ML-adjoint: Learn the adjoint source directly for full-waveform inversion using machine learning

Sun, Bingbing; Alkhalifah, Tariq

doi:10.1190/segam2020-3420587.1

Cited by 3 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consequently, these methods still face the challenge of cycleskipping issue if the standard mean squared error loss (MSE, i.e., the ℓ 2 norm) is used. To further resolve this problem, Sun and Alkhalifah [20] proposed to use meta learning to learn a metric to measure the difference between observed and predicted data. Yang and Ma [21] later proposed a generative adversarial method to learn the metric.…”

Section: Introductionmentioning

confidence: 99%

Optimal Transport with a New Preprocessing for Deep-Learning Full Waveform Inversion

Zhang

2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Full waveform inversion (FWI) has been implemented using deep learning techniques as an analogue recurrent neural network for geophysics. However, the cycle-skipping issue, from which the conventional FWI suffers, troubles the deeplearning aided FWI as well if the least-square loss function is used to measure the misfit between observed and synthetic data. We propose to use a Wasserstein distance loss function combined with a newly designed preprocessing transform, named integration affine scaling, for the inversion. This transform transfers the seismograms into probability densities, and significantly improves the inversion results. Numerical results show that the proposed method outperforms its counterparts in mitigating cycle-skipping, in comparison with other loss functions including the least-square, the absolute, and the quadratic Wasserstein distance losses.

show abstract

Section: Introductionmentioning

confidence: 99%

Optimal Transport with a New Preprocessing for Deep-Learning Full Waveform Inversion

Zhang

2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

show abstract

Hydrocarbon Field Re-Development as Markov Decision Process

Sieberer

Clemens

2021

Day 1 Tue, September 21, 2021

View full text Add to dashboard Cite

Hydrocarbon field (re-)development requires that a multitude of decisions are made under uncertainty. These decisions include the type and size of surface facilities, location, configuration and number of wells but also which data to acquire. Both types of decisions, which development to choose and which data to acquire, are strongly coupled. The aim of appraisal is to maximize value while minimizing data acquisition costs. These decisions have to be done under uncertainty owing to the inherent uncertainty of the subsurface but also of other costs and economic parameters. Conventional Value Of Information (VOI) evaluations can be used to determine how much can be spend to acquire data. However, VOI is very challenging to calculate for complex sequences of decisions with various costs and including the risk attitude of the decision maker. We are using a fully observable Markov-Decision-Process (MDP) to determine the policy for the sequence and type of measurements and decisions to do. A fully observable MDP is characterised by the states (here: description of the system at a certain point in time), actions (here: measurements and development scenario), transition function (probabilities of transitioning from one state to the next), and rewards (costs for measurements, Expected Monetary Value (EMV) of development options). Solving the MDP gives the optimum policy, sequence of the decisions, the Probability Of Maturation (POM) of a project, the Expected Monetary Value (EMV), the expected loss, the expected appraisal costs, and the Probability of Economic Success (PES). These key performance indicators can then be used to select in a portfolio of projects the ones generating the highest expected reward for the company. Combining the production forecasts from numerical model ensembles with probabilistic capital and operating expenditures and economic parameters allows for quantitative decision making under uncertainty.

show abstract

Hydrocarbon Field (Re-)Development as Markov Decision Process

Sieberer

Clemens²

2022

SPE Reservoir Evaluation &Amp; Engineering

View full text Add to dashboard Cite

Summary Hydrocarbon field (re-)development requires that a multitude of decisions are made under uncertainty. These decisions include the type and size of surface facilities, location, configuration, and number of wells but also which data to acquire. Both types of decisions, which development to choose and which data to acquire, are strongly coupled. The aim of appraisal is to maximize value while minimizing data acquisition costs. These decisions have to be done under uncertainty owing to the inherent uncertainty of the subsurface but also of other costs and economic parameters. Conventional value of information (VOI) evaluations can be used to determine how much can be spent to acquire data. However, VOI is very challenging to calculate for complex sequences of decisions with various costs and including the risk attitude of the decision-maker. We are using a partially observable Markov decision process (MDP) to determine the policy for the sequence and type of measurements and decisions to do. A partially observable MDP (POMDP) is characterized by the states (here: description of the system at a certain point in time), actions (here: measurements and development scenario), transition function (probabilities of transitioning from one state to the next), observations (measurements, appraisal activity), and rewards [costs for measurements, expected monetary value (EMV) of development options]. Solving the MDP gives the optimum policy, sequence of the decisions, the probability of maturation (POM) of a project, the EMV, the expected loss, the expected appraisal costs, and the probability of economic success (PES). These key performance indicators can then be used to select in a portfolio of projects the ones generating the highest expected reward for the company. Combining the production forecasts from numerical model ensembles with probabilistic capital and operating expenditures and economic parameters allows for quantitative decision-making under uncertainty.

show abstract

ML-adjoint: Learn the adjoint source directly for full-waveform inversion using machine learning

Cited by 3 publications

References 9 publications

Optimal Transport with a New Preprocessing for Deep-Learning Full Waveform Inversion

Optimal Transport with a New Preprocessing for Deep-Learning Full Waveform Inversion

Hydrocarbon Field Re-Development as Markov Decision Process

Hydrocarbon Field (Re-)Development as Markov Decision Process

Contact Info

Product

Resources

About