A comparative machine learning study for time series oil production forecasting: ARIMA, LSTM, and Prophet

It is challenging to predict the production performance of unconventional reservoirs because of the sediment heterogeneity, intricate flow channels, and complex fluid phase behavior. The traditional oil production prediction methods (e.g., decline curve analysis and reservoir simulation modeling for...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computers & geosciences Ročník 164; s. 105126
Hlavní autoři: Ning, Yanrui, Kazemi, Hossein, Tahmasebi, Pejman
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.07.2022
Témata:
ISSN:0098-3004
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract It is challenging to predict the production performance of unconventional reservoirs because of the sediment heterogeneity, intricate flow channels, and complex fluid phase behavior. The traditional oil production prediction methods (e.g., decline curve analysis and reservoir simulation modeling forecasting) are subjective. This paper presents a machine learning-based time series forecasting method, which considers the existing data as time series and extracts the salient characteristics of historical data to predict values of a future time sequence. We used time series forecasting because of the historical fluctuations in production well and reservoir operations. Three algorithms were studied and compared to address the limitations of traditional production forecasting: Auto-Regressive Integrated Moving Averages (ARIMA), Long-Short-Term Memory (LSTM) network, and Prophet. This study starts with the representative oil production data from a well located in an unconventional reservoir in the Denver-Julesburg (DJ) Basin. 70% of the data was used for model training, whereas the remaining 30% of data was used to evaluate the performance of the above-mentioned methods. Then, the decline curve analysis and reservoir simulation modeling forecasting were applied for comparison. The advantages of the machine-learning models include a simple workflow, no prior assumption about the reservoir type, fast prediction, and reliable performance prediction for a typical fluctuating declining curve. More importantly, the ‘Prophet’ model captures production fluctuation caused by winter impact, which can attract the operator's attention and prevent potential failures. This has rarely been explored and discussed by previous studies. The application of ARIMA, LSTM, and Prophet methods to 65 wells in the DJ Basin show that ARIMA and LSTM perform better than Prophet—probably because not all oil production data include seasonal influences. Furthermore, the wells in the nearby pads can be studied using the same parameter values in ARIMA and LSTM for predicting oil prediction in a transferred learning framework. Specifically, we observed that ARIMA is robust in predicting the oil production rate of wells across the DJ Basin. •ARIMA and LSTM models perform better than Prophet in oil rate prediction.•Prophet model captures production fluctuation caused by seasonality.•R-squared is not an appropriate metric to evaluate non-linear regression models.•The oil rate of wells in nearby pads can be studied using the same parameter values in ARIMA and LSTM.•ARIMA is robust in predicting the oil rate of wells across the unconventional reservoirs.
AbstractList It is challenging to predict the production performance of unconventional reservoirs because of the sediment heterogeneity, intricate flow channels, and complex fluid phase behavior. The traditional oil production prediction methods (e.g., decline curve analysis and reservoir simulation modeling forecasting) are subjective. This paper presents a machine learning-based time series forecasting method, which considers the existing data as time series and extracts the salient characteristics of historical data to predict values of a future time sequence. We used time series forecasting because of the historical fluctuations in production well and reservoir operations. Three algorithms were studied and compared to address the limitations of traditional production forecasting: Auto-Regressive Integrated Moving Averages (ARIMA), Long-Short-Term Memory (LSTM) network, and Prophet. This study starts with the representative oil production data from a well located in an unconventional reservoir in the Denver-Julesburg (DJ) Basin. 70% of the data was used for model training, whereas the remaining 30% of data was used to evaluate the performance of the above-mentioned methods. Then, the decline curve analysis and reservoir simulation modeling forecasting were applied for comparison. The advantages of the machine-learning models include a simple workflow, no prior assumption about the reservoir type, fast prediction, and reliable performance prediction for a typical fluctuating declining curve. More importantly, the ‘Prophet’ model captures production fluctuation caused by winter impact, which can attract the operator's attention and prevent potential failures. This has rarely been explored and discussed by previous studies. The application of ARIMA, LSTM, and Prophet methods to 65 wells in the DJ Basin show that ARIMA and LSTM perform better than Prophet—probably because not all oil production data include seasonal influences. Furthermore, the wells in the nearby pads can be studied using the same parameter values in ARIMA and LSTM for predicting oil prediction in a transferred learning framework. Specifically, we observed that ARIMA is robust in predicting the oil production rate of wells across the DJ Basin. •ARIMA and LSTM models perform better than Prophet in oil rate prediction.•Prophet model captures production fluctuation caused by seasonality.•R-squared is not an appropriate metric to evaluate non-linear regression models.•The oil rate of wells in nearby pads can be studied using the same parameter values in ARIMA and LSTM.•ARIMA is robust in predicting the oil rate of wells across the unconventional reservoirs.
