Zhibing Feng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Zhibing Feng has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
Li Jiang
5 shared publicationsFei Xia
3 shared publicationsBocheng Zhang
2 shared publicationsFengjun Nie
2 shared publicationsHuang Xiao
Geologic Party No.243, China National Nuclear Corporation, Chifeng, China
2 shared publicationsJian Ding
2 shared publications
Latest Publications
- Open Access
- 5 August 2026
- Published by Elsevier in Ore Geology Reviews
- Vol. 196
Quantitative constraints of local tectonic subsidence on sandstone-type uranium mineralization in the Daqing Placanticline, northern Songliao Basin, NE China
- 5 August 2026
- Published by Elsevier in Ore Geology Reviews
- Vol. 196
Open AccessQuantitative constraints of local tectonic subsidence on sandstone-type uranium mineralization in the Daqing Placanticline, northern Songliao Basin, NE China
- Open Access
- 14 July 2026
- Published by Elsevier in Ore Geology Reviews
- Vol. 196
Well-log-based quantitative evaluation of potash mineral potential using an improved stacking model
- 14 July 2026
- Published by Elsevier in Ore Geology Reviews
- Vol. 196
Open AccessWell-log-based quantitative evaluation of potash mineral potential using an improved stacking model
- 10 December 2025
- Published by Springer Nature in Acta Geophysica
- Vol. 74 (1) , 22
Optimization and evaluation of ensemble learning models for intelligent lithology identification based on seismic data
- 10 December 2025
- Published by Springer Nature in Acta Geophysica
- Vol. 74 (1) , 22
Optimization and evaluation of ensemble learning models for intelligent lithology identification based on seismic data
- Open Access
- 9 December 2025
- Published by Elsevier in Nuclear Engineering and Technology
- Vol. 58 (4)
Sandstone-type uranium mineralization coupled with extensional tectonics
- 9 December 2025
- Published by Elsevier in Nuclear Engineering and Technology
- Vol. 58 (4)
Open AccessSandstone-type uranium mineralization coupled with extensional tectonics
- 20 September 2025
- Published by Springer Nature in Applied Geophysics
- Vol. 22 (3) , 757-769
A Seismic Multi-Attribute Sandbody Identification Method Based on the LightGBM-RFECV Coupling Algorithm
- 20 September 2025
- Published by Springer Nature in Applied Geophysics
- Vol. 22 (3) , 757-769
A Seismic Multi-Attribute Sandbody Identification Method Based on the LightGBM-RFECV Coupling Algorithm
- Open Access
- 10 July 2025
- Published by Springer Nature in Research Square
Optimization and Evaluation of Ensemble Learning Models for Intelligent Lithology Identification Using Seismic Data
Lithology identification is one of the key geological interpretation tasks in oil and gas exploration, which directly affects the accuracy of reservoir modeling and resource evaluation. At present, seismic lithology prediction research has the limitation of over-focusing on the optimization of a single algorithm and lacking systematic comparison of ensemble models and hyperparameter strategies. To this end, this study employs recursive feature elimination, NM-SMOTE sampling, and four hyperparameter optimization methods. These are applied to well seismic data from the F3 exploration area in the North Sea to evaluate random forest (RF), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), categorical boosting (CatBoost) and stacked ensemble models (SEM).The experimental results show that in terms of hyperparameter optimization, the Optuna algorithm achieves the best balance between computational efficiency and model performance, and its optimization effect is significantly better than that of the traditional grid search method. In the context of single models, CatBoost shows the best prediction performance (AUC = 0.91), with clear boundaries for sandstone and mudstone identification and the best spatial continuity of the prediction results. The comparative analysis of different ensemble models shows that random forest has the highest stability, followed by LightGBM, while XGBoost is more sensitive to data noise, resulting in a instability in the prediction results. It is worth noting that the classification performance of the SEM is limited under complex geological conditions such as thin interbeds. This study systematically evaluates the technical characteristics of each model and proposes model selection criteria for different geological application scenarios, providing important theoretical basis and method support for the practical application of intelligent lithology identification technology.
- 10 July 2025
- Published by Springer Nature in Research Square
Open AccessOptimization and Evaluation of Ensemble Learning Models for Intelligent Lithology Identification Using Seismic Data
Lithology identification is one of the key geological interpretation tasks in oil and gas exploration, which directly affects the accuracy of reservoir modeling and resource evaluation. At present, seismic lithology prediction research has the limitation of over-focusing on the optimization of a single algorithm and lacking systematic comparison of ensemble models and hyperparameter strategies. To this end, this study employs recursive feature elimination, NM-SMOTE sampling, and four hyperparameter optimization methods. These are applied to well seismic data from the F3 exploration area in the North Sea to evaluate random forest (RF), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), categorical boosting (CatBoost) and stacked ensemble models (SEM).The experimental results show that in terms of hyperparameter optimization, the Optuna algorithm achieves the best balance between computational efficiency and model performance, and its optimization effect is significantly better than that of the traditional grid search method. In the context of single models, CatBoost shows the best prediction performance (AUC = 0.91), with clear boundaries for sandstone and mudstone identification and the best spatial continuity of the prediction results. The comparative analysis of different ensemble models shows that random forest has the highest stability, followed by LightGBM, while XGBoost is more sensitive to data noise, resulting in a instability in the prediction results. It is worth noting that the classification performance of the SEM is limited under complex geological conditions such as thin interbeds. This study systematically evaluates the technical characteristics of each model and proposes model selection criteria for different geological application scenarios, providing important theoretical basis and method support for the practical application of intelligent lithology identification technology.
