Algorithm-X Lab | BY KC Cheung
Machine learning in oil & gas can be used to enhance the capabilities of this increasingly competitive sector. Not only can it help to streamline the workforce. The technology can also be used to optimise extraction and deliver accurate models.
These benefits are just some of the reasons why machine learning in oil & gas is becoming increasingly important.
Here are 10 ways that the impact of machine learning in oil & gas industries is being felt.
Table of Contents
- Accurate Modelling
- Pinpointing Exactly Where to Dig with Machine Learning
- Applying Machine Learning in oil & gas to Improve Subsurface Characterisation
- Optimizing Drilling Operations
- Solving Problems Quickly with Machine Learning Applications
- Predictive Maintenance
- Internet of Things
- Predictive Software For Energy Purchases Customer Market
- Replacing Manual Workers
- Machine Learning to Predict Operational Outcomes
One of the most noticeable impacts of machine learning in oil & gas focused industries is how it transforms discovery processes.
Applications employing machine learning in oil & gas enable computers to quickly and accurately analyse huge amounts of data. This includes being able to sift precisely through signals and noise in seismic data. After this information has been gathered and analysed modern software applications can construct accurate geological models.
This allows operatives to predict, accurately, what is beneath the surface before drilling has begun. It is believed that, if adopted over the entire industry, this will decrease the number of dry wellheads by 10%
Current Applications in Modelling
One current application of machine learning in oil & gas can be seen in the Dutch Central Graben in the North Sea. By using machine learning in oil & gas in this manner has allowed engineers to auto-track a Jurassic seismic horizon. This has been done with only a few manual seed points.
The latest generations of algorithms are producing more detailed and accurate results than any previous modeling. These algorithms also don’t lose their accuracy when asked to analyse difficult terrain.
Faults or stratigraphically complex areas can be accurately mapped in detail. There is always a need for the models to be checked.
However, so far, this application is proving itself to be quicker and just as accurate as a human model.
Machine Learning can Improve Drilling Operations
Despite these developments, scientists have been slow to fully realise the benefits of machine learning in oil & gas industries. Multivariate modelling is now becoming the most reliable way to develop resource plays.
This allows users to maximize tools such as NPV, IP30, or EUR. One of the leaders in this sector is Drilling Infos smart application DI Transform.
This software solution allows for user-directed extraction of geophysical and geological data, robust data QC, and powerful model building. This information can be implemented in a number of different ways.
One of the most useful applications is in the building of detailed, accurate models. A detailed, accurate and reliable model, like those constructed by machine learning, is priceless.
It allows you to know exactly where to drill and what you will be drilling through. This allows problems to be solved almost before they are encountered.
By using these models companies can save money and increase productivity. It is clear that this will be an invaluable application for oil & gas operations.
Pinpointing Exactly Where to Dig with Machine Learning
Geoscience consulting firm Rock Solid Images (RSI), specialise in borehole characterisation. RSI is a leading firm in the field of interpreting seismic data with well log data. This is largely because they have been able to reliably combine complex geologic models with established rock physics methods.
Combining this information allows them to reliably pinpoint where, under rock formations, oil and gas is present. RSI is currently involved in a project that aims to reduce the risks that come with exploration drilling.
If they are successful it could be a significant moment for the oil & gas industry.
RSI is also working to use machine learning algorithms that can accurately model remote, hard to reach locations. This is being done by using models of well explored and documented areas that have similar geology.
It is hoped that, in time, this prediction mapping ability will become portable.
For example, these models will be able to accurately map Barents Sea rock properties using geological information gathered in mid-Norway. This application of machine learning in oil & gas operations can help to optimize the exploration and drilling processes.
Every time a well is dug, many fields of data are recorded. This raw data is analysed by a petrophysicist before being fed into sophisticated software. One such application is RSIs rockAVO software, this allows pattern recognition to take place.
Consequently, users of the software can read the rock physics of existing wells. This information gives the user a detailed picture of the geology of the area.
By studying this known information RSI is aiming to predict the geology elsewhere in the region. This means that less boreholes or test holes need to be dug, saving time and money. By using machine learning this way we can make informed decisions about where to dig.
