John Abish Giftson

Blockchain technology holds immense promise for revolutionizing the Oil and Gas industry. Its decentralized ledger system can enhance supply chain transparency, ensure secure transactions, and optimize asset management processes. Grad students interested in this field could explore research opportunities in developing blockchain-based solutions for efficient resource tracking, transparent trading platforms, and streamlined operational processes. By adopting the power of blockchain, the industry can drive efficiency, reduce costs, and foster greater trust among stakeholders. #BlockchainInOilandGas #FutureResearch #InnovationOpportunities

7

1 Comment

Refreshing the below article while waiting at airport, re-learned a few things; ML- advantages, limitations, conditions 🤔 Are the above limited to Petrophysical applications or generally applied? https://lnkd.in/gGTPqAyU

35

3 Comments

𝗛𝘆𝗱𝗿𝗼𝗰𝗮𝗿𝗯𝗼𝗻 𝗧𝗿𝗮𝗽𝘀 Petroleum traps are geological formations that contain accumulations of oil and gas, making them essential targets for hydrocarbon exploration. Understanding the different types of petroleum traps is crucial for identifying potential reservoirs and optimizing exploration strategies. In this article, we will discuss the main types of petroleum traps, their characteristics, and their significance in the search for oil and gas reserves. *1. Structural Traps* Structural traps are formed by deformation of the Earth's crust, resulting in folds, faults, and other structural features that trap hydrocarbons. The most common types of structural traps include: - **Anticline Traps:** These traps form in areas where rock layers have been folded into an upward arch-like structure called an anticline. Hydrocarbons migrate upwards through permeable reservoir rocks and become trapped beneath impermeable cap rocks. - **Fault Traps:** Faults are fractures in the Earth's crust where movement has occurred. Fault traps occur when hydrocarbons are displaced along fault lines and become trapped against impermeable barriers. *2. Stratigraphic Traps* Stratigraphic traps are formed by variations in the sedimentary rock layers that make up the Earth's crust. These traps are less dependent on structural deformation and more on the characteristics of the sedimentary sequence. Common types of stratigraphic traps include: - **Lenticular Sands:** These traps occur when permeable sandstone layers "pinch out" or terminate abruptly, creating a localized accumulation of hydrocarbons. - **Carbonate Buildups:** In carbonate reservoirs, hydrocarbons can accumulate in porous structures such as reefs, shoals, and buildups formed by the accumulation of calcium carbonate. *3. Combination Traps* Combination traps are traps that exhibit characteristics of both structural and stratigraphic traps. They often result from a combination of structural deformation and variations in sedimentary deposition. Combination traps can be particularly complex and may require sophisticated exploration techniques to identify and assess. *4. Unconventional Traps* Unconventional traps refer to reservoirs that do not fit neatly into the categories of structural or stratigraphic traps. These include unconventional hydrocarbon resources such as shale gas, tight gas, and coalbed methane. The trapping mechanisms in unconventional reservoirs often involve factors such as organic richness, natural fractures, and matrix porosity. Photo refrence, credit : https://lnkd.in/dH9FXumM

291

3 Comments

Learning ML for Oil and Gas Professionals Before you dive into generic machine learning tutorials, pause for a moment and consider this: the oil and gas industry demand specialized knowledge to effectively harness the power of AI and machine learning. That's why we're excited to announce our upcoming workshop tailored specifically for professionals like you! We are having a free Machine Learning for Oil and Gas Workshop Event coming up next week(registration link bellow) https://lnkd.in/e8mr3kW9 Machine learning and AI is booming in all industries and Oil and Gas is no exception however most online tutorials are basic and not relevant to oil and gas data. Imaging learning machine learning by using Flowers Dataset(Iris), or learning Classification using Handwriting Datasets(MNIST). Oil and Gas dataset are special and require domain expertise to teach ML properly because in oil and gas capturing data(features) are usually interrelated(e.g WHP, WHT, Qo, Qg, Pres, etc). We are offering a full 2 Month program on Machine Learning for Oil and Gas using Python (Zero expertise is needed), but you need to know the basics of the industry. Starting next Month. Please it should be noted that this training is 1 program /year event. If you want to learn then Join this Program otherwise you need to wait for 2025 program as we are getting booked as you read this post. Here is the registration link: https://lnkd.in/e8mr3kW9 Please do not hesitate to contact us if you have any further queries or require additional information. Email: info@peassociations.com WhatsApp: +91 6205464268 Warm Regards -Team PEA!

