Scholars@Duke
David Carlson

David Carlson

Associate Professor of Civil and Environmental Engineering
Civil and Environmental Engineering
david.carlson@duke.edu
Hudson Hall, Durham, NC 27705

Selected Publications

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

Journal Article Atmospheric Environment · December 1, 2024 The detrimental impacts of fine particulate matter (PM2.5) on human health, climate, ecosystems, crops, and building materials are well-established. However, there remain unresolved inquiries regarding the precise location of the sources of PM2.5. This stu ... Full text Cite

Model selection to achieve reproducible associations between resting state EEG features and autism.

Journal Article Sci Rep · October 25, 2024 A concern in the field of autism electroencephalography (EEG) biomarker discovery is their lack of reproducibility. In the present study, we considered the problem of learning reproducible associations between multiple features of resting state (RS) neural ... Full text Link to item Cite

Refining Citizen Climate Science: Addressing Preferential Sampling for Improved Estimates of Urban Heat

Journal Article Environmental Science and Technology Letters · August 13, 2024 Studies of urban heat are often limited by their ability to measure air temperature; data are collected either at a few locations over time or at many locations at one point in time. Citizen science approaches to observing temperature provide a way to over ... Full text Cite

A widespread electrical brain network encodes anxiety in health and depressive states.

Journal Article bioRxiv · June 30, 2024 In rodents, anxiety is charactered by heightened vigilance during low-threat and uncertain situations. Though activity in the frontal cortex and limbic system are fundamental to supporting this internal state, the underlying network architecture that integ ... Full text Link to item Cite

Designing electrodes and electrolytes for batteries by leveraging deep learning

Journal Article Nano Research Energy · June 1, 2024 High-performance batteries are poised for electrification of vehicles and therefore mitigate greenhouse gas emissions, which, in turn, promote a sustainable future. However, the design of optimized batteries is challenging due to the nonlinear governing ph ... Full text Cite

Prevalence of bias against neurodivergence-related terms in artificial intelligence language models.

Journal Article Autism Res · February 2024 Given the increasing role of artificial intelligence (AI) in many decision-making processes, we investigate the presence of AI bias towards terms related to a range of neurodivergent conditions, including autism, ADHD, schizophrenia, and obsessive-compulsi ... Full text Link to item Cite

Electome network factors: Capturing emotional brain networks related to health and disease.

Journal Article Cell Rep Methods · January 22, 2024 Therapeutic development for mental disorders has been slow despite the high worldwide prevalence of illness. Unfortunately, cellular and circuit insights into disease etiology have largely failed to generalize across individuals that carry the same diagnos ... Full text Link to item Cite

Estimating the effects of vegetation and increased albedo on the urban heat island effect with spatial causal inference.

Journal Article Scientific reports · January 2024 The urban heat island effect causes increased heat stress in urban areas. Cool roofs and urban greening have been promoted as mitigation strategies to reduce this effect. However, evaluating their efficacy remains a challenge, as potential temperature redu ... Full text Open Access Cite

Identifying Waste Burning Plumes Using High-Resolution Satellite Imagery and Machine Learning: A Case Study in the Maldives

Journal Article Environmental Science and Technology Letters · August 8, 2023 A rapid increase in municipal solid waste generation has far outpaced resources to manage waste in many developing countries, resulting in the burning of trash in designated landfills or public places, the release of harmful air pollutants, and exposure of ... Full text Cite

Estimating a brain network predictive of stress and genotype with supervised autoencoders.

Journal Article J R Stat Soc Ser C Appl Stat · August 2023 Targeted brain stimulation has the potential to treat mental illnesses. We develop an approach to help design protocols by identifying relevant multi-region electrical dynamics. Our approach models these dynamics as a superposition of latent networks, wher ... Full text Link to item Cite

Estimating Causal Effects using a Multi-task Deep Ensemble.

