SAFES seed funding boosts agricultural research data capabilitiesPosted on April 26, 2022
Originally published on Penn State News
UNIVERSITY PARK, Pa. — Four research teams in the College of Agricultural Sciences have tapped in to the computing and software engineering expertise at the Institute for Computational and Data Sciences (ICDS) to improve research workflows.
Seed funding from the Institute for Sustainable Agricultural, Food, and Environmental Science (SAFES) at Penn State was awarded to the teams in June 2021 to help explore how the ICDS Research Innovations with Scientists and Engineers (RISE) team could help researchers in the college overcome challenges related to research computing and data science. The RISE team is comprised of computational scientists and software engineers who collaborate with Penn State investigators to enhance or build research programs that need computing, programming, data management, data visualization and exploration or workflow support.
Moving satellite data off of personal computers
Light detection and ranging (LIDAR) data is giving Penn State researchers, along with colleagues at the Pennsylvania Department of Conservation and Natural Resources (DCNR), the chance to update Pennsylvania’s stream maps. Jon Duncan, assistant professor of hydrology in the College of Agricultural Sciences Department of Ecosystem Science and Management, said this is a task that hasn’t been done in decades, and many of the existing stream maps in the state were hand drawn, dating as far back to the 1950s.
LIDAR technology uses laser-based mapping that captures ground surfaces, building structures and vegetation features, but it also generates extremely large volumes of point cloud datasets. Creating maps from this data is a heavy task for a desktop computer. Duncan, along with Matthew Royer, director of SAFES’ Agriculture and Environment Center, sought SAFES seed funding to alleviate this massive data and computing power log-jam. Colleagues at the Pennsylvania DCNR were also tackling this data, and available computing power was only able to handle mapping one small watershed area at a time.
The RISE team is helping to design and execute a method to move, process and create maps from these datasets. RISE will also help the team tackle longer-term storage issues, and Duncan noted that this newly created process will likely be useful for handling future iterations of LIDAR data. “This has been a very collaborative project,” Duncan said, adding, “I’m grateful to be working with this team, we’re on a really constructive path.”
Creation of the first digital pollen library in Pennsylvania
The public is increasingly interested in installing pollinator-friendly plantings to help support their local bees, insects and other pollinators, and these plantings are being designed for many types of landscapes including urban areas, roadsides and rights of way, and natural and agricultural areas. However, choosing pollinator-friendly practices and plantings has been limited by the current working knowledge of what specific flowering plants provide the best support for pollinating insects.
So researchers have turned to the pollinators themselves to find clues about what types of plantings they prefer — and those clues are often in the form of the pollen that is collected from bees’ and insects’ bodies. In some cases, their preferences have been surprising, and plants thought to be favorites of pollinators actually were rarely visited. In other cases, researchers struggle to identify exactly which plant’s pollen is stuck to the insects. However, a new web application will help researchers and students anywhere identify pollen.
Natalie Boyle, assistant research professor in the College of Agricultural Sciences Department of Entomology, applied to the SAFES-RISE seed funding program, and along with funding from the Insect Biodiversity Center, will be able to the launch of Pennsylvania’s first online pollen library. The library will allow anyone to identify a pollen sample by selecting the characteristics of their sample and comparing the filtered results, which will include images of both he pollen particles and the plants. These features can help individuals to determine the nutritional and foraging preferences of different bee species and guide the selection of future seed mixes and landscaping practices that most benefit the pollinator communities of Pennsylvania.
“We’re still sampling pollen and we’re also now uploading those pollen images and incorporating them into the database,” Boyle said, adding that anyone interested in the project can follow PSU Pollinators on Twitter to find out when the site is launched.
Managing complex data for large teams
As research teams become increasingly diverse — spanning multiple colleges, disciplines and institutions — so do their data management needs. The Thriving Agricultural Systems in Urbanized Landscapes project, a five-year, $9 million project funded by USDA’s National Institute of Food and Agriculture (NIFA), is working to understand and create economically thriving and environmentally beneficial agricultural systems in urbanized landscapes. The project includes 16 task teams from multiple institutions, which quickly created a data management challenge.
Rather than relying on the scientists to try and optimize a solution, Dave Abler, professor of agricultural, environmental and regional economics and demography in the College of Agricultural Sciences, applied for SAFES seed funding to help establish a streamlined data management and storage solution. Thriving Ag Project Manager Margaret Frederick noted that the number of people involved, the differing formats of the data and the sheer amount of it created was a challenge when it came to sharing datasets efficiently between team members. Members had their own preferences for data storage as well, with files spread across personal drives and computers at multiple organizations. The ICDS RISE team is working to create a scalable-long term data management plan that will not only streamline the datasets for current team members, but also provide a long-term platform that is both publicly available and compliant with any restrictions that apply to each dataset. Frederick said that the framework being constructed by the RISE team may be valuable for other large, multi-institutional teams dealing with large and diverse data.
Making crop pest data easier to input and use
The density and activity of several species of moths that exhibit strong migratory behavior affects the timing of management inputs in vegetable crops. The team behind Penn State’s PestWatch program has monitored and mapped the observations of these pests on crops since the 1990s. Through PestWatch, growers can access high-quality visualizations of pest data on the project’s web platform. However, the platform itself was due for modernization, and the project team saw the ICDS-RISE Seed Grant Program as an opportunity to use RISE’s software engineering expertise to make the platform more impactful for today’s users.
