A data scientist at the University of �鶹��ý at Hilo has launched a year-long project to explore how artificial intelligence (AI) can help scientists, students, emergency managers, and the public better understand natural hazards such as volcanic activity, wildfires, tsunamis, and other disasters. The main idea of the project, named VULCAN-AI, is to use AI as a support tool for hazard intelligence and public communication.

“During a disaster, there is often a huge amount of information coming in at once: live camera feeds, satellite images, sensor readings, weather data, maps and scientific reports,” said Sukhwa Hong, UH Hilo associate professor of and who specializes in AI for business analytics. “VULCAN-AI is designed to help organize that information and turn it into clear, plain-language summaries that people can understand.”

With funding from the National Science Foundation (NSF)’s throughout the next year, Hong plans to build and test the AI-agent system using live �鶹��ý Island volcano feeds, environmental data, and example volcanic and wildfire scenarios.

He emphasizes that the goal of the project is not to replace scientists or official emergency alerts. Instead, the goal is to show how AI can responsibly support human experts by helping detect changes, organize information, and explain what is happening more clearly to the public.

“What excites me most is that this project shows a positive use of AI,” said Hong. “AI is often discussed as a threat, but when used carefully and responsibly, it can help communities, support science, improve emergency communication, respect local knowledge, and give students hands-on experience with technology that serves the public good.”

He plans to hire UH Hilo students through NSF’s undergraduate research program to work with him on AI testing, live-feed monitoring, data preparation, visualization and public communication.

—By Susan Enright, UH Hilo Stories

The University of �鶹��ý at Hilo is reshaping how students learn about artificial intelligence (AI)—starting this fall.

The will launch a new AI concentration within its . A new AI certificate will also open to students from all majors. New courses will follow, focused on using AI in business, science and public service.

The shift responds to a clear need in today’s workforce.

“AI is no longer a niche or emerging technology,” said Sukhwa Hong, associate professor of and business administration. “It’s already embedded in how work gets done across almost every field.”

Students will learn how to work with data, evaluate AI-generated results and apply these tools responsibly.

AI confidence

The new program is being led by Hong and Chenbo Shi, an assistant professor of quantitative business analysis, who are working closely with faculty in business, data science and computer science to support the new offerings.

“We want students to graduate knowing that AI will not replace them,” Hong said. “But people who know how to integrate AI into their work will have a clear advantage.”

The AI certificate is designed to be accessible. It welcomes students from education, the arts, social sciences and beyond.

New courses

A new introductory course will teach students how to guide AI tools, evaluate results and communicate findings. A community-based project will tie those skills to real-world issues.

Upper-division courses have also been updated. They now include AI-supported analysis, prediction and decision-making, with a strong focus on ethics.

“Employers aren’t looking for AI specialists in every role,” Hong said. “They’re looking for professionals who can use AI effectively in context.”

—by Susan Enright

For more go to .

While life expectancy across the U.S. declined significantly during the COVID-19 pandemic, a new study led by researchers at the University of �鶹��ý and the found that �鶹��ý experienced a smaller decline compared to national trends.

Yan Yan Wu, Michael Phillips and Kathryn L. Braun from the UH ��å�ԴDz� , along with Lance Ching and Claire Prieto from the , found that life expectancy in �鶹��ý declined by 1.4 years, from 82.1 in 2019 to 80.7 in 2021. Nationwide, the decline over the same period was 2.4 years, from 78.8 to 76.4. Their findings were published in the .

“The smaller magnitude and delayed timing of �鶹��ý’s decline may reflect the state’s geographic isolation and early implementation of public health interventions,” said Wu, the study’s lead author. “In 2022, life expectancy partially rebounded by 0.5 years in �鶹��ý and by 0.9 years nationally, with �鶹��ý remaining about four years higher than the U.S. average throughout the pandemic.”

“�鶹��ý ranks among the top U.S. states for COVID-19 vaccination coverage. By May 2023, data reported by the U.S. Centers for Disease Control and Prevention (CDC) showed that more than 90% of residents received at least one dose and more than 80% were considered fully vaccinated with the primary COVID-19 vaccine series,” said Ching, epidemiologist with the DOH Chronic Disease Prevention & Health Promotion Division. “These high vaccination levels—reached over the course of the pandemic—helped delay the peak of COVID-19 mortality in �鶹��ý by approximately six months compared to the national average and contributed to the state’s distinction of having the lowest age-adjusted COVID-19 death rate in the country.”

Key Findings

• Life expectancy in �鶹��ý remained stable from 2018 to 2020 (82.3, 82.1, and 82.0 years, respectively).
• A decline occurred in 2021 to 80.7 years, followed by a partial rebound to 81.2 years in 2022.
• Among males, life expectancy fell from 79.2 years in 2018 to 77.5 years in 2021, then rose to 78.2 years in 2022.
• Among females, life expectancy fell from 85.4 years in 2018 to 84.0 years in 2021, rebounding to 84.4 years in 2022.
• The gap between female and male life expectancy widened to 6.5 years in 2021 before narrowing to 6.2 years in 2022—the same as in 2019.
• Despite these fluctuations, �鶹��ý‘s overall decline in life expectancy remained less severe than the U.S. average throughout the pandemic.

Policy Implications

The researchers note that �鶹��ý‘s better outcomes underscore the effectiveness of early public health interventions, strong community engagement, and high vaccine uptake. They recommend that future policies build on these strengths by investing in rapid-response infrastructure and maintaining high vaccination coverage to better protect vulnerable communities during future disease outbreaks.

In partnership with the �鶹��ý Department of Health (DOH) and RSM US, the University of �鶹��ý at ����ԴDz� is using data and machine learning tools to identify adverse events and enhance services for �鶹��ý residents with intellectual and developmental disabilities.

Through the Social Science Research Institute’s (OEAIDD), UH researchers are working on a new dashboard that integrates Medicaid claims and case–management data. The tool gives staff a clearer picture of potential unreported adverse events—such as injuries or hospitalizations—and supports faster, more informed decision making across DOH&s (DDD) programs for 3,600 participants statewide.

…we’re helping the state build a more responsive system of care.
—Jack Barile

Historically, under–reporting of adverse events has posed a major challenge in healthcare oversight. Built on Microsoft systems and designed by RSM, the dashboard helps staff identify risks that may have gone unreported. An additional AI–supported component is being developed to help flag participants at higher likelihood of experiencing adverse events, enabling proactive intervention.