It is challenging to predict the production performance of unconventional reservoirs because of the sediment heterogeneity, intricate flow channels, and complex fluid phase behavior. The traditional oil production prediction methods (e.g., decline curve analysis and reservoir simulation modeling forecasting) are subjective. This paper presents a machine learning-based time series forecasting method, which considers the existing data as time series and extracts the salient characteristics of historical data to predict values of a future time sequence. We used time series forecasting because of the historical fluctuations in production well and reservoir operations. Three algorithms were studied and compared to address the limitations of traditional production forecasting: Auto-Regressive Integrated Moving Averages (ARIMA), Long-Short-Term Memory (LSTM) network, and Prophet. This study starts with the representative oil production data from a well located in an unconventional reservoir in the Denver-Julesburg (DJ) Basin. 70% of the data was used for model training, whereas the remaining 30% of data was used to evaluate the performance of the above-mentioned methods. Then, the decline curve analysis and reservoir simulation modeling forecasting were applied for comparison. The advantages of the machine-learning models include a simple workflow, no prior assumption about the reservoir type, fast prediction, and reliable performance prediction for a typical fluctuating declining curve. More importantly, the ‘Prophet’ model captures production fluctuation caused by winter impact, which can attract the operator's attention and prevent potential failures. This has rarely been explored and discussed by previous studies. The application of ARIMA, LSTM, and Prophet methods to 65 wells in the DJ Basin show that ARIMA and LSTM perform better than Prophet—probably because not all oil production data include seasonal influences. Furthermore, the wells in the nearby pads can be studied using the same parameter values in ARIMA and LSTM for predicting oil prediction in a transferred learning framework. Specifically, we observed that ARIMA is robust in predicting the oil production rate of wells across the DJ Basin.
ArticleNumber 105126
Author Kazemi, Hossein
Ning, Yanrui
Tahmasebi, Pejman
Author_xml – sequence: 1
  givenname: Yanrui
  orcidid: 0000-0002-2163-3451
  surname: Ning
  fullname: Ning, Yanrui
  email: yning@mines.edu
  organization: Department of Petroleum Engineering, Colorado School of Mines, USA
– sequence: 2
  givenname: Hossein
  surname: Kazemi
  fullname: Kazemi, Hossein
  organization: Department of Petroleum Engineering, Colorado School of Mines, USA
– sequence: 3
  givenname: Pejman
  surname: Tahmasebi
  fullname: Tahmasebi, Pejman
  organization: Department of Petroleum Engineering, University of Wyoming, USA
BookMark eNqFkLtOAzEQRV2ABAG-gMYlRRJs73ofSBQR4iUFgXjU1qx3Fhzt2sF2IuXvcQgVBVQjzZ0zmjkjsmedRUJOOZtyxovzxVTDO7qpYEKkjuSi2COHjNXVJGMsPyCjEBaMpbSSh8TMqHbDEjxEs0Y6gP4wFmmP4K2x7zTEVbuhnfM0mgFpQG8wUGd6uvSuXelonN3GqCHEBFzQ2fP9w2xM5y-vD2MKtqVP3i0_MB6T_Q76gCc_9Yi83Vy_Xt1N5o-391ez-QQyWccJLxpZalZkeSuqsm47RN7kkDWi5BWkrCmw05Br2TQFh7xKryDKvGwwYzVvsyNyttubDvxcYYhqMEFj34NFtwpKFKWUpRCFTKPZblR7F4LHTi29GcBvFGdqK1Mt1LdMtZWpdjITVf-itImwFRE9mP4f9nLHYjKwNuhV0AatxtYkhVG1zvzJfwGMP5Uc
CitedBy_id crossref_primary_10_3390_designs8030040
crossref_primary_10_1016_j_pce_2025_104063
crossref_primary_10_1007_s12145_025_01745_9