Machine Learning to Provide well Placement Solutions
University of Texas PhD student Azor Nwachukwu, is conducting research into geostatistics and reservoir characterisation.
In particular how these can be optimized by using machine learning in exploration. Nwachukwu is part of a team working to determine a better method for well placement.
Traditionally determining well placement has involved a reservoir simulator being used a function evaluator. This is both time-consuming and expensive.
A data driven model is a more accessible, quicker and more accurate alternative. It is also able to create models in complex situations and inaccessible areas.
It’s hoped that their machine learning in oil & gas based proxy will solve the inefficiencies of traditional reservoir simulators. By including connectivity networks data related to spacing, coverage and well-to-well connectivity is also utilised. This increases the amount of accurate, real-time, useful information that can be analyzed.
This, in turn, improves geological realisations in modelling.
This application of machine learning in oil & gas exploration and extraction allows for a quicker, more accurate process.
This, in turn, will help to make the process more efficient.
Applying Machine Learning in oil & gas to Improve Subsurface Characterisation
Deep and machine learning in oil & gas extraction processes can also help to improve subsurface characterisation.
PhD candidate Hao Li, from the Mewbourne School of Petroleum and Geological Engineering at the University of Oklahoma is one of the leading lights in this field.
Hao Li is researching well logging, machine learning, deep learning and petrophysics. He is combining this with unconventional enhanced oil recovery. The end aim of this process is to use deep learning to improve subsurface characterization.
A consequence of this work concerns NMR logs and their accessibility. NMR logs are used to provide insight into fluid composition. It also informs the users of the pore size distribution of a formation. While this technology is incredibly useful it can be expensive to acquire and implement.
Hao Li is aiming to use deep learning to create a synthetic alternative.
Machine learning in oil & gas, as well as other implementations, uses Bayesian statistics. This is a branch of mathematics that utilises ”degrees of belief” and interpretations of probability.
Applying Bayesian statistics allows machine learning in oil & gas, and other applications, to create algorithms that analyse data. It also enables predictions to be made, based on the information analysed.
There are many potential applications of machine learning in oil & gas exploration. In fact, it is a perfect utilisation of machine learning. Machine learning in oil & gas enables patterns to be quickly identified across multiple variables.
This application of machine learning in oil & gas exploration speeds up what is a time-intensive process.
MORE – Data Science – 8 Powerful Applications
Smart Solutions can Enhance Reservoir Modelling
Known as reservoir modelling this also allows users to predict how formations will react to certain drilling techniques. By using machine learning in oil & gas exploration in this way we will know where and how to drill. A combination of algorithms and fuzzy logic will verify these models.
As well as verifying models, this also allows for accurate predictions to be made when information is incomplete or deemed unreliable. This application allows for a model to be constructed and for virtual drilling will take place.
Allowing engineers to pinpoint the best route through a rock formation. This process can occur long before any physical drilling equipment even arrives on site. Knowing exactly what is beneath the ground, and how the ground will react to drilling, we can avoid further flops like McMoRan’s ultra deepwater well.
Machine learning in oil & gas, as well as AI and case based reasoning, will save time and money. It will also help operatives to learn lessons from past successes and mistakes.
The more this technology is used, and the more information it is given, the more accurate the models will become.
Optimizing Drilling Operations
Applying AI and machine learning in oil & gas industries will improve operations. This will occur by enabling effective decision-making processes and optimizing drilling operations. By constructing complex models, based on collected data, AI will learn from past operations.
This will allow the technology to learn and improve as more data is recorded. The more we implement AI and machine learning in oil & gas industries, the better the potential to revolutionise workflow.
Chiranth Hegde, a data scientist, is helping Shell to incorporate machine learning, analytics and well connectivity. With Shell, Hegde is working to develop an end-to-end coupled drilling optimization advisor.
This will make use of the latest advances in machine learning. In the oil & gas sectors, companies have been slow to realise the potential of these technologies. This is slowly changing as companies become increasingly aware of the possibilities.
