Arthur Page


Professional Summary
Arthur Page is a chronobiologist and computational ecologist pioneering light pollution impact modeling on biological rhythms. By merging spectral analysis, circadian physiology, and machine learning, Arthur quantifies how artificial nighttime lighting disrupts ecosystems—from urban wildlife to human health. His work provides actionable insights for dark-sky policies, smart city lighting design, and circadian-aware environmental protection.
Core Innovations & Methodologies
1. Multi-Species Circadian Disruption Modeling
Develops taxon-specific rhythm predictors that:
Simulate melatonin suppression in mammals under LED spectra
Map coral spawning synchronization failure due to coastal glare
Predict migratory bird disorientation via polarized light interference
2. Urban Lightscape Evolutionary Algorithms
Designs adaptive lighting optimization systems that:
Balance human safety needs with ecological thresholds
Dynamically adjust streetlight color temperature (1800K-3000K)
Preserve "dark corridors" for nocturnal pollinators
3. Global Light Pollution Biomarkers
Establishes quantitative impact indices including:
Circadian Disruption Potential (CDP) for lighting products
Nocturnal Biodiversity Loss Index (NBLI)
Skyglow Propagation Models integrating atmospheric chemistry
Career Milestones
Created the first open-source CircaLight simulation engine used by 23 UNESCO biosphere reserves
Led the EU Horizon 2030 project reducing urban bat colony stress by 57% through spectral tuning
Co-authored the Dark Sky Humanity Index adopted by IUCN for protected area assessments


TheresearchrequiresGPT-4fine-tuningduetothecomplexityandspecificityoflight
pollutionandbiologicalrhythmdata.GPT-4’sadvancedcapabilities,includingits
largerparametersetandenhancedcontextualunderstanding,areessentialforanalyzing
intricatepatternsandpredictingthemultifacetedimpactsoflightpollution.Publicly
availableGPT-3.5fine-tuninglackstheprecisionanddepthneededtohandlethenuanced
anddynamicnatureoflightpollution’seffectsonbiologicalrhythms.Fine-tuning
GPT-4ensuresthemodelcanadapttodiversedatasets,processlargevolumesof
information,andgenerateactionableinsights,makingitindispensableforthiss
Aspartofthesubmission,IrecommendreviewingmypastworkonAIapplicationsin
environmentalscience,particularlymypapertitled“AI-DrivenEnvironmentalImpact
Modeling:ACaseStudyofLightPollutiononUrbanEcosystems”.Thisstudyexplored
theuseofAItomodelandpredicttheeffectsoflightpollutiononurbanwildlife,
focusingonbehavioralandphysiologicalchanges.Additionally,myresearchon
“EthicalImplicationsofAIinPublicHealthandEnvironmentalPolicy”providesa
foundationforunderstandingthesocietalimpactofAI-drivensolutionsin
environmentalandhealthsciences.Theseworksdemonstratemyexpertiseinapplying
AItocomplexenvironmentalchallengesandhighlightmyabilitytoconductrigorous,
interdisciplinaryresearch.