30

2 Comments

Looking to stay ahead of well failures? We use machine learning to analyze data and predict potential failures before they happen. This World Oil article highlights an upcoming deployment from DATAGRATION - Connecting Data | Powering Decisions. #PetroVisor #ESPFailurePrediction #PredictiveMaintenance #ML

15

Have you ever struggled with forecasting young PDP wells? Geology, completions design, and well spacing are critical predictors for well performance, and by incorporating them into early-time forecasting, you can dramatically improve accuracy. Here, I'm showing results from our PDP forecasting models on younger wells from the Permian, Williston, and Appalachia. These models use machine learning to directly forecast declines, incorporating not just prior production but also geology, completions, spacing, parent-child, etc. This data is especially useful for younger wells, where the production data may be too noisy or non-hyperbolic to get a good fit using a traditional Arps curve. This is especially the case with public data sources! Across these three basins, our machine learning PDP forecasts improve accuracy by 32%, 46%, and 29% on the primary production stream, compared with a traditional DCA methodology. Why does this matter? Newer wells (<1.5 years old) make up about half of production in the L48, though it's even higher for some basins and assets. Poor forecasts on young wells leads to incorrect valuations, inaccurate supply models, and bad type curves. Our operator customers have been using these models for over three years now to improve their forecast accuracy, but we have recently released these forecasts as a live, auto-updating data product for our subscribers. At URTeC in two weeks, we are diving deeper into this technology as applied in the Permian Basin. Thanks to lead author Kiran Sathaye for his insightful work in this study. For more information, head to our URTeC page (link in the image). #oilgas #permian #urtec

40

7 Comments

Great article by TGS's very own Andrew Stearns detailing advantages of ConocoPhillips acquisition of Marathon Oil Corporation! Read about it here:

5

Delighted to share that I'll be presenting " Ensuring Pipeline safety for Carbon capture and Storage (CCS) through Real-time monitoring and leak detection” at the 2024 API Pipeline Conference and Expo: Pipeline, Control Room and Cybernetics in Salt Lake City, UT. Carbon capture and storage (CCS) is crucial for decarbonization in the energy sector. Pipelines are essential for efficient CCS projects, providing cost-effective transport of CO2. Preventing leaks is crucial due to the high-pressure and low-temperature conditions of CO2 transport. Real-time simulation-based methods can effectively monitor the pipeline infrastructure and detect potential leaks quickly. This presentation explores the challenges and opportunities of real-time leak detection in CCS. 📍 When? Monday, May 6 | 2:10 p.m. – 2:40 p.m. PT 🌐Want to learn more? Please DM me or catch up with me at booth 502! #DNV #APIPipelineConference2024, #PipelineSafety #CarbonCaptureStorage #LeakDetection

31

1 Comment

Gradient descent is a widely used optimization technique in machine learning, especially for training large language models (LLMs). However, finding the optimal prompt for an LLM is not a trivial task, as it requires careful design and fine-tuning. How can we automate this process and improve the performance of LLMs? In this post, I will introduce a novel method called Automatic Prompt Optimization (APO), which is inspired by numerical gradient descent to automatically improve prompts, assuming access to training data and an LLM API. The algorithm uses minibatches of data to form natural language "gradients" that criticize the current prompt. Then, it updates the prompt by adding or removing tokens based on the gradient direction and magnitude. The process is repeated until convergence or a maximum number of iterations is reached. The authors of APO claim that their method can achieve state-of-the-art results on various LLM tasks, such as sentiment analysis, natural language inference, and text summarization. They also show that APO is more efficient and robust than existing methods that rely on manual or heuristic prompt design. You can read more about APO and its applications in their paper [here](https://lnkd.in/dc_nixQv). I hope you find this post informative and useful. Thank you for reading! 