crossref_primary_10_1016_j_iintel_2023_100037
crossref_primary_10_1007_s10462_024_10865_5
crossref_primary_10_1016_j_rineng_2024_103434
crossref_primary_10_32362_2500_316X_2024_12_3_93_103
crossref_primary_10_1007_s10489_024_06053_1
crossref_primary_10_1016_j_sasc_2023_200067
crossref_primary_10_2118_219774_PA
crossref_primary_10_2118_223940_PA
crossref_primary_10_1007_s10489_024_05468_0
crossref_primary_10_1016_j_jclepro_2024_142336
crossref_primary_10_1016_j_geoen_2025_214100
crossref_primary_10_1016_j_seps_2023_101658
crossref_primary_10_3390_automation5030021
crossref_primary_10_1016_j_fuel_2025_136847
crossref_primary_10_1109_ACCESS_2023_3291999
crossref_primary_10_30657_pea_2023_29_40
crossref_primary_10_1016_j_measurement_2022_112317
crossref_primary_10_1016_j_petsci_2024_11_001
crossref_primary_10_1016_j_energy_2023_128910
crossref_primary_10_3390_fi15080255
crossref_primary_10_1016_j_eswa_2023_122412
crossref_primary_10_3390_app13179827
crossref_primary_10_1016_j_ins_2024_121586
crossref_primary_10_1142_S0218126625503852
crossref_primary_10_3390_ijerph20021167
crossref_primary_10_2298_TSCI2304081T
crossref_primary_10_1016_j_csite_2025_106356
crossref_primary_10_32604_cmc_2025_059869
crossref_primary_10_1016_j_oceaneng_2023_116137
crossref_primary_10_1186_s13677_023_00560_1
crossref_primary_10_12677_AAM_2022_1110774
crossref_primary_10_3390_su152416725
crossref_primary_10_1007_s11356_024_33335_5
crossref_primary_10_1016_j_heliyon_2022_e12239
crossref_primary_10_1016_j_sysarc_2024_103181
crossref_primary_10_1007_s13202_025_01939_3
crossref_primary_10_14254_2071_789X_2022_15_4_2
crossref_primary_10_1016_j_enbenv_2023_07_003
crossref_primary_10_1016_j_geoen_2024_213493
crossref_primary_10_3390_w16131827
crossref_primary_10_1007_s12599_024_00889_0
crossref_primary_10_1016_j_petlm_2024_11_001
crossref_primary_10_3390_en17143482
crossref_primary_10_1002_dug2_70060
crossref_primary_10_3390_su151813840
crossref_primary_10_4236_ti_2025_162005
crossref_primary_10_2118_225411_PA
crossref_primary_10_3390_app131910858
crossref_primary_10_3390_en18020391
crossref_primary_10_1016_j_finr_2025_100006
crossref_primary_10_1016_j_atech_2025_100939
crossref_primary_10_1063_5_0224299
crossref_primary_10_54097_wd8c8r08
crossref_primary_10_1051_e3sconf_202562302017
crossref_primary_10_1016_j_geoen_2023_212407
crossref_primary_10_1016_j_apenergy_2023_122102
crossref_primary_10_1016_j_compchemeng_2025_109068
crossref_primary_10_3390_en17225674
crossref_primary_10_1016_j_geoen_2025_213855
crossref_primary_10_1007_s13349_024_00831_8
crossref_primary_10_1109_ACCESS_2023_3289076
crossref_primary_10_1016_j_agrformet_2023_109863
crossref_primary_10_1016_j_apr_2025_102533
crossref_primary_10_1016_j_rineng_2025_105703
crossref_primary_10_2118_226207_PA
crossref_primary_10_1016_j_energy_2024_132823
crossref_primary_10_1016_j_apenergy_2024_122691
crossref_primary_10_1007_s41066_023_00422_w
crossref_primary_10_1016_j_engappai_2025_111482
crossref_primary_10_3390_ijfs13030167
crossref_primary_10_3390_machines10111042
crossref_primary_10_3390_math12243896
crossref_primary_10_1016_j_jclepro_2024_144309
crossref_primary_10_3390_en16031027
crossref_primary_10_1016_j_eswa_2024_123955
crossref_primary_10_1016_j_jmsy_2023_02_017
crossref_primary_10_1016_j_clwas_2025_100378
crossref_primary_10_1016_j_engappai_2024_108007
crossref_primary_10_1016_j_est_2025_115534
crossref_primary_10_1007_s12517_023_11779_2
