The project’s core ambition involves harnessing artificial intelligence (AI) to transform the way vaccine information is communicated to parents, aiming to dismantle the barriers that fuel hesitancy. With a robust $2.8 million grant from the National Cancer Institute, part of the National Institutes of Health, Nan and her interdisciplinary team are developing a personalized, AI-driven chatbot. This technology is engineered not only to provide accurate health information but to adapt dynamically to parents’ individual concerns, beliefs, and communication preferences in real time—offering a tailored conversational experience that traditional brochures and websites simply cannot match.

HPV vaccination has long struggled with public misconceptions, stigma, and misinformation that discourage uptake. A significant factor behind the reluctance is tied to the vaccine’s association with a sexually transmitted infection, which prompts some parents to believe their children are too young for the vaccine or that vaccination might imply premature engagement with sexual activity. This misconception, alongside a lack of tailored communication strategies, has contributed to persistent disparities in vaccination rates. These disparities are especially pronounced among men, individuals with lower educational attainment, and those with limited access to healthcare, as Professor Cheryl Knott, a public health behavioral specialist at UMD, highlights.

Unlike generic informational campaigns, the AI chatbot leverages cutting-edge natural language processing (NLP) to simulate nuanced human dialogue. However, it does so without succumbing to the pitfalls of generative AI models, such as ChatGPT, which can sometimes produce inaccurate or misleading answers. Instead, the system draws on large language models to generate a comprehensive array of possible responses. These are then rigorously curated and vetted by domain experts before deployment, ensuring that the chatbot’s replies remain factual, reliable, and sensitive to users’ needs. When interacting live, the chatbot analyzes parents’ input in real time, selecting the most appropriate response from this trusted set, thereby balancing flexibility with accuracy.

This “middle ground” model, as described by Philip Resnik, an MPower Professor affiliated with UMD’s Department of Linguistics and Institute for Advanced Computer Studies, preserves the flexibility of conversational AI while instituting “guardrails” to maintain scientific integrity. The approach avoids the rigidity of scripted chatbots that deliver canned, predictable replies; simultaneously, it steers clear of the “wild west” environment of fully generative chatbots, where the lack of control can lead to misinformation. Instead, it offers an adaptive yet responsible communication tool, capable of engaging parents on their terms while preserving public health objectives.

The first phase of this ambitious experiment emphasizes iterative refinement of the chatbot via a user-centered design process. This involves collecting extensive feedback from parents, healthcare providers, and community stakeholders to optimize the chatbot’s effectiveness and cultural sensitivity. Once this foundational work is complete, the team plans to conduct two rigorous randomized controlled trials. The first trial will be conducted online with a nationally representative sample of U.S. parents, compare the chatbot’s impact against traditional CDC pamphlets, and measure differences in vaccine acceptance. The second trial will take place in clinical environments in Baltimore, including pediatric offices, to observe how the chatbot influences decision-making in real-world healthcare settings.

Min Qi Wang, a behavioral health professor participating in the project, emphasizes that “tailored, timely, and actionable communication” facilitated by AI signals a paradigm shift in public health strategies. This shift extends beyond HPV vaccination, as such advanced communication systems possess the adaptability to address other complex public health challenges. By delivering personalized guidance directly aligned with users’ expressed concerns, AI can foster a more inclusive health dialogue that values empathy and relevance, which traditional mass communication methods often lack.

Beyond increasing HPV vaccination rates, the research team envisions broader implications for public health infrastructure. In an era where misinformation can spread rapidly and fear often undermines scientific recommendations, AI-powered tools offer a scalable, responsive mechanism to disseminate trustworthy information quickly. During future pandemics or emergent health crises, such chatbots could serve as critical channels for delivering customized, real-time guidance to diverse populations, helping to flatten the curve of misinformation while respecting individual differences.