“This dashboard helps DDD make more data–informed decisions for the betterment of the community,” said Jack Barile, associate dean for research and principal investigator for OEAIDD. “By partnering with service providers and technical teams like RSM and Microsoft—and by training UH students in real–world analytics—we’re helping the state build a more responsive system of care.”

“This collaboration among DOH, UH and RSM US marks a significant step forward in protecting consumer health and safety by harnessing AI to address the issue of under–reported adverse events,” said Mary Brogan, DDD administrator. “By identifying adverse risks accurately, we can better support our participants’ well–being.”

Strengthening data use statewide

UH researchers are working alongside DDD staff and technical partners RSM and Microsoft to ensure the dashboard is practical, secure and integrated into daily workflows. Researchers on the project team contribute through data analysis and evaluation, while graduate students also gain hands–on experience with public health data.

“Our goal is to help DDD build a culture of data,” said Eva McKinsey, project lead. “The dashboard gives DDD staff access to timely and relevant information that can support stronger programs and better outcomes.”

UH researchers will continue refining the tool and expanding training, with the focus on improving disability services statewide through better data, evaluation and collaboration.

The OEAIDD project team, housed within UH ����ԴDz�’�� , also includes Charles Iwata, Ashlyn Wong, Reinie Gerrits–Goh, Genevieve Manset, Meldrick Ravida, Eric Lin and Grace Mellor.

In preparation for the 2024 Olympic surfing competition, a new judging tower is being constructed in the reef lagoon at Teahupo’o, Tahiti. That construction poses a threat to the reef and its ecosystem, according to researchers from the University of �鶹��ý at Mānoa, UH Hilo, Arizona State University and community partners in Tahiti. The group published a study in that assessed the importance of protecting the valuable reef—both as an integral part of the ecosystem and a resource for the local community.

Although there is an existing judging tower used by the World Surf League, the Paris 2024 Olympic organizers intend to invest approximately $5 million USD to construct a substantially larger tower to provide amenities for judges including toilets, air conditioning and capacity for 40 people.

“We hope the International Olympic Committee, appropriate government officials and the greater international community can see how devastating this impact will be to not only the valuable coral reef habitat, but also the local community who depend on this reef for their livelihood and well-being,” said John Burns, lead author of the study, associate professor in marine science and data science, and member.

In addition to an assessment of the reef where the structure will be built, the team mapped the lagoon area where the reef is being dredged to accommodate barge transport of tower materials. This dredging could directly impact 2,500-square meters of the reef (about half the size of a football field). If this were to occur, the authors report, it could cause a financial impact of at least $1.3 million by damaging the live reef habitat.

The team’s impact estimates are conservative—only accounting for direct impacts and not including the potential financial impacts for communities who depend on these resources or the impact on the much greater lagoon area if water quality is affected.

Mapping the potential impact

The researchers teamed up with community members from Vai Ara O Teahupo’o and used 3D photogrammetry techniques to create high-resolution habitat maps of three sites that will be impacted by dredging and tower construction. The resulting mosaics were analyzed to quantify species diversity, coral colony count, coral colony size, and percent of the ocean floor covered by live coral and other living organisms.

The data show these sites support healthy and diverse coral communities that contribute to the ecological function of the larger reef system at Teahupo’o. In the 322 square meters (about the size of a tennis court) where the tower would be located, they identified the presence of 1,003 corals from 20 different species, indicating this site is a thriving coral habitat.

“Although these organisms’ value will never be fully represented through a capitalistic lens, based on U.S. valuations used by the �鶹��ý Division of Aquatic Resources, our data show the value of just the corals and algae at this small portion of the reef is estimated to be worth at least $170,000,” said Haunani Kane, co-author, assistant professor of Earth sciences in the at UH Mānoa, and MEGA Lab member.

“With information in hand about the ecological impact and community concern, we hope construction of the tower will be reassessed and also that these maps will help to hold any future disruptors accountable,” said Cliff Kapono, co-author, assistant professor at Arizona State University and MEGA Lab member. “There are alternatives to constructing a new tower, such as using the existing tower, which the World Surf League uses for competitions.”

–By Marcie Grabowski

This column by University of �鶹��ý Maui College Chancellor Lui Hokoana was published by .

Five years ago, the third-acre plot of land at the mauka end of our campus’s main parking lot was filled with debris and invasive species. But as I walked through that place with Nicolette van der Lee, our Program Manager of University of �鶹��ý Community Colleges, and UH student Dustin Palos, we saw its potential — as a mini-model for agroforestry, regenerative agriculture, and indigenous knowledge through conservation and security initiatives. Like anything worthwhile, it took laulima — many hands — to bring that early vision to life. It was named the Kauluwehi Garden and now it is definitely, as its name suggests, adorned with greenery.

After last August’s devastating wildfires, the garden was established as a “puʻuhonua,” — a place of refuge — with a new focus. “We switched from working with plants like kalo, ʻuala, and ʻōlena to concentrate on how best to respond to post-fire restoration,” explains Palos, the UH student who took the lead in transforming Kauluwehi into a biocultural garden. It also became the research project for his Natural Resources and Environmental Management advanced degree thesis. “It is filled with some of the most resilient and commonly native trees,” he says. “There are also at least 26 types of endemic plants, five indigenous plants, and 30 food or food/medicinal purpose trees. We hope to inspire and change the vision of what future communities could look like based on the model we have created here.”

“One of our goals is that Kauluwehi be the first in an ‘archipelago’ of similar biocultural refuges all over Maui County,” says van der Lee. “Thousands of plants have already been donated to support Lahaina and other sites throughout Maui Nui. Now that we have new funding, we’re looking to greatly expand our propagation and replanting efforts.”

The funding to which Nicolette refers is a newly awarded $300,000 USDA National Institute of Food and Agriculture (NIFA) grant for a project entitled Puʻuhonua Kauluwehi: Maui Wildfire Rapid Response Strategies for Agroecosystems Resilience, Food Security and Community Well-Being. It will host immersive, ʻāina-based learning experiences for local participants including youth and adults from underserved and displaced communities. The goals are to effectively increase community stakeholders’ access to environmental, human health, and socioeconomic benefits, broaden youth and adult engagement and education in agroecosystem planning and restoration, increase local capacity for agroforestry restoration across �鶹��ý, and enhance awareness of the best practices of biocultural refuges to improve resilience to climate change and extreme events.

