arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2004.13562eess.SPcs.LGstat.ML
收藏

封闭式长短期记忆(EnLSTM)网络

Ensemble long short-term memory (EnLSTM) network

Peng Cheng Laboratory(鹏城实验室);School of Environmental Science and Engineering, Southern University of Science and Technology(南方科技大学环境科学与工程学院)

Yuntian Chen, Dongxiao Zhang

摘要:

在这项研究中,我们提出了一个集成长短期记忆(EnLSTM)网络,它可以在一个小的数据集上训练并处理序列数据。EnLSTM是通过组合集成神经网络(ENN)和级联长短期记忆(C-LSTM)网络来构建的,以利用它们的互补优势。为了解决小数据问题所带来的过收敛和干扰补偿问题,引入了模型参数摄动和高保真观测摄动方法。EnLSTM与已发布数据集上的常用模型进行了比较,并被证明是生成测井曲线的最先进模型,均方误差(MSE)降低了34%。在实例研究中,根据随钻测井(LWD)数据生成了12个不能随钻测量的测井曲线。EnLSTM在实践中能够降低成本和节省时间。

英文摘要:

In this study, we propose an ensemble long short-term memory (EnLSTM) network, which can be trained on a small dataset and process sequential data. The EnLSTM is built by combining the ensemble neural network (ENN) and the cascaded long short-term memory (C-LSTM) network to leverage their complementary strengths. In order to resolve the issues of over-convergence and disturbance compensation associated with training failure owing to the nature of small-data problems, model parameter perturbation and high-fidelity observation perturbation methods are introduced. The EnLSTM is compared with commonly-used models on a published dataset, and proven to be the state-of-the-art model in generating well logs with a mean-square-error (MSE) reduction of 34%. In the case study, 12 well logs that cannot be measured while drilling are generated based on logging-while-drilling (LWD) data. The EnLSTM is capable to reduce cost and save time in practice.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