The integration of AI chatbots into health communication represents a fusion of technological innovation with behavioral science, opening new horizons for personalized medicine and health education. By engaging users empathetically and responsively, these systems can build trust and facilitate informed decision-making, critical components of successful public health interventions. Professor Nan highlights the profound potential of this marriage between AI and public health communication by posing the fundamental question: “Can we do a better job with public health communication—with speed, scale, and empathy?” Project outcomes thus far suggest an affirmative answer.

As the chatbot advances through its pilot phases and into clinical trials, the research team remains committed to maintaining a rigorous scientific approach, ensuring that the tool’s recommendations align with the highest standards of evidence-based medicine. This careful balance between innovation and reliability is essential to maximize public trust and the chatbot’s ultimate impact on vaccine uptake. Should these trials demonstrate efficacy, the model could serve as a blueprint for deploying AI-driven communication tools across various domains of health behavior change.

Moreover, the collaborative nature of this project—bringing together communication experts, behavioral scientists, linguists, and medical professionals—illustrates the importance of interdisciplinary efforts in addressing complex health challenges. Each field contributes unique insights: linguistic analysis enables nuanced conversation design, behavioral science guides motivation and persuasion strategies, and medical expertise ensures factual accuracy and clinical relevance. This holistic framework strengthens the chatbot’s ability to resonate with diverse parent populations and to overcome entrenched hesitancy.

In conclusion, while HPV vaccines represent a major advancement in cancer prevention, their potential remains underutilized due to deeply embedded hesitancy fueled by stigma and misinformation. Leveraging AI-driven, personalized communication stands as a promising strategy to bridge this gap. The University of Maryland’s innovative chatbot project underscores the use of responsible artificial intelligence to meet parents where they are, addressing their unique concerns with empathy and scientific rigor. This initiative not only aspires to improve HPV vaccine uptake but also to pave the way for AI’s transformative role in future public health communication efforts.

Subject of Research: Artificial intelligence-enhanced communication to improve HPV vaccine uptake among parents.

Article Title: Transforming Vaccine Communication: AI Chatbots Target HPV Vaccine Hesitancy in Parents

News Publication Date: Information not provided in the source content.

Web References:
https://sph.umd.edu/people/cheryl-knott
https://sph.umd.edu/people/min-qi-wang

Image Credits: Credit: University of Maryland (UMD)

Keywords: Vaccine research, Science communication

Lightning, a spectacular electrical discharge occurring during thunderstorms, is known to generate nitrogen oxides (NOx), a group of reactive gases traditionally associated with human pollution sources such as vehicle exhaust. These nitrogen oxides play a crucial role in atmospheric chemistry by participating in ozone formation and the breakdown of greenhouse gases. However, pinpointing the precise contribution of lightning to atmospheric NOx levels has long been a challenging endeavor due to the fleeting and sporadic nature of lightning strikes and their occurrence high above surface measurement capabilities.

In an innovative experiment conducted over several days in late June 2025, Professor Kenneth Pickering and Associate Research Scientist Dale Allen of the University of Maryland Atmospheric and Oceanic Science Department leveraged data from NASA’s Tropospheric Emissions: Monitoring of Pollution (TEMPO) satellite. Launched in 2023, TEMPO is uniquely equipped to monitor air pollutants across North America from geostationary orbit approximately 22,000 miles above the Earth’s surface. Critically, the instrument’s advanced sensors enabled measurements of nitrogen dioxide concentrations at 10-minute intervals, dramatically increasing temporal resolution compared to the conventional hourly readings.

This unprecedented temporal acuity allowed the researchers to capture the rapid evolution of thunderstorms, which commonly intensify and dissipate within an hour. By cross-referencing TEMPO’s observations with lightning flash data from NOAA’s Geostationary Lightning Mapper, Pickering and Allen could correlate specific lightning events with spikes in atmospheric nitrogen dioxide in near real-time. These refined snapshots yield powerful insights into the immediate chemical aftermath of lightning strokes, revealing patterns previously obscured within hourly or daily aggregated data.

