Co esponding au ho : Joshua Baba unde Ase e
Copy igh © 2025 Au ho (s) e ain he copy igh o his a icle. This a icle is published unde he e ms o he C ea i e Commons A ibu ion License 4.0.
The in eg a ion o A i icial In elligence in ca bon cap u e, u iliza ion and s o age o
en i onmen al sus ainabili y in he oil and gas indus y
Joshua Baba unde Ase e 1, *, Akachukwu Ma k ed Ijeoma 2, Ha ison Agbo o 3, Tunde Ka eem 4, Samuel Tobi
Adebisi 5 and I eanyi Kingsley Egbuna 6
1 Depa men o En i onmen al Sciences, Indiana Uni e si y Blooming on, USA.
2 Depa men o Elec ical and Elec onics Enginee ing, Michael Okpa a Uni e si y o Ag icul u e Umudike, Nige ia.
3 Depa men o En i onmen al Heal h and Managemen , Uni e si y o New Ha en, USA.
4 Depa men o Geology, Fede al Uni e si y o Technology Minna, Nige ia.
5 Depa men o Geology, Oba emi Awolowo Uni e si y, Nige ia.
6 Depa men o Supply Chain Managemen , Ma ke ing, and Managemen , W igh S a e Uni e si y, USA.
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 359-369
Publica ion his o y: Recei ed on 15 Ma ch 2025; e ised on 02 May 2025; accep ed on 04 May 2025
A icle DOI: h ps://doi.o g/10.30574/wja .2025.26.2.1433
Abs ac
The oil and gas indus y a e he main d i e o he wo ld's g eenhouse gas emissions and coun e measu es a e equi ed
o achie e in e na ional a ge s o educing emissions. Ca bon Cap u e, U iliza ion, and S o age echnologies ha e
become leading emission- educing means bu a e cons ained by high cos o ope a ions, sys em complexi y, and long-
du a ion eliabili y. This e iew pape discusses he applica ion o A i icial Iin elligence o Ca bon Cap u e, U iliza ion,
and S o age sys ems as one o he main pa hways o enhancing en i onmen al sus ainabili y o he oil and gas indus y.
The e iew discusses ecen ad ances in A i icial In elligence, including deep lea ning, ein o cemen lea ning, and
machine lea ning, including means by which hey a e being applied o CCUS alue chain, including CO₂ cap u e,
anspo a ion, s o age, and u iliza ion. This pape examines he oles played by AI o maximize cap u e p ocess,
pipeline leak p e en ion, cap u e p ocess moni o ing accu acy, and CO₂ u iliza ion by enhanced oil eco e y (EOR). I
conside s cons ain s and bo lenecks o AI applica ions including lack o da a, models lack o in e p e abili y,
cybe secu i y ulne abili ies, and limi a ions o in e disciplina y coope a ion. The e iew concludes by asse ing ha
despi e limi a ions, AI holds e olu iona y po en ial o make CCUS e icien , cos -sensi i e, and scalable o posi ion i as
key enable o indus y ansi ion o he e a o low-ca bon p oduc ion.
Keywo ds: A i icial In elligence (AI); Ca bon Cap u e U iliza ion and S o age (CCUS); Oil and Gas Indus y;
En i onmen al Sus ainabili y; Machine Lea ning Op imiza ion
1. In oduc ion
The oil and gas indus y a e one o he la ges con ibu o s o global g eenhouse gas (GHG) emissions, p ima ily h ough
he elease o ca bon dioxide (CO₂) du ing ossil uel ex ac ion, p ocessing, and combus ion. Wi h inc easing
en i onmen al conce ns and in e na ional ag eemen s such as he Pa is Ag eemen , he need o signi ican ly educe
CO₂ emissions has become impe a i e [1]. Ca bon Cap u e, U iliza ion, and S o age (CCUS) has eme ged as a key
echnology o mi iga ing hese emissions by cap u ing CO₂ om indus ial sou ces and ei he s o ing i unde g ound
o eusing i in applica ions such as enhanced oil eco e y (EOR) [2]. Despi e i s po en ial, CCUS aces majo ope a ional
and economic challenges. These include he high ene gy demands o CO₂ cap u e, he isks o leakage du ing
anspo a ion and s o age, and he complexi ies in ol ed in moni o ing and e i ying CO₂ con ainmen o e long
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 359-369
360
pe iods. As he oil and gas sec o aims o align wi h global sus ainabili y goals, inno a i e app oaches a e equi ed o
o e come hese hu dles and make CCUS mo e e icien , scalable, and eliable [3].