1

Any plans for the weekend? 🏖 If not, then checkout our recent Gun Barrel visualization mod. Gun Barrel visualization is a name given to the cross-sectional view through wellbores in a specific area of the reservoir., it helps for e.g. checking the distances between wellbores, here is demo. To Download this Mod: https://lnkd.in/gyCa_AFH To Checkout Our Mods Exchange and Interactive Demos: https://lnkd.in/gQDSYsmY ✅ Whether you're a beginner or need a refresher, check out our enablement hub page here: https://lnkd.in/g2GieCVT ✅ Short on time? Check out our collection of Quick Tips using Spotfire for some bite-sized learning during your lunch break: https://lnkd.in/gtKrJk69 ✅ And for those interested in our spotfire-dsml python package, take a look here: https://lnkd.in/gJhVFsMd ✅ Don't forget to check out our brand new website at https://www.spotfire.com/ for more information on Spotfire and how it can benefit your work. hashtag #Spotfire hashtag #DataScience hashtag #DrSpotfire hashtag #dataanalytics hashtag #oilandgas

22

1 Comment

Combining the power of artificial intelligence (machine learning specifically in this case) and interdisciplinary collaboration will definitely accelerate the attainment of the objectives of digital transformation. This is a case of two companies combining their respective expertise to upscale and commercialize a product that automates advanced seismic interpretation. https://lnkd.in/di-8QjTD #artificialintelligence #ai #machinelearning #ml #collaboration #digitaltransformation #seismicinterpretation #advancedtechnology

18

1 Comment

Explore my updated article "How to Change Well Log DLIS Header Parameter Values using HexEdit 4.0" The Digital Log Interchange Standard (DLIS) was introduced on May 1, 1991, by the American Petroleum Institute (API) as Recommended Practice 66 (RP 66). It serves as an industry-standard format for exchanging digital well log data. Unlike the LAS format, DLIS is binary and requires specialized petrophysical software for manipulation. However, an alternative method outlined in the article involves using binary file editing software, such as HexEdit 4.0, to modify well header parameter values within DLIS files. This article is respectfully dedicated to all wireline logging field engineers, field operators and data specialists in the energy industry, in recognition of their unwavering dedication and hard work, to support the clients in acquiring high quality well log data. Thank you! #upstream #wireline #petrophysical #datamanagement

1

BIOMASS PYROLYSIS VARIABLES FOR BEGINNERS In my latest post, someone asked about the key variables influencing biomass pyrolysis and its outputs. Understanding these factors is crucial for optimizing the process to achieve specific goals. Here's a brief overview: 🌿 **BIOMASS TYPE**: Different compositions impact outputs. High lignin content yields more biochar, while cellulose-rich biomass produces more bio-oil and syngas. Biomass with more volatile matter can produce more syngas. Woody biomass produces more biochar than herbaceous biomass. 💧 **MOISTURE CONTENT**: Excessive moisture reduces process efficiency and dilutes syngas, affecting output concentrations. However, higher moisture produces more hydrogen since about 11.11% of water is hydrogen by mass (ED: approximately 6.3% of biomass is Hydrogen). Biochar yield can be impacted as energy needs to be balanced between drying and pyrolyzing. 🌡️ **TEMPERATURE**: Critical for product distribution, with low temperatures (300°C-400°C) favoring biochar and high temperature (500°C-800°C) enhances syngas and bio-oil formation while reducing tars. Lower temperature produces higher biochar yields with more carbon content. ⏳ **RESIDENCE TIME**: Duration affects biomass decomposition, influencing product yield and quality. Longer times promote complete decomposition, optimizing output, including hydrogen yield. By mastering these variables, one can tailor biomass pyrolysis for energy production or biochar creation, catering to diverse needs. Understanding these nuances is key to maximizing efficiency and output quality. #greenenergy #greenhydrogen #greenelectricity #victorycleanenergy #h2eg #netzeroenergy #donturner #BiomassPyrolysis #RenewableEnergy #SustainablePractices

38

18 Comments

High tide has touched you. You are in the riparian. The encroaching of riparian areas cause funneling of flow. Higher energy flow carries more matter, heavier matter delivering high impact blows. Or CC has caused more than average fall. MWSI now has observable metrics to map riparian areas.