We plan to engage with students in the community in three ways. First, we’re training Lahainaluna students and UHMC Data Science students to be “ʻĀina Data Stewards.” They’ll map the different plants and trees in Kauluwehi and then partner with Maui Nui Botanical Garden to map its site. “We’re excited to provide a place that students can work mapping an extensive native plant collection, some of which has been in place for nearly 50 years,” says Maui Nui Botanical Garden Executive Director Tamara Sherrill. “The work they do could help us in many ways, from outreach to collections management. And the project also supports our long-term vision of cultivating widespread preservation, conservation, and integration of Hawaiian plans throughout Maui Nui.”

Second, students designated as “ʻĀina Data Interns” will lead the Data Stewards teams and work on designing and developing websites for the maps and the data sets. Finally, we’ll recruit “Kauluwehi Community Stewards,” 250 youth and adults to participate monthly throughout the year to propagate native plants, attend art workshops, become involved in community health and wellness initiatives, and more.

Clay Trauernicht is Extension Specialist in Ecosystems and Fire, Department of Natural Resources and Environmental Management at UH Mānoa and the advisor on Dustin Palos’ project. “It’s no secret that the lands around Lahaina and elsewhere in �鶹��ý are no longer the places of abundance they once were. Places like Kauluwehi are a window into what these landscapes could look like,” he says. “Land care starts with people and the Puʻuhonua Kauluwehi project will connect people to the type of work required to restore both cultural landscapes and native ecosystems.”

It will take a lot of work by a lot of people who care a lot. We’re happy and honored that the work starts with us.

For complete information on the Puʻuhonua Kauluwehi Project including ways you can help, please visit https://maui.hawaii.edu/kauluwehi/. For complete information about UH Maui College, please visit http://maui.hawaii.edu/

*Dr. Lui K. Hokoana is Chancellor of the University of �鶹��ý Maui College. Kaʻana Manaʻo, which means “sharing thoughts,” is scheduled to appear on the fourth Sunday of each month. It is prepared with assistance from UH Maui College staff and is intended to provide the community of Maui County information about opportunities available through the college at its Kahului campus and its education centers.

Visitors to the East �鶹��ý Veterans Cemetery No.1 grounds in Hilo have a new map to assist them in locating gravesites thanks to a map created by student geographers from the . The team used drones, hands-on fieldwork and extensive geographic information system (GIS) programming to create the map.

The gives viewers an overhead view of the cemetery allowing them to click on each gravesite to see a photo of each gravestone. Viewers can also search by name.

The project was conducted under the guidance of Ryan Perroy, a professor of and director of the UH Hilo .

“This has been a multi-year effort and we are now ready to share the mapping project with the public,” said Perroy. “We are honored to give something back to our veterans and their families.”

East �鶹��ý Veterans Cemetery No. 1 is a resting place for more than 1,500 fallen soldiers and family members. Veterans from World War I, World War II, Vietnam and Afghanistan are laid to rest there.

GIS is the . Students utilized integrated computer hardware and software to analyze and visualize geographic data.

The project served as a learning experience for 48 students in various classes throughout the past three semesters such as , and . The work involved differential global positioning systems or GPS, GIS, photogrammetry, fieldwork, drones and web mapping. UH Hilo undergraduate geography student Kanoa Lindiwe took the lead on the project, and graduate student Trina “Nikki” Henry, currently in the master’s program, also contributed.

The mapping project was conducted in partnership with the County of �鶹��ý Department of Parks and Recreation. Staff from the UH Hilo Spatial Data Analysis and Visualization Lab also contributed.

—By Susan Enright

A student’s love of math is enabling her to support (100% clean energy by 2045) through research projects at the University of �鶹��ý at Mānoa (SOEST).

Mattox Telwar is working with the (HGGRC), led by Nicole Lautze, in SOEST to better understand the potential for geothermal energy across the state.

“I chose to pursue a minor in mathematics simply because I love it, and I believe that a strong mathematical background would help me in my research efforts,” said Telwar.

Geothermal energy production

HGGRC explores the geologic structures in Hawaiian volcanoes and how those structures influence groundwater storage and flow. On Lānaʻi, HGGRC is exploring Palawai Basin’s groundwater system, an important factor for geothermal energy production.

“Because of �Ჹ�ɲ���ʻ��’s active volcanoes and the presence of subsurface heat, the use of geothermal energy can prove to be a viable option to solve some of the state’s energy woes,” said Lautze.

After the field project, Telwar asked to assist with data processing and translating the group’s data into results. To continue Telwar’s work with the researchers, Lautze offered her a position as an undergraduate research assistant in HGGRC.

“I have had the opportunity to participate in many fieldwork projects, including surveys to map groundwater flow, collecting gravity measurements, working in 3D modeling, and participating in presentations about our work,” said Telwar.

Born and raised in Nashville, Tennessee, Telwar moved to �鶹��ý and joined SOEST after graduating high school. She found a passion for research and Earth sciences during her first semester and is now pursuing a bachelor’s of science degree in Earth Sciences with a concentration in geophysics and tectonics and a minor in mathematics.

Telwar is on track to graduate in spring 2025, and intends to pursue a doctorate degree in geophysics or planetary science in hopes of creating a research career focused on sustainability and discovery efforts.

.

Four University of �鶹��ý-led projects received a total of roughly $800,000 in expedited RAPID grants from the in the wake of the deadly Maui wildfires. RAPID funding is used for proposals having a severe urgency with regard to availability of, or access to data, facilities or specialized equipment, including quick-response research on natural disasters.

Three projects focus on data science, and have a concentrated effort to help prevent and react to future wildfires in �鶹��ý. They include: a multi-hazard monitoring and detection system, computer modeling to assist wildfire response, and wildland and urban fire modeling using high performance computing models. They will address contributors to fires such as invasive grasses and non-native trees such as cook pines and eucalyptus. The fourth project focuses on the human element and involves UH researchers meeting with educators, youth, community members and cultural practitioners to understand the wildfire impact on K–12 education and learn how trauma-informed STEM education could assist with processing and recovery.

