Co esponding au ho : Obunadike ThankGod Chiamaka.
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.
AI-enhanced scena io planning o U.S. ood ade policy: An icipa ing global supply
chain shocks and ood insecu i y isks
Obunadike Thank God Chiamaka 1, * and Adedapo Alawode 2
1 Food Economics and T ade, Poznan Uni e si y o Li e Sciences, Poznan, Poland.
2 Depa men o Ag icul u al Economics and Ag ibusiness, New Mexico S a e Uni e si y, USA.
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 943-962
Publica ion his o y: Recei ed on 31 Ma ch 2025; e ised on 06 May 2025; accep ed on 09 May 2025
A icle DOI: h ps://doi.o g/10.30574/wja .2025.26.2.1786
Abs ac
The inc easing equency o global supply chain dis up ions—exace ba ed by pandemics, geopoli ical ensions, clima e-
ela ed e en s, and economic ola ili y—has exposed c i ical ulne abili ies in U.S. ood ade policy. As he Uni ed
S a es na iga es complex in e dependencies in ag icul u al impo s and expo s, adi ional scena io planning me hods
o en all sho in add essing he eloci y and unce ain y o mode n supply chain shocks. To s eng hen na ional ood
secu i y and esilience, he e is an u gen need o in elligen , da a-d i en amewo ks ha can an icipa e isks and
suppo p oac i e policy o mula ion. This pape in es iga es he ole o a i icial in elligence (AI)-enhanced scena io
planning in ans o ming U.S. ood ade policy amid escala ing global unce ain y. We p esen a mul i-laye ed
amewo k ha in eg a es machine lea ning, agen -based modeling, and geospa ial analy ics o simula e di e se ade
dis up ion scena ios— anging om po closu es and expo bans o clima e-induced yield losses. The p oposed sys em
le e ages eal- ime da a inpu s such as ade lows, clima e p ojec ions, and geopoli ical signals o model cascading
impac s ac oss domes ic supply chains and global ood ma ke s. Case s udies illus a e how AI-enhanced ools can
iden i y ea ly wa ning signs, quan i y ipple e ec s o ade policies, and op imize con ingency s a egies. Special ocus
is gi en o e alua ing implica ions o low-income and ood-insecu e popula ions wi hin he U.S., ensu ing equi able
ou comes in policy esponse. The s udy also discusses he impo ance o e hical AI go e nance, da a anspa ency, and
public-p i a e collabo a ion in shaping esponsi e and inclusi e ood ade policy. In conclusion, AI-enhanced scena io
planning o e s a s a egic impe a i e o sa egua ding U.S. ood sys ems agains eme gen h ea s, while os e ing
adap i e, o wa d-looking ade policy in an inc easingly ola ile global landscape.
Keywo ds: AI Scena io Planning; Food T ade Policy; Supply Chain Shocks; Food Insecu i y; U.S. Ag icul u e;
Geopoli ical Risk
1. In oduc ion
1.1. Backg ound: U.S. Food T ade and Global Dependencies
The Uni ed S a es plays a pi o al ole in he global ood supply sys em, ac ing bo h as a leading expo e o ag icul u al
p oduc s and a signi ican impo e o a ious ood commodi ies. The U.S. ag icul u al sec o expo s mo e han $150
billion in p oduc s annually, including soybeans, co n, whea , and dai y goods, se ing as a c i ical pilla in global ood
secu i y [1]. A he same ime, he coun y depends on impo s o mee domes ic demand o opical ui s, ege ables,
sea ood, and p ocessed ood i ems no p oduced locally o yea - ound. This wo-way ade low has c ea ed a highly
in e connec ed sys em whe e any dis up ion can cascade h ough mul iple supply chains.
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 943-962
944
These global dependencies ha e deepened as U.S. ag ibusinesses inc easingly ely on o e seas labo , inpu s such as
e ilize s, and mul ina ional logis ics ne wo ks. T ade ag eemen s and egional pa ne ships ha e u he in eg a ed
Ame ican p oduce s and consume s in o a dynamic in e na ional ma ke place [2]. Howe e , his in e dependence also
in oduces ulne abili ies, especially when geopoli ical ensions, ade ba ie s, o supply bo lenecks dis up he
equilib ium. Fo example, he eliance on impo s om coun ies wi h ola ile poli ical clima es o clima e-sensi i e
ag icul u al ou pu s c ea es exposu e o uncon ollable isk ac o s.
Mo eo e , shi s in consume p e e ences and popula ion g ow h pa e ns ha e al e ed impo -expo balances. The
U.S. now impo s subs an ial quan i ies o p ocessed ood and o ganic p oduc s, u he inc easing eliance on
in e na ional ce i ica ion and supply con inui y [3]. These complexi ies make i essen ial o policymake s o
unde s and he sys emic isks embedded in ood ade ne wo ks.
The g owing en anglemen o global supply chains in ood ade necessi a es he de elopmen o mo e agile, da a-d i en
s a egic planning ools. In his con ex , a i icial in elligence (AI) eme ges no only as a echnological ad ancemen bu
as a s a egic impe a i e o o ecas ing, isk mi iga ion, and policy de elopmen in he e ol ing U.S. ood ade
ecosys em [4].
1.2. Rise in Global Supply Chain Vola ili y
In ecen yea s, global supply chains ha e expe ienced unp eceden ed ola ili y, d i en by a con luence o economic,
en i onmen al, and geopoli ical dis up ions. The COVID-19 pandemic s a kly e ealed he agili y o in e na ional
logis ics, wi h ood impo s delayed o blocked due o ac o y shu downs, po closu es, and anspo a ion backlogs
[5]. These dis up ions led o p oduc sho ages, p ice spikes, and consume panic—demons a ing how global
dependencies can quickly u n in o ulne abili ies.
T ade con lic s and p o ec ionis policies ha e u he ueled unce ain y. Ta i imposi ions and e alia o y measu es,
pa icula ly in U.S.-China ag icul u al ade, esul ed in dis up ed ma ke access o key Ame ican expo s, including
soybeans and po k. The unp edic abili y o such ade ac ions makes i di icul o p oduce s and impo e s o engage
in long- e m planning o sus ain s able p ice ma gins [6].
Clima e change is ano he compounding ac o . Ex eme wea he e en s such as d ough s, loods, and hea wa es a e
inc easingly a ec ing ha es s, li es ock p oduc ion, and anspo a ion in as uc u e globally. Fo ins ance, g ain
expo s om d ough -a ec ed egions a e o en educed o delayed, igge ing ipple e ec s in dependen coun ies
and global ma ke s [7].
Cybe a acks and labo sho ages ha e added u he laye s o complexi y, c ea ing bo lenecks in ood p ocessing and
dis ibu ion sys ems. Wi h he ise o jus -in- ime in en o y sys ems, e en small delays can esul in signi ican
dis up ions ac oss he supply chain [8].
In his ola ile landscape, adi ional supply chain models a e p o ing inadequa e. The e is a g owing need o
p edic i e, adap able sys ems ha can iden i y s ess poin s and ecommend esponsi e policy measu es in nea eal-
ime—a gap ha AI echnologies a e inc easingly being used o ill.
1.3. The Role o AI in S a egic Policy Planning
A i icial In elligence (AI) is apidly eme ging as a ans o ma i e ool in he domain o s a egic policy planning,
pa icula ly in complex sys ems like ood ade and supply chain managemen . AI enables eal- ime da a in eg a ion,
p edic i e analy ics, and scena io modeling, equipping policymake s wi h deepe insigh in o in e dependencies,
ulne abili ies, and po en ial in e en ions. In he U.S. ood ade con ex , hese capabili ies a e inc easingly c i ical as
unce ain y and ola ili y challenge adi ional decision-making amewo ks [9].