1.1. Eme gence o A i icial In elligence in he Ene gy Sec o
A i icial In elligence (AI) has apidly gained a en ion ac oss indus ial sec o s o i s abili y o p ocess as da ase s,
ecognize pa e ns, make p edic ions, and au oma e decision-making p ocesses. In he ene gy sec o , especially in oil
and gas, AI has al eady been applied success ully o asks such as p edic i e main enance, seismic in e p e a ion, d illing
op imiza ion, and p oduc ion o ecas ing [4]. These successes ha e opened new a enues o he applica ion o AI in
en i onmen al sus ainabili y e o s, including CCUS. AI’s s eng h lies in i s capaci y o imp o e accu acy, e iciency,
and eal- ime esponsi eness o sys ems ha ely on la ge-scale da a collec ion and complex models. In he con ex o
CCUS, AI can be le e aged o enhance CO₂ cap u e e iciency, p edic and p e en s o age si e leaks, op imize CO₂
anspo logis ics, and imp o e moni o ing and epo ing mechanisms. These capabili ies no only lowe cos s and
ope a ional isks bu also inc ease he c edibili y and scalabili y o CCUS as a long- e m clima e mi iga ion s a egy [5].
1.2. Aim and Scope o he Re iew
This e iew aims o explo e he cu en and eme ging oles o AI in imp o ing he e ec i eness and sus ainabili y o
CCUS sys ems in he oil and gas indus y. Speci ically, i in es iga es how AI echnologies anging om machine lea ning
algo i hms o neu al ne wo ks a e being in eg a ed in o each s age o he CCUS alue chain: om cap u e and
comp ession o anspo a ion, s o age, and u iliza ion. The scope o he pape includes a de ailed examina ion o ecen
li e a u e (2020–2025), p ac ical case s udies whe e AI has enhanced CCUS ope a ions, and discussions on
echnological and egula o y challenges ha may hinde AI deploymen . Ul ima ely, his pape seeks o p o ide a
comp ehensi e unde s anding o how AI can d i e en i onmen al inno a ion in one o he mos emission-in ensi e
sec o s, and how i s in eg a ion can suppo he global ansi ion owa d a low-ca bon ene gy u u e.
2. Li e a u e Re iew
2.1. O e iew o CCUS in Oil & Gas
Ca bon Cap u e, U iliza ion, and S o age (CCUS) is a sui e o echnologies designed o educe ca bon dioxide (CO₂)
emissions om indus ial sou ces by cap u ing CO₂, anspo ing i o s o age o u iliza ion si es, and ei he s o ing i
in geological o ma ions o epu posing i o indus ial use [6]. In he oil and gas sec o , CCUS plays a pi o al ole no
only in emissions educ ion bu also in suppo ing enhanced oil eco e y (EOR), whe e cap u ed CO₂ is injec ed in o
ese oi s o imp o e hyd oca bon eco e y [7]. The h ee main componen s o CCUS include: Cap u e - Technologies
include pos -combus ion (e.g., amine sc ubbing), p e-combus ion (e.g., gasi ica ion), and oxy- uel combus ion. These
a y in e ms o ene gy demand and cos . T anspo - Mos ly ia pipelines, hough ships and ucks a e used o small-
scale ope a ions. S o age/U iliza ion - S o age occu s in deep saline aqui e s, deple ed oil ields, and unmineable coal
seams. U iliza ion includes EOR, chemical syn hesis, and mine aliza ion. CCUS is conside ed essen ial o deca bonizing
ha d- o-aba e sec o s like oil and gas, bu i s comme cial deploymen emains limi ed due o cos and ope a ional
complexi ies [8].
2.2. Challenges o T adi ional CCUS Sys ems
Al hough CCUS has been echnically alida ed, i aces signi ican ba ie s ha limi i s widesp ead deploymen : High
Ene gy and Ope a ional Cos s - CO₂ cap u e, especially in pos -combus ion sys ems, is ene gy-in ensi e and can educe
he o e all e iciency o oil and gas ope a ions [9]. Sys em Complexi y and Ine iciency -T adi ional models used o
designing and ope a ing CCUS sys ems a e o en s a ic and de e minis ic, lacking he adap abili y equi ed o deal wi h
dynamic eal-wo ld condi ions [10]. Leakage and Long-Te m S o age Risks: Ensu ing he in eg i y o CO₂ s o age o e
decades is challenging. The isk o leakage due o aul s o poo cap ock in eg i y can comp omise en i onmen al sa e y
[11]. Moni o ing and Ve i ica ion Limi a ions: T adi ional moni o ing elies on expensi e geophysical su eys and
limi ed well da a, which can be slow and incomple e [12]. Regula o y and Social Ba ie s: Regula o y unce ain y and
communi y opposi ion o unde g ound s o age p ojec s can delay o p e en implemen a ion [13]. These limi a ions
ha e c ea ed a demand o sma e , mo e adap able solu ions ha can op imize CCUS pe o mance in eal- ime; his is
whe e AI comes in.
