Journal ArticleDOI
Web-based machine learning tool that determines the origin of natural gases
TLDR
A web-based tool powered by a machine learning model that determines the origin of gases in samples with unknown origin accompanied by model accuracy and the confidence score for each possible origin is developed.About:
This article is published in Computers & Geosciences.The article was published on 2020-12-01. It has received 19 citations till now.read more
Citations
More filters
Journal ArticleDOI
Mixed gas sources induced co-existence of sI and sII gas hydrates in the Qiongdongnan Basin, South China Sea
Jiangong Wei,Tingting Wu,Linqi Zhu,Yunxin Fang,Jinqiang Liang,Hailong Lu,Wenjiu Cai,Zhiyuan Xie,Peixin Lai,Jun Cao,Tianbang Yang +10 more
TL;DR: In 2018, the Guangzhou Marine Geological Survey carried out its fifth natural gas hydrate drilling expedition (GMGS5) in the Qiongdongnan basin of the South China Sea as mentioned in this paper.
Journal ArticleDOI
New approaches to distinguish shale-sourced and coal-sourced gases in petroleum systems
TL;DR: In this article, a large global dataset of molecular and isotopic properties of gases from unconventional shale and coal reservoirs is used to evaluate the best separation of shale sourced and coal sourced gases.
Journal ArticleDOI
Gas Origin and Constraint of δ13C(CH4) Distribution in the Dafosi Mine Field in the Southern Margin of the Ordos Basin, China
TL;DR: Coalbed gas or coalbed methane (CBM) is a vital hydrocarbon gas which is mainly absorbed in the surface of the coal matrix and has multiple benefits as in being effective in development and utiliza...
Journal ArticleDOI
A review of machine learning in geochemistry and cosmochemistry: Method improvements and applications
TL;DR: In this paper , a review of the main applications of machine learning methods in geochemistry and cosmochemistry are discussed, including rock and sediment identification, digital mapping, water and soil quality prediction, and deep space exploration.
Journal ArticleDOI
Molecular hydrogen in surface and subsurface natural gases: Abundance, origins and ideas for deliberate exploration
TL;DR: In this article , a global dataset of 6246 natural gases with reported H2 concentrations from 16 different geological habitats was used to study the distribution, abundance and origins of geologic molecular hydrogen (H2).
References
More filters
Journal ArticleDOI
Random Forests
TL;DR: Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the forest, and are also applicable to regression.
Book
Introduction to Machine Learning
TL;DR: Introduction to Machine Learning is a comprehensive textbook on the subject, covering a broad array of topics not usually included in introductory machine learning texts, and discusses many methods from different fields, including statistics, pattern recognition, neural networks, artificial intelligence, signal processing, control, and data mining.
Proceedings ArticleDOI
Random decision forests
TL;DR: In this article, the authors proposed a method to construct tree-based classifiers whose capacity can be arbitrarily expanded for increases in accuracy for both training and unseen data, which can be monotonically improved by building multiple trees in different subspaces of the feature space.
Journal ArticleDOI
Carbon and hydrogen isotope systematics of bacterial formation and oxidation of methane
TL;DR: In this paper, the major dissolved carbon species in diagenetic settings are represented by the two carbon redox endmembers CH4 and CO2, and they can be tracked with the aid of carbon ( 13 C / 12 C ) and hydrogen ( D/H≡ 2 H/ 1 H ) isotopes.
Journal ArticleDOI
Biogenic methane formation in marine and freshwater environments: CO2 reduction vs. acetate fermentation—Isotope evidence
TL;DR: In this paper, the carbon and hydrogen stable isotope composition of the methane as a function of the coexisting carbon dioxide and formation water precursors is used to distinguish two primary methanogenic pathways.