Machine lea ning algo i hms can analyze la ge olumes o s uc u ed and uns uc u ed da a— anging om sa elli e
image y o c op yields o shipping logs, wea he epo s, and ade lows— o o ecas dis up ions be o e hey mani es
ma e ially. Fo example, na u al language p ocessing ools can scan global news and policy b ie ings o de ec eme ging
isks such as ade emba goes o disease ou b eaks in ag icul u al zones [10].
AI-powe ed dashboa ds also suppo scena io planning by simula ing he e ec s o policy changes, clima e e en s, o
logis ical cons ain s on na ional ood supply chains. These simula ions help decision-make s e alua e he ade-o s
and ipple e ec s o a ious in e en ions, including subsidies, impo es ic ions, o di e si ica ion e o s [11].
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 943-962
945
Mo eo e , AI ools enhance collabo a ion be ween ede al agencies, ag icul u al s akeholde s, and logis ics p o ide s
by enabling cen alized, da a-d i en policy pla o ms. These pla o ms can o e ea ly wa ning sys ems, isk maps, and
op imized con ingency s a egies ha educe exposu e o dis up ions and ensu e ood secu i y [12].
Ul ima ely, in eg a ing AI in o policy de elopmen enhances esponsi eness, p ecision, and anspa ency. As global
p essu es on he ood sys em in ensi y, le e aging AI becomes essen ial no only o c isis managemen bu also o
building long- e m esilience in he U.S. ood ade sys em.
2. The U.S. ood ade landscape and global ulne abili ies
2.1. Key Commodi ies and T ade Pa ne s
The U.S. ag icul u al expo po olio is bo h di e se and s a egically signi ican . Key commodi ies include soybeans,
co n, whea , bee , poul y, and dai y p oduc s, which oge he ep esen a subs an ial sha e o o al expo s. Soybeans
a e he mos expo ed commodi y by alue, o en d i en by s ong demand om Asia. Co n and whea a e c i ical s aples
ha eed bo h human popula ions and li es ock ac oss he globe [5]. Meanwhile, high- alue expo s like bee , po k, and
dai y ha e gained g ound in p emium ma ke s, unde sco ing he compe i i eness o he U.S. ag i- ood sec o .
T ade ela ionships wi h key pa ne s unde pin he s abili y and g ow h o hese expo lows. China, Mexico, and
Canada ank among he op h ee des ina ions o U.S. ag icul u al expo s. China’s demand o soybeans and po k,
especially a e domes ic supply shocks such as he A ican swine e e ou b eak, has made i a cen al ade pa ne in
ecen yea s. Canada and Mexico, h ough he Uni ed S a es-Mexico-Canada Ag eemen (USMCA), suppo high le els o
in eg a ed ade, especially in g ains, ui s, ege ables, and mea p oduc s [6].
Addi ionally, Japan, Sou h Ko ea, and he Eu opean Union emain c i ical o special y expo s and p ocessed oods. The
s ong p esence o U.S. ood b ands and long-s anding diploma ic ela ions enhance access o hese egula ed, high-
income ma ke s. T ade in hese egions is o en go e ned by bo h a i educ ions and ha moniza ion o sa e y
s anda ds [7].
The U.S. also elies on impo s o p oduc s such as opical ui s, nu s, co ee, and sea ood om La in Ame ica and
Sou heas Asia. These lows complemen domes ic p oduc ion and espond o consume demand o a ie y,
a ailabili y, and seasonal con inui y [8]. Unde s anding he na u e and dependency o hese bila e al and mul ila e al
lows is essen ial o e ec i e ade policy, especially amid e ol ing global isk dynamics.
2.2. Cu en T ade Ag eemen s and Policy Ins umen s
The U.S. ood ade sys em ope a es unde a complex web o ade ag eemen s and policy ools ha shape bo h expo
compe i i eness and impo access. Among he mos pi o al is he Uni ed S a es-Mexico-Canada Ag eemen (USMCA),
which eplaced he No h Ame ican F ee T ade Ag eemen (NAFTA). USMCA p ese es a i - ee access o mos
ag icul u al p oduc s and mode nizes ade p o isions ela ed o bio echnology, sani a y s anda ds, and dispu e
esolu ion—s eamlining ag icul u al comme ce ac oss he con inen [9].
O he key bila e al and mul ila e al ag eemen s include he U.S.-Japan T ade Ag eemen , which educes a i s on bee ,
po k, and wine, and he U.S.-Ko ea F ee T ade Ag eemen (KORUS), which has acili a ed a s eady inc ease in Ame ican
g ain, dai y, and ui expo s o Sou h Ko ea. These ag eemen s a e c ucial o main aining compe i i eness in high-
alue ma ke s, pa icula ly whe e domes ic subsidies o a i s p e iously limi ed access [10].
Despi e he bene i s o ade libe aliza ion, he U.S. also employs a ange o policy ins umen s o p o ec domes ic
p oduce s and manage ma ke ola ili y. These include expo subsidies, a i - a e quo as, and sani a y o
phy osani a y (SPS) measu es ha go e n ood sa e y and quali y. The Fa m Bill, eau ho ized e e y i e yea s, also
con ains p o isions ha impac ade, including c op insu ance p og ams, expo ma ke de elopmen unding, and
eme gency ood aid mechanisms [11].
The U.S. go e nmen equen ly nego ia es ad hoc ade a angemen s o espond o eme ging economic o poli ical
p essu es. Fo example, du ing ade ensions wi h China, e alia o y a i s led o expanded pu chases om B azil and
A gen ina, p omp ing he U.S. o o e subsidies and al e na i e ma ke access p og ams o i s a ec ed a me s [12].
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 943-962
946
Al hough ade ag eemen s c ea e amewo ks o s abili y, hei e ec i eness depends on en o cemen , diploma ic
goodwill, and he adap abili y o domes ic indus ies. As global condi ions e ol e, including ising p o ec ionism and
egula o y di e gence, ade policy mus become inc easingly agile, da a-in o med, and esilien o ex e nal shocks.
2.3. Vulne abili ies o Dis up ions (Pandemics, Con lic s, Clima e)
The U.S. ood ade sys em is inc easingly ulne able o a ange o global dis up ions, many o which lie ou side he
di ec con ol o domes ic policy. Pandemics, geopoli ical con lic s, and clima e- ela ed e en s can signi ican ly dis up
ag icul u al p oduc ion, in e na ional logis ics, and ade lows. The COVID-19 pandemic demons a ed how a public
heal h c isis could escala e in o a ull-blown ood supply chain eme gency. Lockdowns, po es ic ions, and labo
sho ages caused signi ican delays in bo h expo s and impo s, a ec ing pe ishables, inpu s like seeds and e ilize ,
and p ocessing capaci y [13].
Con lic s, bo h ade- ela ed and mili a y, also pose subs an ial isks. Escala ing ensions be ween he U.S. and majo
ade pa ne s—such as he U.S.-China a i wa —ha e esul ed in e alia o y measu es ha dis up ed billions in
ag icul u al expo s. Poli ical un es in key expo o impo egions, such as Eas e n Eu ope o pa s o he Middle Eas
and A ica, can a ec ade ou es, ma ke s abili y, and he sa e y o supply chain ac o s [14]. Addi ionally, he
weaponiza ion o ood ade— h ough sanc ions, expo bans, o he poli iciza ion o SPS s anda ds—c ea es
unce ain ies ha a e di icul o mi iga e h ough adi ional policy ools alone.
Clima e change ep esen s a longe - e m bu inc easingly acu e h ea . D ough s, loods, wild i es, and shi ing wea he
pa e ns impac plan ing cycles, c op yields, and wa e a ailabili y. These e ec s a e une en ac oss geog aphies,
c ea ing bo h su pluses and sho ages ha shi he global balance o supply and demand. Fo ins ance, hea wa es in
key g ain-p oducing egions ha e educed ou pu , o cing impo e s o seek al e na i e supplie s—o en a highe cos s
and longe lead imes [15].