2.3. Eme gence o AI in Indus ial Op imiza ion
A i icial In elligence, pa icula ly machine lea ning (ML), deep lea ning (DL), and ein o cemen lea ning (RL), has
demons a ed he abili y o e olu ionize indus ial p ocess op imiza ion. In he oil and gas indus y, AI is al eady being
used o p edic i e main enance, eal- ime d illing analy ics, p oduc ion o ecas ing, and anomaly de ec ion [14].
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 359-369
361
Table 1 Compa a i e e iew o ele an li e a u es
Pape s
Re e ences
Objec i es
Resul s
Findings
P ac ical Implica ions
[18]
• Explo e AI's ole in
enhancing CCS supply chains.
• Assess impac on supplie
quali y and ope a ional
e iciency.
• AI enhances ca bon cap u e
e iciency and supplie quali y.
• P edic i e analy ics imp o e
decision-making and isk
managemen .
• AI-d i en sys ems enhance
ca bon cap u e e iciency
signi ican ly.
• Imp o ed supplie
managemen educes
emissions and ope a ional
cos s.
• AI op imizes CCS supply chains
and educes cos s.
• Enhances supplie quali y and
ca bon cap u e e iciency.
[19]
• Syn hesize CCUS elemen s
o e 50 yea s o emission
educ ion.
• E alua e ca bon cap u e
echniques and hei
economic easibili y.
• E alua es CCUS echnologies'
mi iga ion po en ial o global
emissions.
• Highligh s economic easibili y
and en i onmen al impac o
a ious echniques.
• E alua es CCUS echniques'
mi iga ion po en ial and
economic easibili y.
• Highligh s in eg a ion o CCUS
in clima e s a egies o ne -
ze o emissions.
• E alua es CCUS echniques o
global emission educ ion
po en ial.
• Highligh s economic easibili y
and en i onmen al impac o
CCUS echnologies.
[20]
• Sys ema ic e iew o
machine lea ning in CCUS
applica ions.
• Iden i y pa hways o
ad ancing CCUS
comme cializa ion and
esea ch.
• ML enhances CCUS knowledge and
deploymen ac oss alue chain.
• Recommenda ions o u he
esea ch o de elop ML ole in
CCUS.
• Machine lea ning enhances
CCUS e iciency and cos -
e ec i eness.
• Sys ema ic e iew accele a es
CCUS comme cializa ion and
esea ch expansion.
• ML can accele a e esea ch in
CO2 cap u e.
• ML is applied in adso ben
syn hesis and cha ac e isa ion.
[21]
• Summa ize AI ad ancemen s
in nanoma e ials disco e y.
• Discuss limi a ions and
u u e esea ch di ec ions o
AI applica ions.
• AI accele a es nanoma e ials
disco e y o clean ene gy.
• AI aids in CO2 cap u e and
con e sion ma e ials.
• AI accele a es nanoma e ials
disco e y o clean ene gy
echnologies.
• Iden i ies challenges and u u e
di ec ions o AI in
nanoma e ials.
• Accele a es nanoma e ial
disco e y o clean ene gy and
ca bon cap u e echnologies.
• Enhances AI applica ions in
ma e ial esea ch o
sus ainable ene gy solu ions.
[22]
• Focus on AI in eg a ion wi h
ca bon cap u e echnology.
• Op imize ca bon cap u e
p ocesses and minimize CO2
emissions.
• AI enhances e iciency in ca bon
cap u e echnologies.
• Op imizes CO2 injec ion p ocesses
and minimizes emissions.
• AI enhances e iciency in
ca bon cap u e echnology
ope a ions.
• AI op imizes injec ion
p ocesses and minimizes CO2
emissions.
• AI enhances e iciency in ca bon
cap u e echnologies.
• Op imizes CO2 injec ion
p ocesses and educes
emissions.
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 359-369
362
[23]
• Enhance ca bon cap u e
e iciency using AI
au oma ion.
• Imp o e p edic i e
main enance in oil and gas
acili ies.
• AI au oma ion enhances ca bon
cap u e e iciency and
main enance.
• Imp o ed CO2 seques a ion a es
wi h minimized ope a ional
in e up ions.
• AI au oma ion enhances ca bon
cap u e e iciency and
p edic i e main enance.
• Real-li e examples show
success ul AI in eg a ion in CCS.
• Enhances ca bon cap u e
e iciency in oil and gas
acili ies.
• Imp o es p edic i e
main enance h ough AI-d i en
au oma ion p ocesses.
[24]
• In eg a e digi al echnology
and AI in CCUS moni o ing.
