Sheila Burton
Professional Summary
Sheila Burton is a distinguished marine hydrodynamicist specializing in resistance prediction for biofouling growth on ship hulls. Combining expertise in fluid dynamics, marine biology, and computational modeling, Sheila develops predictive frameworks to quantify how biofouling communities (e.g., barnacles, algae, tube worms) impact vessel performance. Her work enables data-driven hull cleaning schedules, fuel efficiency optimization, and eco-friendly antifouling solutions for the shipping industry.
Core Innovations & Methodologies
1. Biofouling-Hydrodynamics Modeling
Pioneers multiscale simulations integrating:
Macroscale: CFD (Computational Fluid Dynamics) of hull roughness effects (10μm–10mm)
Microscale: Lattice Boltzmann methods for boundary layer-biofilm interactions
Biological Dynamics: Growth rate models based on water temperature, salinity, and nutrient flux
2. Operational Impact Prediction
Quantifies resistance penalties across fouling stages:
Early Stage (1–30 days): 2–8% drag increase from microbial slime
Mature Fouling (6+ months): Up to 40% fuel penalty from hard fouling
Correlates fouling types with CO₂ emissions using IMO DCS (Data Collection System) benchmarks
3. Sustainable Solutions
Develops AI-powered hull monitoring systems using:
Underwater drones with hyperspectral imaging
Acoustic sensors for real-time fouling thickness detection
Advises on non-toxic coating performance through accelerated aging tests
Career Highlights
Led the FoulPredict Consortium, reducing fleet fuel costs by $4.2M/year for a 50-vessel operator.
Patented a dynamic roughness metric adopted by ClassNK and Lloyd’s Register.
Published in Ocean Engineering on barnacle clustering patterns’ hydrodynamic effects.




Fine-tuningGPT-4isessentialforthisresearchbecausepubliclyavailableGPT-3.5
lacksthespecializedcapabilitiesrequiredforanalyzingcomplexbiofoulingand
hydrodynamicdata.Theintricatenatureofbiofoulinggrowth,theneedforprecise
resistanceprediction,andtherequirementforoptimizingshipperformancedemanda
modelwithadvancedadaptabilityanddomain-specificknowledge.Fine-tuningGPT-4
allowsthemodeltolearnfrombiofoulingdatasets,adapttotheuniquechallengesof
thedomain,andprovidemoreaccurateandactionableinsights.Thislevelof
customizationiscriticalforadvancingAI’sroleinmaritimesustainabilityand
ensuringitspracticalutilityinhigh-stakesapplications.
Tobetterunderstandthecontextofthissubmission,Irecommendreviewingmyprevious
workontheapplicationofAIinmaritimeandenvironmentalscience,particularlythe
studytitled"EnhancingShipPerformanceUsingAI-DrivenBiofoulingResistance
Prediction."Thisresearchexploredtheuseofmachinelearningandoptimization
algorithmsforimprovinghydrodynamicefficiency.Additionally,mypaper"Adapting
LargeLanguageModelsforDomain-SpecificApplicationsinMaritimeAI"provides
insightsintothefine-tuningprocessanditspotentialtoenhancemodelperformance
inspecializedfields.