Conference Proceedings of machine learning research · July 2023 A number of methods have been proposed for causal effect estimation, yet few have demonstrated efficacy in handling data with complex structures, such as images. To fill this gap, we propose Causal Multi-task Deep Ensemble (CMDE), a novel framework that le ... Cite

Prenatal environmental stressors impair postnatal microglia function and adult behavior in males.

Journal Article Cell Rep · August 2, 2022 Gestational exposure to environmental toxins and socioeconomic stressors is epidemiologically linked to neurodevelopmental disorders with strong male bias, such as autism. We model these prenatal risk factors in mice by co-exposing pregnant dams to an envi ... Full text Link to item Cite

Predicting emerging chemical content in consumer products using machine learning.

Journal Article The Science of the total environment · August 2022 Chemical ingredients in consumer products are continually changing. To understand our exposure to chemicals and their consequent risk, we need to know their concentrations in products, or chemical weight fractions. Unfortunately, manufacturers rarely repor ... Full text Cite

Improving spatial variation of ground-level PM2.5 prediction with contrastive learning from satellite imagery

Journal Article Science of Remote Sensing · June 1, 2022 Convolutional Neural Networks (CNNs) are a promising technique to predict highly localized fine particulate matter (i.e., PM2.5 levels) based on high-resolution satellite imagery. Unfortunately, CNNs typically require large amounts of supervised data to pe ... Full text Cite

Brain-wide electrical dynamics encode individual appetitive social behavior.

Journal Article Neuron · May 18, 2022 The architecture whereby activity across many brain regions integrates to encode individual appetitive social behavior remains unknown. Here we measure electrical activity from eight brain regions as mice engage in a social preference assay. We then use ma ... Full text Link to item Cite

Learning to Weight Filter Groups for Robust Classification

Conference Proceedings - 2022 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022 · January 1, 2022 In many real-world tasks, a canonical 'big data' problem is created by combining data from several individual groups or domains. Because test data will likely come from a new group of data, we want to utilize the grouped structure of our training data to e ... Full text Cite

Supervising the Decoder of Variational Autoencoders to Improve Scientific Utility.

Journal Article IEEE transactions on signal processing : a publication of the IEEE Signal Processing Society · January 2022 Probabilistic generative models are attractive for scientific modeling because their inferred parameters can be used to generate hypotheses and design experiments. This requires that the learned model provides an accurate representation of the input data a ... Full text Cite

Directed Spectral Measures Improve Latent Network Models Of Neural Populations.

Journal Article Adv Neural Inf Process Syst · December 2021 Systems neuroscience aims to understand how networks of neurons distributed throughout the brain mediate computational tasks. One popular approach to identify those networks is to first calculate measures of neural activity (e.g. power spectra) from multip ... Link to item Cite

6.28 Identifying Networks Underlying Sleep Disruption in Autism Spectrum Disorder Mouse Models

Conference Journal of the American Academy of Child & Adolescent Psychiatry · October 2021 Full text Cite

Geometric deep learning enables 3D kinematic profiling across species and environments.

Journal Article Nat Methods · May 2021 Comprehensive descriptions of animal behavior require precise three-dimensional (3D) measurements of whole-body movements. Although two-dimensional approaches can track visible landmarks in restrictive environments, performance drops in freely moving anima ... Full text Link to item Cite

Local PM2.5 hotspot detector at 300 m resolution: A random forest-convolutional neural network joint model jointly trained on satellite images and meteorology

Journal Article Remote Sensing · April 1, 2021 Satellite-based rapid sweeping screening of localized PM2.5 hotspots at fine-scale local neighborhood levels is highly desirable. This motivated us to develop a random forest- convolutional neural network-local contrast normalization (RF-CNN-LCN) pipeline ... Full text Cite

Estimating Uncertainty Intervals from Collaborating Networks

Journal Article Journal of Machine Learning Research · 2021 Link to item Cite

AugmentedPCA: A Python Package of Supervised and Adversarial Linear Factor Models

Journal Article NeurIPS Workshop on Learning Meaningful Representations of Life · 2021 Open Access Link to item Cite

Machine learning does not improve upon traditional regression in predicting outcomes in atrial fibrillation: an analysis of the ORBIT-AF and GARFIELD-AF registries.