crossref_primary_10_1016_j_apenergy_2023_121032
crossref_primary_10_1007_s10479_025_06491_1
crossref_primary_10_1038_s41467_025_61660_x
crossref_primary_10_1007_s10553_024_01693_y
crossref_primary_10_1016_j_fss_2023_108657
crossref_primary_10_1007_s10462_024_10790_7
crossref_primary_10_3390_en18133584
crossref_primary_10_1061_JBENF2_BEENG_6710
crossref_primary_10_1007_s41066_023_00389_8
crossref_primary_10_3390_app122010617
crossref_primary_10_1029_2024JG008375
crossref_primary_10_1016_j_geoen_2025_213749
crossref_primary_10_32604_iasc_2023_035799
crossref_primary_10_1007_s10596_024_10298_7
crossref_primary_10_1016_j_geoen_2024_213603
crossref_primary_10_32362_2500_316X_2024_12_4_106_116
Cites_doi 10.1016/j.neucom.2016.01.106
10.1016/j.fuel.2019.116758
10.1080/00031305.2017.1380080
10.3354/cr030079
10.1186/1471-2210-10-6
10.1016/j.advwatres.2020.103619
10.1007/s10596-020-10005-2
ContentType Journal Article
Copyright 2022 Elsevier Ltd
Copyright_xml – notice: 2022 Elsevier Ltd
DBID AAYXX
CITATION
7S9
L.6
DOI 10.1016/j.cageo.2022.105126
DatabaseName CrossRef
AGRICOLA
AGRICOLA - Academic
DatabaseTitle CrossRef
AGRICOLA
AGRICOLA - Academic
DatabaseTitleList
AGRICOLA
DeliveryMethod fulltext_linktorsrc
Discipline Geology
ExternalDocumentID 10_1016_j_cageo_2022_105126
S009830042200084X
GroupedDBID --K
--M
.DC
.~1
0R~
1B1
1RT
1~.
1~5
29F
4.4
457
4G.
5GY
5VS
7-5
71M
8P~
9JN
AABNK
AACTN
AAEDT
AAEDW
AAHBH
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AATTM
AAXKI
AAXUO
AAYFN
ABBOA
ABFNM
ABJNI
ABMAC
ABQEM
ABQYD
ABWVN
ABXDB
ACDAQ
ACGFS
ACLVX
ACNNM
ACRLP
ACRPL
ACSBN
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
ADNMO
AEBSH
AEIPS
AEKER
AENEX
AFJKZ
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AKRWK
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
AOUOD
ASPBG
ATOGT
AVWKF
AXJTR
AZFZN
BKOJK
BLXMC
BNPGV
CS3
DU5
EBS
EFJIC
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
GBLVA
GBOLZ
HLZ
HMA
HVGLF
HZ~
IHE
IMUCA
J1W
KOM
LG9
LY3
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
ROL
RPZ
SBC
SDF
SDG
SDP
SEP
SES
SEW
SPC
SPCBC
SSH
SSV
SSZ
T5K
TN5
WUQ
ZCA
ZMT
~02
~G-
9DU
AAYWO
AAYXX
ACLOT
ACVFH
ADCNI
ADXHL
AEUPX
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKYEP
APXCP
CITATION
EFKBS
EFLBG
SSE
~HD
7S9
L.6
ID FETCH-LOGICAL-a359t-16b57c0634d2879dfee1b4a3b2718ab57b6efca4c5bb61a48000ee547be3091d3
ISICitedReferencesCount 111
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000802782400003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0098-3004
IngestDate Sat Sep 27 22:19:15 EDT 2025
Sat Nov 29 07:23:37 EST 2025
Tue Nov 18 21:20:27 EST 2025
Sun Apr 06 06:53:13 EDT 2025
IsPeerReviewed true
IsScholarly true
Keywords Time series forecasting
Oil production prediction
LSTM
ARIMA
Machine learning
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-a359t-16b57c0634d2879dfee1b4a3b2718ab57b6efca4c5bb61a48000ee547be3091d3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0002-2163-3451
PQID 2675572265
PQPubID 24069
ParticipantIDs proquest_miscellaneous_2675572265
crossref_primary_10_1016_j_cageo_2022_105126
crossref_citationtrail_10_1016_j_cageo_2022_105126
elsevier_sciencedirect_doi_10_1016_j_cageo_2022_105126
PublicationCentury 2000
PublicationDate July 2022
2022-07-00
20220701
PublicationDateYYYYMMDD 2022-07-01
PublicationDate_xml – month: 07
  year: 2022
  text: July 2022
PublicationDecade 2020
PublicationTitle Computers & geosciences
PublicationYear 2022