Fundamentally, lightning initiates powerful chemical transformations within the storm environment. The extreme heat generated by a lightning bolt—temperatures soaring up to 30,000 Kelvin—breaks the strong bonds of nitrogen (N₂) and oxygen (O₂) molecules, causing them to recombine into nitrogen oxides. While these NOx molecules contribute to the production of tropospheric ozone, which is a greenhouse gas, their formation altitude matters deeply. Lightning-produced nitrogen oxides form high in the atmosphere, where they catalyze ozone production far more efficiently than the same compounds generated at the surface through fossil fuel combustion.

Quantitatively, lightning accounts for approximately 10 to 15 percent of global nitrogen oxide emissions, a significant natural source amid predominantly anthropogenic contributions. The high-altitude genesis of these oxides results in ozone accumulation in atmospheric layers that exert a pronounced warming effect by absorbing infrared radiation. Occasionally, turbulent atmospheric motions transport lightning-derived ozone downward, adversely impacting surface air quality hundreds of miles from the storm origin. This is especially consequential during summer months when enhanced ultraviolet radiation and higher temperatures amplify photochemical ozone production.

Intriguingly, lightning’s atmospheric influence extends beyond pollution generation; it also sets in motion cleansing processes. The powerful electrical discharges lead to the formation of hydroxyl radicals—highly reactive molecules that act as the atmosphere’s “detergent” by decomposing methane and other potent greenhouse gases as well as lingering organic compounds. Understanding this dualistic chemical role of lightning—both as a pollutant source and an atmospheric cleanser—is essential for framing its net effect on climate and air quality.

Estimations from past studies suggest that any individual lightning flash produces roughly 250 moles of nitrogen oxides, though this figure carries considerable uncertainty and varies widely with flash intensity and storm conditions. The University of Maryland’s TEMPO experiment aims to reduce this uncertainty by quantifying NOx production across a spectrum of lightning intensities. Early evidence from the study indicates that more intense storms may produce shorter, less NOx-rich flashes, a finding that challenges conventional assumptions and has profound implications for modeling lightning’s role in the atmospheric nitrogen budget.

The broader implications of this research stretch into climate science and public health domains alike. Given that lightning-generated NOx can travel vast distances via atmospheric currents, understanding its spatial distribution is critical for anticipating shifts in regional air quality. For communities situated in mountainous areas, such as Colorado, lightning-induced ozone pollution at altitude has tangible health ramifications, exacerbating respiratory conditions during storm seasons. Improved high-frequency monitoring data promise to refine meteorological models used to predict such air quality impacts more accurately.

Moreover, the capacity to differentiate between nitrogen oxides originating from natural lightning versus human activities equips scientists to better evaluate the human footprint on atmospheric composition. This distinction is vital for calibrating climate models and implementing regulatory policies aimed at pollution mitigation. The wealth of high-temporal-resolution data provided by TEMPO can inform simulations that forecast the response of atmospheric chemistry to increasing storm intensity in an era marked by climate change-driven weather extremes.

Professor Pickering emphasizes that the concerted use of satellite treasure troves and lightning mapping technology exemplifies a new era in atmospheric research—one where real-time, granular data enables researchers to dissect complex environmental processes as they unfold. Dr. Allen concurs, noting that “better data leads to better predictions and ultimately better strategies to protect human health and the environment from the intertwined threats of natural and anthropogenic pollution.”

As the University of Maryland team continues to analyze TEMPO’s initial datasets, the science community eagerly anticipates further revelations regarding lightning’s nuanced chemical footprint. This research not only advances fundamental understanding of storm chemistry but also holds promise for practical advancements in weather forecasting, climate modeling, and air quality management. Through such cutting-edge investigations, the fleeting brilliance of lightning is transformed from a meteorological curiosity into a key player in Earth’s atmospheric system.

The TEMPO mission exemplifies a pioneering partnership between NASA and the Smithsonian Astrophysical Observatory, with daily instrument operations and data processing managed by Harvard University’s Center for Astrophysics. This collaboration underscores the scientific rigor and interdisciplinary approach necessary to dissect the fleeting, powerful phenomena embedded within Earth’s atmospheric complexity.