2

A North American operator needed to obtain a Class VI injection permit for a #CCUS well. To combat a corrosive environment, Halliburton proposed a 3-sting cement solution to achieve zonal isolation. A CBL was run to further to confirm successful coverage from TD to the surface. Read the case study to learn how this operator minimized cyclic loading on the barrier >> https://lnkd.in/eVYYD4jW

11

🔐 The potential of utilizing feature importance in clustering often goes unrecognized. However, with careful observation, it can greatly enhance our understanding of the underlying knowledge and patterns within our dataset. 📕 Explore its application on geoscience domain in this article: https://lnkd.in/gtabRGk2

24

Last week at CERAWeek 2024, energy leaders explored strategies for a multidimensional, multispeed and multifuel #EnergyTransition. Check out Baker Hughes' highlights below: ✔️ Lorenzo Simonelli joined leaders from ExxonMobil, ONEOK, & Chevron to discuss the role of natural gas in the global economy and sat down with Maria Claudia Borras for a candid conversation on ‘Advancing Women in Energy’. ✔️ Ganesh Ramaswamy participated in a roundtable on the U.S.-India energy and climate partnership and also joined industry leaders from Equinor and QazaqGaz for a discussion that focused on how policy, technology and economics all need to interplay in balancing energy security, affordability and sustainability. ✔️ Alessandro Bresciani joined a panel discussion to share insights on the importance of #decarbonization in the energy and industrial sector, including the challenges and opportunities to scale and accelerate the deployment of #CCUS, #hydrogen, and electrification to achieve global goals. ✔️ Alessandro Bresciani joined Danny Rice of NET Power and Rick Callahan of Oxy for a discussion on the role of collaboration as a critical enabler for a #NetZero future & the need for innovative solutions and new business models to accelerate the transition. ✔️ Daniela Abate participated in a panel discussion covering the policies and economic solutions required to realize the full potential of #CarbonCapture Utilization and Storage solutions. ✔️ Alessandro Bresciani, Senior Vice President of Climate Technology Solutions, spoke with CNBC about CCUS - the technologies we have invested in, trends we’re seeing across the market, and the application of CCUS to address climate change and drive decarbonization in hard-to-abate industrial sectors. ✔️ Ajit Menon, Vice President of Geothermal and Energy Transition, gave an update on next steps for our Wells2Watts Geothermal Consortium and shared his thoughts on the current state of the U.S. geothermal market, the latest innovations in the geothermal energy space, and the essential role of partnerships to fuel the energy transition in an interview with AFP. ✔️ Simone Corbò shared insights on the environmental and economic incentives for & benefits of retrofitting end-use assets for hydrogen to reach net-zero targets. ✔️ Carlos M. Gomez and Timothy Sykes of Augury spoke to how customers are leveraging Cordant™ MachineHealth to extend machine runtime, eliminate reactive firefighting and increase performance. #BakerHughes #WeAreBakerHughes #CERAWeek2024  #EnergyTransition #EnergyTrilemma #Sustainaiblity #CarbonCapture #Geothermal

6

How do you solve a problem like greenhouse gas emissions at the Port of Houston? That's the challenge that two students, Mustafa Khan and Aaron Hinkle, are tackling at the University of Houston's Energy Transition Institute (ETI). Mustafa and Aaron are part of the Energy Scholars Program, which connects students with research faculty and industry partners on projects focusing on energy matters and is supported by the Baker Hughes Foundation. Find out how their project is shaping their vision for the future and what the energy transition means to them. #BakerHughes #BHStories #WeAreBakerHughes #GoGoogs #EnergyTransition

2

Moving pipeline integrity into the future, supporting smarter decisions backed by data, analytics and experts. Continuously building experience with models, data and subject matter expertise! #pipelineintegrity

26