This third installment of the Digital Data Acquisition Technology Focus will deal with pc imaginative and prescient (CV) for improved information acquisition. CV is outlined as a area of examine that seeks to develop strategies to assist computer systems “see” and perceive the content material of digital pictures similar to pictures and movies.The area of pc imaginative and prescient has seen vital progress lately due to the convergence of a number of occasions, similar to developments in machine-learning expertise (e.g., deep studying), an exponential improve in availability of visible information from cell phones and platforms similar to YouTube, and the expansion of recent use circumstances similar to autonomous driving. As such, it’s no surprise that CV can also be having a significant impact on the oil and fuel trade, mirrored within the variety of papers this 12 months on this topic alone.The oil and fuel trade is awash with picture and video information similar to core pictures, seismic profiles, maps, video feeds for monitoring distant operations, and, nowadays, even drone pictures. The conventional method to deciphering and appearing on this information has been extremely guide, which could be extraordinarily time-consuming and susceptible to bias and error. CV expertise intends to automate these processes and considerably enhance the turnaround time from information to choices.The papers chosen this 12 months embody utility of CV for reservoir characterization, similar to source-rock reconstruction, facies identification, and seismic information enhancement; and security purposes similar to rig-state identification and automatic corrosion mapping. Given the flexibility of CV expertise, its utility throughout the oil and fuel trade clearly will proceed to develop.This Month’s Technical PapersMachine-Learning Techniques Characterize Source-Rock Images on the Pore ScaleComputer Vision Analytics Enables Determination of Rig StateArtificial-Intelligence and Machine-Learning Technique for Corrosion MappingRecommended Additional ReadingSPE 204216 Deep-Learning-Based Vuggy Facies Identification From Borehole Images by Jiajun Jiang, Baylor University, et al.SPE 202710 Machine-Learning-Based Seismic Data Enhancement Toward Overcoming Geophysical Limitations by Shotaro Nakayama, INPEX, et al.SPE 205347 Machine-Learning-Assisted Segmentation of Focused Ion Beam Scanning Electron Microscopy Images With Artifacts for Improved Void-Space Characterization of Tight Reservoir Rocks by Andrey Kazak, Skolkovo Institute of Science and Technology, et al.
Pallav Sarma, SPE, is cofounder and chief scientist at Tachyus accountable for the modeling and optimization applied sciences underlying the Tachyus platform. He is an professional in closed-loop reservoir administration and holds a number of patents and has written greater than 50 papers on varied subjects, together with simulation, optimization, information assimilation, and machine studying. Sarma has greater than 13 years of expertise working for Chevron and Schlumberger earlier than forming Tachyus. He has acquired many awards, together with the Dantzig Dissertation award from INFORMS, Miller and Ramey Fellowships at Stanford University, Chevron’s Excellence in Reservoir Management award, and a SIAM award for excellence in analysis. Sarma holds a PhD diploma in petroleum engineering, a PhD minor diploma in operations analysis from Stanford University, and a bachelor of expertise diploma from the Indian School of Mines. He at the moment serves on committees for the SPE Reservoir Simulation Conference and the EAGE European Conference on the Mathematics of Oil Recovery and on the JPT Editorial Review Committee.
https://jpt.spe.org/digital-data-acquisition-2022
