We investigate using machine learning techniques to infer various physical properties of rocks from hyperspectral imaging data. In particular, we demonstrate that deep neural networks (DNN) can infer mechanical and geochemical properties based on high-resolution Fourier transform spectrograms. Our goal is to enable real-time petrophysical analysis of subsurface rocks and fluids. The ongoing work encompasses the development of sensors and algorithms that facilitate non-destructive, fast, and high-resolution mapping of petrophysical properties. We acquired high-resolution mappings of mechanical, chemical, and electromagnetic properties at sub-millimeter scale (> 100 um) using a scanning system fitted with multiphysics probes, including impulse hammer geomechanical probe designed to measure the rebound hardness and the reduced Young modulus; Fourier transform spectrometer (FTIR) to acquire the diffuse reflectance; acoustic transducers to measure unconstrained sonic velocities; and near-surface gas permeability. We have characterized over two hundred thousand samples across various lithologies, including limestone, sandstones, and shales from outcrops and cores from unidentified wells. We present the results of machine-learning models and algorithms that predict, based on the IR reflectance data, the rock types, and the unconstrained geomechanical properties. The method could be extended to characterize other solids from subsurface, terrestrial, or non-terrestrial environments. The combination of photonic measurements and machine learning provides the means to find non-causal relations between materials' electromagnetic/photonic response and their other physical properties under various stress states and environmental configurations. This work presents the foundational blocks to achieve this objective and develop optical sensors for sustainable energy extraction.
This study provides experimental results in investigating the use of a 5.34 kW ytterbium-doped multiclad fiber laser with an emission wavelength of 1.07 microns for creating deep hole configurations in different types of rock for production applications in oil and gas wells. Recent developments in high power fiber lasers offer technical advantages when compared to other industrial lasers that may now allow economic subsurface applications to rock formations, delivering the beam through optical fiber from the surface via the wellbore. Successful applications in this manner would provide an alternative to conventional methods that employ rotary drilling and shaped charge explosives. Various parameters affecting laser penetration into samples of sandstone and limestone were studied and optimized. A maximum penetration depth of 30 cm for 8.9-mm hole diameter was achieved in limestone, while 15 cm penetration depth was achieved in sandstone with the same hole diameter. In all cases, the hole diameter was no greater than the beam diameter applied.
This paper describes the experimental results of selective rock removal using different types of high power lasers. US military owned continuous wave laser systems such as MIRACL and COIL with maximum powers of 1.2 MW and 10 kW and wavelengths of 3.8 and 1.3 mm respectively, were first used on a series of rock types to demonstrate their capabilities as a drilling tool for petroleum exploitation purposes. It was found that the power deposited by such lasers was enough to drill at speeds much faster than conventional drilling. In order to sample the response of the rocks to the laser action at shorter wavelengths, another set of rock samples was exposed to the interaction of the more commercially available high power pulsed Nd:YAG laser. To isolate the effects of the laser discharge properties on the rock removal efficiency, a versatile 1.6 kW Nd:YAG laser capable of providing pulses between 0.1 millisec and 10 millisec in width, with a maximum peak power of 32 kW and a variable repetition rate between 25 and 800 pulses/sec was chosen. With this choice of parameters, rock vaporization and melting were emphasized while at the same time minimizing the effects of plasma shielding. Measurements were performed on samples of sandstone, shale, and limestone. It was found that each rock type requires a specific set of laser parameters to minimize the average laser energy required to remove a unit volume of rock. It was also found that the melted material is significantly reduced in water saturated rocks while the drilling speed is still kept higher than conventional drilling.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.