The con e gence o hese ulne abili ies necessi a es p oac i e policy and echnological adap a ion. T adi ional
o ecas ing models and ade policies a e o en oo igid o slow o espond o apidly e ol ing h ea s. Le e aging eal-
ime da a analy ics, AI-based o ecas ing, and dynamic ade isk assessmen s can help decision-make s build a mo e
esilien ood ade in as uc u e capable o wi hs anding mul i-dimensional shocks [16].
Figu e 1 Global ood ade low map showing U.S. impo /expo dependencies
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 943-962
947
3. T adi ional s. AI-based scena io planning app oaches
3.1. O e iew o S a egic Fo esigh in Policy
S a egic o esigh e e s o he s uc u ed explo a ion o po en ial u u e de elopmen s o in o m p esen -day decision-
making. In policy con ex s, i enables go e nmen s o p oac i ely an icipa e long- e m ends, eme ging isks, and
ans o ma i e oppo uni ies, especially in complex and unce ain domains such as na ional ood secu i y and global
ade. Unlike o ecas ing, which o en p ojec s a single ou come based on cu en ajec o ies, o esigh emb aces
mul iple u u es and uses scena io de elopmen , ho izon scanning, and expe elici a ion o p epa e o a ious
con ingencies [11].
Policymake s use s a egic o esigh o s ess es assump ions, unco e blind spo s, and design adap i e s a egies ha
emain obus unde di e en u u e condi ions. Fo example, an icipa ing how demog aphic shi s, echnological
ad ancemen s, o clima e change migh eshape global ood supply chains helps in c a ing lexible ade and
sus ainabili y policies. Fo esigh does no p edic he u u e bu encou ages sys ems hinking and esilience-building
by conside ing low-p obabili y, high-impac e en s alongside mains eam de elopmen s [12].
Go e nmen agencies, including he U.S. Depa men o Ag icul u e and in e na ional o ganiza ions like he OECD and
FAO, inc easingly in eg a e s a egic o esigh in o ood policy planning. These ini ia i es suppo decision-make s in
iden i ying ea ly wa ning signals and p epa ing o scena ios such as supply chain dis up ions, geopoli ical
ealignmen s, o ab up shi s in die a y p e e ences. When combined wi h s akeholde engagemen and
in e disciplina y esea ch, o esigh ools os e mo e inclusi e and o wa d-looking go e nance [13].
Despi e i s s eng hs, he alue o s a egic o esigh is maximized when suppo ed by dynamic and e idence- ich
analy ics. The ise o a i icial in elligence and big da a echnologies p esen s new oppo uni ies o s eng hen o esigh
p ocesses wi h mo e g anula , imely, and adap i e insigh s in o complex policy en i onmen s.
3.2. Limi a ions o T adi ional Scena io Planning
While adi ional scena io planning has long been used o in o m public policy and s a egic decision-making, i su e s
om se e al s uc u al limi a ions ha hinde i s e ec i eness in apidly changing en i onmen s. One o he p ima y
weaknesses is i s eliance on s a ic, p ede ined na a i es ha o en ail o accommoda e eal- ime de elopmen s o
sudden dis up ions. This igidi y limi s he u ili y o such scena ios when policymake s mus espond o as -mo ing
c ises o complex, mul i-dimensional isks like pandemics o cybe a acks [14].
T adi ional scena ios a e ypically gene a ed h ough expe wo kshops o Delphi me hods, which, al hough aluable
o iden i ying key d i e s o change, a e ime-consuming and dependen on subjec i e judgmen . These quali a i e
me hods o en ail o inco po a e eal- ime da a s eams o dynamically model he in e ac ions among economic, social,
and en i onmen al a iables. As a esul , many scena io exe cises lack p edic i e p ecision and canno adap o
unexpec ed de elopmen s o eedback loops [15].
Ano he limi a ion is he endency o ocus on linea ex apola ions o he pas a he han non-linea , eme gen
dynamics. Fo ins ance, s anda d ood secu i y scena ios may ail o accoun o he cascading e ec s o supply chain
digi aliza ion, AI-d i en a ming p ac ices, o he geopoli ical weaponiza ion o ag icul u al ade. Mo eo e , adi ional
app oaches seldom in eg a e unce ain y quan i ica ion, lea ing policymake s unsu e abou he con idence o
p obabili y associa ed wi h di e en ou comes [16].
Gi en hese cons ain s, con en ional scena io planning ools a e inc easingly insu icien o na iga ing he ola ili y
and in e dependence o mode n ood ade sys ems. To emain ele an , hey mus e ol e o inco po a e eal- ime
compu a ion, machine lea ning, and p obabilis ic o ecas ing models.
3.3. How AI Enhances P edic i e Agili y and P ecision
A i icial In elligence (AI) signi ican ly enhances he capaci y o s a egic o esigh by add essing he limi a ions o
adi ional scena io planning and enabling mo e agile, da a-d i en policymaking. Th ough machine lea ning algo i hms,
na u al language p ocessing (NLP), and neu al ne wo ks, AI can analyze as , mul idimensional da ase s a high speed,
iden i ying sub le pa e ns, anomalies, and leading indica o s ha human analys s migh o e look [17]. This capaci y is
pa icula ly aluable in he con ex o global ood ade, whe e commodi y lows, wea he e en s, poli ical decisions,
and consume beha io s a e deeply in e linked and apidly e ol ing.
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 943-962
948
AI enables he con inuous upda ing o o ecas s as new da a becomes a ailable, shi ing o esigh om s a ic scena io
cons uc ion o dynamic isk an icipa ion. Fo ins ance, eal- ime sa elli e da a and clima e models can be in eg a ed
wi h ade lows and yield o ecas s o simula e he e ec s o d ough in one egion on global g ain p ices and
a ailabili y. These p edic i e insigh s can in o m imely in e en ions, such as p e-emp i e impo policy adjus men s
o s a egic s ockpiling [18].
Fu he mo e, AI models can gene a e p obabilis ic o ecas s ha quan i y unce ain y. Tools such as Bayesian neu al
ne wo ks and ensemble models can exp ess he likelihood o a ious ou comes, helping policymake s p io i ize high-
impac isks and alloca e esou ces mo e e ec i ely. This p obabilis ic hinking aligns well wi h s a egic o esigh
p inciples by encou aging lexible, con ingen planning a he han ixed-pa h assump ions [19].
AI also suppo s s akeholde inclusi i y by isualizing complex da a and scena ios h ough dashboa ds and decision-
suppo ools. These pla o ms democ a ize access o insigh s, enabling collabo a ion ac oss agencies and sec o s.
Ul ima ely, AI ans o ms s a egic o esigh in o a eal- ime, adap i e p ocess ha enhances p epa edness,
esponsi eness, and long- e m esilience in ood ade go e nance [20].
Table 1 Compa ison o T adi ional s AI-Enhanced Scena io Planning F amewo ks
Fea u e
T adi ional Scena io Planning
AI-Enhanced Scena io Planning
Da a Usage
Limi ed, his o ical, o en s a ic
Real- ime, mul idimensional, and con inuously
upda ed
Scena io Gene a ion
Expe -d i en, na a i e-based
Algo i hmic, da a-d i en, dynamic
Adap abili y
In equen upda es, manual
e isions
Con inuous lea ning and adap i e simula ions
Risk Quan i ica ion
Quali a i e o heu is ic
P obabilis ic, wi h unce ain y bounds
S akeholde In ol emen
Wo kshop-based, episodic
Scalable dashboa ds, li e decision suppo
Geog aphic and Commodi y
Resolu ion
Na ional-le el ocus
Subna ional and commodi y-speci ic g anula i y
Timeliness
Pe iodic (e.g., annual exe cises)
On-demand, eal- ime ecalib a ion
4. Key AI echniques o scena io modeling
4.1. Machine Lea ning o Demand and P ice Fo ecas ing
Machine lea ning (ML) has become a powe ul ool o o ecas ing ood demand and p ice luc ua ions in complex global
ade sys ems. T adi ional econome ic models, such as ARIMA o linea eg ession, o en ely on s ong assump ions
abou da a s a iona i y and linea i y. In con as , ML me hods like andom o es s, suppo ec o eg ession, and deep
neu al ne wo ks can unco e hidden pa e ns and nonlinea ela ionships wi hin as da ase s, imp o ing p edic i e
accu acy in dynamic ma ke en i onmen s [15].
