首页|Study Data from Xinjiang University Provide New Insights into Machine Learning ( Improved Pore Structure Prediction Based On a Stacking Machine Learning Model fo r Low-permeability Reservoir In Tazhong Area, Tarim Basin)
Study Data from Xinjiang University Provide New Insights into Machine Learning ( Improved Pore Structure Prediction Based On a Stacking Machine Learning Model fo r Low-permeability Reservoir In Tazhong Area, Tarim Basin)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
New research on Machine Learning is th e subject of a report. According to news reporting originating from Xinjiang, Pe ople's Republic of China, by NewsRx correspondents, research stated, "Stacking i s an ensemble machine learning method designed to improve overall performance by combining the predictions of multiple base learners. The core idea of Stacking is to use the output of different base learners as input and make final predicti ons through a meta-learner, allowing the model to benefit from the strengths of various base learners and adapt better to complex data patterns." Financial support for this research came from Tianchi talent project. Our news editors obtained a quote from the research from Xinjiang University, "P redicting pore structures in low permeability is a sophisticated nonlinear model ing issue affected by multiple factors, including sedimentary and diagenetic eff ects on the structure. An individual model to predict pore structure is not sati sfactory. In this paper, we applied a fusion of random forest and Adaboost model s as base learners, which emerges as the cornerstone of this research, showcasin g remarkable versatility and integration of diverse learner strengths. The Silur ian system in Tazhong area features a vast expanse of lithological reservoirs wi th low abundance and high heterogeneity. Capillary pressure plays a crucial role in the distribution of these less permeable reservoirs by pore structure type i nfluence. Aiming to predict the pore structure for the low-permeability reservoi r in the field, which is characterized by low abundance and high heterogeneity, the study strategically integrates geological theory into specialized databases and harnesses machine learning methods. The resulting machine learning modeling dataset leverages geological factors and logging response characteristics to str engthen the ensemble machine learning stacking model. This sophisticated model n ot only achieves exceptional accuracy but also undergoes rigorous validation by analyzing predicted pore structure types alongside production data. The model's average accuracy was 79.4%, which practically hit the test set's ac curacy threshold, meaning that the model was in an optimal state."
XinjiangPeople's Republic of ChinaAs iaCyborgsEmerging TechnologiesMachine LearningXinjiang University
NETL
NSTL
