Article
Energy & Fuels
Gang Hui, Zhangxin Chen, Jun Yan, Muming Wang, Hai Wang, Dongmei Zhang, Fei Gu
Summary: The integrated experiment logging-based strategy is proposed to evaluate high-quality shale in the West Duvernay Shale Basin. Through core measurements and logging interpretations, the geographic distribution of high-quality shales is determined. Machine learning techniques are then used to quantify the relationships between shale productivity and reservoir characteristics and predict the spatial distribution of high-quality shales. The strategy reveals that the Duvernay shale consists of four sublayers, with the D2 and D3 sublayers considered high-quality.
Article
Energy & Fuels
Gang Hui, Fei Gu, Junqi Gan, Erfan Saber, Li Liu
Summary: Forecasting shale gas production is challenging due to the uncertainty and lack of comprehensive reservoir characterization. This study evaluated the relationship between shale gas production and reservoir parameters using multiple linear regression analysis. The findings showed that the Duvernay shale is predominantly composed of quartz, clay, and calcite, with an average effective porosity of 3.96% and permeability of 137.2 nD. The MLR method identified several key factors influencing shale productivity, and accurately predicted shale gas output. This research has implications for the effective development of shale resources in other reservoirs.
Article
Energy & Fuels
Fahad I. Syed, Temoor Muther, Amirmasoud K. Dahaghi, Shahin Negahban
Summary: This paper introduces the application of AI and ML in shale gas production performance evaluation, highlighting the enhancement of performance accuracy through data-driven methods, and discusses the utilization of various ML methods.
JOURNAL OF PETROLEUM EXPLORATION AND PRODUCTION TECHNOLOGY
(2021)
Article
Energy & Fuels
Mohammad Abdideh, Fawzi Dastyaft
Summary: This study investigates the effect of stress analysis on azimuth wells in deviated drilling in an oil field in southwestern Iran. A mechanical model of the earth is designed using laboratory data and well logging, and the most stable drilling path is validated through results obtained from laboratory rock mechanics.
JOURNAL OF PETROLEUM EXPLORATION AND PRODUCTION TECHNOLOGY
(2022)
Article
Multidisciplinary Sciences
Mohd Anul Haq, Ahsan Ahmed, Ilyas Khan, Jayadev Gyani, Abdullah Mohamed, El-Awady Attia, Pandian Mangan, Dinagarapandi Pandi
Summary: The main goal of this research is to use a deep neural network model to forecast environmental variables in time series. The study focuses on snow cover, temperature, and normalized difference vegetation index (NDVI), using the Long Short Term Memory (LSTM) model. The research provides a coarse-to-fine analysis strategy and uses the dataset from Himachal Pradesh to forecast the environmental factors.
SCIENTIFIC REPORTS
(2022)
Article
Computer Science, Information Systems
Weisi Chen, Zoran Milosevic, Fethi A. Rabhi, Andrew Berry
Summary: With the proliferation of intelligent devices, social media, and the Internet of Things, a huge amount of new data is being generated, resulting in an increasing pace. Real-time analytics has emerged as a branch of big data analytics that focuses on the velocity aspect, where data is processed and analyzed as it arrives, aiming to provide insights and create business value in near real-time. This paper provides an overview of key concepts and architectural approaches for designing real-time analytics solutions, including infrastructure, processing and analytics platforms, machine learning, and artificial intelligence. It also presents real-life application scenarios and discusses the integration of machine learning and artificial intelligence into real-time analytics solutions. Future research directions and challenges are also discussed.
Review
Pharmacology & Pharmacy
Chinmayee Choudhury, N. Arul Murugan, U. Deva Priyakumar
Summary: The global health emergency caused by the COVID-19 pandemic has emphasized the need for fast, accurate, and efficient drug discovery pipelines. Traditional drug discovery projects that rely on in vitro high-throughput screening are expensive and limited to big biopharmaceutical companies. Therefore, the utilization of efficient computational methods and modern artificial intelligence algorithms for rapid screening of repurposable chemical space has become a powerful option to save resources and time. This review discusses the use of traditional and modern AI-based computational methods and tools in structure-based drug discovery pipelines, highlighting the role of generative models in generating molecules with specific structures.