What makes Hegde’s work stand out is that until now optimization studies have looked at drilling metric, mechanical specific energy (MSE), or vibrations.
This has been looked at in isolation, independent of other factors. As a result, it doesn’t represent bottomhole conditions accurately. By combining a number of factors, Hegde is developing a coupled model.
While difficult to achieve it will be able to fully represent the complex parameters of a downhole.
Drilling can involve a great number of people all trying to carry out their individual, complex tasks. Each of these tasks must be carried out safely and correctly, often within a set time frame, for the rest of the operation to run smoothly.
Being able to access real-time information detailing all the operations is a valuable tool. Applying machine learning in oil & gas extraction in this way makes the industry safer and more efficient.
Today modern rigs are equipped with a number of sensors. These can measure all the relevant parameters connected with vessel and drilling operations. The sensors are also able to monitor the actual hole as drilling takes place.
Coupled with machine learning in oil & gas applications engineers are able to make advanced interpretations of computer-based video information. This can be done quickly and efficiently, meaning that little time is lost.
Increasingly operators, such as Anadarko, are using machine learning in oil & gas exploration to operate in deepwater areas such as the Gulf of Mexico.
Solving Problems Quickly with Machine Learning Applications
Applying machine learning in oil & gas operations allows for complex problems to be solved quickly and efficiently. In particular, machine learning algorithms can be used for case-based reasoning (CBR).
This means that the algorithms can be used to quickly sort through massive databases of recorded problems. The algorithms are then able to identify similar cases.
Once a similar case, or cases, is identified the software identifies how the issue has previously been solved. This can speed up problem resolution times, saving money and improving efficiency.
Another positive implication of machine learning in oil & gas is in the field of predictive maintenance. At every stage from exploration to delivery, the oil & gas industry relies on a number of large, expensive machines. If these aren’t working and well maintained then delays can occur and money will be lost.
By using predictive maintenance machine learning in oil & gas will keep the machines working and delivering.
This uses machine learning in oil & gas to create automated analytical models. This, otherwise known as predictive maintenance, will keep industrial equipment working. The machine learning algorithms used in Predix can process data from equipment sensors.
It will then analyse all the relevant information.
As well as performance levels this includes other factors such as weather and environmental conditions. This information is then compared against ideal performance data already stored in the database.
Should a discrepancy be noted the technicians are alerted. The machine can then be restored to its maximum before a fatal break down occurs.
Predictive Maintenance Models can Improve Productivity
GE Digital’s predictive maintenance models have already been adopted by the Administracion Nacional de Combustibles, Alcohol y Portland (ANCAP) of Uruguay.
A state company ANCAP is responsible for providing the fuel to heat the nations homes and businesses. Additionally, it is responsible for everything from ovens to agricultural machines and transportation.
Predix has enabled ANCAP to manage large amounts of data quickly and accurately. Creating an efficient system and a stable company. By centralizing the system ANCAP can track field data such as liquid and gas flow rates. It also allows for real-time analysis of tank levels and volumes.
This enables the company to monitor not only the effectiveness of their equipment. They can also monitor other important factors such as daily throughputs from process units.
They can also analyse, and then predict how weather conditions will affect their business and demand levels. Thanks to the implementation of machine learning in oil & gas this can all be done automatically.
When processed the software can then format the data into spreadsheets and upload it to the relevant websites.
Machine Learning in oil & gas can be used to Improve Efficiency
The value of being able to quickly collate and interpret this information can’t be underestimated. For example, ANCAP is now able to not only calculate but also project the efficiency of their furnaces.
This allows for trends to be easily spotted and for more accurate predictions to be made. It also allows for an accurate assessment of each furnace’s performance. GE Digital has announced that by implementing Predix, ANCAP has cut the time its employees spend on routine processes by 60%.
The company has also managed to cut fuel usage by 20%. Predix is a potentially powerful tool. By implementing this and similar applications of machine learning, in Gas & Oil significant savings may be made.
Not only in terms of data analysis time but also by helping to increase efficiency and cut waste. It is estimated that predictive maintenance may increase asset uptime by up to five percent.