• Enhance e iciency, sa e y,
and eliabili y in CCUS
ope a ions.
• Enhanced moni o ing and
anomaly de ec ion in CCUS
sys ems.
• Op imized pe o mance h ough
AI-d i en p edic i e main enance.
• Ad anced sensing in eg a es
nano sensing, IoT, and AI
echnologies.
• Enhances CCUS e iciency,
sa e y, and eliabili y h ough
eal- ime moni o ing.
• Enhances eal- ime moni o ing
and anomaly de ec ion in CCUS.
• Op imizes sys em pe o mance
h ough AI-d i en p edic i e
main enance.
[25]
• Op imize pos -combus ion
CO2 cap u e using AI
echniques.
• Iden i y c i ical ac o s
a ec ing CO2 cap u e
e iciency.
• CNN models ela ionships in C02
cap u e p ocess e icien ly.
• Bayesian ne wo ks iden i y c i ical
ac o s o op imizing C02 cap u e
le els.
• Op imized CO2 cap u e using
AI-enabled CNN and Bayesian
ne wo ks.
• Iden i ied c i ical ac o s
a ec ing CO2 cap u e
e iciency.
• Op imizes CO2 cap u e
e iciency using AI echniques.
• Suppo s ca bon neu ali y
goals h ough enhanced CCUS
p ocesses.
[26]
• De elop a obus hyb id
assessmen ool o CCUS.
• Op imize CCUS sys ems
design and ope a ion cos s.
• Iden i ied need o obus hyb id
assessmen ool o CCUS.
• P oposed AI me hods o op imize
CCUS design and ope a ion.
• Need o obus hyb id
assessmen ool o CCUS.
• AI me hods can op imize CCUS
design and ope a ion.
• AI op imizes CCUS design and
ope a ion cos s.
• AI me hods accele a e ma e ials
selec ion and p ocess
op imiza ion.
[27]
• Op imize ca bon cap u e and
s o age p ocesses in oil and
gas.
• Iden i y op imal geological
o ma ions o ca bon
s o age.
• Op imized ca bon s o age using
da a science and geological
insigh s.
• Add essed challenges in da a
he e ogenei y and geological
complexi y.
• In eg a es da a science wi h
geological insigh s o CCS
op imiza ion.
• Iden i ies op imal o ma ions
and p edic s seques a ion
capaci ies.
• Op imizes ca bon cap u e and
s o age p ocesses in oil and gas.
• Iden i ies op imal geological
o ma ions o ca bon s o age.
[28]
• E alua e CO2 wo k capaci y
and MOF selec i i y
p edic ions.
• Op imize machine lea ning
me hodologies o CO2/N2
analysis.
• Mean absolu e e o s o CO2/N2
selec i i y: 25 and 0.8 mmol/g.
• Nega i e co ela ion be ween CO2
capaci y and chemical makeup.
• Neu al ne wo k model p edic s
CO2/N2 selec i i y accu a ely.
• Po e size and su ace a ea a ec
gas abso babili y.
• Enhances CO2 cap u e
e iciency using machine
lea ning models.
• Imp o es p edic abili y o MOF
cha ac e is ics o CO2/N2
selec i i y.
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 359-369
363
[29]
• Op imize CO2 emo al om
lue gas using RL.
• Minimize ope a ing ene gy in
ca bon cap u e applica ions.
• Lowe ene gy cos s achie ed in
o e 70% o cases.
• E alua ion o RL me hod o CO2
cap u e p ocess op imiza ions
p esen ed.
• RL algo i hm educes ene gy
cos s in o e 70% o cases.
• Op imizes CO2 emo al om
lue gas e ec i ely.
• Op imizes CO2 emo al wi h
lowe ene gy cos s.
• Enhances AI implemen a ion in
oil and gas indus ies.
[30]
• Highligh in eg a ion o AI
and CDR echnology.
• Imp o e e iciency and
educe en i onmen al
impac .
• Highligh s in eg a ion o AI and
CDR o ene gy op imiza ion.
• Sugges s u u e esea ch
di ec ions o imp o ed e iciency
and iabili y.
• In eg a ion o AI enhances CDR
echnology e ec i eness.
• Fu u e esea ch ocuses on
e iciency and economic
iabili y.
• Enhances ene gy e iciency and
educes en i onmen al impac .
• P omo es in e disciplina y
collabo a ion o e ec i e
policy amewo ks.
[31]
• Enhance CO2 solubili y using
AI and op imiza ion
echniques.
• De elop cos -e icien ca bon
cap u e and s o age
me hods.
• ANFIS model ou pe o ms ANOVA
in CO2 solubili y p edic ion.
• IGWO op imiza ion inc eases CO2
solubili y by 13.4%.
