2024
A hybrid approach for integrating micro-satellite images and sensors network-based ground measurements using deep learning for high-resolution prediction of fine particulate matter (PM2.5) over an indian city, lucknow
Jain V, Mukherjee A, Banerjee S, Madhwal S, Bergin M, Bhave P, Carlson D, Jiang Z, Zheng T, Rai P, Tripathi S. A hybrid approach for integrating micro-satellite images and sensors network-based ground measurements using deep learning for high-resolution prediction of fine particulate matter (PM2.5) over an indian city, lucknow. Atmospheric Environment 2024, 338: 120798. DOI: 10.1016/j.atmosenv.2024.120798.Peer-Reviewed Original ResearchFine particulate matterGround-based measurementsPM2.5 concentrationsParticulate matterPredictions of fine particulate matterPrediction mapsAmbient air quality monitoring networkImpact of fine particulate matterAir quality monitoring networkSources of PM2.5Estimate PM2.5 concentrationsPM2.5 exposure assessmentGround measurementsQuality monitoring networkDeterminants of PM2.5Satellite-based estimatesDaily PM2.5High-resolution predictionPM2.5Monitoring networkLowest root mean square errorHuman healthPost-monsoonExposure assessmentRoot mean square errorModel selection to achieve reproducible associations between resting state EEG features and autism
Carson W, Major S, Akkineni H, Fung H, Peters E, Carpenter K, Dawson G, Carlson D. Model selection to achieve reproducible associations between resting state EEG features and autism. Scientific Reports 2024, 14: 25301. PMID: 39455733, PMCID: PMC11511871, DOI: 10.1038/s41598-024-76659-5.Peer-Reviewed Original ResearchConceptsElectroencephalography spectral powerCustom machine learning modelsPredictive performanceGamma powerMachine learning modelsRegularized generalized linear modelModel selectionBiomarker discoverySpectral powerMidline regionMultiple featuresLearning modelsFunctional connectivity featuresPosterior midline regionsRefining Citizen Climate Science: Addressing Preferential Sampling for Improved Estimates of Urban Heat
Calhoun Z, Black M, Bergin M, Carlson D. Refining Citizen Climate Science: Addressing Preferential Sampling for Improved Estimates of Urban Heat. Environmental Science & Technology Letters 2024, 11: 845-850. DOI: 10.1021/acs.estlett.4c00296.Peer-Reviewed Original ResearchUrban heatUrban heat island dataUrban heat islandMeasured air temperatureLong time scalesCitizen science dataHeat islandHeat extremesIsland dataObserved temperatureAir temperatureTime scalesHeat riskPreferential samplingCitizen scientistsScience dataPoor neighborhoodsCitizen science approachNorth CarolinaSpatial statisticsCitizensNeighborhoodNOAALocationNorthDesigning electrodes and electrolytes for batteries by leveraging deep learning
Sui C, Jiang Z, Higueros G, Carlson D, Hsu P. Designing electrodes and electrolytes for batteries by leveraging deep learning. Nano Research Energy 2024, 3: e9120102. DOI: 10.26599/nre.2023.9120102.Peer-Reviewed Original ResearchPrevalence of bias against neurodivergence‐related terms in artificial intelligence language models
Brandsen S, Chandrasekhar T, Franz L, Grapel J, Dawson G, Carlson D. Prevalence of bias against neurodivergence‐related terms in artificial intelligence language models. Autism Research 2024, 17: 234-248. PMID: 38284311, DOI: 10.1002/aur.3094.Peer-Reviewed Original ResearchConceptsObsessive-compulsive disorderGroup of wordsControl sentencesTest wordsAutistic individualsAutismSentencesWordsAverage associationNegative conceptNegative associationStrength of associationLevel of biasPrevalence of biasAssociated with groupsArtificial intelligenceSchizophreniaADHDEncodingBiasAssociationDisordersNeurodiversityDisabilityModel encodingElectome network factors: Capturing emotional brain networks related to health and disease