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Zhao, Jiang, Li, Wang, Gao, Yu, Su (bib34) 2017
Hu (bib13) 2002
Ruse, Ahmadov, Liu, Mokhtari (bib24) 2021
Zhang, Lipton, Li, Smola (bib33) 2019
Duke (bib10) 2014
Kellogg, Chessum, Kwong (bib16) 2018
Sneed (bib26) 2017
Brownlee (bib7) 2017
Box, Jenkins, Reinsel, Ljung (bib6) 2015
Arps (bib2) 1945; 160
Jain (bib15) 2016
Salvi (bib25) 2019; 27
Brownlee (bib8) 2018
Eshel (bib11) 2003; 2
Olah (bib21) 2015
You, Ampomah, Sun (bib32) 2020; 264
Bai, Tahmasebi (bib3) 2021; 25
Mohammed, Naugler, Far (bib17) 2015
Bogacka (bib5) 2007
Srivastava (bib28) 2015
Bakshi, Uniacke, Korjani, Ershaghi (bib4) 2017
Chai, Draxler (bib9) 2014; 7
Ning (bib18) 2017
Gupta, Fuehrer, Jeyachandra (bib12) 2014
Ahmadi (bib1) 2016; 211
Noshi, Assem, Schubert (bib20) 2018
Taylor, Letham (bib30) 2018; 72
Willmott, Matsuura (bib31) 2005; 30
Noshi, Schubert (bib19) 2018
PennState (bib22) 2014
Prophet (bib23) 2017
Spiess, Neumeyer (bib27) 2010; 10
Tahmasebi, Kamrava, Bai, Sahimi (bib29) 2020; 142
Hu (10.1016/j.cageo.2022.105126_bib13)
PennState (10.1016/j.cageo.2022.105126_bib22)
Tahmasebi (10.1016/j.cageo.2022.105126_bib29) 2020; 142
Bai (10.1016/j.cageo.2022.105126_bib3) 2021; 25
Box (10.1016/j.cageo.2022.105126_bib6) 2015
Chai (10.1016/j.cageo.2022.105126_bib9) 2014; 7
Ruse (10.1016/j.cageo.2022.105126_bib24) 2021
Mohammed (10.1016/j.cageo.2022.105126_bib17) 2015
Taylor (10.1016/j.cageo.2022.105126_bib30) 2018; 72
Brownlee (10.1016/j.cageo.2022.105126_bib7) 2017
Sneed (10.1016/j.cageo.2022.105126_bib26) 2017
Srivastava (10.1016/j.cageo.2022.105126_bib28)
Duke (10.1016/j.cageo.2022.105126_bib10)
Kellogg (10.1016/j.cageo.2022.105126_bib16) 2018
Zhang (10.1016/j.cageo.2022.105126_bib33)
Eshel (10.1016/j.cageo.2022.105126_bib11) 2003; 2
Bakshi (10.1016/j.cageo.2022.105126_bib4) 2017
Spiess (10.1016/j.cageo.2022.105126_bib27) 2010; 10
Gupta (10.1016/j.cageo.2022.105126_bib12) 2014
Prophet (10.1016/j.cageo.2022.105126_bib23)
Ning (10.1016/j.cageo.2022.105126_bib18) 2017
Noshi (10.1016/j.cageo.2022.105126_bib19) 2018
Ahmadi (10.1016/j.cageo.2022.105126_bib1) 2016; 211
Bogacka (10.1016/j.cageo.2022.105126_bib5) 2007
You (10.1016/j.cageo.2022.105126_bib32) 2020; 264
Noshi (10.1016/j.cageo.2022.105126_bib20) 2018
Arps (10.1016/j.cageo.2022.105126_bib2) 1945; 160
Brownlee (10.1016/j.cageo.2022.105126_bib8) 2018
Willmott (10.1016/j.cageo.2022.105126_bib31) 2005; 30
Olah (10.1016/j.cageo.2022.105126_bib21)
Zhao (10.1016/j.cageo.2022.105126_bib34) 2017
Salvi (10.1016/j.cageo.2022.105126_bib25) 2019; 27
Jain (10.1016/j.cageo.2022.105126_bib15) 2016
References_xml – year: 2017
  ident: bib7
  article-title: White Noise Time Series with Python
– year: 2018
  ident: bib16
  article-title: Machine learning application for wellbore damage removal in the wilmington field
  publication-title: SPE Western Regional Meeting
– year: 2015
  ident: bib28
  article-title: A complete tutorial on time series modeling in R. Analytics Vid
– year: 2018
  ident: bib19
  article-title: The role of machine learning in drilling operations; a review
  publication-title: SPE/AAPG Eastern Regional Meeting
– year: 2017
  ident: bib23
– year: 2017
  ident: bib18
  article-title: Production Potential of Niobrara and Codell: Integrating Reservoir Simulation with 4D Seismic and Microseismic Interpretation
– volume: 7
  start-page: 1525
  year: 2014
  end-page: 1534
  ident: bib9
  article-title: Root mean square error (RMSE) or mean absolute error (MAE)?