This, in the competitive oil and gas industry, can give a company a real edge.
Internet of Things
Falling prices in recent years have squeezed cash flows.
This has forced companies to reconsider exploration and production strategies. By using machine learning in oil & gas industries we may be able to better respond to fluctuations in cost and demand.
This is one of the ways that machine learning in oil & gas will transform business models and processes.
Meaning that oil & gas companies will be able to compete effectively in the digital age. The internet of things, sensor data and applications associated with machine learning in oil & gas allow for information to be accessed across multiple touchpoints.
Benjamin Beberness, vice president and global head of the Oil and Gas Industry Business Unit at SAP, highlighted the importance of machine learning in the oil & gas industry.
Speaking on the S.M.A.C. Talk Technology Podcast, Beberness highlighted the importance of employees being able to access the information they need at their fingertips.
Beberness said, “Companies don’t want their employees to have to be going back and forth between the office and the field.”
What happens When Data is Available?
It is not just that the data must be accessible.
It must also be used correctly. In this area, artificial intelligence and machine learning in oil & gas can make a significant impact. When oil prices rise many companies adopt a “production at all costs approach”.
Using AI tools and machine learning in oil & gas areas allows companies to move away from this established business model. By doing so companies can maximise all their assets, reducing waste and needless expenditure.
For example, remote sensors can be connected to wireless networks. This allows for remote data collection. Once collected the data can be centrally analyzed before being processed into forecasting models.
Applications of Machine Learning in oil & gas can Transform Business Models
Implementing AI and machine learning in oil & gas allow companies to predict profits, and losses precisely. This will allow for production costs to be optimized, accounting for a number of ever-changing factors.
The information gained from data visualisation could be combined with current market demand and financial reports.
This allows companies to plan their next drilling operation. Using AI and machine learning in oil & gas in this way will allow companies to shift business models. The traditional “produce at all costs” model will be replaced by a “produce in context” model.
This shift, Beberness thinks, will allow companies to be more flexible and able to deal with low oil prices.
When implemented in this way AI algorithms and machine learning in oil & gas will help companies navigate market ebbs, such as a consumer shift towards electric cars.
Predictions by McKinsey suggests that adopting AI and machine learning in oil & gas supply chains could gain $50 billion in savings, increasing profits.
Many Companies are Already Seeking to Implement Machine Learning
HortonWorks, based in San Francisco, offers similar applications of AI and machine learning in oil & gas industries. Their Hybrid Data Platform (HDP) software is an open-source application.
It is able to process large datasets from multiple sources. Thus helping companies to predict well yield and know when to do maintenance on equipment.
The HDP, like similar applications, can store sensor and seismic data as well as weather data, drilling information and geolocation reports. Additionally, it can also store text files, videos, emails, social media pages in a large data repository.
The implication for this application of machine learning in oil & gas is great. It will allow engineers to use collected data to set benchmarks to achieve a high margin yield. Should the system notice that the current yields are not meeting the benchmark it will warn engineers, highlighting the causes.
This allows for problems to be solved quickly and yields to be optimized. Noble Energy has worked with Horton to predict and prevent downtime in its hydrocarbon infrastructure. In future Noble Energy also aims to use Hortons HDP to improve safety across its sites.
In addition to Noble Energy, HortonWorks has worked with a number of major companies and organisations.
These include John Hopkins University, Mayo Clinic, Expedia, Fuso and Nissan.
Predictive Software For Energy Purchases Customer Market
Enterprise Miner is the name of a predictive software program developed by SAS. The company hopes that it can use machine learning in oil & gas operations to develop predictive models.
This is can be done by employing deep learning, natural language processing (NLP) and computer vision. SAS uses NLP algorithms to extract business insight and emerging trends from speech, sound and text.
It also aims to use computer vision algorithms to determine the objects shown in videos and images. This information can then be processed and analyzed by deep learning algorithms.
These identify patterns that can be used to make predictions and preventative recommendations. SAS haven’t confined themselves to AI and machine learning in oil & gas industries.
