Development of machine learning predictive models for history matching tight gas carbonate reservoir production profiles

Brantson, Eric Thompson; Ju, Binshan; Omisore, Busayo Oreoluwa; Wu, Dan; Selase, Aphu Elvis; Liu, Nannan

doi:10.1088/1742-2140/aaca44

Cited by 15 publications

(4 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Again, the focus of their work was on blasting effects but not in relation to presplit blasting technique. Lastly, it can be observed from the above literature reviewed that more attention needs to be geared towards this technique using AI tools [48][49][50].…”

Section: Artificial Intelligence Application In Drilling and Blastingmentioning

confidence: 99%

A Comprehensive Review of Traditional, Modern and Advanced Presplit Drilling and Blasting in the Mining and Construction Industries

Brantson,

Appiah,

Alhassan

et al. 2024

Journal of Petroleum and Mining Engineering

View full text Add to dashboard Cite

Presplit drilling and blasting are frequent excavation methods used in the mining and construction industries, but they can be challenging to implement which can also lead to inconsistent results. This review identifies the key mechanisms behind presplit drilling and blasting, and discusses the significant impact that this technique has on the industry. It also emphasizes the major issues that must be addressed before presplit drilling and blasting can be properly implemented, such as the drilling program.The review then introduces the potential application of Artificial Intelligence (AI) tools in presplitting, and discusses how AI can be used to optimize the future design of presplit blast patterns, predict the performance of presplit blasts, and monitor the progress of presplit blasts in real time. The application of AI tools in presplitting has the potential to improve the safety, efficiency, and cost-effectiveness of blasting operations. The review concludes by discussing the future of drilling and blasting in the mining and construction industries, and emphasizes the role of AI optimization as a future tool in moving this field into the autonomous dimension.

show abstract

Section: Artificial Intelligence Application In Drilling and Blastingmentioning

confidence: 99%

A Comprehensive Review of Traditional, Modern and Advanced Presplit Drilling and Blasting in the Mining and Construction Industries

Brantson,

Appiah,

Alhassan

et al. 2024

Journal of Petroleum and Mining Engineering

View full text Add to dashboard Cite

show abstract

“…Apart from the widely used ANNs, many more ML techniques can help solve the inverse HM problem. Brantson et al [127] tried several ML techniques to match tight gas reservoirs, namely Multi-variate Adaptive Regression Splines (MARS) [128], the Stochastic Gradient Boosting (SGB) algorithm, which entails growing DTs using a training set that is split to form new trees that boost the predictions [129], and single-pass GRNNs. The results were compared with those of a random forest (RF) model.…”

Section: History Matching Based On ML Models Other Than Annsmentioning

confidence: 99%

“…ANNs with stochastic optimization [106,107] ANNs with dimensionality reduction methods [108] Ensembles of ANNs [109] RBFNNs, Generalized Regression ANNs, FSSC and ANFIS stochastic optimization [110][111][112] Direct history matching Supervised ANNs [114][115][116][117][118][119][120]126] Bayesian ML models [121,122,124,125] MARS, DTs, single-pass GRNNs [127] Unsupervised Self-Organizing Map (SOM) [131] Supervised SVR with dimensionality reduction and optimization [135] RNN [142,143] CNN [148,158] Unsupervised GAN [149,159] Piecewise Reconstruction from a Dictionary (PRaD) with pluri-PCA [151] Convolutional AutoEncoders [152,157] Reinforcement learning Reinforcement learning models [103,162] Currently, dozens of professional products used to set up ML models are available to developers, might that be related to research or commercial products. This palette includes client tools developed by major players in the market such as Google and Microsoft (Google cloud AI platform, Azure machine learning) as well as free tools such as TensorFlow by Google and the Anaconda distribution for Python.…”

Section: Indirect History Matching Supervisedmentioning

confidence: 99%

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

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 that guide engineers toward better decision making. The most powerful tool that most production development decisions rely on is reservoir simulation with applications in numerous modeling procedures, such as individual simulation runs, history matching and production forecast and optimization. However, all these applications lead to considerable computational time- and resource-associated costs, and rendering reservoir simulators is not fast or robust, thus introducing the need for more time-efficient and smart tools like ML models which can adapt and provide fast and competent results that mimic simulators’ performance within an acceptable error margin. The first part of the present study (Part I) offers a detailed review of ML techniques in the petroleum industry, specifically in subsurface reservoir simulation, for cases of individual simulation runs and history matching, whereas ML-based production forecast and optimization applications are presented in Part II. This review can assist engineers as a complete source for applied ML techniques since, with the generation of large-scale data in everyday activities, ML is becoming a necessity for future and more efficient applications.

show abstract

“…large amounts of data, high dimensionality, and non-linearity of the input data. These applications include but are not limited to groundwater flow modelling (e.g., Sahoo et al, 2017), geophysics (e.g., Ehret, 2010Köhler et al, 2010;Raiche, 1991), pore-scale modelling (e.g., Menke et al, 2021;Wang et al, 2021), reservoir geology (e.g., Demyanov et al, 2019;Su et al, 2018), subsurface modelling (e.g., Pyrcz et al, 2006;Scheidt et al, 2015), geological uncertainty (e.g., Caers et al, 2010;Maldonado-Cruz and Pyrcz, 2021), reservoir engineering (e.g., Brantson et al, 2018), or production optimization (e.g., Insuasty et al, 2015).…”

Section: Manuscript Submitted To Transport In Porous Mediamentioning

confidence: 99%

Automated Classification of Well Test Responses in Naturally Fractured Reservoirs Using Unsupervised Machine Learning

Freites¹,

Corbett²,

Rongier

et al. 2022

Preprint

View full text Add to dashboard Cite

Understanding the impact of fractures on fluid flow is fundamental for developing geoenergy reservoirs. Pressure Transient Analysis (PTA) could play a key role for fracture characterization purposes if proper links are built between the pressure derivative responses () and the fracture properties; however, the PTA process is particularly challenging in the presence of fractures because they can manifest themselves in many different . Our work aims at providing a tool for effectively handling the diversity in fracture-induced by automatically classifying them and identifying characteristic patterns in the data. To represent this diversity of in naturally fractured reservoirs, we created a synthetic dataset from numerical simulation that comprised 2560 , corresponding to 10 stochastic realizations of 256 combinations of different fracture intensities and average fracture apertures, organized in two orthogonal fracture sets. To group the , we developed an unsupervised maching learning approach that can distinguish beyond the variable temporality of the signals by leveraging the dynamic time warping algorithm in a k-medoids clustering. Our results suggest that the approach is effective at recognizing similar shapes in the first pressure derivatives if the second pressure derivatives are used as the classification variable. The analysis of the Naturally Fracture Reservoirs dataset indicated that 12 clusters were appropriate to describe the full collection of . We suggest that the respective cluster medoids can be regarded as reference curves for various Naturally Fractured Reservoirs and be used as a guide in the interpretation of real well tests. The classification exercise also allowed us to identify the key geological features that influence the , namely 1) the distance from the wellbore to the closest fracture(s), 2) the local/global fracture connectivity, and 3) the local/global fracture intensity.

show abstract

Development of machine learning predictive models for history matching tight gas carbonate reservoir production profiles

Cited by 15 publications

References 43 publications

A Comprehensive Review of Traditional, Modern and Advanced Presplit Drilling and Blasting in the Mining and Construction Industries

A Comprehensive Review of Traditional, Modern and Advanced Presplit Drilling and Blasting in the Mining and Construction Industries

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

Automated Classification of Well Test Responses in Naturally Fractured Reservoirs Using Unsupervised Machine Learning

Contact Info

Product

Resources

About