EnviTrace

AI software and services for energy and environmental solutions

HomeBlogVideosSupportNewsletterSaaSTerms
© 2025 EnviTrace LLC. All rights reserved. Text, artwork, animations, videos, and images are exclusive property of EnviTrace LLC.
EnvitraceEnvitrace Logo
Your browser does not support the video tag.
PetroAI Logo

PRODUCE MORE

Our software and our services help you get more out of your oil & gas extraction projects.

Oit & Gas + AI

Extraction of oil & gas is a complex process. Data are typically limited and uncertain. The processes are complex and non-linear. Physics models to predict the behavior of the reservoir are challenging to develop and take a long time to run.

PetroAI addresses these challenges.

PetroAI develops and applies science-informed ML models to predict oil & gas extraction based on site data and models.

PetroAI accounts for complex geomechanics processes.

PetroAI estimates uncertainties of model parameters and ML predictions.

PetroAI estimates sensitivities and provides decision support to extract actionable information.

Related publications

  • Detecting and Characterizing Fluid Leakage Through Wellbore Flaws Using Fiber-Optic Distributed Acoustic Sensing (2022) — Ishtiaque Anwar et al. — 56th U.S. Rock Mechanics/Geomechanics Symposium
    Abstract
    ABSTRACT: A primary concern associated with the utilization of subsurface systems is that there may be pathways for fluid leakage from the resource storage, or disposal reservoir. Leakage of any fluid can contaminate groundwater, cause geo-environmental pollution, generate hazardous surface conditions, and potentially compromise the functionality of the subsurface system. A low-cost, innovative technique to detect and characterize fracture leakage that is functional over many years is needed for applications such as geothermal reservoirs, CO2 sequestration wells, deep borehole storage of nuclear waste, and strategic petroleum reserve caverns. In this experimental study, we investigate the use of fiber-optic distributed acoustic sensing (DAS) to measure dynamic strain changes caused by acoustic signals induced by fluid flow with an eventual goal of developing instrumentation and analytical techniques to detect and characterize the movement of fluids through leaky wellbores. In the first phase of the experiments reported here, we conducted fluid flow tests in a porous medium as an analog to a fracture filled with comminuted material. The measured effective permeability is then compared with the signals generated by the fiber-optic cable. The study indicated that acoustic signals generated from fluid flow through porous media could be effectively captured by the fiber-optic cable DAS technology. 1. INTRODUCTION Wellbores are used for gaining access to various subsurface systems such as underground fluid reserve (Miyazaki, 2009), CO2 sequestration (Watson and Bachu, 2008; Zhang and Bachu, 2011), geothermal energy development (Shadravan, Ghasemi, & Alfi, 2015), waste disposal, oil and gas exploration (Davies et al., 2014), etc. A primary concern associated with the utilization of subsurface systems is that there may be pathways for fluid leakage from the resource storage, or disposal reservoir through the wellbore flaws. Leakage of any fluid from a leaky wellbore can contaminate groundwater, cause geo-environmental pollution (Davies et al., 2014; Ingraffea, Wells, Santoro, & Shonkoff, 2014; Jackson, 2014), generate hazardous surface conditions, and potentially compromise the functionality of the subsurface system (Gasda, Celia, Wang, & Duguid, 2013). Researchers has identified different potential leakage pathways, including fractures in the cement or micro annuli from de-bonding at the cement-casing or cement-formation interface (Celia, Bachu, Nordbotten, Gasda, & Dahle, 2005; Theresa L Watson & Bachu, 2009) or the casing corrosion product (Anwar, Chojnicki, Bettin, Taha, & Stormont, 2019; Beltrán-Jiménez et al., 2021).
  • SmartTensors: Unsupervised and physics-informed machine learning framework for the geoscience applications (2022) — Bulbul Ahmmed, Velimir V. Vesselinov, Maruti K. Mudunuru — Second International Meeting for Applied Geoscience & Energy
    Abstract
    SmartTensors (https://github.com/SmartTensors) is a novel framework for unsupervised and physics-informed machine learning for geoscience applications. The methods in SmartTensors AI platform are developed using advanced matrix/tensor factorization constrained by penalties enforcing robustness and interpretability (e.g., nonnegativity, sparsity, physics, and mathematical constraints;etc.). This framework has been applied to analyze diverse datasets related to a wide range of problems: from COVID-19 to wildfires and climate. Here, we will focus on the analysis of geothermal prospectivity of the Great Basin, U.S. The basin covers a vast area that is yet to be thoroughly explored to discover new geothermal resources. The available regional geochemical data are expected to provide critical information about the geothermal reservoir properties in the basin, including temperature, fluid/heat flow, boundary conditions, and spatial extent. The geochemical data may also include hidden (latent) information that is a proxy for geothermal prospectivity. We processed the sparse geochemical dataset of 18 geochemical attributes observed at 14,341 locations. The data are analyzed using our GeoThermalCloud toolbox for geothermal exploration (https://github.com/SmartTensors/GeoThermalCloud.jl) whichis also a part of the SmartTensors framework. An unsupervised machine learning using non-negative matrix factorization with customized k-means clustering (NMFk) as implemented in SmartTensors identified three hidden geothermal signatures representing low-, medium-, and high-temperature reservoirs, respectively (Fig). NMFk also evaluated the probability of occurrence of these types of resources through the studied region. NMFk also reconstructed attributes from sparse into continuous over the study domain. Future work will add in the ML analyses other regional- and site-scale datasets including geological, geophysical, and geothermal attributes. © 2022 Society of Exploration Geophysicists and the American Association of Petroleum Geologists.
  • Nonlinear Acoustics Applications for Near-Wellbore Formation Evaluation (2021) — Christopher Skelt et al. — Petrophysics – The SPWLA Journal of Formation Evaluation and Reservoir Description
    Abstract