• ANFIS model ou pe o ms
adi ional ANOVA in CO2
solubili y p edic ion.
• IGWO op imizes pa ame e s,
inc easing CO2 solubili y by
13.4%.
• Enhances CO2 solubili y o
e ec i e ca bon cap u e.
• P omo es sus ainable ene gy
and en i onmen al
sus ainabili y solu ions.
[32]
• De elop geologically ealis ic
he e ogeneous ese oi
models using AI.
• Op imize CO2 s o age
e iciency and p edic plume
mig a ion beha io .
• De eloped AI-based 3D geologic
models o CO2 seques a ion.
• Enhanced geological
he e ogenei y cha ac e iza ion
educes p ojec unce ain y.
• De eloped AI-based geologic
modeling o CO2
seques a ion.
• Enhanced geological
he e ogenei y cha ac e iza ion
imp o es CO2 s o age
e iciency.
• Enhanced CO2 plume mig a ion
p edic ions and op imiza ion.
• Imp o ed geological
he e ogenei y cha ac e iza ion
o CO2 s o age e iciency.
[33]
• E alua e new emissions
moni o ing echnologies o
deploymen in Oman.
• Suppo AI/MoS as pa o
emissions moni o ing
po olio.
• AI/MoS-based echnologies
e ec i ely moni o emissions in
ex eme condi ions.
• Valuable da a suppo s con inuous
emissions moni o ing in Oil & Gas.
• AI/MoS echnologies e ec i ely
moni o emissions in ex eme
condi ions.
• Con inuous moni o ing
enhances da a quali y and
comple eness.
• AI/MoS echnologies imp o e
emissions moni o ing
e ec i eness and cos .
• Suppo s deca boniza ion
e o s in Oil & Gas indus y.
[34]
• Analyze AI applica ions in oil
and gas p ojec s
• P o ide ecommenda ions
o sus ainable de elopmen
in he indus y
• Posi i e end in AI esea ch
ela ed o oil and gas cons uc ion
p ojec s
• Insigh in o p omising AI
applica ions and me hodologies
• Posi i e end in AI esea ch
since 2016.
• AI enhances sus ainabili y in oil
and gas p ojec s.
• Imp o ed esea ch on AI
applica ions in oil and gas
p ojec s a e 2018.
• AI can imp o e cons uc ion
wo k and p ojec e iciency in
oil and gas p ojec s.
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 359-369
364
o sus ainable de elopmen in he
indus y
[35]
• Explo e AI in eg a ion in oil
and gas sus ainabili y.
• Examine op imiza ion
echniques o p oduc ion
p ocess e iciency.
• AI op imizes oil p oduc ion o
sus ainabili y, e iciency, and
p o i abili y.
• Case s udies show educed
emissions, wa e usage, and
ope a ional isks.
• AI op imizes oil and gas
p oduc ion o sus ainabili y.
• Enhances e iciency, educes
en i onmen al impac , and
maximizes esou ce eco e y.
• Enhances sus ainabili y in oil
and gas p oduc ion p ocesses.
• Reduces en i onmen al impac
and ope a ional isks.
[36]
• E alua e e ec i eness o IT
solu ions o emission
educ ion.
• Analyze eal-wo ld
implemen a ions and hei
impac on emissions.
• Ad anced IT solu ions show
p omise o emission educ ion in
oil/gas.
• IoT, AI, Big Da a aid in emissions
acking and op imiza ion.
• Ad anced IT solu ions show
p omise o emission educ ion
in oil indus y.
• IoT, AI, and Big Da a analy ics
aid in emissions managemen .
• Ad anced IT solu ions educe
emissions in oil and gas sec o .
• Real- ime moni o ing,
p edic i e main enance,
emissions acking, and
epo ing bene i s.
[37]
• Examine IoT-enabled CCS o
Enhanced Oil Reco e y.
• Op imize ca bon cap u e
e iciency and educe
emissions.
• IoT enhances CCS e iciency and
sus ainabili y in EOR.
• P omo es ca bon-neu al oil and
gas ope a ions.
• IoT enhances ca bon cap u e
e iciency and educes cos s.
• Enables ca bon-neu al oil and
gas ope a ions h ough eal-
ime moni o ing.
• Op imizes ca bon cap u e
e iciency and lowe s ope a ing
cos s.
• Enhances en i onmen al
sus ainabili y h ough emo e
moni o ing and p edic i e
main enance.
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 359-369
365
AI excels in: Handling la ge olumes o s uc u ed and uns uc u ed da a, iden i ying hidden pa e ns and co ela ions,
Making as , accu a e p edic ions unde unce ain y [15]. In he con ex o CCUS, AI can help build p edic i e models o
CO₂ beha io in s o age o ma ions, op imize p ocess con ol in cap u e sys ems, de ec leaks in pipelines, and educe
ene gy consump ion du ing comp ession and anspo . The e sa ili y and lea ning capabili y o AI make i a aluable
ool o add essing he mul i ace ed challenges o CCUS, especially in achie ing highe e iciency and eliabili y [16].