  publication-title: Geosci. Model Dev. Discuss. (GMDD)
– volume: 2
  start-page: 68
  year: 2003
  end-page: 73
  ident: bib11
  article-title: The yule walker equations for the AR coefficients
  publication-title: Internet resource
– year: 2014
  ident: bib12
  article-title: Production forecasting in unconventional resources using data mining and time series analysis
  publication-title: SPE/CSUR Unconventional Resources Conference–Canada
– volume: 264
  start-page: 116758
  year: 2020
  ident: bib32
  article-title: Development and application of a machine learning based multi-objective optimization workflow for CO2-EOR projects
  publication-title: Fuel
– year: 2007
  ident: bib5
  article-title: ACF and PACF of ARMA
– year: 2018
  ident: bib8
  article-title: How to Develop LSTM Models for Time Series Forecasting
– year: 2002
  ident: bib13
  article-title: ARMA model
– year: 2021
  ident: bib24
  article-title: An integrated analytics and machine learning solution for predicting the anisotropic static geomechanical properties of the Tuscaloosa marine shale
  publication-title: SPE/AAPG/SEG Unconventional Resources Technology Conference. OnePetro
– start-page: 863
  year: 2017
  end-page: 869
  ident: bib26
  article-title: Predicting ESP lifespan with machine learning
  publication-title: Unconventional Resources Technology Conference, Austin, Texas, 24-26 July 2017
– volume: 72
  start-page: 37
  year: 2018
  end-page: 45
  ident: bib30
  article-title: Forecasting at scale
  publication-title: Am. Statistician
– volume: 27
  year: 2019
  ident: bib25
  article-title: Significance of ACF and PACF plots in time series analysis
  publication-title: Towards Daa Science
– year: 2018
  ident: bib20
  article-title: The role of big data analytics in exploration and production: a review of benefits and applications
  publication-title: SPE International Heavy Oil Conference and Exhibition
– year: 2019
  ident: bib33
  article-title: Dive into deep learning. Unpublished Draft
– volume: 160
  start-page: 228
  year: 1945
  end-page: 247
  ident: bib2
  article-title: Analysis of decline curves
  publication-title: Transactions of the AIME
– year: 2016
  ident: bib15
  article-title: A Comprehensive Beginner's Guide to Create a Time Series Forecast
– year: 2015
  ident: bib21
  article-title: Understanding LSTM networks
– volume: 25
  start-page: 285
  year: 2021
  end-page: 297
  ident: bib3
  article-title: Efficient and data-driven prediction of water breakthrough in subsurface systems using deep long short-term memory machine learning
  publication-title: Comput. Geosci.
– year: 2017
  ident: bib4
  article-title: A novel adaptive non-linear regression method to predict shale oil well performance based on well completions and fracturing data
  publication-title: SPE Western Regional Meeting
– volume: 211
  start-page: 143
  year: 2016
  end-page: 149
  ident: bib1
  article-title: Toward reliable model for prediction drilling fluid density at wellbore conditions: a LSSVM model
  publication-title: Neurocomputing
– year: 2014
  ident: bib10
– year: 2017
  ident: bib34
  article-title: Study on the classification and formation mechanism of microscopic remaining oil in high water cut stage based on machine learning
  publication-title: Abu Dhabi International Petroleum Exhibition & Conference
– year: 2014
  ident: bib22
– volume: 142
  start-page: 103619
  year: 2020
  ident: bib29
  article-title: Machine learning in geo-and environmental sciences: from small to large scale
  publication-title: Adv. Water Resour.
– volume: 10
  start-page: 6
  year: 2010
  ident: bib27
  article-title: An evaluation of R 2 as an inadequate measure for nonlinear models in pharmacological and biochemical research: a Monte Carlo approach
  publication-title: BMC Pharmacol.
– year: 2015
  ident: bib6
  article-title: Time Series Analysis: Forecasting and Control
– volume: 30
  start-page: 79
  year: 2005
  end-page: 82
  ident: bib31
  article-title: Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance
  publication-title: Clim. Res.