PestWatch’s web interface was limited due to an older data structure; for example, getting data out of PestWatch had to be done manually by an administrator. Shelby Fleischer, professor of entomology in the College of Agricultural Sciences, proposed to SAFES an improvement project that would move the platform from a single-point data entry method to a system where data was integrated with regional integrated pest management (IPM) program. The ICDS-RISE team is working to help PestWatch enable users to submit data from their own datafiles, query the data and get output in a wider variety of useful formats, and create a method for mobile data input.
The ICDS RISE team, with design input from multiple northeastern states, are on track to have PestWatch dataflow running through the regional Southeast IPM Center supported with mobile data input capacity. More than 200,000 historical data records have been transferred and curated which will enable data mining. Data will be ported nightly to a redesigned interactive mapping visualization tool on a virtual server designed to optimize utility in Extension programming and more rapidly visualize dynamic time series at point, local and regional scales.
Seed funding available for new projects
College of Agricultural Sciences faculty are invited to apply for the 2022 SAFES-RISE Seed Grant Program. Tenured, tenure track and fixed-term faculty who hold an appointment of half-time or greater at University Park or any Penn State Commonwealth Campus are eligible to apply. Proposals may support new or existing research programs that seek to increase research impact, grow faculty expertise in data and computing, or overcome hurdles in implementing such programs. Projects may utilize the expertise in RISE in data management platform creation, computing, programming, data visualization, and data exploration. Applications are due May 10, and the complete RFP with additional details on the seed grant program can be found on the SAFES web site. For questions, email email@example.com.
- Multi-institutional team to use AI to evaluate social, behavioral science claims
- Featured Researcher: Nick Tusay
- NSF invests in cyberinfrastructure institute to harness cosmic data
- Center for Immersive Experiences set to debut, serving researchers and students
- Distant Suns, Distant Worlds
- CyberScience Seminar: Researcher to discuss how AI can help people avoid adverse drug interactions
- AI could offer warnings about serious side effects of drug-drug interactions
- Taking RTKI drugs during radiotherapy may not aid survival, worsens side effects
- Cost-effective cloud research computing options now available for researchers
- Costs of natural disasters are increasing at the high end
- Model helps choose wind farm locations, predicts output
- Virus may jump species through ‘rock-and-roll’ motion with receptors
- Researchers seek to revolutionize catalyst design with machine learning
- Resilient Resumes team places third in Nittany AI Challenge
- ‘AI in Action’: Machine learning may help scientists explore deep sleep
- Clickbait Secrets Exposed! Humans and AI team up to improve clickbait detection
- Focusing computational power for more accurate, efficient weather forecasts
- How many Earth-like planets are around sun-like stars?
- Professor receives NSF grant to model cell disorder in heart
- SMH! Brains trained on e-devices may struggle to understand scientific info
- Whole genome sequencing may help officials get a handle on disease outbreaks
- New tool could reduce security analysts’ workloads by automating data triage
- Careful analysis of volcano’s plumbing system may give tips on pending eruptions
- Reducing farm greenhouse gas emissions may plant the seed for a cooler planet
- Using artificial intelligence to detect discrimination
- Four ways scholars say we can cut the chances of nasty satellite data surprises
- Game theory shows why stigmatization may not make sense in modern society
- Older adults can serve communities as engines of everyday innovation
- Pig-Pen effect: Mixing skin oil and ozone can produce a personal pollution cloud
- Researchers find genes that could help create more resilient chickens
- Despite dire predictions, levels of social support remain steady in the U.S.
- For many, friends and family, not doctors, serve as a gateway to opioid misuse
- New algorithm may help people store more pictures, share videos faster
- Head named for Ken and Mary Alice Lindquist Department of Nuclear Engineering
- Scientific evidence boosts action for activists, decreases action for scientists
- People explore options, then selectively represent good options to make difficult decisions
- Map reveals that lynching extended far beyond the deep South
- Gravitational forces in protoplanetary disks push super-Earths close to stars
- Supercomputer cluster donation helps turn high school class into climate science research lab
- Believing machines can out-do people may fuel acceptance of self-driving cars
- People more likely to trust machines than humans with their private info
- IBM donates system to Penn State to advance AI research
- ICS Seed Grants to power projects that use AI, machine learning for common good
- Penn State Berks team advances to MVP Phase of Nittany AI Challenge
- Creepy computers or people partners? Working to make AI that enhances humanity
- Sky is clearing for using AI to probe weather variability
- ‘AI will see you now’: Panel to discuss the AI revolution in health and medicine
- Privacy law scholars must address potential for nasty satellite data surprises
- Researchers take aim at hackers trying to attack high-value AI models
- Girls, economically disadvantaged less likely to get parental urging to study computers
- Seed grants awarded to projects using Twitter data
- Researchers find features that shape mechanical force during protein synthesis
- A peek at living room decor suggests how decorations vary around the world
- Interactive websites may cause antismoking messages to backfire
- Changing how government assesses risk may ease fallout from extreme financial events
- Predictability limit: Scientists find bounds of weather forecasting
- NSF funds three-year study of virtual-reality engineering simulations
- Mechanical force controls the speed of protein synthesis