RECORD
Design of borehole resistivity measurement acquisition systems using deep learning
Machine Learning · Submitted 12 Jan 2021
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Numerical results show that the obtained measurement acquisition system is sufficient to identify and characterize both resistive and conductive layers above and below the logging instrument.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Borehole resistivity measurements recorded with logging-while-drilling (LWD) instruments are widely used for characterizing the earth's subsurface properties. They facilitate the extraction of natural resources such as oil and gas. LWD instruments require real-time inversions of electromagnetic measurements to estimate the electrical properties of the earth's subsurface near the well and possibly correct the well trajectory. Deep Neural Network (DNN)-based methods are suitable for the rapid inversion of borehole resistivity measurements as they approximate the forward and inverse problem offline during the training phase and they only require a fraction of a second for the evaluation (aka prediction). However, the inverse problem generally admits multiple solutions. DNNs with traditional loss functions based on data misfit are ill-equipped for solving an inverse problem. This can be partially overcome by adding regularization terms to a loss function specifically designed for encoder-decoder architectures. But adding regularization seriously limits the number of possible solutions to a set of a priori desirable physical solutions. To avoid this, we use a two-step loss function without any regularization. In addition, to guarantee an inverse solution, we need a carefully selected measurement acquisition system with a sufficient number of measurements. In this work, we propose a DNN-based iterative algorithm for designing such a measurement acquisition system. We illustrate our DNN-based iterative algorithm via several synthetic examples. Numerical results show that the obtained measurement acquisition system is sufficient to identify and characterize both resistive and conductive layers above and below the logging instrument. Numerical results are promising, although further improvements are required to make our method amenable for industrial purposes.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Borehole resistivity measurements recorded with logging-while-drilling (LWD) instruments are widely used for characterizing the earth's subsurface properties. | background 1.00 | 0.05 | 0.01 | asserted 1.00 |
| s1 | They facilitate the extraction of natural resources such as oil and gas. | background 1.00 | 0.04 | 0.01 | asserted 1.00 |
| s2 | LWD instruments require real-time inversions of electromagnetic measurements to estimate the electrical properties of the earth's subsurface near the well and possibly correct the well trajectory. | background 1.00 | 0.06 | 0.02 | asserted 0.76 |
| s3 | Deep Neural Network (DNN)-based methods are suitable for the rapid inversion of borehole resistivity measurements as they approximate the forward and inverse problem offline during the training phase and they only require a fraction of a second for the evaluation (aka prediction). | background 0.88 | 0.10 | 0.05 | asserted 0.94 |
| s4 | However, the inverse problem generally admits multiple solutions. | background 0.88 | 0.07 | 0.02 | asserted 0.96 |
| s5 | DNNs with traditional loss functions based on data misfit are ill-equipped for solving an inverse problem. | background 0.55 | 0.11 | 0.03 | asserted 0.99 |
| s6 | This can be partially overcome by adding regularization terms to a loss function specifically designed for encoder-decoder architectures. | background 0.67 | 0.13 | 0.04 | hedged possibility 0.69 |
| s7 | But adding regularization seriously limits the number of possible solutions to a set of a priori desirable physical solutions. | background 0.54 | 0.13 | 0.04 | asserted 0.98 |
| s8 | To avoid this, we use a two-step loss function without any regularization. | method 0.83 | 0.91 | 0.08 | asserted 1.00 |
| s9 | In addition, to guarantee an inverse solution, we need a carefully selected measurement acquisition system with a sufficient number of measurements. | background 0.54 | 0.14 | 0.07 | asserted 0.98 |
| s10 | In this work, we propose a DNN-based iterative algorithm for designing such a measurement acquisition system. | contribution 0.98 | 0.93 | 0.17 | asserted 1.00 |
| s11 | We illustrate our DNN-based iterative algorithm via several synthetic examples. | method 0.61 | 0.93 | 0.04 | asserted 0.98 |
| s12 | Numerical results show that the obtained measurement acquisition system is sufficient to identify and characterize both resistive and conductive layers above and below the logging instrument. | result 0.98 | 0.96 | 0.54 | asserted 1.00 |
| s13 | Numerical results are promising, although further improvements are required to make our method amenable for industrial purposes. | limitation 0.83 | 0.87 | 0.19 | asserted 0.71 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Borehole resistivity measurements recorded with logging-while-drilling (LWD) instruments are widely used for characterizing the earth's subsurface properties. They facilitate the extraction of natural resources such as oil and gas. LWD instruments require real-time inversions of electromagnetic measurements to estimate the electrical properties of the earth's subsurface near the well and possibly correct the well trajectory. Deep Neural Network (DNN)-based methods are suitable for the rapid inversion of borehole resistivity measurements as they approximate the forward and inverse problem offline during the training phase and they only require a fraction of a second for the evaluation (aka prediction). However, the inverse problem generally admits multiple solutions. DNNs with traditional loss functions based on data misfit are ill-equipped for solving an inverse problem. This can be partially overcome by adding regularization terms to a loss function specifically designed for encoder-decoder architectures. But adding regularization seriously limits the number of possible solutions to a set of a priori desirable physical solutions. To avoid this, we use a two-step loss function without any regularization. In addition, to guarantee an inverse solution, we need a carefully selected measurement acquisition system with a sufficient number of measurements. In this work, we propose a DNN-based iterative algorithm for designing such a measurement acquisition system. We illustrate our DNN-based iterative algorithm via several synthetic examples. Numerical results show that the obtained measurement acquisition system is sufficient to identify and characterize both resistive and conductive layers above and below the logging instrument. Numerical results are promising, although further improvements are required to make our method amenable for industrial purposes.
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.