Conference Europace · November 1, 2020 AIMS: Prediction models for outcomes in atrial fibrillation (AF) are used to guide treatment. While regression models have been the analytic standard for prediction modelling, machine learning (ML) has been promoted as a potentially superior methodology. W ... Full text Link to item Cite

Attention-Based Network for Weak Labels in Neonatal Seizure Detection.

Journal Article Proc Mach Learn Res · August 2020 Seizures are a common emergency in the neonatal intesive care unit (NICU) among newborns receiving therapeutic hypothermia for hypoxic ischemic encephalopathy. The high incidence of seizures in this patient population necessitates continuous electroencepha ... Link to item Cite

Relative Average Look Duration and its Association with Neurophysiological Activity in Young Children with Autism Spectrum Disorder.

Journal Article Sci Rep · February 5, 2020 Autism Spectrum Disorder (ASD) is characterized by early attentional differences that often precede the hallmark symptoms of social communication impairments. Development of novel measures of attentional behaviors may lead to earlier identification of chil ... Full text Link to item Cite

Gaussian-Process-Based Dynamic Embedding for Textual Networks

Conference AAAI Conference on Artificial Intelligence · 2020 Cite

Gaussian process regression model for dynamically calibrating and surveilling a wireless low-cost particulate matter sensor network in Delhi

Journal Article Atmospheric Measurement Techniques · September 26, 2019 Wireless low-cost particulate matter sensor networks (WLPMSNs) are transforming air quality monitoring by providing particulate matter (PM) information at finer spatial and temporal resolutions. However, large-scale WLPMSN calibration and maintenance remai ... Full text Cite

Storygan: A sequential conditional gan for story visualization

Conference Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition · June 1, 2019 In this work, we propose a new task called Story Visualization. Given a multi-sentence paragraph, the story is visualized by generating a sequence of images, one for each sentence. In contrast to video generation, story visualization focuses less on the co ... Full text Cite

Continuing progress of spike sorting in the era of big data

Journal Article Current opinion in neurobiology · 2019 Cite

On Target Shift in Adversarial Domain Adaptation

Conference International Conference on Artificial Intelligence and Statistics · 2019 Cite

Field evaluation of low-cost particulate matter sensors in high-and low-concentration environments

Journal Article Atmospheric Measurement Techniques · August 22, 2018 Low-cost particulate matter (PM) sensors are promising tools for supplementing existing air quality monitoring networks. However, the performance of the new generation of low-cost PM sensors under field conditions is not well understood. In this study, we ... Full text Cite

Brain-wide Electrical Spatiotemporal Dynamics Encode Depression Vulnerability.

Journal Article Cell · March 22, 2018 Brain-wide fluctuations in local field potential oscillations reflect emergent network-level signals that mediate behavior. Cracking the code whereby these oscillations coordinate in time and space (spatiotemporal dynamics) to represent complex behaviors w ... Full text Link to item Cite

A Shared Vision for Machine Learning in Neuroscience.

Journal Article J Neurosci · February 14, 2018 With ever-increasing advancements in technology, neuroscientists are able to collect data in greater volumes and with finer resolution. The bottleneck in understanding how the brain works is consequently shifting away from the amount and type of data we ca ... Full text Link to item Cite

Video Generation From Text

Conference AAAI Conference on Artificial Intelligence · 2018 Cite

Extracting relationships by multi-domain matching

Conference Advances in Neural Information Processing Systems · 2018 Cite

Dynamically Timed Stimulation of Corticolimbic Circuitry Activates a Stress-Compensatory Pathway.