    We present experimental and modeling results and a downhole logging tool concept resulting from a research collaboration between Chevron Energy Technology Company and Los Alamos National Laboratory investigating using nonlinear acoustics applications for natural fracture characterization and assessing near-wellbore mechanical integrity or drilling-induced damage. The generation of a scattered wave by noncollinear mixing of two acoustic plane waves in an acoustically nonlinear medium was first documented several decades ago. If the frequency ratio and convergence angle of the two waves and the compressional-to-shear velocity ratio of the medium where they intersect meet certain conditions, their interaction creates a scattered third wave, propagating in a predictable direction, with a frequency equal to the sum or difference between the two primary wave frequencies and an amplitude dependent on the nonlinearity at the intersection location. The conditions resulting in this scattering and the properties of the scattered wave are thus governed by the physics of the interaction, resulting in a set of “selection rules” that are the key to the measurement principle introduced here. If the two transmitted plane waves are oriented such that the third wave returns to the borehole, the phenomenon may be used as the basis for a logging tool measuring acoustic nonlinearity around the wellbore circumference, with a secondary measurement of the compressional-to-shear velocity ratio. Laboratory measurements supported by finite-difference and analytical modeling confirmed that the mixing of two plane compressional waves generated a shear wave as predicted by the selection rules in a large Berea sandstone block, confirming the potential for a downhole tool with a depth of investigation in the range 15 to 20 cm. Historical data show that nonlinearity in core samples is primarily caused by a lack of mechanical integrity. In the oil field, this may be microfractures in tight rock unconventional reservoirs or incipient near-wellbore failure while drilling. This prompts applications to fracture characterization and calibration of mechanical earth models. The main practical challenge for a downhole logging tool is injecting powerful directional acoustic energy into the formation. We envisage an openhole tool making sequential station measurements using transmitters built into hydraulically controlled pads contacting the borehole wall. Noncollinear mixing may be activated by maintaining the frequency of one transmitter constant while sweeping the other through the range of frequency ratios predicted by the selection rules, resulting in a received sum or difference frequency signal that rises to a peak and then falls. Alternatively, the frequency ratio may be maintained while steering one of the acoustic beams. The peak signal amplitude indicates the coefficient of nonlinearity, which is sensitive to lack of mechanical integrity caused by natural fractures or mechanical disaggregation. The frequency ratio at which it occurs is an indicator of the shear-to-compressional velocity at the location where the two beams cross. In this manner, a record of nonlinearity along or around the borehole can be envisaged. The physics of acoustic nonlinearity is well established, and our laboratory measurements have determined that the phenomenon of interest should occur and be measurable in the subsurface. Overcoming the engineering challenges would bring new formation evaluation insights unique to this measurement principle.
  • Two-Stage Fracturing Wastewater Management in Shale Gas Development (2017) — Xiaodong Zhang et al. — Industrial & Engineering Chemistry Research
  • Experimental implementation of reverse time migration for nondestructive evaluation applications (2011) — Brian E. Anderson et al. — The Journal of the Acoustical Society of America
    Abstract
    Reverse time migration (RTM) is a commonly employed imaging technique in seismic applications (e.g., to image reservoirs of oil). Its standard implementation cannot account for multiple scattering/reverberation. For this reason it has not yet found application in nondestructive evaluation (NDE). This paper applies RTM imaging to NDE applications in bounded samples, where reverberation is always present. This paper presents a fully experimental implementation of RTM, whereas in seismic applications, only part of the procedure is done experimentally. A modified RTM imaging condition is able to localize scatterers and locations of disbonding. Experiments are conducted on aluminum samples with controlled scatterers.
  • In-Situ Physical Properties Using Crosswell Acoustic Data (1985) — P. A. Johnson, J. N. Albright — SPE/DOE Low Permeability Gas Reservoirs Symposium
    Abstract
    Abstract Crosswell acoustic surveys enable the in situ measurements of elastic moduli, Poisson's ratio, porosity, and apparent seismic Q of gas-bearing low-permeability formations represented at the Department of Energy Multi-Well Experiment (MWX) site near Rifle, Colorado. These measurements, except for Q, are compared with laboratory measurements on core taken from the same depths at which the crosswell measurements are made. Seismic Q determined in situ is compared to average values for sandstone. Porosity was determined from crosswell data using the empirical relationship between acoustic velocity, porosity, and effective pressure developed by Domenico. in situ porosities are significantly greater than the core-derived values. Sources of the discrepancy may arise from (i) the underestimation of porosity that can result when Boyle's Law measurements are made on low-permeability core and (ii) the application of Dominico's relationship, which is developed for clean sands, to the mixed sandstone and shale lithologies represented at the MWX site. Values for Young's modulus and Poisson's ratio derived from crosswell measurements are comparable to values obtained from core. Apparent seismic Q measured in situ between wells is lower than Q measured on core and clearly shows the heterogeneity of sandstone deposited in a fluvial environment.
Envitrace Logo

1048 Mansion Ridge Road

Santa Fe, New Mexico, USA

+1 (505) 310 4367

+1 (505) 473 4150

info@envitrace.com

AI Products

  • EnviCloud
  • GeoTGo
  • GeoML
  • ChemML
  • UrbanAI
  • LAPIS

.

  • PetroAI
  • WEFx
  • GAIA
  • SmartTensors
  • MADS
  • WELLS

Company

  • Capabilities
  • Products
  • Expertise
  • Awards
  • Our Team
  • Updates
  • Blog

.

  • Community
  • Careers
  • Terms & Conditions
  • Email us
  • Subscribe
  • Unsubscribe
  • Workshop