In ood ade policy, accu a e demand and p ice o ecas s a e c i ical o planning impo s, egula ing subsidies, and
a oiding bo h glu s and sho ages. ML models can inges eal- ime da a om mul iple sou ces—such as his o ical p ice
ends, mac oeconomic indica o s, wea he pa e ns, and ade olumes— o p edic sho - and long- e m ou comes
mo e e ec i ely han s a ic models. Fo example, neu al ne wo ks ha e been success ully applied o o ecas p ice
ola ili y in commodi y ma ke s such as whea , ice, and co n, cap u ing seasonal pa e ns and sudden shocks due o
clima e o geopoli ical e en s [16].
Mo eo e , ML echniques can suppo subna ional o ecas ing, helping policymake s unde s and consump ion ends
ac oss di e en egions o demog aphic g oups. This g anula iew suppo s a ge ed policy in e en ions, such as
localized ood assis ance o in as uc u e in es men o add ess an icipa ed bo lenecks [17].
When in eg a ed in o supply chain managemen sys ems, ML o ecas s enable be e in en o y planning, p ocu emen
decisions, and logis ics coo dina ion. Go e nmen s can use hese models o p e-posi ion s a egic ese es o adjus
impo schedules, educing cos s and mi iga ing isks. By cap u ing he complexi y o global ood ma ke s, ML
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 943-962
949
con ibu es o mo e agile, in o med, and da a-d i en decision-making amewo ks ha a e essen ial in oday’s ola ile
economic landscape [18].
4.2. Na u al Language P ocessing (NLP) o T ade In elligence
Na u al Language P ocessing (NLP), a sub ield o a i icial in elligence, enables machines o p ocess and in e p e
human language om uns uc u ed ex sou ces. In he con ex o ood ade policy, NLP can se e as a powe ul ool
o ade in elligence by ex ac ing ac ionable insigh s om news a icles, policy documen s, social media, and
diploma ic communica ions. These sou ces o en con ain ea ly signals o dis up ions, such as expo bans, egula o y
shi s, o labo un es , which may no ye be e lec ed in quan i a i e da ase s [19].
By applying en i y ecogni ion, sen imen analysis, and opic modeling, NLP ools can moni o global na a i es
su ounding ood ma ke s and ade ag eemen s. Fo ins ance, a sudden ise in nega i e sen imen owa d whea
expo s in majo p oducing coun ies may signal a pending policy shi o domes ic sho age. NLP models can ale
policymake s o hese ends in nea eal- ime, suppo ing p oac i e esponses o mi iga e impac s on domes ic ood
p ices o a ailabili y [20].
Mul ilingual capabili ies allow NLP sys ems o scan local media in mul iple languages, inc easing geog aphic co e age
and con ex ual awa eness. This is pa icula ly aluable in acking de elopmen s in poli ically sensi i e o high- isk
egions. Go e nmen s and in e na ional o ganiza ions can use NLP-d i en dashboa ds o enhance si ua ional
awa eness and imp o e diploma ic coo dina ion in ade nego ia ions.
When in eg a ed wi h p edic i e models, NLP ou pu s can s eng hen o ecas ing sys ems by adding quali a i e,
con ex - ich inpu s. This syne gy be ween s uc u ed and uns uc u ed da a sou ces enables a mo e comp ehensi e
unde s anding o global ade dynamics, ensu ing ha ood policy emains esponsi e o bo h da a and discou se [21].
4.3. Agen -Based Modeling and Rein o cemen Lea ning
Agen -based modeling (ABM) and ein o cemen lea ning (RL) o e inno a i e amewo ks o simula ing ood ade
dynamics and es ing he e ec i eness o policy in e en ions unde a ious condi ions. ABM in ol es cons uc ing
i ual en i onmen s popula ed by au onomous agen s—such as go e nmen s, ade s, consume s, and p oduce s—
each wi h dis inc goals, cons ain s, and adap i e beha io s. These agen s in e ac based on de ined ules, allowing he
eme gence o complex, sys em-le el phenomena such as ma ke luc ua ions, supply chain bo lenecks, o coope a i e
alliances [22].
ABMs a e pa icula ly sui ed o explo ing non-linea , pa h-dependen sys ems whe e op-down equa ions may ail o
cap u e dynamic eedback loops. Fo example, policymake s can use ABMs o simula e he impac o expo a i s on
soybean lows, obse e how domes ic p oduce s and impo e s adap , and iden i y unin ended consequences such as
egional ood insecu i y o p ice in la ion [23]. This ype o modeling enables obus scena io analysis, highligh ing
policy le e age poin s and ade-o s.
Rein o cemen lea ning complemen s ABM by enabling agen s o lea n op imal s a egies h ough ial and e o wi hin
simula ed en i onmen s. In an RL amewo k, agen s ecei e ewa ds o penal ies based on he ou comes o hei
ac ions, allowing hem o i e a i ely imp o e decision-making. Applied o ood ade, RL algo i hms can simula e supply
chain op imiza ion, impo subs i u ion s a egies, o eme gency esponse planning unde unce ain y [24].
Toge he , ABM and RL c ea e a sandbox o es ing adap i e policies in ola ile condi ions. Fo ins ance, an RL agen
ep esen ing a ood secu i y agency migh lea n he bes iming and quan i y o g ain impo s o s abilize p ices while
minimizing cos s. These ools can also simula e compe i i e beha io s, such as ade e alia ion o hoa ding, enabling
policymake s o an icipa e geopoli ical consequences.
By cap u ing adap i e, decen alized decision-making, ABM and RL help b idge he gap be ween echnical models and
eal-wo ld complexi y, o e ing lexible pla o ms o u u e-p oo ing ood ade policy [25].
4.4. Gene a i e Models o Hypo he ical Dis up ion Scena ios
Gene a i e models, including Gene a i e Ad e sa ial Ne wo ks (GANs) and Va ia ional Au oencode s (VAEs), a e
inc easingly being applied in policymaking o simula e hypo he ical dis up ion scena ios and assess esilience in
complex sys ems like global ood ade. These models lea n he unde lying s uc u e o high-dimensional da a and
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 943-962
950
gene a e syn he ic ou pu s ha esemble eal-wo ld phenomena, making hem powe ul ools o s ess es ing and isk
o ecas ing [26].
In ood policy, gene a i e models can simula e low- equency, high-impac e en s—such as coo dina ed expo bans,
cybe a acks on po in as uc u e, o simul aneous c op ailu es ac oss majo p oducing egions. T adi ional models
may s uggle wi h hese ou lie e en s due o da a spa si y o es ic i e assump ions. By con as , gene a i e models
can p oduce ealis ic, da a-in o med scena ios ha policymake s can use o es eme gency p epa edness plans o
e alua e supply chain edundancy [27].
Fo example, a VAE ained on his o ical ade and p ice da a can be used o gene a e al e na e eali ies whe e speci ic
dis up ions occu , enabling he explo a ion o cascading e ec s on ood a ailabili y, p ice ola ili y, and egional hunge
isks. GANs, meanwhile, can gene a e syn he ic clima e anomalies o es he sensi i i y o ag icul u al ou pu s and ade
balances unde ex eme wea he condi ions [28].