Multi-hazard monitoring and detection system

The Lahaina fire was exacerbated by drought, high temperatures and winds from Hurricane Dora which passed south of the islands. This project combines UH’s climate mesonet system (a densely located set of observation stations) with Northwestern University’s Sage Artificial Intelligence-enhanced instrument platform to build a multi-hazard monitoring and detection station for natural disasters such as fires, high winds and floods. The system is being deployed near the Lahaina fire site, to gather data vital to the recovery effort.

The project will gather essential climate and pollutant data to aid clean-up activities in Lahaina, and obtain performance and reliability data, guiding both instrument enhancements and Lahaina’s recovery planning. This project provides essential data for informing Lahaina’s recovery, while highlighting the advantages of adopting recent climate science and cyber-infrastructure advancements. Where possible, local students on Maui will be recruited to participate in the instrument construction, data gathering, analysis and visualization effort.

The project is led by principal investigator and Professor Jason Leigh, and co-principal investigators Thomas Giambelluca and Christopher Shuler from UH ����ԴDz�’s .

“We are deeply pained by the tragic loss of lives and property in the Lahaina fire,” Leigh said. “It’s a somber reminder of the powerful forces of nature that are poised to impact our islands at any time. We hope that our insights and advancements in state-of-the-art technology can help pave the way for better understanding and perhaps preventing such heart-wrenching incidents in the future.”

Computational modeling of wildfire management

Accurate and timely predictions of how a wildfire could spread are essential to inform people, minimize the loss of lives and mitigate damage through effective suppression activities. It is critical to improve on these processes in the aftermath of the devastation of the Lahaina fires. This project, led by UH ����ԴDz� graduate faculty and Maui resident Alice Koniges, will develop wildfire computer models that have the potential to save human lives and infrastructure in future wildfires using mathematical concepts called level-set methods and Hamilton-Jacobi equations.

This research will produce a new model to provide an understanding of the complex algorithmic and mathematical basis for wildfire response that can aid in resource allocation in a real-time disaster situation such as the Lahaina wildfire. A particular emphasis is on improving human evacuation models. The project is joint with Professors Andrea Bertozzi and Stanley Osher from UCLA and Professor Hannah Kerner of Arizona State University. The project will also involve high school and community college students from the ʻĀ���Բ� Data Stewards program on Maui, a program co-founded/co-led by Kerner that teaches students basic concepts in machine learning and data science while enabling them to contribute to active research projects through field data collection. The project will consider the additional risks due to fuel from non-native trees and grasses as well as terrain effects in the wildfire modeling. Additionally the project will engage and train PhD students in mathematically-based methods of disaster mitigation and modeling.

“We are grateful to have experts in mathematical modeling help us to better understand and prepare for future disaster events,” lead principal investigator Koniges said. “Additionally, the training of the next generation of modeling experts will help the future of our island communities.”

Wildland and urban fire modeling

With Lahaina being in an isolated location with limited wind and environmental observations, other data sources will help to advance modeling and simulation research before these sources are lost. This project will capture data from multiple sources including social media and time-stamped photos—organized with AI-enhanced methods for data gathering, processing and infusion. students will play a critical role in this project.

The work will show the importance of data in the understanding of how a wildfire is propagated inside a community and its interaction with urban structures, with an additional goal of educating the public and enabling the �鶹��ý government and emergency response personnel to make decisions in the aftermath of the disaster. The project will use advanced AI techniques deployed on UH’s high performance computing resources, as well as resources from the National Science Foundation and other national infrastructure to process the large volumes of data needed to tune and validate fire propagation and atmospheric simulations. The collected data will be archived and made publicly available.

The principal investigator of the project is Maui resident David Eder who is on UH ����ԴDz�’�� graduate faculty in the Physics and Astronomy Department, and co-principal investigators Sean Cleveland, a computational scientist with UH’s , and fire modeling experts at University of Nevada, Reno, University at Buffalo, and the National Center for Atmospheric Research.

“We focus on the use of high performance computing facilities, both at UH and nationally, and the best available computational models to help understand better the sequence of tragic events that have touched and devastated so much on Maui,” Eder said. “Working directly with students to understand and prevent similar events is one small thing we can do to help.”

Trauma-informed STEM education

In this project, UH researchers will focus on Maui’s educators and youth. They believe that to move forward from the tragedy, it is important to understand the impact of the multiple layers of immediate trauma on K–12 education and learn how trauma-informed STEM education could assist with processing, healing and recovery. As residents and STEM educators in the state of �鶹��ý with rich and deep roots in communities on Maui, the researchers will apply a framework that was developed by principal investigator and Professor Tara O’Neill. It involves connecting with communities, learning from the place, people, kūpuna and moʻolelo. It requires asking and providing kokua and engaging at the invitation of the people in the place.

The horrific fires provide an invaluable source of knowledge related to both the layers of trauma resulting from catastrophic events, such as wildfires, and how trauma-informed STEM education can provide tools for recovery from trauma. There are several excellent schools and community-based STEM education programs on the island of Maui. The project’s goal is to partner with the individual educators, community members and cultural practitioners connected with several of these programs to build knowledge (understand the nature and impact of trauma), and work with the community to build emotionally healthy STEM learning environments where the focus is processing and healing and STEM content and activities are applied as tools for processing and healing.

This project is led by O’Neill, and co-principal investigators UH ����ԴDz� Professor Monique Chyba, Associate Professor Yuriy Mileyko and UH Maui College Assistant Professor Thomas Blamey.

“Our goal is to understand the impact of the multiple layers of immediate trauma on K–12 education to work with the community to build long-term interventions,” O’Neill said. “We believe the information we learn can help inform more mindful short-term and long-term planning by the �鶹��ý Department of Education and other state institutions.”

Chyba added, “Learning, teaching and helping is why I came into academia, and I am honored to be able to try to do exactly that with this project.”

Every curve and every angle of a coral colony holds the key to sustaining an array of marine species, according to public impact research. UH Hilo graduate student Sofia Ferreira led a on predicting how coral reefs in Guam influence habitat complexity.

Ferreira, who hails from Paraguay, and marine scientists from UH Hilo analyzed data collected from overseas in UH �ᾱ����’s , or MEGA Lab, which specializes in the study of coral reefs.

“Underneath the shimmering waves, coral reefs flourish as underwater cities, carefully designed by nature’s architects, corals themselves,” said Ferreira. “Much like architects design unique houses for different people, corals create diverse habitats and refuge for the ocean’s inhabitants. This diversity within coral refuges is the foundation to the health and resilience of coral reef ecosystems.”