Journal Article Biol Psychiatry · December 15, 2017 BACKGROUND: The prefrontal cortex plays a critical role in regulating emotional behaviors, and dysfunction of prefrontal cortex-dependent networks has been broadly implicated in mediating stress-induced behavioral disorders including major depressive disor ... Full text Link to item Cite

Stochastic Bouncy Particle Sampler

Conference International Conference on Machine Learning · 2017 Cite

YASS: Yet Another Spike Sorter

Journal Article Advances in Neural Information Processing Systems · 2017 Cite

Targeting EEG/LFP Synchrony with Neural Nets

Journal Article Advances in Neural Information Processing Systems · 2017 Cite

Cross-Spectral Factor Analysis

Journal Article Advances in Neural Information Processing Systems · 2017 Cite

Targeting EEG/LFP synchrony with neural nets

Conference Advances in Neural Information Processing Systems · January 1, 2017 We consider the analysis of Electroencephalography (EEG) and Local Field Potential (LFP) datasets, which are "big" in terms of the size of recorded data but rarely have sufficient labels required to train complex models (e.g., conventional deep learning me ... Cite

Cross-spectral factor analysis

Conference Advances in Neural Information Processing Systems · January 1, 2017 In neuropsychiatric disorders such as schizophrenia or depression, there is often a disruption in the way that regions of the brain synchronize with one another. To facilitate understanding of network-level synchronization between brain regions, we introdu ... Cite

Dysregulation of Prefrontal Cortex-Mediated Slow-Evolving Limbic Dynamics Drives Stress-Induced Emotional Pathology.

Journal Article Neuron · July 20, 2016 Circuits distributed across cortico-limbic brain regions compose the networks that mediate emotional behavior. The prefrontal cortex (PFC) regulates ultraslow (<1 Hz) dynamics across these networks, and PFC dysfunction is implicated in stress-related illne ... Full text Link to item Cite

Preconditioned stochastic gradient Langevin dynamics for deep neural networks

Conference AAAI Conference on Artificial Intelligence · 2016 Cite

Partition functions from rao-blackwellized tempered sampling

Conference 33rd International Conference on Machine Learning, ICML 2016 · January 1, 2016 Partition functions of probability distributions are important quantities for model evaluation and comparisons. We present a new method to compute partition functions of complex and multi-modal distributions. Such distributions are often sampled using simu ... Open Access Cite

Neuroprosthetic decoder training as imitation learning

Journal Article PLoS computational biology · 2016 Open Access Cite

Learning sigmoid belief networks via Monte Carlo expectation maximization

Conference Artificial Intelligence and Statistics · 2016 Cite

Bridging the gap between stochastic gradient MCMC and stochastic optimization

Conference Artificial Intelligence and Statistics · 2016 Cite

Deep temporal sigmoid belief networks for sequence modeling

Journal Article Advances in Neural Information Processing Systems · 2015 Cite

Learning deep sigmoid belief networks with data augmentation

Conference Artificial Intelligence and Statistics · 2015 Cite

Stochastic spectral descent for restricted Boltzmann machines

Conference Artificial Intelligence and Statistics · 2015 Cite

GP kernels for cross-spectrum analysis

Conference Advances in neural information processing systems · 2015 Cite

Preconditioned spectral descent for deep learning

Conference Advances in Neural Information Processing Systems · 2015 Cite

Analysis of Brain States from Multi-Region LFP Time-Series

Conference Advances in Neural Information Processing Systems · 2014 Cite

On the Relationship Between LFP & Spiking Data

Conference Advances in Neural Information Processing Systems · 2014 Cite

Latent Gaussian models for topic modeling

Conference Artificial Intelligence and Statistics · 2014 Cite

Designed measurements for vector count data

Journal Article Advances in neural information processing systems · 2013 Cite

Real-time inference for a gamma process model of neural spiking

Journal Article Advances in Neural Information Processing Systems · 2013 Cite

Detection of viruses via statistical gene expression analysis.

Journal Article IEEE Trans Biomed Eng · March 2011 We develop a new bayesian construction of the elastic net (ENet), with variational bayesian analysis. This modeling framework is motivated by analysis of gene expression data for viruses, with a focus on H3N2 and H1N1 influenza, as well as Rhino virus and ... Full text Link to item Cite

On the analysis of multi-channel neural spike data

Conference Advances in Neural Information Processing Systems · 2011 Cite