These models also suppo da a augmen a ion o a e-e en aining in machine lea ning pipelines, imp o ing he
obus ness o p edic i e sys ems in c isis de ec ion and esponse. When in eg a ed wi h decision-suppo ools,
gene a i e scena ios help s ess es p ocu emen s a egies, ese e managemen , and diploma ic esponses unde
di e se and complex dis up ion p o iles.
Ul ima ely, gene a i e models expand he s a egic ho izon o policymake s by enabling “wha -i ” analysis beyond
his o ical p eceden , os e ing inno a ion in isk assessmen and adap i e planning o global ood ade [29].
Figu e 2 A chi ec u e o an AI-d i en scena io planning sys em in ood ade
5. An icipa ing and modeling global supply chain shocks
5.1. Simula ing Shock E en s: D ough s, Expo Bans, Con lic s
Simula ing shock e en s such as d ough s, expo bans, and geopoli ical con lic s is c ucial o building esilien ood
ade sys ems and in o ming policy design. These shocks o en un old unp edic ably, ye hei impac s can be
de as a ing, cascading h ough global ood ne wo ks wi h speed and in ensi y. Ad anced simula ion ools—pa icula ly
hose powe ed by agen -based modeling, p obabilis ic o ecas ing, and scena io gene a ion—enable policymake s o
an icipa e how hese e en s migh dis up supply chains, a ec ma ke p ices, and endange ood secu i y [19].
D ough s a e among he mos equen and impac ul na u al shocks o ag icul u e. By in eg a ing sa elli e-de i ed
clima e da a wi h c op models and ade low da abases, simula ions can es ima e educ ions in yield and p oduc ion,
especially in key g ain-expo ing egions. These p ojec ions can be used o igge ea ly wa nings o ood-impo ing
coun ies and guide impo di e si ica ion s a egies o he elease o s a egic ese es [20]. Fo example, modeling a
d ough in he Midwes Uni ed S a es can e eal po en ial downs eam e ec s on co n p ices, e hanol p oduc ion, and
li es ock eed cos s globally.
Expo bans ep esen ano he common policy-induced shock. Coun ies may implemen empo a y bans o p ese e
domes ic ood supply du ing imes o c isis, bu such ac ions o en dis up global ade lows and ampli y sca ci y in
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 943-962
951
ood-impo ing na ions. Simula ions can help e alua e he global implica ions o hese decisions, showing how ood
p ices espond and how o he expo e s adjus hei ade pa e ns in esponse [21].
A med con lic s, especially in ag icul u ally p oduc i e egions, dis up no only a ming ac i i ies bu also anspo
in as uc u e and labo a ailabili y. Simula ing hese dis up ions in ol es modeling ade e ou ing, po closu es, and
commodi y subs i u ion. Fo example, dis up ions in he Black Sea egion can impac whea and sun lowe oil ma ke s,
p omp ing ipple e ec s in A ica and Sou h Asia [22].
By ep oducing hese scena ios unde a ying in ensi ies and du a ions, simula ion ools help assess policy op ions
such as subsidies, bu e s ocks, o eme gency impo au ho iza ions. They p o ide aluable insigh s ha can imp o e
p epa edness and accele a e coo dina ed esponses ac oss go e nmen s and in e na ional agencies.
5.2. Cascading E ec s Ac oss T ade Ne wo ks
Food ade ne wo ks a e cha ac e ized by in ica e in e dependencies ha ampli y he e ec s o localized dis up ions
in o global supply shocks. Unde s anding hese cascading e ec s equi es sys ems-le el modeling ha cap u es how
shocks p opaga e ac oss egions, commodi ies, and supply chain ac o s. Ne wo k-based simula ions, which ea
coun ies o ade hubs as nodes connec ed by ade lows, help e eal poin s o ulne abili y, esilience, and isk
ampli ica ion in eal ime [23].
When one coun y expe iences a supply shock—due o d ough , expo es ic ions, o labo s ikes— he immedia e
e ec is a educ ion in expo capaci y. This leads o sho ages o p ice inc eases o impo ing na ions. Howe e , he
impac s seldom emain isola ed. Impo e s mus quickly seek al e na i e supplie s, o en u ning o coun ies wi h
ma ginal excess capaci y. This sudden demand spike can s ess hose seconda y supplie s, leading o p ice in la ion and
supply a ioning in un ela ed ma ke s [24].
Such chain eac ions a e especially p onounced o s aple commodi ies like whea , ice, and soybeans, whe e a hand ul
o coun ies domina e global expo s. Fo ins ance, a es ic ion on palm oil expo s om a majo supplie may esul in
inc eased global demand o soybean and sun lowe oil, in la ing p ices ac oss edible oil ma ke s [25]. These seconda y
e ec s a e di icul o de ec wi hou de ailed simula ions ha model elas ici y, subs i u ion, and ma ke ealloca ion
dynamics.
Cascading e ec s also mani es in logis ics in as uc u e, such as po conges ion, shipping delays, and s o age
o e low. Fo example, i po s in one egion become bo lenecked due o edi ec ed lows, pe ishable goods may spoil,
and landlocked na ions may lose access o c i ical impo s. Ne wo k simula ions help isualize such s ess poin s and
es mi iga ion s a egies like in as uc u e scaling, ansshipmen ag eemen s, o al e na e co ido de elopmen [26].
C ucially, cascading e ec s a e no only economic— hey also include social and poli ical dimensions. Rapid ood p ice
in la ion has his o ically igge ed social un es , pa icula ly in ulne able egions. By modeling hese second- and hi d-
o de impac s, ade policymake s can ake a p oac i e app oach o c isis p e en ion and sys emic s abili y [27].
5.3. Mul i-Scena io Simula ions o Policy Impac Assessmen
Mul i-scena io simula ion is a co ne s one o mode n policy analysis, especially in domains ma ked by unce ain y and
in e dependence like in e na ional ood ade. Unlike single-e en modeling, which e alua es he impac o a p ede ined
shock, mul i-scena io simula ions es a ange o condi ions—including compound e en s, eco e y ajec o ies, and
beha io al adap a ions— o assess he obus ness o policy decisions ac oss po en ial u u es [28].
Using p obabilis ic models, agen -based simula ions, o sys em dynamics, policymake s can explo e “wha -i ” ques ions
unde a ying assump ions. Fo ins ance, a go e nmen migh assess how simul aneously expe iencing a domes ic
d ough and an in e na ional expo ban would a ec na ional ood secu i y, o eign ese es, and ade balances. Each
scena io o e s di e en policy implica ions— equi ing dis inc esponses such as scaling up ood assis ance, ac i a ing
ade con ingency plans, o adjus ing a i schedules [29].
Scena ios can also accoun o g adual ends, such as declining soil e ili y o shi ing die a y pa e ns, in addi ion o
acu e shocks. This allows policymake s o assess long- e m in es men s like di e si ica ion o c op po olios,
in as uc u e esilience, o egional ade in eg a ion. When combined wi h cos -bene i analysis, scena io modeling
enables be e p io i iza ion o limi ed policy esou ces [30].
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 943-962
958
need o in es in in e ope able digi al in as uc u e, ensu e c oss-agency collabo a ion, and ins i u ionalize AI in o
ou ine ade planning wo k lows. Fu u e adap a ions mus ocus on scaling hese ools, enhancing anspa ency, and
b idging da a gaps o ensu e equi able and esilien ood sys ems capable o wi hs anding u u e shocks and s a egic
unce ain ies [40].