Ferreira worked on the study alongside researchers at MEGA Lab. She is enrolled in the UH �ᾱ����’s and earned a and from UH Hilo in 2022.

Reef city

Ferreira’s teams’ research sought to determine how the design of each coral home shapes a “reef city.” Using high-tech underwater cameras, Ferreira and fellow MEGA Lab researchers mapped 208 coral reef sites surrounding the island of Guam. The team used 3D photogrammetry techniques to survey the plots. From these reef maps, more than 12,000 corals were individually assessed, capturing their size and growth shape. The innovative study found that every curve and every angle of a coral colony holds the key to sustaining an array of marine species.

Coral conclusions

According to the study, the authors concluded that the traits of coral colony size and morphology are strong predictors of habitat complexity in Guam’s reefs and should be included in coral reef monitoring programs.

Ferreira explained that coral reefs, the lifelines of coastal and island communities, are facing escalating threats from both local and global stressors. “[Our] findings offer a glimpse of hope, casting light on the inner workings of these vital ecosystems.”

The research team hopes the study can offer vital insights and a foundation for future research to assess the overall impact fluctuation reef habitats can have on reef-associated organisms under climate change.

.

–By Susan Enright

The University of �鶹��ý is part of an international group of researchers and Indigenous practitioners that has been awarded a $23-million (Canadian and approximately $17-million U.S.) grant from Canada’s to work on improving artificial intelligence (AI) through Indigenous knowledge.

The project, “Abundant Intelligences: Expanding Artificial Intelligence through Indigenous Knowledge Systems,” is Indigenous-led and involves 37 co-investigators and collaborators from eight universities and 12 Indigenous community-based organizations from Canada, the United States and New Zealand.

The teams will coalesce in locally rooted “pods” to collaborate with Indigenous communities. In this way, each team will learn from, and alongside, Indigenous knowledge keepers to bring novel perspectives to transforming AI.

“The �鶹��ý Pod will be a key site and significant resource for Abundant Intelligences. �鶹��ý has one of the greatest concentrations of Indigenous technological talent in the world,” said Concordia University Professor Jason Lewis, who is the principal investigator for the grant. “It has already played a key role in the Indigenous AI discussion by hosting the Indigenous Protocol and AI Workshops in 2019. These were grounded in part in the extensive and vibrant discussion within the Kanaka Maoli (Native Hawaiian) community regarding the long history of kanaka innovation, and how that community has always developed and taken advantage of new technological tools and methods.”

Weaving a lei

The �鶹��ý pod will be based at ’s .

“You see in Create(x) there are a lot of flowers on the table to weave a lei from,” said UH Director of Indigenous Innovation Kamuela Enos, who was a co-applicant for the grant. “What’s really important is that we will do it all in mindfulness of what is our responsibility as Hawaiians to protect our [intellectual property] and its use, which is always front of mind for us.”

Other UH co-applicants included:

• Jason Leigh, UH ����ԴDz� professor of information and computer sciences
• Bryan Kuwada, UH ����ԴDz� assistant professor of Hawaiian studies
• Susan Crow, UH ����ԴDz� associate professor of natural resources and environmental management
• Manulani Meyer, UH West Oʻahu konohiki (facilitator) of Kūlana o Kapole​i

Leigh, founding director of and co-director of the said, “AI will impact every part of our lives in this decade and beyond. This project is an unprecedented opportunity to influence the future of AI to make it more inclusive in its use, development and evolution.”

Create(x)

The Create(x) lab is located in the new Academy for Creative Media (ACM) building and features projection onto three walls and the floor for various virtual environments. The lab provides students access to immersive technologies where diverse projects—designed to perpetuate Indigenous knowledge and narratives—range from visualizing the first few lines of the Kumulipo (Hawaiian creation chant), teaching Hawaiian vocabulary of native species and environmental change, modern Hawaiian wayfinding and the retelling of famous moʻolelo (stories).

Create(x) co-director and �鶹��ý Pod Coordinator Kari Noe said she is excited about the opportunity to discuss how the grant may translate to current and future projects and overall protocol and data management.

“[The grant] is giving us the capability, resources and time to think through and talk through a new way of interacting with technology that AI is providing us,” Noe said.

The $37-million state-of-the-art ACM facility opened in 2021 as part of the UH ACM System, which supports 16 programs at all 10 campuses statewide.

ACM System Founder and Director Chris Lee added, “This extraordinary grant is exactly the kind of opportunity envisioned when including the specific space for Create(x) in the design for the ACM Student Production Facility at UH West Oʻahu. Congratulations to everyone at both campuses on the success of this first collaboration between ACM supported programs at UH ����ԴDz� and UH West Oʻahu.”

Genealogy of a grant

The Abundant Intelligences grant is for six years and includes funding to involve other community-based experts and for community engagement events. UH’s share is approximately $850,000 Canadian or $637,500 U.S.

Enos pointed out that the grant also has a “genealogy.” In 2019, Lewis co-organized with Leigh and others the series of workshops in �鶹��ý on Indigenous AI, which resulted in a position paper, “” (PDF) that was published in 2020.

—By Kelli Abe Trifonovitch

From overdose deaths to crisis calls in �鶹��ý, data related to drug trends is now available to the public through a new online dashboard. The is a web site of the �鶹��ý ’s (DOH) Behavioral Health Administration.

The dashboard, a collaboration between the University of �鶹��ý, DOH and 14 partner organizations from across the state, was released in October. UH Associate Director of Cyberinfrastructure and his team, as a part of the , built this new substance use disorder and mental health dashboard.

It displays �鶹��ý’s current behavioral health trends in drug overdose, polysubstance abuse, co-occurring substance use and mental health disorders. The ongoing collaboration between UH and DOH will include more available datasets, updates to usability, accessibility and improved mobile support. Stakeholder meetings will also be held to collect feedback on the dashboard’s design and features.

“This behavioral health dashboard is of importance to �鶹��ý because it promotes the use of public health surveillance data to improve interventions for substance use and mental disorders. Also, this dashboard provides information to the healthcare community and non-profit groups that support those who experience and/or are in recovery from these conditions, along with their ʻohana,” said Principal Investigator Treena Becker, a researcher at the Center on Aging in UH ����ԴDz�’s .

The project was funded by an almost $4.4-million grant from the Centers for Disease Control and Prevention Overdose Data to Action aimed at expanding public health surveillance to allow for high quality, timely and comprehensive data collection for drug-related misuse and overdose morbidity and mortality and using these data to drive prevention strategies.