Subject of Research: Atmospheric chemistry and physics; lightning-induced nitrogen oxide production; air quality impacts of thunderstorms

Article Title: High-Frequency Satellite Observations Unveil Lightning’s Impact on Atmospheric Pollution and Climate

News Publication Date: June 2025

Web References: NASA TEMPO mission (https://science.nasa.gov/mission/tempo/), University of Maryland Atmospheric and Oceanic Science Department (https://aosc.umd.edu/people/pickering-kenneth)

Image Credits: Kenneth Pickering, University of Maryland

Keywords: Lightning, Atmospheric physics, Atmosphere, Atmospheric chemistry, Atmospheric pressure, Cloud physics, Meteorology, Climatology, Earth atmosphere, Atmospheric gases, Atmospheric nitrogen, Greenhouse gases, Humidity, Atmospheric methane, Weather, Extreme weather events, Precipitation, Storms, Rain, Weather forecasting, Weather simulations

This landmark achievement is the product of a collaborative effort among the University of Maryland, Baltimore County (UMBC), the Environmental Protection Agency’s Chesapeake Bay Program (CBP), and the Chesapeake Conservancy (CC), bringing together academic expertise, government oversight, and nonprofit stewardship. UMBC alumni actively participated within the EPA and CC teams, ensuring a continuation of knowledge and innovation across institutional boundaries. The new data set is not merely an improvement in quantity but embodies a qualitative breakthrough made possible by employing novel artificial intelligence (AI) techniques alongside cutting-edge remote sensing technologies.

At the core of this initiative lies the utilization of high-resolution Light Detection and Ranging (LiDAR) technology, a remote sensing method that utilizes laser pulses from airborne platforms to generate densely detailed, three-dimensional elevation models of terrain surfaces. The centimeter-scale precision of LiDAR data allows researchers to discern subtle topographical features otherwise undetectable through conventional surveying methods. Such detail is indispensable when charting intricate water networks, especially in complex and human-altered landscapes where stream channels may be obscured or distorted.

Processing this voluminous LiDAR data was made feasible through UMBC’s High-Performance Computing Facility (HPCF), where sophisticated AI algorithms, developed using computer vision methodologies, automated the identification and classification of stream channels across the entire watershed. This automation reduced what historically required years of painstaking manual mapping down to only two weeks of computational work. The AI models leveraged pattern recognition to differentiate genuine stream channels from other hydrologically irrelevant features such as detention ponds, swales, or agricultural furrows—an initial challenge that necessitated iterative refinement of the algorithms.

Validation of the AI-generated maps demonstrates remarkable accuracy, with a 94 percent match rate for streams that were previously documented and between 67 and 82 percent accuracy for newly identified streams. These estimates were rigorously cross-checked against multiple datasets, including aerial imagery and LiDAR-derived topographic maps. Manual verification efforts, led by Chesapeake Conservancy’s senior geospatial technical lead David Saavedra, entailed detailed assessment of more than 7,000 individual stream reaches, underscoring the reliability and robustness of the new hydrography data.

One of the most revolutionary aspects of the dataset is its ability to provide not just spatial coordinates but also morphometric estimates for each stream channel, including width and depth variations along their entire lengths. Such dimensionality affords ecologists and resource managers an enhanced understanding of hydrological connectivity and habitat quality, facilitating more precise modeling of water flow, sediment transport, and nutrient cycling within the watershed’s ecosystems. This granular insight is essential for safeguarding blue crabs, migrating shorebirds, and numerous other species dependent on the region’s aquatic habitats.

The expanded stream network maps yield a tenfold improvement in resolution, advancing from the traditional USGS cartographic scale of 1:24,000 to a remarkable 1:2,400 scale, where each pixel corresponds to a square meter on the landscape. Importantly, these hydrographic data align seamlessly with concurrently released land cover maps developed at the same spatial resolution, enabling integrative analyses that couple hydrology with land use practices. Such synergistic datasets have the potential to illuminate previously hidden relationships between terrestrial activities and water quality outcomes.

