文件名称：Machine learning for graph-based representations
文件大小：3.52MB
文件格式：PDF
更新时间：2022-03-03 21:17:02
机器学习
In this paper, we develop an alternative network reduction approach to characterizing transport in DFNs, by combining graph theoretical and ma- chine learning methods. We consider a graph representation where nodes sig- nify fractures and edges denote their intersections. Using random forest and support vector machines, we rapidly identify a subnetwork that captures the flow patterns of the full DFN, based primarily on node centrality features in the graph. Our supervised learning techniques train on particle-tracking backbone paths found by dfnWorks, but run in negligible time compared to those simulations. We find that our predictions can reduce the network to ap- proximately 20% of its original size, while still generating breakthrough curves consistent with those of the original network.