9. Challenges and e hical conside a ions
9.1. Da a Gaps and Model T anspa ency
Despi e he g owing in eg a ion o a i icial in elligence in o ood ade policy, pe sis en da a gaps and model opaci y
emain signi ican challenges. In many egions, pa icula ly low-income and poli ically uns able a eas, eliable da a on
ag icul u al p oduc ion, p ices, logis ics, and consump ion is ei he ou da ed, incomple e, o una ailable. This lack o
co e age weakens he p edic i e powe o AI ools and skews he accu acy o global ood ade simula ions [38].
Fu he mo e, many AI and machine lea ning models, pa icula ly deep lea ning a chi ec u es, unc ion as "black
boxes"—p o iding p edic ions wi hou clea explana ions o how hose ou comes we e de i ed. Fo policymake s, his
lack o model anspa ency impedes us , in e p e abili y, and accoun abili y. When decisions in ol ing subsidies,
ade es ic ions, o eme gency aid a e based on opaque algo i hms, i becomes di icul o alida e hei ai ness o
assess hei pe o mance in hindsigh [39].
Add essing hese conce ns equi es building in e ope able, open-sou ce pla o ms ha s anda dize ood ade da a
collec ion and documen a ion. I also calls o adop ing explainable AI echniques—such as model in e p e abili y
laye s, decision ees, o SHAP alues— ha cla i y a iable impo ance and causal pa hways. T anspa en model
documen a ion and audi able codebases a e essen ial o aligning p edic i e sys ems wi h ins i u ional no ms and
public o e sigh equi emen s [40].
9.2. Bias, Fai ness, and Equi y in P edic i e Tools
As p edic i e ools become mo e p e alen in guiding ood ade policy, conce ns o e algo i hmic bias and ai ness
g ow inc easingly u gen . AI models ained on his o ical ade da a may ep oduce exis ing inequali ies, such as
a o ing expo e s wi h mo e es ablished logis ics in as uc u e o unde ep esen ing smallholde a me s om
de eloping na ions. These biases can skew policy ecommenda ions, u he ma ginalizing ulne able s akeholde s
[41].
Mo eo e , models ha op imize pu ely o e iciency o ma ke esponsi eness may o e look equi y-o ien ed
ou comes, such as access o a o dable ood in emo e egions o he economic iabili y o subsis ence a ming
communi ies. Wi hou delibe a e a en ion o dis ibu i e ai ness, AI sys ems isk ein o cing exis ing s uc u al
imbalances in global ood ade [42].
Ensu ing equi y equi es embedding ai ness cons ain s di ec ly in o model design and aining p ocesses. This
includes balancing pe o mance ac oss di e se popula ion g oups, explici ly modeling ade-o s be ween e iciency and
social goals, and consul ing ma ginalized communi ies in da a go e nance and sys em design. Fu he mo e, impac
assessmen s should be conduc ed o e alua e how AI-d i en decisions a ec di e en s akeholde s—pa icula ly in
egions wi h limi ed ba gaining powe o oice in in e na ional ade o ums [43].
P omo ing ai ness in AI o ood ade is no only a echnical challenge—i is an e hical and go e nance impe a i e o
sus ainable and inclusi e ood sys ems.
9.3. Legal and Go e nance Implica ions
The applica ion o AI in ood ade o ecas ing and policy ca ies signi ican legal and go e nance implica ions,
pa icula ly as au oma ed decisions inc easingly in luence ma ke access, ade nego ia ions, and c isis esponses. A
p esen , he e is limi ed egula o y cla i y on he s anda ds and liabili ies associa ed wi h algo i hmic decision-making
in ade policy. This c ea es a g ay zone whe e accoun abili y o e o s, bias, o unin ended ou comes may be di icul
o assign [44].
Issues such as da a p i acy, c oss-bo de da a sha ing, and in ellec ual p ope y igh s also complica e AI deploymen .
Many ood ade models ely on sensi i e comme cial da a o geopoli ical in elligence, aising ques ions abou how such
in o ma ion is sha ed, p o ec ed, and used. Wi hou clea legal sa egua ds, bo h da a p o ide s and go e nmen s may
hesi a e o engage in collabo a i e p edic i e analy ics [45].
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 943-962
959
Mo eo e , he adop ion o AI mus align wi h exis ing in e na ional ade ag eemen s and amewo ks, including WTO
p o isions on anspa ency, non-disc imina ion, and science-based decision-making. Any AI-de i ed policy ac ion—
such as imposing impo es ic ions based on p edic i e isk—mus be de ensible unde in e na ional law o a oid
ade dispu es [46].
To add ess hese conce ns, na ional and in e na ional ins i u ions mus de elop AI go e nance amewo ks speci ic o
he ood ade con ex , ensu ing ha anspa ency, legali y, and e hical in eg i y a e main ained h oughou he li ecycle
o p edic i e decision-making sys ems [47].
Table 4 Sample AI-In o med Policy Responses Unde Di e en S ess Scena ios
S ess Scena io
AI Tool Applied
Policy Response Enabled
Se e e expo es ic ion in op
whea -expo ing na ions
Bayesian o ecas model
Di e si ica ion o sou cing and
eme gency quo a exemp ions
Clima e-induced mul i-coun y
c op ailu e
Gene a i e scena io modeling
S a egic ese e ac i a ion and p ice
con ol mechanisms
Po closu e due o labo
dis up ion
Agen -based logis ics simula ion
Al e na i e ou ing policy and
empo a y impo wai e s
T ade con lic escala ion wi h
majo pa ne
NLP and sen imen analysis o
diploma ic communica ions
Bila e al enego ia ion wi h allback
clauses
Pandemic esu gence wi h global
shipmen delays
ML p edic i e analy ics wi h eal- ime
logis ics inpu s
Impo iming adjus men s and subsidy
igge s o pe ishables
10. Conclusion
Summa y o Key Insigh s and Con ibu ions
This a icle has explo ed how a i icial in elligence (AI), combined wi h ad anced modeling echniques, can eshape he
landscape o U.S. ood ade policy. In an e a de ined by supply chain ola ili y, clima e unp edic abili y, and geopoli ical
ins abili y, adi ional ools o policy planning—while ounda ional—a e no longe su icien o managing complex and
dynamic global ood sys ems. AI echnologies such as machine lea ning, na u al language p ocessing, gene a i e models,
and agen -based simula ions o e scalable solu ions o p edic i e analy ics, c isis esponse, and scena io planning.
Key insigh s e eal ha AI can signi ican ly enhance demand o ecas ing, p ice ola ili y analysis, and dis up ion
an icipa ion. F om COVID-19- ela ed supply chain b eakdowns o he whea sho age esul ing om he Uk aine-Russia
con lic , AI sys ems ha e al eady demons a ed alue in suppo ing eal- ime policy decisions and esou ce ealloca ion.
Mo eo e , AI augmen s ade nego ia ions and ede al planning by enabling dynamic a i adjus men s, p obabilis ic
isk simula ions, and ea ly-wa ning sys ems o ma ke and supply shi s.
The a icle also highligh s challenges ha mus be add essed o AI’s ull po en ial o be ealized in his domain. These
include da a spa si y in eme ging ma ke s, opaci y in complex models, he isk o algo i hmic bias, and he need o
e hical gua d ails in policymaking. Despi e hese ba ie s, he oppo uni ies o AI o suppo equi able, anspa en ,
and esilien ade sys ems a e p o ound.
Th ough case s udies, simula ion examples, and policy ecommenda ions, his a icle con ibu es a amewo k o
in eg a ing AI in o he ins i u ional ab ic o ood ade go e nance. I ad oca es o a shi om eac i e o an icipa o y
s a egies, empowe ing U.S. agencies o no only espond o c ises bu o p oac i ely manage isk and s eng hen he
long- e m esilience o domes ic and global ood sys ems.
Call o Mul i-S akeholde Collabo a ion in AI Go e nance
E ec i e AI in eg a ion in o ood ade policy canno es solely on go e nmen agencies o p i a e-sec o inno a ion.