They have also helped Old Dominion Electric Cooperative (ODEC) to forecast energy demand. ODEC provides power to 11 distribution cooperatives in Virginia, Delaware and Maryland, serving over 1 million customers. Linking up with SAS has allowed the company to purchase and provide energy at an affordable price.
SAS has provided ODEC with industry-specific models. This has allowed for accurate forecast modelling and predictions. Case studies suggest that this partnership has helped to save the utility companies customers millions.
This allows ODEC to plan, with confidence, its markets power need up to 20 years into the future.
Replacing Manual Workers
Machine learning in oil & gas will not replace manual operatives entirely.
While it will account for some streamlining, human operatives will still be required. Using machine learning in oil & gas industries will allow skilled workers to become more efficient. It can also save them from conducting needless tasks.
Finally adopting more applications centred on machine learning in oil & gas can make the industry safer. Geoscientists will still need to have strong core geoscience skills, this aspect will never change.
However as machine learning in oil & gas becomes more widespread geoscientists will also need other skills. They will have to embrace the next generation of machine learning in oil & gas based toolsets.
The geoscientists who do this will be able to thrive in the industry of tomorrow. They will be equipped with a hybrid skillset, combining geoscience with mathematical fluency, coding ability and creative problem-solving.
There will also be a need to communicate across domains, allowing information to be accessed and understood by a wide audience.
A new Skill set for Workers
All of this may alienate, or seem scary to the current workforce. However, it is necessary and workers will soon become adept at these skills.Workers who can properly deliver all these skills will become commonplace.
They will also be best served by machine learning algorithms that are fed by standardised, quality data. This will yield the best possible results. Data companies such as TGS are aiming to provide both.
Tasks such as collecting and maintaining data will fall increasingly on AI and machine learning, in oil & gas as well as other industries. While this will allow for a standardised information base to be created it won’t completely negate the need for human workers.
Geoscientists and engineers will still be required to interpret and vet the information. Data scientists will also be required, helping the experts within the industry to continue developing algorithms. As these algorithms become increasingly complex there will also be a need for data scientists to help understand the systems.
Machine Learning to Predict Operational Outcomes
One company hoping to implement machine learning in oil & gas is Maana. Based in California, the company has developed a software called Knowledge Platform.
This, they hope, will help oil and gas companies to predict operational outcomes. Machine learning and natural language processing will also help employees to make informed decisions.
Maana claims that its software can quickly process unstructured data. This is data such as weather reports, call center records, job reports and everything else. The Knowledge platform algorithms can then interpret this data, searching through the platform’s database looking for similar patterns.
This information is presented in the form of graphs, illustrating trends in performance or expenditure. Experts on the subject matter can then interpret the graphs quickly and easily. This can speed up problem-solving by quickly highlighting potential solutions.
Smart Tools can also Optimize Performance and Output
In addition to language-based data Knowledge platforms can also be used to collect detailed sensor data during pumping operations.
This is then analyzed identifying patterns that could lead to pump failures. If this pattern is highlighted before the pump fails it can save time and money.
It will also prevent hours being lost to broken machinery.
This can optimize drilling performance.
Maana’s software, as well as similar applications in machine learning in oil & gas, can also affect savings across the industry. The application can also increase billable hours, reduce overall costs and streamline operations. Maersk, Airbus, Chevron and Shell are all clients of Maana as is General Electric.
Machine learning in oil and gas operations, according to McKinsey are yet to be fully maximised. The 2017 McKinsey report suggests that the average offshore platform operates at about 77% of its maximum production potential. When this is spread across the industry it equates to a daily loss of 10 million barrels.
That is about $200 billion in annual revenue.
As time progresses our world is increasingly influenced by the abilities of AI and Machine learning. In oil & gas operations adoption and realisation have been slow. However slowly AI and machine learning in oil & gas are taking hold.
Machine Learning in Oil & Gas Applications can Transform the Industry
Machine learning in oil & gas will not only improve the customer experience but can also help to keep costs low across the process.
The possible advantages that can be brought by machine learning in oil & gas to this competitive sector are massive.
Images: Flickr Unsplash Pixabay Wiki & Others