DRUG DISCOVERY TODAY
(2022)
Article
Computer Science, Hardware & Architecture
Tarik Taleb, Chafika Benzaid, Rami Akrem Addad, Konstantinos Samdanis
Summary: This article surveys the application of artificial intelligence and machine learning in 5G and 6G mobile communications. It introduces the key technologies of AI/ML in network planning and optimization, service request, data collection and distribution, and summarizes the main AI/ML algorithms. The article also discusses the standardization and open source activities of AI/ML, as well as the challenges that need to be addressed in using AI/ML for automation.
Review
Pharmacology & Pharmacy
Divya Vemula, Perka Jayasurya, Varthiya Sushmitha, Yethirajula Naveen Kumar, Vasundhra Bhandari
Summary: Computer-aided drug design (CADD) is an emerging field that has the potential to expedite and lower the cost of the drug development process. CADD, combined with AI, ML, and DL technologies, has significantly impacted the drug discovery research by reducing time and cost.
EUROPEAN JOURNAL OF PHARMACEUTICAL SCIENCES
(2023)
Review
Computer Science, Artificial Intelligence
Onur Dogan, Sanju Tiwari, M. A. Jabbar, Shankru Guggari
Summary: The use of AI/ML methods in addressing the COVID-19 outbreak has increased due to their significant advantages, providing satisfactory solutions to the disease. However, the diversity in these solutions can lead to confusion. This study systematically analyzes and summarizes related studies to address this issue.
COMPLEX & INTELLIGENT SYSTEMS
(2021)
Article
Materials Science, Multidisciplinary
Davis Unruh, Venkata Surya Chaitanya Kolluru, Arun Baskaran, Yiming Chen, Maria K. Y. Chan
Summary: Advances in instrumentation have resulted in a vast amount of information on materials chemistry, structures, and transformations, but interpreting microscopy and spectroscopy data is becoming more challenging due to their growing volume and complexity. This article discusses the use of theoretical modeling, artificial intelligence/machine learning (AI/ML), and AI/ML combined with theory for interpreting microscopy and spectroscopy data.
Review
Green & Sustainable Science & Technology
A. Jiran Meitei, Pratibha Rai, S. S. Rajkishan
Summary: This paper reviews the application of AI and ML techniques in achieving the UN Sustainable Development Goals based on studies from 2017 to 2022. The findings suggest that while AI holds promise, there is a tendency for overexuberance regarding its positive outcomes. The study emphasizes the need for regulatory requirements and regular verification to ensure that AI adheres to ethical standards for sustainable development.
ENVIRONMENT DEVELOPMENT AND SUSTAINABILITY
(2023)
Article
Chemistry, Multidisciplinary
Lauren M. Petrick, Noam Shomron
Summary: This article discusses the application of artificial intelligence (AI) and machine learning (ML) in untargeted metabolomics and exposomics, and their significant findings in disease screening and diagnosis. It introduces the principles of metabolomics and exposomics and explores the potential opportunities to improve data quality and chemical identification using AI and ML.
CELL REPORTS PHYSICAL SCIENCE
(2022)
Article
Biochemistry & Molecular Biology
Jiho Yoo, Tae Yong Kim, InSuk Joung, Sang Ok Song
Summary: Drug discovery aims to address unmet clinical needs by selecting appropriate targets and drug candidates. Recent developments in artificial intelligence and machine learning have led to the creation of data-driven platforms covering the entire drug discovery process. Identifying elusive targets increases the diversity of discovery pipelines and enhances the ability to meet these needs. Modern machine learning technologies complement traditional computer-aided drug discovery by accelerating candidate optimization. This review summarizes the latest advancements in AI/ML methods from target identification to molecule optimization and provides an overview of current trends in end-to-end AI/ML platforms.
CURRENT OPINION IN STRUCTURAL BIOLOGY
(2023)
Article
Geosciences, Multidisciplinary
Luis Stinco, Silvia Barredo
Summary: The Los Molles Formation is the second most important source rock in the Neuque acute accent n Basin, with abundant organic content and potential gas resources, as well as conventional and unconventional reservoirs. Utilizing deductive and inductive methodologies in studying the petroleum system related to Los Molles Formation can provide a comprehensive understanding of its characteristics and potential for exploration and development.
JOURNAL OF SOUTH AMERICAN EARTH SCIENCES
(2021)