Wyniki wyszukiwania - Biblioteka Nauki

Ten serwis zostanie wyłączony 2025-02-11.

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

2 Acta Geophysica

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: pre-stack simultaneous inversion

Sortuj według:

Ogranicz wyniki do:

Prestack simultaneous inversion of P-wave impedance and gas saturation using multi-task residual networks

100%

Sang W. , Ding Z. , Li M. , Liu X. , Liu Q. , Yuan S.

Acta Geophysica

2024

tom Vol. 72, no. 2

875--892

It is challenging to realize the gas saturation (GS) estimation via the integration of seismic data and more complementary data (e.g., elastic attributes) in a traditional physical framework. Machine learning, especially multi-task learning (MTL), provides an alternative way for the fuse of multiple information and simultaneous inversion of two or multiple reservoir parameters without model-driven limitations and interactive operators. To improve the estimation accuracy of GS, we propose the prestack simultaneous inversion of P-wave impedance (PI) and GS using the multi-task residual network (MT-ResNet). The designed MT-ResNet consists of two task-related subnets. The first subnet establishes the nonlinear links among low-frequency PI, prestack seismic data, and well-log derived PI. Furthermore, seismic data and the inverted PI via the first subnet are jointly entered into the second subnet and evolved into the well-log interpreted GS. A model based on measured petrophysical parameters associated with the field deep tight dolomite reservoir is used to test the proposed method. Tests on the synthetic data example and the field example demonstrate that the MT-ResNet can simultaneously estimate PI and GS models with the highest reliability, in comparison with single-task residual network (ST-ResNet) and the conventional seismic inversion and rock-physics equations-based method. And the MT-ResNet inverted PI can be utilized as complementary information for improving the prediction accuracy of MT-ResNet inverted GS. Our proposed MT-ResNet has the potential to guide the design of the MTL-based multiple reservoir parameters prediction and practical application.

Quantitative characterization of unconventional (tight) hydrocarbon reservoir by integrating rock physics analysis and seismic inversion: a case study from the Lower Indus Basin of Pakistan

84%

Talib M. , Durrani M. Z. A. , Palekar A. H. , Sarosh B. , Rahman S. A.

Acta Geophysica

2022

tom Vol. 70, no 6

2715--2731

The paper demonstrates a successful application of Bayesian classification method to accurately predict petrophysical properties and lithofacies classification in the deep unconventional (tight gas) hydrocarbon resource potential of early Cretaceous in the Lower Indus Basin of Pakistan. To explore the true potential for exploration and development phases, we quantitatively characterized the tight gas reservoir based on an integrated methodology using the Bayesian approach constraint with rock physics analysis which utilized deterministic petrophysical results from a well information to extract the desired lithofacies at seismic scale. The employed methodology relied on stepwise sequential integration of all available data through petrophysical, rock physics analysis and seismic inversion technique. Simultaneous inversion approach is used to invert elastic properties for reservoir interpretation. Seismic-based petrophysical properties are predicted using regression analysis by establishing a functional relationship between well logs for Sembar formation. The rock physics template (acoustic impedance versus Vs/ Vs ratio) model helped to differentiate lithological units of sand and shale in the well. Three lithofacies (HC sands, shale and shalier sand) are properly classified in rock physics template, and their probabilities are accurately defined using Bayes’ theorem. Finally, estimated lithofacies and hydrocarbon probability map from the Bayesian approach are meticulously validated from well data. The quantitative seismic reservoir characterization study provided important support for the unconventional prospect evaluation and hydrocarbon reserve estimations necessary to delineate unexplored parts which could prove helpful in effectively planning for the horizontal well placement and optimal reservoir development.