– start-page: 577
  year: 2015
  end-page: 602
  ident: bib17
  article-title: Emerging Business Intelligence Framework for a Clinical Laboratory through Big Data Analytics. Emerging Trends in Computational Biology, Bioinformatics, and Systems Biology: Algorithms and Software Tools
– year: 2016
  ident: 10.1016/j.cageo.2022.105126_bib15
– volume: 27
  year: 2019
  ident: 10.1016/j.cageo.2022.105126_bib25
  article-title: Significance of ACF and PACF plots in time series analysis
– year: 2014
  ident: 10.1016/j.cageo.2022.105126_bib12
  article-title: Production forecasting in unconventional resources using data mining and time series analysis
– year: 2018
  ident: 10.1016/j.cageo.2022.105126_bib20
  article-title: The role of big data analytics in exploration and production: a review of benefits and applications
– year: 2007
  ident: 10.1016/j.cageo.2022.105126_bib5
– ident: 10.1016/j.cageo.2022.105126_bib22
– volume: 211
  start-page: 143
  year: 2016
  ident: 10.1016/j.cageo.2022.105126_bib1
  article-title: Toward reliable model for prediction drilling fluid density at wellbore conditions: a LSSVM model
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2016.01.106
– year: 2018
  ident: 10.1016/j.cageo.2022.105126_bib19
  article-title: The role of machine learning in drilling operations; a review
– ident: 10.1016/j.cageo.2022.105126_bib13
– volume: 264
  start-page: 116758
  year: 2020
  ident: 10.1016/j.cageo.2022.105126_bib32
  article-title: Development and application of a machine learning based multi-objective optimization workflow for CO2-EOR projects
  publication-title: Fuel
  doi: 10.1016/j.fuel.2019.116758
– year: 2017
  ident: 10.1016/j.cageo.2022.105126_bib34
  article-title: Study on the classification and formation mechanism of microscopic remaining oil in high water cut stage based on machine learning
– volume: 72
  start-page: 37
  issue: 1
  year: 2018
  ident: 10.1016/j.cageo.2022.105126_bib30
  article-title: Forecasting at scale
  publication-title: Am. Statistician
  doi: 10.1080/00031305.2017.1380080
– ident: 10.1016/j.cageo.2022.105126_bib23
– volume: 160
  start-page: 228
  year: 1945
  ident: 10.1016/j.cageo.2022.105126_bib2
  article-title: Analysis of decline curves
– year: 2015
  ident: 10.1016/j.cageo.2022.105126_bib6
– start-page: 863
  year: 2017
  ident: 10.1016/j.cageo.2022.105126_bib26
  article-title: Predicting ESP lifespan with machine learning
– ident: 10.1016/j.cageo.2022.105126_bib28
– year: 2018
  ident: 10.1016/j.cageo.2022.105126_bib8
– year: 2021
  ident: 10.1016/j.cageo.2022.105126_bib24
  article-title: An integrated analytics and machine learning solution for predicting the anisotropic static geomechanical properties of the Tuscaloosa marine shale
– ident: 10.1016/j.cageo.2022.105126_bib33
– volume: 30
  start-page: 79
  issue: 1
  year: 2005
  ident: 10.1016/j.cageo.2022.105126_bib31
  article-title: Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance
  publication-title: Clim. Res.
  doi: 10.3354/cr030079
– year: 2017
  ident: 10.1016/j.cageo.2022.105126_bib18
– volume: 10
  start-page: 6
  issue: 1
  year: 2010
  ident: 10.1016/j.cageo.2022.105126_bib27
  article-title: An evaluation of R 2 as an inadequate measure for nonlinear models in pharmacological and biochemical research: a Monte Carlo approach
  publication-title: BMC Pharmacol.
  doi: 10.1186/1471-2210-10-6
– volume: 7
  start-page: 1525
  issue: 1
  year: 2014
  ident: 10.1016/j.cageo.2022.105126_bib9
  article-title: Root mean square error (RMSE) or mean absolute error (MAE)?
  publication-title: Geosci. Model Dev. Discuss. (GMDD)
– ident: 10.1016/j.cageo.2022.105126_bib10
– ident: 10.1016/j.cageo.2022.105126_bib21
– year: 2017
  ident: 10.1016/j.cageo.2022.105126_bib7
– volume: 142
  start-page: 103619
  year: 2020
  ident: 10.1016/j.cageo.2022.105126_bib29
  article-title: Machine learning in geo-and environmental sciences: from small to large scale
  publication-title: Adv. Water Resour.