I equi es a conce ed, mul i-s akeholde app oach ha b ings oge he policymake s, echnologis s, ag icul u al
p oduce s, da a scien is s, academic ins i u ions, ci il socie y, and in e na ional o ganiza ions. Each ac o plays a c i ical
ole in shaping no jus he echnical capabili ies o AI sys ems, bu also hei e hical, legal, and social implica ions.
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 943-962
960
Collabo a ion mus s a wi h sha ed da a in as uc u e—s anda dized, secu e, and in e ope able ac oss agencies and
bo de s. Public-p i a e pa ne ships can accele a e he de elopmen o open-access models, inclusi e da a collec ion
e o s, and localized applica ions ailo ed o he needs o unde se ed egions. A he same ime, academic and ci il
socie y ac o s should con ibu e o independen impac assessmen s, ai ness audi s, and anspa ency benchma ks
ha keep powe ul ools accoun able.
Policy go e nance bodies mus c ea e pa icipa o y amewo ks whe e all s akeholde s ha e a oice in he design and
deploymen o AI sys ems. This includes in eg a ing eedback om smallholde a me s, ade unions, and ood secu i y
expe s o ensu e echnology aligns wi h socie al goals. Only h ough collec i e go e nance can AI e ol e as a o ce o
equi able and esilien ood ade, add essing cu en ulne abili ies while p epa ing o u u e unce ain ies.
Final Though s on Fu u e-P oo ing U.S. Food T ade Policy
Fu u e-p oo ing U.S. ood ade policy equi es bold inno a ion g ounded in adap abili y and o esigh . AI o e s he
ools o an icipa e dis up ion, op imize esponses, and os e esilience in he ace o unce ain y. Ye i s success hinges
on anspa en go e nance, inclusi e collabo a ion, and he e hical use o da a and algo i hms. As isks become mo e
complex and in e connec ed, policymake s mus emb ace AI no as a s andalone solu ion, bu as a s a egic enable
embedded in a b oade ision o ood secu i y, economic s abili y, and global coope a ion. P oac i e, in elligence-d i en
policy is no longe op ional—i is essen ial o sus aining he u u e o ood ade.
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] Dhal SB, Ka D. T ans o ming Ag icul u al P oduc i i y wi h AI-D i en Fo ecas ing: Inno a ions in Food Secu i y
and Supply Chain Op imiza ion. MDPI Fo ecas ing. 2024 Oc 19;6(INL/JOU-24-81560-Re 000).
[2] Khan RS, Si azy MR, Das R, Rahman S. An ai and ml-enabled amewo k o p oac i e isk mi iga ion and
esilience op imiza ion in global supply chains du ing na ional eme gencies. Sage Science Re iew o Applied
Machine Lea ning. 2022;5(2):127-44.
[3] How ML, Chan YJ, Cheah SM. P edic i e insigh s o imp o ing he esilience o global ood secu i y using a i icial
in elligence. Sus ainabili y. 2020 Aug 4;12(15):6272.
[4] Olu emi-Phillips AQ, Igwe AN, To omade AS, Louis N. Global ade dynamics' impac on ood p icing and supply
chain esilience: A quan i a i e model.
[5] Enemosah A. Implemen ing De Ops Pipelines o Accele a e So wa e Deploymen in Oil and Gas Ope a ional
Technology En i onmen s. In e na ional Jou nal o Compu e Applica ions Technology and Resea ch.
2019;8(12):501–515. A ailable om: h ps://doi.o g/10.7753/IJCATR0812.1008
[6] Noah GU. In e disciplina y s a egies o in eg a ing o al heal h in na ional immune and in lamma o y disease
con ol p og ams. In J Compu Appl Technol Res. 2022;11(12):483-498. doi:10.7753/IJCATR1112.1016.
[7] A ah RU, Ga ba BM, Gil-Ozoudeh I, Iwuanyanwu O. Enhancing supply chain esilience h ough a i icial
in elligence: Analyzing p oblem-sol ing app oaches in logis ics managemen . In e na ional Jou nal o
Managemen & En ep eneu ship Resea ch. 2024;5(12):3248-65.
[8] Riad M, Naimi M, Oka C. Enhancing Supply Chain Resilience Th ough A i icial In elligence: De eloping a
Comp ehensi e Concep ual F amewo k o AI Implemen a ion and Supply Chain Op imiza ion. Logis ics. 2024
No 6;8(4):111.
[9] Chukwunweike Joseph, Salaudeen Habeeb Dolapo. Ad anced Compu a ional Me hods o Op imizing Mechanical
Sys ems in Mode n Enginee ing Managemen P ac ices. In e na ional Jou nal o Resea ch Publica ion and
Re iews. 2025 Ma ;6(3):8533-8548. A ailable om: h ps://ij p .com/uploads/V6ISSUE3/IJRPR40901.pd
[10] Channe PS. The Impac o AI on Economic Fo ecas ing and Policy-Making: Oppo uni ies and Challenges o
Fu u e Economic S abili y and G ow h. Yo k Uni e si y. 2024.
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 943-962
961
[11] Olu emi-Phillips AQ, O odile OC, To omade AS, Igwe AN, Adewale TT. S a egies o adap ing ood supply chains
o clima e change using simula ion models. S a egies. 2024 No ;20(11):1021-40.
[12] Bahangulu JK. 6G wi eless ne wo ks and e ahe z communica ions: In elligen e lec ing su aces, MIMO, and
ene gy-e icien IoT a chi ec u es. Wo ld J Ad Res Re . 2025;25(2):1712–36. doi:
h ps://doi.o g/10.30574/wja .2025.25.2.0570
[13] Changa a hil T. AI & Food Sys ems: The Fu u e o he Canadian Economy.
[14] Moghaddam GK, Ka imzadeh M. AI-D i en Digi al T ans o ma ion and Sus ainable Logis ics: Inno a ions in
Global Supply Chain Managemen .
[15] Aliyu Enemosah. In elligen decision suppo sys ems o oil and gas con ol ooms using eal- ime AI in e ence.
In J Eng Technol Res Manag [In e ne ]. 2021 Dec;5(12):236. A ailable om: h ps://www.ije m.com/; DOI:
h ps://doi.o g/10.5281/zenodo.15362005
[16] Yewande RM. AI Enhanced Re enue Modeling and Financial Fo esigh o Risk-Responsi e G ow h in Mino i y-
Led En e p ises.
[17] Emi-Johnson Oluwabukola, Fasanya Oluwa unmibi, Adeniyi Ayodele. P edic i e c op p o ec ion using machine
lea ning: A scalable amewo k o U.S. Ag icul u e. In J Sci Res A ch. 2024;15(01):670-688. A ailable om:
h ps://doi.o g/10.30574/ijs a.2024.12.2.1536
[18] Campbell J, Ko i BA. The Role o AI-powe ed inancial analy ics in shaping economic policy: A new e a o isk
managemen and na ional g ow h in he Uni ed S a es. Wo ld Jou nal o Ad anced Resea ch and Re iews. 2024
Sep;23(3):2816-25.
[19] Adepoju Adekola Geo ge, Adepoju Daniel Adeyemi. Bioma ke disco e y in clinical biology enhances ea ly
disease de ec ion, p ognosis, and pe sonalized ea men s a egies. In e na ional Jou nal o Ad ance Resea ch
Publica ion and Re iews. 2025 Ap ;2(4):229–52. A ailable om: h ps://doi.o g/10.5281/zenodo.15244690
[20] Kababii o Lillian. Ha nessing A i icial In elligence o Real-Time Compliance in he U.S. Oil & Gas Sec o :
Enhancing Tax Accu acy, Cu bing E asion, and Unlocking Re enue G ow h h ough In elligen Au oma ion.
In e na ional Jou nal o Compu e Applica ions Technology and Resea ch. 2025;14(05):55–70.
doi:10.7753/IJCATR1405.1006.