Figu e 1 Challenges and Oppo uni ies in Scaling A i icial In elligence o Ca bon Cap u e and S o age [17]
3. Discussion
3.1. AI in CO₂ Cap u e Op imiza ion
CO₂ cap u e, pa icula ly pos -combus ion cap u e using chemical sol en s, is he mos ene gy-in ensi e and cos -
de ining componen o CCUS. AI has he po en ial o signi ican ly op imize his p ocess. Machine lea ning algo i hms
such as a i icial neu al ne wo ks (ANNs), suppo ec o machines (SVMs), and decision ees a e inc easingly being
employed o model and p edic CO₂ cap u e e iciency unde a ying ope a ional condi ions. These models enable
adap i e con ol s a egies ha can dynamically adjus sol en low a es, empe a u e, and p essu e based on eal-
ime p ocess da a, leading o subs an ial ene gy sa ings and ope a ional e iciency (Zhou e al., 2021). Mo eo e , AI is
being in eg a ed wi h p ocess simula o s o de elop digi al wins o cap u e plan s which a e i ual eplicas ha
con inuously lea n om eal- ime da a and p edic u u e pe o mance. These AI-powe ed digi al wins can iden i y
ope a ional anomalies, o ecas deg ada ion in sol en pe o mance, and sugges p e en i e measu es, hus educing
down ime and main enance cos s. In addi ion, AI is aiding he disco e y o no el cap u e ma e ials (e.g., me al-o ganic
amewo ks) h ough high- h oughpu sc eening and molecula simula ion echniques, accele a ing he inno a ion
cycle.
3.2. AI in CO₂ T anspo a ion and Comp ession
T anspo ing cap u ed CO₂ h ough pipelines o o he means in oduces addi ional challenges such as p essu e
op imiza ion, leakage de ec ion, and ou e selec ion. AI-based p edic i e models can o ecas pipeline low beha io ,
p essu e d ops, and empe a u e a ia ions using his o ical and eal- ime da a. These p edic ions help op imize
comp esso ope a ions o ensu e e icien CO₂ low wi h minimal ene gy inpu . Fu he mo e, AI is e olu ionizing leak
de ec ion sys ems by analyzing senso and acous ic emission da a o de ec anomalies ha may signal pipeline up u e
o leakage. Techniques such as con olu ional neu al ne wo ks (CNNs) and ecu en neu al ne wo ks (RNNs) ha e been
applied o ime-se ies da a om dis ibu ed ibe op ic senso s and sma pigging ools, signi ican ly imp o ing he
accu acy and speed o aul de ec ion.
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 359-369
366
Geospa ial AI ools a e also being used o op imal CO₂ anspo ou ing, aking in o accoun en i onmen al cons ain s,
popula ion densi y, e ain complexi y, and cos ac o s enhancing sa e y and economic e iciency simul aneously.
3.3. AI in CO₂ S o age Moni o ing and Risk Assessmen
Ensu ing he long- e m in eg i y o geological s o age si es is essen ial o he c edibili y o CCUS. T adi ional
moni o ing app oaches a e o en eac i e and limi ed in spa ial- empo al esolu ion. AI in oduces a p oac i e pa adigm
by enabling p edic i e analy ics and pa e n ecogni ion in la ge geophysical, geochemical, and senso da ase s. AI
algo i hms can p ocess seismic su ey da a o iden i y cap ock in eg i y, ack plume mig a ion, and de ec ea ly signs
o leakage. Fo example, unsupe ised lea ning me hods such as clus e ing and p incipal componen analysis (PCA)
ha e been used o de ec abno mal shi s in seismic signals wi hou p io labeling. AI can also use da a om mul iple
moni o ing ools like p essu e senso s, gas composi ion analyze s, and sa elli e image y o p o ide a holis ic and eal-
ime unde s anding o s o age si e beha io . Mo eo e , p obabilis ic AI models suppo quan i a i e isk assessmen s
by simula ing di e en leakage scena ios and es ima ing he likelihood o hei occu ence, allowing ope a o s o
de elop p eemp i e mi iga ion s a egies and ensu e egula o y compliance.
