, with the generation of large-scale data in everyday activities, ML is becoming a necessity for future and more efficient applications.

show abstract

“…A recent study that discussed the use of RNN-LSTM to estimate oil, gas, and water outputs of wells based on injection patterns in a time-series manner was investigated by the author. The RNN-LSTM model was able to estimate oil, water, and gas production with a first-year accuracy of over 90% and production values for up to 5 years with a 73.63 percent accuracy [ 7 ].…”

Section: Related Workmentioning

confidence: 99%

Well Performance Classification and Prediction: Deep Learning and Machine Learning Long Term Regression Experiments on Oil, Gas, and Water Production

Ibrahim

Alharbi

Alzahrani

et al. 2022

Sensors

View full text Add to dashboard Cite

In the oil and gas industries, predicting and classifying oil and gas production for hydrocarbon wells is difficult. Most oil and gas companies use reservoir simulation software to predict future oil and gas production and devise optimum field development plans. However, this process costs an immense number of resources and is time consuming. Each reservoir prediction experiment needs tens or hundreds of simulation runs, taking several hours or days to finish. In this paper, we attempt to overcome these issues by creating machine learning and deep learning models to expedite the process of forecasting oil and gas production. The dataset was provided by the leading oil producer, Saudi Aramco. Our approach reduced the time costs to a worst-case of a few minutes. Our study covered eight different ML and DL experiments and achieved its most outstanding R2 scores of 0.96 for XGBoost, 0.97 for ANN, and 0.98 for RNN over the other experiments.

show abstract

On application of machine learning method for history matching and forecasting of times series data from hydrocarbon recovery process using water flooding

Cited by 17 publications

References 22 publications

Unlocking Geothermal Energy: A Thorough Literature Review of Lithuanian Geothermal Complexes and Their Production Potential

Unlocking Geothermal Energy: A Thorough Literature Review of Lithuanian Geothermal Complexes and Their Production Potential

Applications of Machine Learning in Subsurface Reservoir Simulation—A Review—Part II

Well Performance Classification and Prediction: Deep Learning and Machine Learning Long Term Regression Experiments on Oil, Gas, and Water Production

Contact Info

Product

Resources

About