Researchers across the 10-campus University of �鶹��ý system will be able to process larger datasets and models and accelerate existing workflows with a new intercampus data-storage platform called KoaStore. The platform is being established with a $500,000 National Science Foundation grant.

“KoaStore will help support and power UH investigators’ research through its high-performance, large size and fast connection to the rest of the world. Further, KoaStore will help enable analysis of data at a scale not previously possible on the Mana high performance computing cluster, allowing larger simulations and discovery,” said Sean Cleveland, principal investigator and associate director of cyberinfrastructure at UH .

KoaStore will be integrated into the and focus on supporting research in the areas of astronomy, atmospheric science, climate science, microbiome and computer and data science.

Serving national and local research

The new platform will also serve the national research community through partnership with the , leveraging existing UH, Pacific region and national high-speed research networks. This partnership federates national computing resources to offer high-speed storage and shorter wait-times on shared compute resources for UH researchers.

“The public datasets hosted on KoaStore will make it possible for researchers in �鶹��ý, across the nation and around the world to use astronomy data produced by the UH (IfA),” said Curt Dodds, IT manager at IfA and KoaStore co-investigator. “We plan to share data from cosmological simulations, a dynamic database of the entire night sky, and machine learning models of the Sun’s atmosphere and distant galaxies.”

Data from the , also known as StePS, a novel astrophysics simulation method, are an example of public datasets available for download through KoaStore.

KoaStore will be integrated with the NSF cloud computing infrastructure and allow researchers to easily span cloud computing environments to support new deep learning and artificial intelligence workflows, visualization and applications.

Additionally, the platform will aid hands-on training in data and computational science for the next generation of researchers and data scientists through a partnership with the and local community to provide workshops and classroom access.

University of �鶹��ý researchers and students will soon have access to some of the most powerful computing power at their fingertips thanks to a joint project with several universities around the country and the National Science Foundation (NSF).

UH is part of a newly available national cloud computing resource that allows researchers to access powerful cloud-based environments on demand to explore and understand immense amounts of data from a laptop or tablet.

The NSF supported project is an update to the widely used Jetstream cloud computing system. Jetstream2 provides eight petaFLOPS of virtual supercomputing power, allowing researchers to simplify data analysis, boost scientific discovery and leverage artificial intelligence (AI) tools.

“A 1 petaFLOPS (PFLOPS) computer system is capable of performing one quadrillion (1015) floating-point operations per second. The rate 1 PFLOPS is equivalent to 1,000 TFLOPS. To match what a 1 PFLOPS computer system can do in just one second, you’d have to perform one calculation every second for 31,688,765 years,” according to Indiana University.

“Our participation in Jetstream2 ensures our researchers, faculty and students have access to a national-scale cloud computing resource platform to effectively collaborate with their peers and research partners and leverage state-of-the-art technology and techniques to drive science forward,” said Garret Yoshimi, UH vice president for information technology services. “We are grateful to NSF for their generous support in making Jetstream2 a reality for our UH community.”

Related: UH part of $10M cloud computing coalition, June 4, 2020

With five computational systems, Jetstream2 spans the nation with partners at UH, Indiana University, Arizona State University, Cornell University and the Texas Advanced Computing Center. The system is designed to be easily used by researchers who have limited experience with cloud computing and to serve smaller academic communities with no previous access to such resources.

The 24/7 user-friendly cloud computing environment provides virtual infrastructure that allows for more access to high-end technologies that enable deep learning and AI techniques. The Jetstream2 system is easy to expand and reconfigure and supports diverse modes of on-demand access. In addition, it extends a broad range of hardware and services that include larger and faster storage systems, graphics processing units, large memory nodes, virtual clusters and much more.

Jetstream2 also supports experimentation and teaching. The system will serve more students than any other NSF-funded cyberinfrastructure resource, better equipping them to fully participate in the evolving STEM workforce.

Additional partnerships with the University of Arizona, Johns Hopkins University and University Corporation for Atmospheric Research will contribute to Jetstream2’s unparalleled usability and support for a broad range of scientific efforts.

Researchers may request several allocation types through NSF’s .

The University of �鶹��ý System has received more than $427 million from the (NSF) over a 10-year period from fiscal year 2012 through 2021 for cutting-edge research in a variety of fields. On August 30, NSF Director Sethuraman Panchanathan visited UH ����ԴDz� to learn more about the world-class research conducted by faculty, students and staff.

Panchanathan is a computer scientist and engineer, and the 15th director of NSF, a $8.8 billion independent federal agency and the only government agency charged with advancing all fields of scientific discovery, technological innovation and STEM education.

“The National Science Foundation essentially is responsible for unleashing great ideas and talent all across our nation, and in the state of �鶹��ý, there is tremendous talent and ideas,” said Panchanathan. “There is also amazing context. If you look at the domain of sustainability, or if you want to understand climate and oceanography, and understanding astronomy, here is a place that is a living laboratory. …The University of �鶹��ý and other institutions in the islands are doing a fantastic job.”

In FY 2021, UH was receiving the most funding from NSF, ranking higher than Harvard University and Duke University.

“We are grateful that the National Science Foundation awards an average of more than $42 million annually to UH research projects over the past 10 years. This is a testament to the high quality of research being conducted throughout the UH System by our world-class faculty, students and staff,” said Vassilis L. Syrmos, UH vice president for research and innovation.

UH hosted Panchanathan’s visit at C-MORE Hale on the ����ԴDz� campus. Several faculty members presented their NSF-funded research:

• —Professor David Karl, UH ����ԴDz� School of Ocean and Earth Science and Technology (SOEST)
• —Professor Angelicque White, SOEST
• (EPSCoR)/—�鶹��ý EPSCoR Director Gwen Jacobs and Professor Jason Leigh, director of the UH ����ԴDz�
• NSF CAREER: Soil Pedogenesis, Agroecology, and Their Interactions—Assistant Professor Noa Lincoln, UH ����ԴDz� Indigenous Crops and Cropping Systems
• Ola I Ka ʻAina: Reviving Ecosystems Utilizing Science, Math and Indigenous Knowledge—Associate Professor Esther Widiasih, UH West Oʻahu
• Hoʻomalu Haleleʻa: Community-led Innovation for Integrated Flood Resilience—Associate Professor Mehana Vaughan, UH ����ԴDz�

—By Marc Arakaki

Editor’s note: The federal government withdrew grant funding for this research in 2025.