Environmental organizations and government bodies are already expressing excitement about the implications of these maps for restoration planning and environmental policy enforcement. Targeted interventions such as streamside reforestation and erosion control can now be guided by high-precision data identifying areas of severe channel incision or bank steepness—factors closely linked to sedimentation and pollutant filtering inefficiencies. Likewise, agricultural and urban planners can incorporate this data into decisions aimed at reducing runoff impacts, managing flood risks, and protecting fragile wildlife habitats.

UMBC geography professor Matthew Baker emphasizes the transformative nature of the mapping process, noting how the high-resolution depiction captures the profound extent of human modifications to natural water pathways. Such visualizations allow stakeholders to recognize the full scope of anthropogenic effects on watershed hydrology and strategize mitigation efforts accordingly. Moreover, Baker highlights that this project marks the first time that AI and LiDAR have been successfully combined for automated, large-scale stream mapping, introducing efficiencies that could be replicated in watersheds worldwide.

The technological sophistication underpinning this project ensures that updates can be efficiently incorporated as new data becomes available, meaning that the maps will evolve dynamically alongside environmental change and land use trends. Beyond the Chesapeake Bay, this AI-powered workflow represents a scalable model for hydrography mapping that can accelerate scientific discovery and resource management on a global scale, particularly in regions where traditional mapping remains cost-prohibitive or logistically challenging.

Geographer Labeeb Ahmed, representing the EPA’s Chesapeake Bay Program, underscores the importance of consistent, high-resolution hydrographic data for achieving critical conservation goals outlined in the Chesapeake Bay Watershed Agreement. These goals include accurate mapping of forest buffers, wetlands, and species habitats, all fundamental for maintaining stream health and biodiversity. Ahmed anticipates that the release of this dataset will catalyze a range of new research endeavors and practical applications, fostering innovation in ecosystem restoration and policy formulation.

The seamless integration of artificial intelligence with high-fidelity LiDAR inputs has opened a new frontier in hydrographic science, bridging data density with computational power. The approach circumvents the extensive manual labor traditionally associated with stream mapping, permitting rapid, repeatable, and scalable assessments of hydrological networks. As a result, researchers and practitioners can now visualize and interpret the fluid connections that sculpt landscapes with greater clarity and confidence than ever before. This dataset is poised not only to transform environmental stewardship in the Chesapeake Bay Watershed but also to serve as a benchmark for hydrological studies worldwide.

In conclusion, the release of the Hyper-Resolution Hydrography Data heralds a paradigm shift in watershed analysis, offering a tool of unprecedented accuracy, resolution, and scope. By illuminating the intricate web of streams flowing through the Chesapeake Bay region, this dataset empowers diverse stakeholders—from ecologists to urban planners—to make informed decisions that balance human needs with ecosystem integrity. As the natural and built environments continue to evolve, having access to such cutting-edge hydrographic information will be indispensable in navigating the multifaceted challenges of water resource management and ecological resilience.

Subject of Research: Hydrography mapping of the Chesapeake Bay Watershed using AI and LiDAR technology

Article Title: New AI-Driven High-Resolution Stream Maps Reveal Vastly Expanded Chesapeake Bay Watershed Hydrography

News Publication Date: Information not provided

Web References:
– https://www.sciencebase.gov/catalog/item/66d72996d34eef5af66ca61b
– https://ges.umbc.edu/baker/
– https://hpcf.umbc.edu/
– https://www.chesapeakebay.net/
– https://www.chesapeakeconservancy.org/

Image Credits: Courtesy of Matthew Baker

Keywords: Chesapeake Bay Watershed, hydrography, AI-supported stream mapping, LiDAR, high-resolution data, environmental restoration, hydrology, geographic information systems, artificial intelligence, remote sensing, stream networks, watershed management