[21] Nweje U, Taiwo M. Le e aging A i icial In elligence o p edic i e supply chain managemen , ocus on how AI-
d i en ools a e e olu ionizing demand o ecas ing and in en o y op imiza ion. In e na ional Jou nal o Science
and Resea ch A chi e. 2025 Jan;14(1):230-50.
[22] Abdulsalam A, Okechukwu M, Oluko un K, Onagun Q. Analysis o bio-enhance s o pH and iscosi y con ol in
d illing luid sys ems. In . J. Res. Inno . Appl. Sci.(IJRIAS). 2020(I).
[23] Enemosah A, Chukwunweike J. Nex -Gene a ion SCADA A chi ec u es o Enhanced Field Au oma ion and Real-
Time Remo e Con ol in Oil and Gas Fields. In J Compu Appl Technol Res. 2022;11(12):514–29.
doi:10.7753/IJCATR1112.1018.
[24] Kunle e AS, Pe e OE. No el Solu ions o Comba ing Nu i ional De iciencies in a C isis o G owing Global Food
Insecu i y.
[25] Emi-Johnson Oluwabukola, Nk umah Kwame, Folasole Ade ayo, Amusa Tope Kolade. Op imizing machine
lea ning o imbalanced classi ica ion: Applica ions in U.S. heal hca e, inance, and secu i y. In J Eng Technol Res
Manag. 2023 No ;7(11):89. A ailable om: h ps://doi.o g/10.5281/zenodo.15188490
[26] Anjum MA. Le e aging a i icial in elligence o enhancing in e na ional supply chain managemen .
[27] Swa son H, Alabi D, Naidoo K, Coopoosamy R, A hu G. BRICS Ag icul u al Food Sys em and Inno a ions: Hope
o Global Food Secu i y. InInno a ion and De elopmen o Ag icul u al Sys ems: Cases om B azil, Russia, India,
China and Sou h A ica (BRICS) 2024 Jul 20 (pp. 183-209). Singapo e: Sp inge Na u e Singapo e.
[28] Chukwunweike J, Lawal OA, A ogundade JB, Alade B. Na iga ing e hical challenges o explainable AI in
au onomous sys ems. In e na ional Jou nal o Science and Resea ch A chi e. 2024;13(1):1807–19.
doi:10.30574/ijs a.2024.13.1.1872. A ailable om: h ps://doi.o g/10.30574/ijs a.2024.13.1.1872.
[29] Mon oy Lopez ES. NATIONAL AND EU GAS SUPPLY SECURITY IN-BETWEEN GEOPOLITICS AND ENERGY
INFRASTRUCTURES (Doc o al disse a ion, Poli ecnico di To ino).
Wo ld Jou nal o Ad anced Resea ch and Re iews, 2025, 26(02), 943-962
962
[30] Olayinka OH. Big da a in eg a ion and eal- ime analy ics o enhancing ope a ional e iciency and ma ke
esponsi eness. In J Sci Res A ch. 2021;4(1):280–96. A ailable om:
h ps://doi.o g/10.30574/ijs a.2021.4.1.0179
[31] Olagunju E. In eg a ing AI-d i en demand o ecas ing wi h cos -e iciency models in biopha maceu ical
dis ibu ion sys ems. In J Eng Technol Res Manag. 2022 Jun 6.
[32] Kuma VV, Sahoo A, Balasub amanian SK, Ghols on S. Mi iga ing heal hca e supply chain challenges unde
disas e condi ions: a holis ic AI-based analysis o social media da a. In e na ional Jou nal o P oduc ion
Resea ch. 2025 Jan 17;63(2):779-97.
[33] Olayinka OH. Da a d i en cus ome segmen a ion and pe sonaliza ion s a egies in mode n business in elligence
amewo ks. Wo ld Jou nal o Ad anced Resea ch and Re iews. 2021;12(3):711–726. doi:
h ps://doi.o g/10.30574/wja .2021.12.3.0658.
[34] Anjo in K, Ijomah T, To omade A, Akinsuli e A, Eyo-Udo N. E alua ing business de elopmen se ices' ole in
enhancing SME esilience o economic shocks. Global Jou nal o Resea ch in Science and Technology.
2024;2(01):029-45.
[35] Enemosah A. In elligen Decision Suppo Sys ems o Oil and Gas Con ol Rooms Using Real-Time AI In e ence.
In e na ional Jou nal o Enginee ing Technology Resea ch & Managemen . 2021 Dec;5(12):236–244. A ailable
om: h ps://doi.o g/10.5281/zenodo.15363753
[36] Qud a -Ullah H. Applica ions in Va ious Domains. InNa iga ing Complexi y: AI and Sys ems Thinking o Sma e
Decisions 2025 Feb 9 (pp. 93-118). Cham: Sp inge Na u e Swi ze land.
[37] S ini asan N, Eden L. Going digi al mul ina ionals: Na iga ing economic and social impe a i es in a pos -
pandemic wo ld. Jou nal o In e na ional Business Policy. 2021 Ap 23;4(2):228.
[38] Gal ez E. Scaling up inclusi e inno a ions in ag i ood chains in Asia and he Paci ic. Food & Ag icul u e O g.; 2022
Jun 21.
[39] Olayinka OH. E hical implica ions and go e nance o AI models in business analy ics and da a science
applica ions. In e na ional Jou nal o Enginee ing Technology Resea ch & Managemen . 2022 No ;6(11). doi:
h ps://doi.o g/10.5281/zenodo.15095979.
[40] Gup a S, Campos Zeballos J, del Río Cas o G, Tomičić A, And és Mo ales S, Mah ouz M, Osemwegie I, Phemia
Comlan Sessi V, Schmi z M, Mahmoud N, Inya egh M. Ope a ionalizing Digi ainabili y: Encou aging mind ulness
o ha ness he powe o digi aliza ion o sus ainable de elopmen . Sus ainabili y. 2023 Ap 18;15(8):6844.
[41] Dwi edi A, S i as a a S, Ag awal D, Jha A, Paul SK. Analyzing he in e - ela ionships o business eco e y
challenges in he manu ac u ing indus y: implica ions o pos -pandemic supply chain esilience. Global Jou nal
o Flexible Sys ems Managemen . 2023 Dec;24(Suppl 1):31-48.
[42] Dau e gne P. AI in he Wild: Sus ainabili y in he Age o A i icial In elligence. MIT P ess; 2020 Sep 15.
[43] Pa hmanaban P, Gnana el BK, Anandan SS, Sa hiyamu hy S. Ad ancing pos -ha es ui handling h ough AI-
based he mal imaging: applica ions, challenges, and u u e ends. Disco e Food. 2023 Dec 21;3(1):27.
[44] Ogbuke N, Yusu YY, Gunaseka an A, Col on N, Ko u i D. Da a-d i en echnologies o global heal hca e p ac ices
and COVID-19: oppo uni ies and challenges. Annals o Ope a ions Resea ch. 2023 Jul 1:1-36.
[45] Vajjhala NR, S ang KD, edi o s. Cybe secu i y in Knowledge Managemen : Cybe h ea s and Solu ions. CRC
P ess; 2025 Aug 7.
[46] Sajadieh SM, Noh SD. F om Simula ion o Au onomy: Re iews o he In eg a ion o A i icial In elligence and
Digi al Twins. In e na ional Jou nal o P ecision Enginee ing and Manu ac u ing-G een Technology. 2025 May
3:1-32.
[47] Legai P. Op imizing Collec ion, T ansmission, and T ans o ma ion o Space Da a o Take up Secu i y Challenges,
Towa d Imp o ed C isis P e en ion and Response. InSpace Da a Managemen 2024 Ma 14 (pp. 127-139).
Singapo e: Sp inge Na u e Singapo e.