The National Science Foundation (NSF) has awarded $10 million to a consortium of institutions, including the University of �鶹��ý at ����ԴDz� (JABSOM), to focus on building capacity and workforce for data analytics across �鶹��ý and the U.S.-affiliated Pacific region. The consortium is led by , and includes the East-West Center and Texas Advanced Computing Center.

The award, “Alliance Supporting Pacific Impact through Computational Excellence (ALL–SPICE/),” is made possible through NSF’s INCLUDES () program as part of a $39-million effort to address diversity, inclusion and participation challenges in STEM at a national scale.

“This award will critically support further development of data science in �鶹��ý and the Pacific, empowering stakeholders, developing a workforce that knows the utility and power of using data, and subsequently improving data informed decision-making abilities across multiple industries, domains and disciplines,” said co-principal investigator Alex Stokes, JABSOM assistant professor in cell and molecular biology and member of the .

Stokes was also recently awarded a $1.5-million NSF S-STEM program grant that will provide training and tuition scholarships to talented low income undergraduate and graduate students with a focus on biological application of data science.

• Related UH News story: $1.5M STEM scholarships to advance future biologists with data science skills, July 19, 2022

“Data science education provides opportunities for students to qualify for a wide range of great jobs that are in high demand everywhere in multiple public and private sector organizations,” said UH President David Lassner. “ALL–SPICE will enable us to serve students and communities throughout �鶹��ý as we also extend our commitments into the Pacific in a critical area of need.”

The consortium partners are Chaminade University’s new United Nations CIFAL Center (PI Helen Turner); the Texas Advanced Computing Center; the UH-Data Science Institute and JABSOM (co-PI Alex Stokes); and the East-West Center (co-PI Mary Perez-Hattori).

The program will also work closely with UH �ᾱ����’s “Islands of Opportunity” NSF Alliance which engages colleges and universities across the U.S.-affiliated Pacific Islands.

ALL–SPICE co-PI Kelly Gaither, director of health analytics at Texas Advanced Computing Center and a professor in maternal health at the Dell Medical School at UT Austin, said, “Data science is a non-negotiable 21st century skill set both for individuals and whole communities. Data can be both a source and a solution for injustice and inequity. I am delighted that every partner in this Alliance shares the values of building data analytics capacity to empower �鶹��ý-Pacific communities to address their own challenges such as poverty, ecosystem decline and health disparities, and to do so in a way that is inclusive and ethical.”

The ALL–SPICE Alliance will begin offering programming and opportunities on September 1, 2022.

The University of �鶹��ý at ����ԴDz� has been awarded $1.5 million for scholarships for low-income students who are pursuing degrees focusing on the biological application of data science. The five-year grant through the National Science Foundation’s , Student Training through Immersive Data Science Education (STRIDE) and will fund 67 scholarships for undergraduate and graduate students.

“The progressively more data-rich nature of biological sciences creates the need for enhanced professional preparation in data science to improve the competitiveness and employability of our graduates,” said UH ����ԴDz� Provost Michael Bruno.“This is a tremendous opportunity to give our students invaluable skills to advance them in their future careers.”

In addition to receiving tuition, selected students in the STRIDE program will benefit from professional development resources, including workshops and internships to build their resumes and develop career readiness skills. Majors include: biology/biological sciences, biochemistry, botany, biological engineering, microbiology, molecular biosciences and biotechnology, molecular cell biology, natural resources and environmental management, tropical plant sciences and zoology.

“Biology is an increasingly computational discipline,” said Principal Investigator Alexander Stokes, Assistant Professor in Cell and Molecular Biology with the . “Today’s biologists, whether they are health practitioners, medical researchers or ecosystem scientists, are all living in the era of big data. This program is about making sure that the future biologists trained by UH have the data science skills they need to be successful in their field.”

(HI-DSI) Director and STRIDE co-principal investigator, Gwen Jacobs, echoes the need for data science training for future biologists. “Our state is really recognizing that data science is central to our future health, sustainability and economic development. Programs like this will foster the workforce we need and at HI-DSI we are delighted that STRIDE students will benefit from the training workshops and professional development programs we have developed.”

Eligibility requirements

Eligible undergraduate students should have unmet financial need and at least 30 credits with a 3.0 cumulative GPA in a biological science major. Eligible graduate students should be enrolled in an MS or PhD program with an estimated three years to graduate in a non-clinical program.

As part of the two or three year program, students will participate in weekly seminars with guest speakers sharing their expertise in various areas of data science, training workshops, DataSkills training modules, projects and a data-intensive thesis or dissertation project paired with a HI-DSI collaborating research supervisor.

Stokes said they were inspired to write the grant having seen their own biomedical research pivot toward using techniques like artificial intelligence and machine learning in drug discovery and health equity.

“I realized firsthand the need for workforce development and training in this area, coupled with the fact that we have many talented students in �鶹��ý and the Pacific that need financial support in higher education, so S-STEM Scholarships can really help those students pursue their dreams,” Stokes said.

For more information, email astokes@hawaii.edu.

A second high-performance computing (HPC) cluster at the University of �鶹��ý has been seeded with a $400,000 National Science Foundation grant. Much like the existing HPC, , the new cluster called Koa will serve as a free inter-campus resource for advancing research in such areas as astronomy, chemistry, oceanography, bioinformatics and data science.

“We are excited about the capacity that Koa will bring the existing computational resource specifically the increase in throughput the new high speed storage system will provide speed-up across existing and new hardware as well as the ability for transferring and processing larger datasets,” said Sean Cleveland, UH Information Technology Services (ITS) cyberinfrastructure senior project manager and principal investigator. “We look forward to enhancing scientific workflows with our science partners in the Institute for Astronomy and the departments of Information and Computer Sciences and Atmospheric Sciences for some targeted, larger datasets and model simulations projects to push science and research forward at UH.”

Computational performance boost

The deployment of Koa will bring 750 terabytes of high-speed storage, eight computational nodes with (48 cores, 256 GB of memory) and two compute nodes that provide another 20 graphics processing units with newer architectures to support machine learning and deep learning workflows.

The new high speed storage infrastructure will integrate with the existing Mana HPC to decrease the runtime for many workloads impacted by read and write speeds and significantly increase Mana’s computational throughput.

