Wavelet analysis for spectral inversion of seismic reflection data

Accurate traffic speed forecasting not only can help traffic management departments make better judgments and improve the efficacy of road monitoring but also can help drivers plan their driving routes and arrive safely and smoothly at their destination. This paper focuses on the lack of traffic speed data and proposes a method for traffic speed forecasting based on the multitemporal traffic flow volume of the previous and later moment states. First, according to traffic flow volume data, the different traffic patterns of previous and later moment states were extracted. Second, the performance of five forecasting models, namely, long short-term memory (LSTM), backpropagation (BP), classification and regression trees, k-nearest neighbor, and support vector regression, were compared. Finally, the model with the best prediction results was used to conduct sensitivity analysis experiments for different traffic patterns. Through a real-data case study, we found that the LSTM model has the highest prediction accuracy compared to other models in both time and space. This traffic pattern "previous = 3 and later = 3" can forecast traffic speed more accurately, and its forecasting ability is robust across a range of scenarios.

show abstract

“…Here, five points around the abnormal point are determined as abnormal data [41]. Next, it is necessary to reestimate the abnormal data.…”

Section: Figure 3 Distribution Of Five Detectors On the Third Ring Ex...mentioning

confidence: 99%

Short-Term Traffic Speed Forecasting Using a Deep Learning Method Based on Multitemporal Traffic Flow Volume

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Obtaining geothermal source information accurately, especially the flux is crucial for the efficient evaluation and rational utilization of geothermal energy. Currently, the geophysics inversion methods [1][2] are mainly applied, which always need huge drilling and geological information [3]. However, these methods often require lots of drilling to obtain data, which not only needs a lot of cost, but also the obtained geological abnormal area cannot be directly confirmed as a geothermal heat source.…”

Section: Introductionmentioning

confidence: 99%

Modified Fuzzy Inference Method for Heat Flux Inversion of Geothermal Reservoir Heat Source

Zhou

Liu

et al. 2022

E3S Web Conf.

View full text Add to dashboard Cite

The key to determine the performance of fuzzy inference inversion is to select a reasonable domain. However, there is no universal method for selecting domain at present. According to the characteristics of heat flux of geothermal heat source and the research of fuzzy inference inversion process, this paper modified the fuzzy inference method from two aspects of domain setting and iteration termination condition. The recommended domain and selection scheme for solving the problem of geothermal heat flux are given, and the modified fuzzy inference inversion method is applied to Rucheng geothermal field to verify the method. The results showed that the modified fuzzy inference inversion method could overcome the problem that the solution of the traditional method fell into a cycle, and the relative error of the verification term was less than 5%. Compared with the traditional method, the modified method greatly improved the computational efficiency, and the number of iterations was reduced to only 7. This method has a good application prospect for geothermal heat source inversion and resource evaluation.

show abstract

“…Many scholars have focused on optimizing this theory, and their research is divided into two main aspects: the accurate acquisition of seismic wavelets and the application of various constraints. Extracting accurate seismic wavelet is critical (Baziw and Ulrych, 2006;Mirko and pham, 2008;Sacchi, 2010;Nasser and Mauricio, 2014;Macedo et al, 2016;Cabrera et al, 2020). These researchers analyzed and optimized seismic wavelets and proposed various methods for sparse deconvolution.…”

mentioning

confidence: 99%

A novel high-resolution imaging method based on sparsity in the time domain and spectral fitting in the frequency domain

Guo,

Gao,

Yong

et al. 2024

Front. Earth Sci.

View full text Add to dashboard Cite

During the propagation of seismic waves underground, the high-frequency seismic response of thin reservoir is absorbed and attenuated, which poses a challenge in seismic thin reservoir prediction. The high-resolution processing techniques have the capability to significantly expand the frequency range of the seismic data, so it becomes a key technique for thin reservoir prediction. Most of these techniques necessitate the extraction of seismic wavelets. However, the spatial and temporal variations of seismic data result in multiple solutions for wavelet extraction. Simultaneously, the majority of techniques fail to consider the influence of spatial tectonic features on the high-resolution processing. In this paper, we propose a novel solution to address these two fundamental challenges by utilizing seismic spectral expansion, sparse reflection coefficients, and spatial continuity constraints. First, we propose an innovative spectral fitting method that aims to expand the frequency bandwidth while adhering to the desired wavelet constraints. This method allows us to fully utilize the effective frequency information. It not only obtains broadband seismic data but also captures precise wavelets. Then, sparse deconvolution is employed to further extend the frequency range by utilizing the accurately expected wavelet and obtaining a high-resolution reflection coefficient. Finally, the Hessian matrix regularization is employed to constrain the spatial continuity of the reflection coefficient. This method is validated in both the model and real seismic data. Compared to traditional sparse deconvolution and spectral modeling deconvolution with spatial constraints, this method not only expands the frequency bandwidth and enhances seismic resolution but also preserves operational frequency information and improves the spatial continuity of seismic data. It has been verified that this approach can be used to forecast thin reservoir and reconstruct spatial tectonic characteristics.

show abstract

Wavelet analysis for spectral inversion of seismic reflection data

Cited by 12 publications

References 8 publications

Short-Term Traffic Speed Forecasting Using a Deep Learning Method Based on Multitemporal Traffic Flow Volume

Short-Term Traffic Speed Forecasting Using a Deep Learning Method Based on Multitemporal Traffic Flow Volume

Modified Fuzzy Inference Method for Heat Flux Inversion of Geothermal Reservoir Heat Source

A novel high-resolution imaging method based on sparsity in the time domain and spectral fitting in the frequency domain

Contact Info

Product

Resources

About