  doi: 10.1016/j.advwatres.2020.103619
– year: 2018
  ident: 10.1016/j.cageo.2022.105126_bib16
  article-title: Machine learning application for wellbore damage removal in the wilmington field
– volume: 2
  start-page: 68
  year: 2003
  ident: 10.1016/j.cageo.2022.105126_bib11
  article-title: The yule walker equations for the AR coefficients
– volume: 25
  start-page: 285
  issue: 1
  year: 2021
  ident: 10.1016/j.cageo.2022.105126_bib3
  article-title: Efficient and data-driven prediction of water breakthrough in subsurface systems using deep long short-term memory machine learning
  publication-title: Comput. Geosci.
  doi: 10.1007/s10596-020-10005-2
– year: 2017
  ident: 10.1016/j.cageo.2022.105126_bib4
  article-title: A novel adaptive non-linear regression method to predict shale oil well performance based on well completions and fracturing data
– start-page: 577
  year: 2015
  ident: 10.1016/j.cageo.2022.105126_bib17
SSID ssj0002285
Score 2.6257076
Snippet It is challenging to predict the production performance of unconventional reservoirs because of the sediment heterogeneity, intricate flow channels, and...
SourceID proquest
crossref
elsevier
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 105126
SubjectTerms ARIMA
artificial intelligence
basins
LSTM
Machine learning
neural networks
Oil production prediction
oils
prediction
sediments
time series analysis
Time series forecasting
Title A comparative machine learning study for time series oil production forecasting: ARIMA, LSTM, and Prophet
URI https://dx.doi.org/10.1016/j.cageo.2022.105126
https://www.proquest.com/docview/2675572265
Volume 164
WOSCitedRecordID wos000802782400003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  issn: 0098-3004
  databaseCode: AIEXJ
  dateStart: 19950101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0002285
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Zb9NAEF6FFCReEKdaLi0Sb8QoXu_64M1CBYpoVEFA4cnatdfBUexWOaqC-PHMXnbSiog-8GJZPlarzOfZmc033yD0MmBFJEuWeyxOhh6NC-IJ7pdeHrBAliENpRbT-fYpGo3iySQ56fV-u1qY83nUNPHFRXL2X00N18DYqnT2GuZuB4ULcA5GhyOYHY7_ZPjU8sqNonetyZLSdYeYGj1ZQy6savlKTUnpzlZzRdUqjJasui1zvnTV0Onno-NUZ_BfxseO73myUJIEW1v7rkXEUgNqKq1QZkdTHNkOKt95s1hXrbPnv2RtumfDki2rjhvMf9SwyorKMIlntYWy3aUgHaO19bxJ7Cl1ry3PG9IN3wmRnm-q56-4dbPDMIOUfaorNgl53T29LaJ9aXFrKYeOzTbL9CCZGiQzg9xAeyRiSdxHe-nR4eRju5ITEjOnuarm7lSrND_wylz-FtlcWuN14DK-i-7YjAOnBin3UE8299Gt97qj888HqErxBl6wxQt2eMEaLxgAgRVesMELBrzgDi94Ay9vsEbLACusDDAgBVukPERf3x2O337wbP8NjwcsWXl-KFiUQwxLC8irk6KU0heUB4JAQMPhnghlmXOaMyFCn1PIPYZSMhoJGUAYWgSPUL85beQ-wnmp-gpwCH1oQJM4EcGwgMiS0zBUtWLxASLut8tyK06veqTMsx12O0CD9qUzo82y-_HQGSWz8DdhYwYw2_3iC2fCDJyv-keNN_J0vcwIpNssggyGPb7eXJ6g291X8hT1V4u1fIZu5uerarl4bnH4B6SZpas
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+comparative+machine+learning+study+for+time+series+oil+production+forecasting%3A+ARIMA%2C+LSTM%2C+and+Prophet&rft.jtitle=Computers+%26+geosciences&rft.au=Ning%2C+Yanrui&rft.au=Kazemi%2C+Hossein&rft.au=Tahmasebi%2C+Pejman&rft.date=2022-07-01&rft.issn=0098-3004&rft.volume=164&rft.spage=105126&rft_id=info:doi/10.1016%2Fj.cageo.2022.105126&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_cageo_2022_105126
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0098-3004&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0098-3004&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0098-3004&client=summon