“We’re grateful for the National Science Foundation support to further expand and enhance our institutional HPC resources,” said Garret Yoshimi, ITS vice president for information technology and chief information officer. “The addition of Koa to our Mana HPC foundation will help us increase the depth and breadth of support for high performance data analytics, AI (artificial intelligence) and visualization efforts to our diverse community of researchers and students. Elimination of the historically high cost of entry to HPC assets is critical to ensure that our community can build on the benefits of leading edge technologies that will support future discoveries and innovation.“

Related UH News stories:

• ‘Machine learning’ improves rainfall mapping, water plans, May 10, 2022
• UH boosts research computing power with arrival of new equipment, October 1, 2020
• Students dive into high-performance computing, February 10, 2020

In addition to adding state-of-the-art computing equipment, the grant will also support advanced technical training and expanded educational and research opportunities for UH students through hands-on immersive training workshops hosted by UH Information Technology Services Cyberinfrastructure and the . Koa resources will also be integrated with , a national consortium that builds and operates shared computing and data capacity high-throughput computing, allowing researchers increased access to resources nationwide.

–By Maria Dumanlang

The National Science Foundation has awarded the (�鶹��ý EPSCoR) a five-year $20-million grant to fund research and capacity building in support of actionable climate science through a collaboration called Change HI.

�鶹��ý faces unique challenges as climate change impacts resource availability, ecological sustainability, economic vitality and human health in the islands. To help the state face the critical issues brought on by climate change, this multidisciplinary research effort will integrate expertise in climate and data science to enhance fundamental knowledge and develop new climate models, data products and tools.

As a collaborative program with multiple partners inside and outside the UH System, Change HI will advance education and workforce readiness in these areas for �鶹��ý and help build a new data-driven knowledge economy statewide, targeting the growth of computer and data science that can be applied in critical areas of state need and growth.

“Change HI represents an amazing opportunity for us to advance even further one of our globally distinctive strengths, climate change and resilience,” said UH President David Lassner. “At the same time we will continue to build fundamental capacity in �鶹��ý in data science, which is increasingly vital across the full spectrum of inquiry and activity in academia, business and government.”

Integrated climate and data science research

Change HI research comprises eight data and climate science-focused projects. The team of researchers will work in areas of climate downscaling, numerical modeling sensitivity studies, functional trait analysis, carbon sequestration, cloud water interception and soil moisture characterization. All areas of research will use a variety of advanced data science techniques such as computational simulations, data visualization, natural language processing, machine learning, artificial intelligence and statistical modeling.

“This exciting project brings together an outstanding team of scientists and educators and has enormous potential to address two critical challenges for our state—preparing for the impacts of climate change and building a resilient data driven economy,” said Information Technology Services Director of Cyberinfrastructure and Principal Investigator Gwen Jacobs.

In addition, Change HI will build research capacity through new data science faculty hires, developing and creating access to climate data and products and building immersive data analytics environments to aid in decision making.

Education and training programs

Change HI will support data science education and workforce development for the state through a variety of programs. These programs include graduate fellowships, summer undergraduate research experiences, internships and data science training and certification.

The focus of both science and education efforts of the Change HI collaboration are to increase the state’s climate resilience through leveraging climate and data science research and support diversification and growth of �鶹��ý’s economy through data analytics.

“Change HI will deliver human and program infrastructure that supports critical education and workforce development initiatives to ensure �鶹��ý has the highly skilled, data-ready workforce that will power our future economy,” said Garret Yoshimi, Information Technology Services vice president and chief information officer. “Broad-based training efforts under Change HI will also help to ensure opportunities for everyone in our community to strengthen our support for equity and inclusion in our STEM-powered future workforce.”

Participating organizations include: UH System, UH ����ԴDz�, UH Hilo, Chaminade University, Island of Opportunity Pacific Louis Stokes Alliance for Minority Participation (LSAMP), �鶹��ý IDeA Networks of Biomedical Research Excellence (INBRE), UH LGBTQ+ Center, UH Office of Innovation and Commercialization, Waianae Mountains Watershed Partnership, �鶹��ý State Energy Office and �鶹��ý Community Foundation.

Rainfall map accuracy is vital in climate and hydraulic modeling and supports environmental management decision making, water resource planning and weather forecasting. University of �鶹��ý and East-West Center researchers have developed more accurate monthly rainfall maps by using machine learning. According to IBM, machine learning is a branch of artificial intelligence (AI) and computer science that focuses on the use of data and algorithms to imitate the way that humans learn, gradually improving its accuracy.

Funded by the National Science Foundation’s ʻIke Wai project, a team of researchers used a machine learning technique to detect erroneous rainfall maps. The results of this study were recently published in the .

“This approach demonstrates how, with a moderate amount of data, a low-level machine learning algorithm can be used to train, evaluate and classify an unrealistic map output,” said lead author Matthew Lucas, a climate data analyst for the UH . “This allows for minor corrections of automated interpolation (the process of calculating an approximate value based on values that are already known) that can produce a much more accurate and realistic map of the spatial patterns of rainfall. If this workflow can work in �鶹��ý with its extreme climate gradients it can definitely work elsewhere.”

Supported with computational resources from , this finding was made during the development of the �鶹��ý Climate Data Portal (HCDP), which was made publicly available this past March. The online portal offers an innovative automated solution that works well and preserves the overall accuracy of the map outputs.

The study resulted in high-resolution, gridded monthly rainfall time series data for the state of �鶹��ý spanning a period of 30 years. Rainfall maps range from as early as 1990 up to 2019 using data from more than 600 weather observation stations located throughout the islands.

“Having a wide range of gridded products will allow researchers the opportunity to develop important decision support for the state such as fire, flood and drought risk and early warning systems,” said co-author Ryan Longman, an Oceania research fellow at East-West Center. “Now that high-quality rainfall maps are available in near-real-time, researchers can spend less time processing data and more time answering important questions that can help us better understand and adapt to changing environmental conditions.”

In addition to ongoing improvements of current climate data products, researchers are in the process of developing methods to automate the production of daily rainfall maps and other gridded climate products for the state of �鶹��ý. All data products are available for data visualization and download to the public through the �鶹��ý Climate Data Portal.

• Related UH News story: Revolutionary climate data portal critical to future planning, March 3, 2022

—By Maria Dumanlang