HRHongjia Ren

Hongjia Ren

*This is an algorithmically generated author record based on publicly available information.

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


Hongjia Ren has a total of 33 co-authors. Here are the top co-authors by number of shared publications:

  • Qiulin Guo

    Research Institute of Petroleum Exploration & Development, PetroChina, Beijing, China

    5 shared publications
  • Jingdu Yu

    Research Institute of Petroleum Exploration & Development, PetroChina, Beijing, China

    4 shared publications
  • Jifeng Liu

    Beijing Tinten Grid Technology Co, Ltd., Beijing, China

    3 shared publications
  • Haoyun Liu

    School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China

    2 shared publications
  • Ningsheng Chen

    Research Institute of Petroleum Exploration & Development, PetroChina, Beijing, China

    2 shared publications
  • Xianchang Wang

    College of Computer Science and Technology, Jilin University, Changchun, China

    2 shared publications

Latest Publications

  • Unsupervised Fault Segmentation Method Based on Geological Constraints

    by Hongjia Ren, Xu Guo, Yongcai Wang, Rong Chu, Qi Wang, Xihao Fan, Yougong Wang

  • DWOA-BNC: Discrete whale optimization algorithm for Bayesian network classifier learning and its application

    by Xihao Fan, Fengda Zhao, Jingdu Yu, Peiliang Wu, Chang Gao, Hongbing Xie, Qiulin Guo, Hongjia Ren


  • Open Access

    A Deep Learning Model Combining Multimodal Factors to Predict the Overall Survival of Transarterial Chemoembolization

    by Zhongqi Sun, Xin Li, Hongwei Liang, Zhongxing Shi, Hongjia Ren

    Background: To develop and validate an overall survival (OS) prediction model for transarterial chemoembolization (TACE). Methods: In this retrospective study, 301 patients with hepatocellular carcinoma (HCC) who received TACE from 2012 to 2015 were collected. The residual network was used to extract prognostic information from CT images, which was then combined with the clinical factors adjusted by COX regression to predict survival using a modified deep learning model (DLOPCombin). The DLOPCombin model was compared with the residual network model (DLOPCTR), multiple COX regression model (DLOPCox), Radiomic model (Radiomic), and clinical model. Results: In the validation cohort, DLOPCombin shows the highest TD AUC of all cohorts, which compared with Radiomic (TD AUC: 0.96vs 0.63) and clinical model (TD AUC: 0.96 vs 0.62) model. DLOPCombin showed significant difference in C index compared with DLOPCTR and DLOPCox models (P < 0.05). Moreover, the DLOPCombin showed good calibration and overall net benefit. Patients with DLOPCombin model score ≤ 0.902 had better OS (33 months vs 15.5 months, P < 0.0001). Conclusion: The deep learning model can effectively predict the patients’ overall survival of TACE.


  • Open Access

    A novel Mahalanobis distance method for predicting oil and gas resource spatial distribution

    by Qiulin Guo, Hongjia Ren, Haoyun Liu, Jifeng Liu, Ningsheng Chen, Jingdu Yu

    Accurate prediction of spatial distribution of petroleum resources is important for petroleum exploration. Mahalanobis distance is a popular and effective method to predict the spatial distribution of oil and gas. However, this method has equal weights for each variable, exaggerates secondary variables, and is prone to misjudge when the distance is close or equal, which impairs the accuracy of classification. To solve these problems, this paper proposes a novel Mahalanobis distance method based on genetic algorithm (GA-MD) to optimize attribute weights. The Sangonghe Formation in the hinterland of the Junggar Basin was used as an example, the validity of GA-MD was evaluated in the exploratory well data set. Compared with the current mainstream methods, the results show that the accuracy of GA-MD method is the highest, and the accuracy is improved by 2–6.2%. The application effect of the proposed method is verified by the prediction result of oil and gas probability map, the GA-MD method not only shows higher oil and gas bearing probability in the reserve areas but also has better trend extrapolation ability compared with other methods. Based on the GA-MD results, the favorable zones with remaining petroleum resources in the Sangonghe Formation in the hinterland of the Junggar Basin were visualized. Three types of favorable oil and gas distribution areas are selected. The favorable areas provide a basis for quantitative decision-making for the optimization of the next drilling strategy and determination of oil and gas exploration deployment direction in the study area.


