Long Short-Term Memory Network for High-Fidelity Tracking of Greenhouse Gas Emission

Author:

Kumar V.1,Roy A.2,Misra S.1

Affiliation:

1. Harold Vance Department of Petroleum Engineering, Texas A&M University, College Station, Texas, USA

2. Bently Nevada, Baker Hughes, Texas, USA

Abstract

AbstractThis paper investigates the use of machine learning to rapidly predict the solutions of a high-fidelity, complex physics model using a simpler physics model. Two different closed-form solutions of the advection-diffusion partial differential equation (A-D PDE), known as the Gaussian plume model and Gaussian puff model, are typically used to model the atmospheric dispersion of gas emission. The Gaussian puff model is a more complex physics-based model that requires more computational effort to generate the high-fidelity solutions, as compared to the simpler Gaussian plume model that has several assumptions and approximations. An encoder-decoder architecture of Long Short-Term Memory (LSTM) network is trained to predict the solutions of the more complex Gaussian puff model using the solutions of the simpler Gaussian plume model for various leak rate, wind speed, and wind direction. The LSTM model, with 3 LSTM layers with 16 neurons each, efficiently simulated the concentrations of the entire set of 2014 samples in a mere 1.34 minutes. This presents a significant contrast to the traditional software's time-consuming simulation process, which took 14 hours to achieve similar concentration outcomes in this study. The implementation of LSTM network has achieved a computational speed up of 625.15 times.

Publisher

SPE

Reference24 articles.

1. Air Pollution Meteorology and dispersion;Arya,1999

2. Handbook on Atmospheric Diffusion;Briggs,1982

3. Brownlee, J. (2021, July6). A gentle introduction to long short-term memory networks by the experts. Machine Learning Mastery.com. https://machinelearningmastery.com/gentle-introduction-long-short-term-memory-networks-experts/

4. Chollet, F. (2017, September). The keras blog. The Keras Blog ATOM. Retrieved January 11, 2023, from https://blog.keras.io/a-ten-minute-introduction-to-sequence-to-sequence-learning-in-keras.html

5. Hazardous weather phenomena wind shear - Bureau of Meteorology. (n.d.). Retrieved from http://www.bom.gov.au/aviation/data/education/wind-shear.pdf

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3