A machine learning-driven stochastic simulation of underground sulfide distribution with multiple constraints

The increase of sulfide (S2−) during the water flooding process has been regarded as an essential and potential risk for oilfield development and safety. Kriging and stochastic simulations are common methods for assessing the element distribution. However, these traditional simulation methods are no...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ji Qiuyan, Han Feilong, Qian Wei, Guo Qing, Wan Shulin
Formato:	article
Lenguaje:	EN
Publicado:	De Gruyter 2021
Materias:	machine learning stochastic simulation sulfide chemical estimation multiple constraints Geology QE1-996.5
Acceso en línea:	https://doaj.org/article/015e003323524026b1921c406a8bc82a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:015e003323524026b1921c406a8bc82a
record_format	dspace
spelling	oai:doaj.org-article:015e003323524026b1921c406a8bc82a2021-12-05T14:10:49ZA machine learning-driven stochastic simulation of underground sulfide distribution with multiple constraints2391-544710.1515/geo-2020-0274https://doaj.org/article/015e003323524026b1921c406a8bc82a2021-07-01T00:00:00Zhttps://doi.org/10.1515/geo-2020-0274https://doaj.org/toc/2391-5447The increase of sulfide (S2−) during the water flooding process has been regarded as an essential and potential risk for oilfield development and safety. Kriging and stochastic simulations are common methods for assessing the element distribution. However, these traditional simulation methods are not able to predict the continuous changes of underground S2− distribution in the time domain by limited known information directly. This study is a kind of attempt to combine stochastic simulation and the modified probabilistic neural network (modified PNN) for simulating short-term changes of S2− concentration. The proposed modified PNN constructs the connection between multiple indirect datasets and S2− concentration at sampling points. These connections, which are treated as indirect data in the stochastic simulation processes, is able to provide extra supports for changing the probability density function (PDF) and enhancing the stability of the simulation. In addition, the simulation process can be controlled by multiple constraints due to which the simulating target has been changed into the increment distribution of S2−. The actual data test provides S2− distributions in an oil field with good continuity and accuracy, which demonstrate the outstanding capability of this novel method.Ji QiuyanHan FeilongQian WeiGuo QingWan ShulinDe Gruyterarticlemachine learningstochastic simulationsulfidechemical estimationmultiple constraintsGeologyQE1-996.5ENOpen Geosciences, Vol 13, Iss 1, Pp 807-819 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	machine learning stochastic simulation sulfide chemical estimation multiple constraints Geology QE1-996.5
spellingShingle	machine learning stochastic simulation sulfide chemical estimation multiple constraints Geology QE1-996.5 Ji Qiuyan Han Feilong Qian Wei Guo Qing Wan Shulin A machine learning-driven stochastic simulation of underground sulfide distribution with multiple constraints
description	The increase of sulfide (S2−) during the water flooding process has been regarded as an essential and potential risk for oilfield development and safety. Kriging and stochastic simulations are common methods for assessing the element distribution. However, these traditional simulation methods are not able to predict the continuous changes of underground S2− distribution in the time domain by limited known information directly. This study is a kind of attempt to combine stochastic simulation and the modified probabilistic neural network (modified PNN) for simulating short-term changes of S2− concentration. The proposed modified PNN constructs the connection between multiple indirect datasets and S2− concentration at sampling points. These connections, which are treated as indirect data in the stochastic simulation processes, is able to provide extra supports for changing the probability density function (PDF) and enhancing the stability of the simulation. In addition, the simulation process can be controlled by multiple constraints due to which the simulating target has been changed into the increment distribution of S2−. The actual data test provides S2− distributions in an oil field with good continuity and accuracy, which demonstrate the outstanding capability of this novel method.
format	article
author	Ji Qiuyan Han Feilong Qian Wei Guo Qing Wan Shulin
author_facet	Ji Qiuyan Han Feilong Qian Wei Guo Qing Wan Shulin
author_sort	Ji Qiuyan
title	A machine learning-driven stochastic simulation of underground sulfide distribution with multiple constraints
title_short	A machine learning-driven stochastic simulation of underground sulfide distribution with multiple constraints
title_full	A machine learning-driven stochastic simulation of underground sulfide distribution with multiple constraints
title_fullStr	A machine learning-driven stochastic simulation of underground sulfide distribution with multiple constraints
title_full_unstemmed	A machine learning-driven stochastic simulation of underground sulfide distribution with multiple constraints
title_sort	machine learning-driven stochastic simulation of underground sulfide distribution with multiple constraints
publisher	De Gruyter
publishDate	2021
url	https://doaj.org/article/015e003323524026b1921c406a8bc82a
work_keys_str_mv	AT jiqiuyan amachinelearningdrivenstochasticsimulationofundergroundsulfidedistributionwithmultipleconstraints AT hanfeilong amachinelearningdrivenstochasticsimulationofundergroundsulfidedistributionwithmultipleconstraints AT qianwei amachinelearningdrivenstochasticsimulationofundergroundsulfidedistributionwithmultipleconstraints AT guoqing amachinelearningdrivenstochasticsimulationofundergroundsulfidedistributionwithmultipleconstraints AT wanshulin amachinelearningdrivenstochasticsimulationofundergroundsulfidedistributionwithmultipleconstraints AT jiqiuyan machinelearningdrivenstochasticsimulationofundergroundsulfidedistributionwithmultipleconstraints AT hanfeilong machinelearningdrivenstochasticsimulationofundergroundsulfidedistributionwithmultipleconstraints AT qianwei machinelearningdrivenstochasticsimulationofundergroundsulfidedistributionwithmultipleconstraints AT guoqing machinelearningdrivenstochasticsimulationofundergroundsulfidedistributionwithmultipleconstraints AT wanshulin machinelearningdrivenstochasticsimulationofundergroundsulfidedistributionwithmultipleconstraints
_version_	1718371699514146816

A machine learning-driven stochastic simulation of underground sulfide distribution with multiple constraints

Ejemplares similares