Prediction of high-quality reservoirs using the reservoir fluid mobility attribute computed from seismic data

Zhang, Yijiang; Wen, Xiangming; Jiang, Lian; Liu, Jie; Yang, Jixin; Liu, Songming

doi:10.1016/j.petrol.2020.107007

Cited by 11 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For further study, more effective pretreatment methods of noise reduction for passenger flow data should be explored and applied to further enhance the algorithm performance. The methods that could be explored include variational mode decomposition [ 42 ], synchrosqueezing wavelet transform [ 43 ], savitzky-golay filter [ 44 ], etc.…”

Section: Discussionmentioning

confidence: 99%

CEEMDAN-IPSO-LSTM: A Novel Model for Short-Term Passenger Flow Prediction in Urban Rail Transit Systems

Zeng

Yang

et al. 2022

IJERPH

View full text Add to dashboard Cite

Urban rail transit (URT) is a key mode of public transport, which serves for greatest user demand. Short-term passenger flow prediction aims to improve management validity and avoid extravagance of public transport resources. In order to anticipate passenger flow for URT, managing nonlinearity, correlation, and periodicity of data series in a single model is difficult. This paper offers a short-term passenger flow prediction combination model based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and long-short term memory neural network (LSTM) in order to more accurately anticipate the short-period passenger flow of URT. In the meantime, the hyperparameters of LSTM were calculated using the improved particle swarm optimization (IPSO). First, CEEMDAN-IPSO-LSTM model performed the CEEMDAN decomposition of passenger flow data and obtained uncoupled intrinsic mode functions and a residual sequence after removing noisy data. Second, we built a CEEMDAN-IPSO-LSTM passenger flow prediction model for each decomposed component and extracted prediction values. Third, the experimental results showed that compared with the single LSTM model, CEEMDAN-IPSO-LSTM model reduced by 40 persons/35 persons, 44 persons/35 persons, 37 persons/31 persons, and 46.89%/35.1% in SD, RMSE, MAE, and MAPE, and increase by 2.32%/3.63% and 2.19%/1.67% in R and R2, respectively. This model can reduce the risks of public health security due to excessive crowding of passengers (especially in the period of COVID-19), as well as reduce the negative impact on the environment through the optimization of traffic flows, and develop low-carbon transportation.

show abstract

Section: Discussionmentioning

confidence: 99%

CEEMDAN-IPSO-LSTM: A Novel Model for Short-Term Passenger Flow Prediction in Urban Rail Transit Systems

Zeng

Yang

et al. 2022

IJERPH

View full text Add to dashboard Cite

show abstract

“…Xue et al (2018) employed the synchrosqueezed wavelet transforms to improve the estimation precision of fluid mobility. Zhang et al (2020) further use fluid mobility to predict the highquality reservoir based on a modified high-precision timefrequency transform. These studies illustrate that reservoirrelated fluid mobility is a key attribute for reservoir delineation.…”

Section: Introductionmentioning

confidence: 99%

A New Fluid Mobility Calculation Method Based on Frequency-Dependent AVO Inversion

Luo

Chen

Duan³

et al. 2022

Front. Earth Sci.

View full text Add to dashboard Cite

Fluid mobility (i.e., permeability to viscosity ratio) is a key parameter that can evaluate the reservoir permeability and delineate the fluid characteristic in hydrocarbon-saturated reservoirs. Based on the asymptotic representation for the frequency-dependent reflections in the fluid-saturated pore-elastic media and frequency-dependent AVO inversion, we propose a novel method for estimating fluid mobility from poststack seismic data. First, we establish the relationship between fluid mobility and frequency-dependent AVO analysis. Then, the fluid mobility is estimated using the theory of frequency-dependent AVO inversion. Tests on synthetic data reveal that the fluid mobility shows excellent imageability for the fluid-saturated reservoirs and can accurately delineate the spatial distribution shape of the gas-saturated reservoir. The application of field data examples demonstrates that the fluid mobility calculated by the proposed method produces less background interferences caused by elastic layers compared with the conventional frequency-dependent fluid indicator. The frequency-dependent fluid mobility takes into account the dispersion features associated with hydrocarbon reservoirs, and it provides a new way to detect the location of hydrocarbon reservoirs and characterize their spatial distribution.

show abstract

“…It is necessary to find a universal seismic attribute indicating hydrocarbon directly. In recent years, some post-stack fluid mobility attributes have been applied to hydrocarbon identification in deep-water sandstone reservoirs [7,10,15,16]. Fluid mobility is the direct reflection of the rock permeability and fluid viscosity of hydrocarbon reservoirs.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Shale Gas Reservoirs Using Fluid Mobility Attribute Driven by Post-Stack Seismic Data: A Case Study from Southern China

et al. 2020

View full text Add to dashboard Cite

Paleozoic marine shale gas resources in Southern China present broad prospects for exploration and development. However, previous research has mostly focused on the shale in the Sichuan Basin. The research target of this study is expanded to the Lower Silurian Longmaxi shale outside the Sichuan Basin. A prediction scheme of shale gas reservoirs through the frequency-dependent seismic attribute technology is developed to reduce drilling risks of shale gas related to complex geological structure and low exploration level. Extracting frequency-dependent seismic attribute is inseparable from spectral decomposition technology, whereby the matching pursuit algorithm is commonly used. However, frequency interference in MP results in an erroneous time-frequency (TF) spectrum and affects the accuracy of seismic attribute. Firstly, a novel spectral decomposition technology is proposed to minimize the effect of frequency interference by integrating the MP and the ensemble empirical mode decomposition (EEMD). Synthetic and real data tests indicate that the proposed spectral decomposition technology provides a TF spectrum with higher accuracy and resolution than traditional MP. Then, a seismic fluid mobility attribute, extracted from the post-stack seismic data through the proposed spectral decomposition technology, is applied to characterize the shale reservoirs. The application result indicates that the seismic fluid mobility attribute can describe the spatial distribution of shale gas reservoirs well without well control. Based on the seismic fluid mobility attribute section, we have learned that the shale gas enrich areas are located near the bottom of the Longmaxi Formation. The inverted velocity data are also introduced to further verify the reliability of seismic fluid mobility. Finally, the thickness map of gas-bearing shale reservoirs in the Longmaxi Formation is obtained by combining the seismic fluid mobility attribute with the inverted velocity data, and two favorable exploration areas are suggested by analyzing the thickness, structure, and burial depth. The present work can not only be used to evaluate shale gas resources in the early stage of exploration, but also help to design the landing point and trajectory of directional drilling in the development stage.

show abstract

Prediction of high-quality reservoirs using the reservoir fluid mobility attribute computed from seismic data

Cited by 11 publications

References 12 publications

CEEMDAN-IPSO-LSTM: A Novel Model for Short-Term Passenger Flow Prediction in Urban Rail Transit Systems

CEEMDAN-IPSO-LSTM: A Novel Model for Short-Term Passenger Flow Prediction in Urban Rail Transit Systems

A New Fluid Mobility Calculation Method Based on Frequency-Dependent AVO Inversion

Prediction of Shale Gas Reservoirs Using Fluid Mobility Attribute Driven by Post-Stack Seismic Data: A Case Study from Southern China

Contact Info

Product

Resources

About