3.4. AI o CO₂ U iliza ion in Enhanced Oil Reco e y (EOR)
In CO₂-EOR, accu a e ese oi modeling and eal- ime decision-making a e c ucial o op imize bo h oil eco e y and
CO₂ seques a ion. AI models ained on his o ical p oduc ion and injec ion da a can p edic ese oi esponses o CO₂
injec ion unde a ious ope a ional scena ios. These models can guide op imal well placemen , injec ion a es, and
scheduling s a egies o maximize eco e y and minimize CO₂ b eak h ough. In addi ion, AI enhances composi ional
simula ion by lea ning complex phase beha io ela ionships om expe imen al da a, educing he need o ex ensi e
physical measu emen s. Coupling AI wi h ese oi simula o s allows o as e his o y ma ching, educing he ime and
e o equi ed in calib a ing geological models o ma ch obse ed da a. AI also suppo s adap i e op imiza ion o
su ac an and sol en injec ion in EOR p ocesses, helping o balance pe o mance and economic e u ns.
3.5. Ba ie s o AI-CCUS In eg a ion
Despi e i s ans o ma i e po en ial, he in eg a ion o AI in o CCUS in oil and gas is no wi hou challenges. These
include; Da a Sca ci y and Quali y - AI models equi e la ge olumes o high-quali y da a. In many cases, CCUS p ojec s
a e ela i ely new, and his o ical da a a e limi ed o siloed. Model T anspa ency and In e p e abili y - Complex AI
models, pa icula ly deep lea ning ne wo ks, o en unc ion as “black boxes,” making i di icul o enginee s o
in e p e hei decisions, his a ec s us and egula o y accep ance. Cybe secu i y and In as uc u e - Digi aliza ion
in oduces new ulne abili ies. Secu e da a ans e , s o age, and AI model p o ec ion a e c ucial o widesp ead
adop ion. In e disciplina y Gaps - Success ul AI-CCUS in eg a ion equi es collabo a ion be ween da a scien is s,
pe oleum enginee s, geologis s, and en i onmen al expe s, an alignmen ha is s ill e ol ing in many o ganiza ions.
These challenges highligh he need o s anda dized amewo ks, open-access da ase s, and egula o y guidelines ha
can os e inno a ion while ensu ing sa e y, anspa ency, and accoun abili y.
4. Conclusion
The in eg a ion o A i icial In elligence (AI) in o Ca bon Cap u e, U iliza ion, and S o age (CCUS) sys ems ep esen s a
ans o ma i e oppo uni y o he oil and gas indus y o achie e i s en i onmen al sus ainabili y goals. As global
p essu e moun s o ca bon neu ali y, CCUS emains a pi o al s a egy o mi iga ing CO₂ emissions om ossil uel
ope a ions. Howe e , adi ional CCUS sys ems a e limi ed by high cos s, complex p ocess dynamics, and signi ican
isks associa ed wi h long- e m CO₂ s o age. AI o e s a no el and da a-d i en app oach o o e coming hese challenges
by enabling eal- ime moni o ing, dynamic op imiza ion, and p edic i e main enance ac oss he en i e CCUS alue
chain. This e iew highligh s ha AI applica ions in CO₂ cap u e can signi ican ly educe ene gy consump ion and
imp o e p ocess e iciency h ough ad anced modeling and con ol s a egies. In anspo a ion and comp ession, AI
enhances pipeline in eg i y managemen and low op imiza ion, con ibu ing o sa e and mo e cos -e ec i e CO₂
logis ics. AI's impac on geological s o age is especially c i ical h ough seismic analysis, isk o ecas ing, and mul i-
senso da a usion, AI imp o es he eliabili y o long- e m s o age moni o ing. Fu he mo e, in CO₂-EOR, AI suppo s
ese oi modeling, injec ion op imiza ion, and p oduc ion o ecas ing, imp o ing bo h economic e u ns and
seques a ion e ec i eness. Despi e i s bene i s, he adop ion o AI in CCUS is s ill in i s ea ly s ages. Challenges such as
da a a ailabili y, model anspa ency, in e disciplina y skill gaps, and cybe secu i y conce ns mus be add essed o
acili a e la ge-scale implemen a ion. Ne e heless, wi h con inued esea ch, egula o y suppo , and indus y
collabo a ion, AI-d i en CCUS solu ions hold immense po en ial o accele a e deca boniza ion in he oil and gas sec o .
In conclusion, he syne gy be ween AI and CCUS no only enhances ope a ional e iciency bu also s eng hens he
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 359-369
367
indus y's abili y o mee clima e a ge s. As digi al echnologies ma u e and CCUS p ojec s scale up, in eg a ing AI in o
hese sys ems will be a c i ical enable o a low-ca bon, sus ainable u u e in he oil and gas indus y.
Compliance wi h e hical s anda ds
Disclosu e o con lic o in e es
No con lic o in e es o be disclosed.
Re e ences
[1] Die z, S., Ga dine , D., Jahn, V., & Noels, J. (2021). How ambi ious a e oil and gas companies’ clima e goals?.
