首页|Jilin University Reports Findings in Machine Learning (An ensemble optimizer wit h a stacking ensemble surrogate model for identification of groundwater contamin ation source)
Jilin University Reports Findings in Machine Learning (An ensemble optimizer wit h a stacking ensemble surrogate model for identification of groundwater contamin ation source)
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
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Machine Learning is th e subject of a report. According to news reporting originating in Changchun, Peo ple’s Republic of China, by NewsRx journalists, research stated, “The applicatio n of the simulation-optimization method for groundwater contamination source ide ntification (GCSI) encounters two main challenges: the substantial time cost of calling the simulation model, and the limitations on the accuracy of identificat ion results due to the complexity, nonlinearity, and ill-posed nature of the inv erse problem. To address these issues, we have innovatively developed an inversi on framework based on ensemble learning strategies.” The news reporters obtained a quote from the research from Jilin University, “Th is framework comprises a stacking ensemble model (SEM), which integrates three d istinct machine learning models (Extremely Randomized Trees, Adaptive Boosting, and Bidirectional Gated Recurrent Unit), and an ensemble optimizer (E-GKSEEFO), which combines two newly proposed swarm intelligence optimizers (Genghis Khan Sh ark Optimizer and Electric Eel Foraging Optimizer). Specifically, the SEM serves as a surrogate model for the groundwater numerical simulation model. Compared t o the original simulation model, it significantly reduces time cost while mainta ining accuracy. The E-GKSEEFO, functioning as the search strategy for the optimi zation model, greatly enhances the accuracy of the optimization results. We have verified the performance of the SEM-E-GKSEEFO ensemble inversion framework thro ugh two hypothetical scenarios derived from an actual coal gangue pile. The resu lts are as follows. (1) The SEM exhibits improved fitting performance compared t o single machine learning models when dealing with high-dimensional nonlinear da ta from GCSI. (2) The E-GKSEEFO achieves significantly higher accuracy in the id entification results of GCSI than individual optimizers.”
ChangchunPeople’s Republic of ChinaA siaCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