  • Open Access

    A Fractal Simulation Method for Simulating the Resource Abundance of Oil and Gas and Its Application

    by Qiulin Guo, Hongjia Ren, Xiaozhi Wu, Zhuangxiaoxue Liu, Yanzhao Wei, Jifeng Liu, Haoyun Liu, Jingdu Yu, Qian Zhang

    In this study, a fractal simulation method for simulating resource abundance is proposed based on the evaluation results of the exploration risk and prediction technology for the spatial distribution of oil and gas resources at home and abroad. In addition, a key technical workflow for simulating resource abundance was developed. Furthermore, the model for predicting resource abundance has been modified, and the objective functions for conditional simulation have been improved. A series of prediction technologies for predicting the spatial distribution of oil and gas resources have been developed, and the difficulties in visualizing the exploration risks and predicting the spatial distribution of oil and gas resources have been solved. Prediction technologies have been applied to the Jurassic Sangonghe Formation in the hinterland of the Junggar Basin, and good results have been obtained. The results indicated that within the known area, taking the known abundance as the constraint condition, the coincidence rate of the simulated quantities of the original model and the improved model with the actual reserves reached 99.98% after the conditional simulation, indicating that the conditional simulation was effective. In addition, with the improved model, the predicted remaining resources are 0.7899 $$\times 10^{8}$$ × 10 8 t, which is 65% of the discovered reserves, and the original model predicts that the remaining resources are 3.5033 $$\,\times \,10^{8}$$ × 10 8 t, which is 2.89 times greater than the discovered reserves. Compared with the area in the middle stage of exploration, the results of the improved model are more consistent, and the results of the original model are obviously larger, indicating that the improved model has a good predictive effect for the unknown area. Finally, according to the risk probability and remaining resource distribution, the favorable areas for exploration were optimized as follows: the neighborhood of the triangular area formed by Well Lunan1, Well Shimo1, and Well Shi008, the area near Well Mo11, the area east of Well Mo5, the area west of Well Pen7, the area southwest of Well Shidong1, and the surroundings, as well as the area north of Well Fang2. The application results show that these prediction technologies are effective and can provide important reference and decision-making for resource evaluation and target optimization.


  • Open Access

    Scalable Structure Learning of K-Dependence Bayesian Network Classifier

    by Hongjia Ren, Xianchang Wang

    K-dependence Bayesian network classifier(KDB) has been widely used in data mining and machine learning. To enhance the expression ability and classification performance of KDB, the present study proposes a scalable k-dependence Bayesian classifier (SKDB), which is an extension of the classic KDB algorithm. SKDB introduces a novel attribute sorting method to pre-determine the optimal attribute order and a filtering mechanism to eliminate weak conditional dependence. Experimental results on 30 datasets from the University of California at Irvine (UCI) machine learning repository demonstrate that the above two techniques exert a positive impact on the classification performance of KDB. The proposed algorithm(SKDB) achieves better classification performance compared with several state-of-the-art BNCs (such as Naïve Bayes, tree-augmented Naïve Bayes, averaged one-dependence estimators, and KDB) in terms of 0-1 loss, bias, and variance.


  • Open Access

    Spatial Distribution Prediction of Oil and Gas Based on Bayesian Network with Case Study

    by Hongjia Ren, Xianchang Wang, Hongbo Ren, Qiulin Guo

    Effectively predicting the spatial distribution of oil and gas contributes to delineating promising target areas for further exploration. Determining the location of hydrocarbon is a complex and uncertain decision problem. This paper proposes a method for predicting the spatial distribution of oil and gas resource based on Bayesian network. In this method, qualitative dependency relationship between the hydrocarbon occurrence and key geologic factors is obtained using Bayesian network structure learning by integrating the available geoscience information and the current exploration results and then using Bayesian network topology structure to predict the probability of hydrocarbon occurrence in the undiscovered area; finally, the probability map of hydrocarbon-bearing is formed by interpolation method. The proposed method and workflow are further illustrated using an example from the Carboniferous Huanglong Formation (C2hl) in the eastern part of the Sichuan Basin in China. The prediction results show that the coincidence rate between the results of 248 known exploration wells and the predicted results reaches 89.5%, and it has been found that the gas fields are basically located in the high value area of the hydrocarbon-bearing probability map. The application results show that the Bayesian network method can effectively predict the spatial distribution of oil and gas resources, thereby reducing exploration risks, optimizing exploration targets, and improving exploration benefits.