Walder-Christensen K, Abdelaal K, Klein H, Thomas G, Gallagher N, Talbot A, Adamson E, Rawls A, Hughes D, Mague S, Dzirasa K, Carlson D. Electome network factors: Capturing emotional brain networks related to health and disease. Cell Reports Methods 2024, 4: 100691. PMID: 38215761, PMCID: PMC10832286, DOI: 10.1016/j.crmeth.2023.100691.Peer-Reviewed Original ResearchConceptsCognitive processesEmotional brain networksBrain networksMental disordersFunctional connectomeTranslational biomarkersBrain statesBehavioral contextDisordersHeterogeneous disorderRelevant networksPrevalence of illnessBiologically relevant networksMoodCircuit insightAffectConvergence mechanismConnectomeBrainIllnessNext-generation therapeuticsDisease etiologyTherapeutic developmentIndividualsEstimating the effects of vegetation and increased albedo on the urban heat island effect with spatial causal inference
Calhoun Z, Willard F, Ge C, Rodriguez C, Bergin M, Carlson D. Estimating the effects of vegetation and increased albedo on the urban heat island effect with spatial causal inference. Scientific Reports 2024, 14: 540. PMID: 38177220, PMCID: PMC10766998, DOI: 10.1038/s41598-023-50981-w.Peer-Reviewed Original Research
2023
Estimating Causal Effects using a Multi-task Deep Ensemble.
Jiang Z, Hou Z, Liu Y, Ren Y, Li K, Carlson D. Estimating Causal Effects using a Multi-task Deep Ensemble. Proceedings Of Machine Learning Research 2023, 202: 15023-15040. PMID: 38169983, PMCID: PMC10759931.Peer-Reviewed Original Research
2022
Estimating Potential Outcome Distributions with Collaborating Causal Networks.
Zhou T, Carson W, Carlson D. Estimating Potential Outcome Distributions with Collaborating Causal Networks. Transactions On Machine Learning Research 2022, 2022 PMID: 38187355, PMCID: PMC10769464.Peer-Reviewed Original ResearchConditional average treatment effectPotential outcome distributionsOutcome distributionData generating processAverage treatment effectCausal networksCausal inference approachRestrictive assumptionsTreatment effectsGeneration processAdjustment approachInference approachDecision making processEstimationAssumptionsSemi-synthetic dataDistribution estimationBayesianDeep generative methodsComprehensive decision making processDecisionPredicting emerging chemical content in consumer products using machine learning
Thornton L, Carlson D, Wiesner M. Predicting emerging chemical content in consumer products using machine learning. The Science Of The Total Environment 2022, 834: 154849. PMID: 35405240, DOI: 10.1016/j.scitotenv.2022.154849.Peer-Reviewed Original Research
2021
6.28 Identifying Networks Underlying Sleep Disruption in Autism Spectrum Disorder Mouse Models
Bey A, Walder-Christensen K, Goffinet J, Adamson E, Lanier N, Mague S, Carlson D, Dzirasa K. 6.28 Identifying Networks Underlying Sleep Disruption in Autism Spectrum Disorder Mouse Models. Journal Of The American Academy Of Child & Adolescent Psychiatry 2021, 60: s167. DOI: 10.1016/j.jaac.2021.09.101.Peer-Reviewed Original Research
2018
Video Generation From Text
Li Y, Min M, Shen D, Carlson D, Carin L. Video Generation From Text. Proceedings Of The AAAI Conference On Artificial Intelligence 2018, 32 DOI: 10.1609/aaai.v32i1.12233.Peer-Reviewed Original ResearchGenerative adversarial networkVariational autoencoderGenerative modelConditional generative modelDeep learning modelsInception ScoreVideo generationSmooth videosInput textAdversarial networkImage generationImage filteringStatic featuresBaseline modelVideoLayout structureHybrid frameworkOnline videosExperimental resultsDynamic informationBackground colorGeneration procedureDynamic featuresTextAutoencoder