- 20 February 2023
- Published by Springer Nature in Journal of Earth Science
- Vol. 34 (1) , 54-69
Roles of Multisourced Fluids in the Formation of Sandstone-Hosted Uranium Deposits in the SW Songliao Basin, NE China
- 20 February 2023
- Published by Springer Nature in Journal of Earth Science
- Vol. 34 (1) , 54-69
Roles of Multisourced Fluids in the Formation of Sandstone-Hosted Uranium Deposits in the SW Songliao Basin, NE China
- 27 September 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Oceanic Engineering
- Vol. 43 (4) , 1179-1186
Measurements of Midfrequency Acoustic Backscattering From a Sandy Bottom in the South Yellow Sea of China
Acoustic bottom scattering is the main source of reverberation background in target detection and recognition near the seafloor. Accurate estimation of bottom scattering strength is necessary for prediction of sonar performance in the presence of reverberation in shallow-water environments. A measurement of bottom backscattering strength at midfrequency in a shallow-water environment of the South Yellow Sea of China was carried out in April 2016, where the water depth was 39 m. The surface of the seafloor was relatively flat and covered by some shell fragments observed through a digital camera system. Core data showed that the main component of sediment at this experiment site was fine sand. The backscattering strength as a function of grazing angle (20°–70°) in the frequency range of 6–12 kHz was extracted from monostatic backscattering data, employing an omni-directional source and an omni-directional hydrophone. The measured backscattering strength increases with the increase of the grazing angle, and changes more rapidly at large grazing angles (60°–70°). Comparing the data at different frequencies, it is found that the measured backscattering strength slightly increases with the increase of the acoustic frequency. A fit of Lambert's law to the measured data shows that the backscattering strength deviates from the Lambert's law at large grazing angles. Finally, the fitted result of a scattering model to the measured data suggests that seafloor roughness scattering is larger than that from sediment volume heterogeneity in the measurement frequency band.
- 27 September 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Oceanic Engineering
- Vol. 43 (4) , 1179-1186
Measurements of Midfrequency Acoustic Backscattering From a Sandy Bottom in the South Yellow Sea of China
Acoustic bottom scattering is the main source of reverberation background in target detection and recognition near the seafloor. Accurate estimation of bottom scattering strength is necessary for prediction of sonar performance in the presence of reverberation in shallow-water environments. A measurement of bottom backscattering strength at midfrequency in a shallow-water environment of the South Yellow Sea of China was carried out in April 2016, where the water depth was 39 m. The surface of the seafloor was relatively flat and covered by some shell fragments observed through a digital camera system. Core data showed that the main component of sediment at this experiment site was fine sand. The backscattering strength as a function of grazing angle (20°–70°) in the frequency range of 6–12 kHz was extracted from monostatic backscattering data, employing an omni-directional source and an omni-directional hydrophone. The measured backscattering strength increases with the increase of the grazing angle, and changes more rapidly at large grazing angles (60°–70°). Comparing the data at different frequencies, it is found that the measured backscattering strength slightly increases with the increase of the acoustic frequency. A fit of Lambert's law to the measured data shows that the backscattering strength deviates from the Lambert's law at large grazing angles. Finally, the fitted result of a scattering model to the measured data suggests that seafloor roughness scattering is larger than that from sediment volume heterogeneity in the measurement frequency band.
- 1 July 2017
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 82 (4) , G77-G86
A versatile solution for the gravity anomaly of 3D prism-meshed bodies with depth-dependent density contrast
We have developed a generalized solution for computing the gravity anomalies of 3D irregular-mass bodies with complicated density-contrast variation. The 3D irregular-shaped bodies can be approximated flexibly by a collection of finite-juxtaposed right-rectangular prisms. The complicated density-contrast variation of each prism can be well-represented by a depth-dependent polynomial function. A novel analytic solution of gravity anomalies due to a right-rectangular prism with an arbitrary order of polynomial density-contrast function of depth is then derived. The solution is singularity free in the upper half-space over the prism, and its singularity in the lower half-space containing the prism is resolved by assigning their limit values to the singular terms. The numerical stability of the solution is also evaluated through numerical tests. Hence, the solution can be used to compute the gravity anomalies of 3D irregular bodies with variable density contrasts without singularities when computation points are within the numerical stability range. Based on synthetic models with variable density contrast, our solution is validated by using other solutions in the literature. We also simulated the gravity anomalies of the Los Angeles basin and compared them with the observed anomalies and with those computed using the analytic solutions of other workers. These tests confirm the accuracy and efficiency of our analytic solution.
- 1 July 2017
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 82 (4) , G77-G86
A versatile solution for the gravity anomaly of 3D prism-meshed bodies with depth-dependent density contrast
We have developed a generalized solution for computing the gravity anomalies of 3D irregular-mass bodies with complicated density-contrast variation. The 3D irregular-shaped bodies can be approximated flexibly by a collection of finite-juxtaposed right-rectangular prisms. The complicated density-contrast variation of each prism can be well-represented by a depth-dependent polynomial function. A novel analytic solution of gravity anomalies due to a right-rectangular prism with an arbitrary order of polynomial density-contrast function of depth is then derived. The solution is singularity free in the upper half-space over the prism, and its singularity in the lower half-space containing the prism is resolved by assigning their limit values to the singular terms. The numerical stability of the solution is also evaluated through numerical tests. Hence, the solution can be used to compute the gravity anomalies of 3D irregular bodies with variable density contrasts without singularities when computation points are within the numerical stability range. Based on synthetic models with variable density contrast, our solution is validated by using other solutions in the literature. We also simulated the gravity anomalies of the Los Angeles basin and compared them with the observed anomalies and with those computed using the analytic solutions of other workers. These tests confirm the accuracy and efficiency of our analytic solution.