Science, 374(6566), 405-408.
[2] Liang, B., Chen, C., Jia, C., Wang, C., Wang, X., Zha, Y., ... & Wang, H. (2024). Ca bon cap u e, u iliza ion and s o age
(CCUS) in oil and gas ese oi s in China: S a us, oppo uni ies and challenges. Fuel, 375, 132353.
[3] Rui, Z., Zeng, L., & Dindo uk, B. (2025). Challenges in he la ge-scale deploymen o CCUS. Enginee ing, 44, 17-20.
[4] Kakolu, S. R. I. D. E. V. I., & Faheem, M. A. (2024). P edic i e Analy ics and Gene a i e AI in Oil & Gas: T ans o ming
Wellbo e S abili y and Haza d De ec ion. Iconic Resea ch And Enginee ing Jou nals, 8(1), 635-649.
[5] Manikandan, S., Ka iya, R. S., Sh eeha an, D. H., Subbaiya, R., Vick am, S., Ka megam, N., ... & Go a hanan, M.
(2025). A i icial in elligence‐d i en sus ainabili y: Enhancing ca bon cap u e o sus ainable de elopmen
goals–A e iew. Sus ainable De elopmen , 33(2), 2004-2029.
[6] Saxena, A., P akash Gup a, J., Tiwa y, J. K., Kuma , A., Sha ma, S., Pandey, G., ... & Ragha Cha u edi, K. (2024).
Inno a i e Pa hways in Ca bon Cap u e: Ad ancemen s and S a egic App oaches o E ec i e Ca bon Cap u e,
U iliza ion, and S o age. Sus ainabili y, 16(22), 10132.
[7] Liang, B., Chen, C., Jia, C., Wang, C., Wang, X., Zha, Y., ... & Wang, H. (2024). Ca bon cap u e, u iliza ion and s o age
(CCUS) in oil and gas ese oi s in China: S a us, oppo uni ies and challenges. Fuel, 375, 132353.
[8] Khei inik, M., Ahmed, S., & Rahmanian, N. (2021). Compa a i e echno-economic analysis o ca bon cap u e
p ocesses: P e-combus ion, pos -combus ion, and oxy- uel combus ion ope a ions. Sus ainabili y, 13(24), 13567.
[9] Chen, S., Liu, J., Zhang, Q., Teng, F., & McLellan, B. C. (2022). A c i ical e iew on deploymen planning and isk
analysis o ca bon cap u e, u iliza ion, and s o age (CCUS) owa d ca bon neu ali y. Renewable and Sus ainable
Ene gy Re iews, 167, 112537.
[10] Yan, Y., Bo hani, T. N., Sub a e i, S. G., Pai, K. N., P asad, V., Rajend an, A., ... & Clough, P. T. (2021). Ha nessing he
powe o machine lea ning o ca bon cap u e, u ilisa ion, and s o age (CCUS)–a s a e-o - he-a e iew. Ene gy
& En i onmen al Science, 14(12), 6122-6157.
[11] Gholami, R., Raza, A., & Iglaue , S. (2021). Leakage isk assessmen o a CO2 s o age si e: A e iew. Ea h-Science
Re iews, 223, 103849.
[12] Al-Qasim, A. S., Kokal, S. L., & Al-Ghamdi, M. S. (2021, Ap il). The S a e o he A in Moni o ing and Su eillance
Technologies o IOR, EOR and CCUS P ojec s. In SPE Wes e n Regional Mee ing (p. D031S014R006). SPE.
[13] Rocha, H., & de Medei os Cos a, H. K. (2021). Legal and egula o y ba ie s o CO2 geological s o age in B azil:
Lessons om he Eu opean Union. In Ca bon cap u e and s o age in in e na ional ene gy policy and law (pp.
263-283). Else ie .
[14] Goweka , G. S. (2024). A i icial in elligence o p edic i e main enance in oil and gas ope a ions. Wo ld J Ad
Res Re , 23(3), 1228-33.
[15] Hopkins, D., Rickwood, D. J., Hall o d, D. J., & Wa s o d, C. (2022). S uc u ed da a s. uns uc u ed da a in machine
lea ning p edic ion models o suicidal beha io s: A sys ema ic e iew and me a-analysis. F on ie s in digi al
heal h, 4, 945006.
[16] Yan, Y., Bo hani, T. N., Sub a e i, S. G., Pai, K. N., P asad, V., Rajend an, A., ... & Clough, P. T. (2021). Ha nessing
he powe o machine lea ning o ca bon cap u e, u ilisa ion, and s o age (CCUS)–a s a e-o - he-a e iew.
Ene gy & En i onmen al Science, 14(12), 6122-6157.
