Jinlin Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Jinlin Liu has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Wenkai Lu
Department of Automation, Tsinghua University, Beijing, China
2 shared publications - Lei Liu
Tsinghua University, Easysignal Group, State Key Laboratory of Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Automation, Beijing, China.
1 shared publication - Lideng Gan
PetroChina RIPED
1 shared publication - Xiaofeng Dai
PetroChina 2 , Research Institute of Petroleum Exploration and Development, Beijing, China
1 shared publication
Latest Publications
- 1 March 2018
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 83 (2) , O25-O30
Supervised seismic facies analysis based on image segmentation
Seismic facies analysis aims to characterize the seismic expression of a reservoir by placing seismic attributes into classes that are presumably related to geologic heterogeneities. Supervised seismic facies analysis can be used to classify the seismic expression of reservoirs in oil field development using well control as the training samples. Manual seismic facies analysis is often subjective, and it is usually time-consuming. Pattern recognition techniques such as support vector machine and neural networks have been used to automate seismic facies analysis. However, they often do not produce satisfactory spatial continuity in their results. The spurious spatial discontinuities are usually caused by the so-called “over-fitting” problem inherent in these methods. To avoid this issue, we have developed a supervised seismic facies analysis method based on image segmentation that promotes spatial continuity of the classified seismic facies. The seed region growing technique borrowed from image segmentation is used to segment attribute maps outward from points of well control. In addition, we calculate the seismic facies probability distribution at every grid point in the seismic image. We use this probability distribution as a weighting coefficient to allow regions to grow anisotropically. As demonstrated by the results on a field data set, this approach improves spatial continuity and indicates promising results.
- 1 March 2018
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 83 (2) , O25-O30
Supervised seismic facies analysis based on image segmentation
Seismic facies analysis aims to characterize the seismic expression of a reservoir by placing seismic attributes into classes that are presumably related to geologic heterogeneities. Supervised seismic facies analysis can be used to classify the seismic expression of reservoirs in oil field development using well control as the training samples. Manual seismic facies analysis is often subjective, and it is usually time-consuming. Pattern recognition techniques such as support vector machine and neural networks have been used to automate seismic facies analysis. However, they often do not produce satisfactory spatial continuity in their results. The spurious spatial discontinuities are usually caused by the so-called “over-fitting” problem inherent in these methods. To avoid this issue, we have developed a supervised seismic facies analysis method based on image segmentation that promotes spatial continuity of the classified seismic facies. The seed region growing technique borrowed from image segmentation is used to segment attribute maps outward from points of well control. In addition, we calculate the seismic facies probability distribution at every grid point in the seismic image. We use this probability distribution as a weighting coefficient to allow regions to grow anisotropically. As demonstrated by the results on a field data set, this approach improves spatial continuity and indicates promising results.
- 22 December 2015
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 81 (1) , V69-V78
Adaptive multiple subtraction based on multiband pattern coding
Adaptive multiple subtraction is the key step of surface-related multiple elimination methods. The main challenge of this technique resides in removing multiples without distorting primaries. We have developed a new pattern-based method for adaptive multiple subtraction with the consideration that primaries can be better protected if the multiples are differentiated from the primaries. Different from previously proposed methods, our method casts the adaptive multiple subtraction problem as a pattern coding and decoding process. We set out to learn distinguishable patterns from the predicted multiples before estimating the multiples contained in seismic data. Hence, in our method, we first carried out pattern coding of the predicted multiples to learn the special patterns of the multiples within different frequency bands. This coding process aims at exploiting the key patterns contained in the predicted multiples. The learned patterns are then used to decode (extract) the multiples contained in the seismic data, in which process those patterns that are similar to the learned patterns were identified and extracted. Because the learned patterns are obtained from the predicted multiples only, our method avoids the interferences of primaries in nature and shows an impressive capability for removing multiples without distorting the primaries. Our applications on synthetic and real data sets gave some promising results.
- 22 December 2015
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 81 (1) , V69-V78
Adaptive multiple subtraction based on multiband pattern coding
Adaptive multiple subtraction is the key step of surface-related multiple elimination methods. The main challenge of this technique resides in removing multiples without distorting primaries. We have developed a new pattern-based method for adaptive multiple subtraction with the consideration that primaries can be better protected if the multiples are differentiated from the primaries. Different from previously proposed methods, our method casts the adaptive multiple subtraction problem as a pattern coding and decoding process. We set out to learn distinguishable patterns from the predicted multiples before estimating the multiples contained in seismic data. Hence, in our method, we first carried out pattern coding of the predicted multiples to learn the special patterns of the multiples within different frequency bands. This coding process aims at exploiting the key patterns contained in the predicted multiples. The learned patterns are then used to decode (extract) the multiples contained in the seismic data, in which process those patterns that are similar to the learned patterns were identified and extracted. Because the learned patterns are obtained from the predicted multiples only, our method avoids the interferences of primaries in nature and shows an impressive capability for removing multiples without distorting the primaries. Our applications on synthetic and real data sets gave some promising results.