Featured Researcher: Weiming HuPosted on April 30, 2021
With an interest in geography, machine learning, and data-intensive research, Weiming Hu considers himself lucky to have been admitted into Penn State’s Geography Ph.D. program, where he works on ensemble weather forecast models with his advisor, Guido Cervone. Weiming hopes his research can impact renewable energy forecasts, and he hopes to one day collaborate with the National Center for Atmospheric Research.
How did you get into this research field?
I studied Geographic Information Science during my undergraduate and I was intrigued by what data enable us to accomplish. That was the time when I was exposed to ideas like Internet of Things and Big Data. I started to believe that an adequate ability to process data and summarize information would be increasingly important throughout the process of scientific discovery and industrial innovation.
I was looking for opportunities to pursue my interest that is both data intensive and geographic. I came across Penn State Geography and my current advisor, Guido Cervone. He holds a doctorate in Computer Science and he specializes in Machine Learning, Numerical Modeling, and Computational Algorithms. This was exactly what I was looking for, a niche that is both geographic and computational. I submitted my application and I am lucky to spend my five years at Penn State as a graduate student.
How does supercomputing enable your research?
Supercomputers play a crucial role in my research. My research focuses on ensemble weather forecasts and how to utilize machine learning to improve our status quo forecasts. Weather simulations take time, mostly due to its complex equations and the high spatio-temporal resolution. Running an ensemble of such weather simulations is even more tasking. Supercomputers make it possible to run computational tasks at scale so that I discover phenomena that might not be observable on a small scale.
Data management is another reason for me to use supercomputers. Forecast ensemble data can easily exceed TB. Transferring and analyzing such bulk of data locally on a desktop is not feasible. There are a series of toolboxes on Roar that enables me to directly interact with data on Roar. Supercomputers have made the analysis and visualization process much more accessible.
What is your academic background?
I received my B.Sci. from Wuhan University in Geographic Information Science. After undergraduate, I came to Penn State to pursue my M.S. and Ph.D. in Geography. I received my M.S. in 2018 and I’m currently working towards my Ph.D. under the supervision of Prof. Guido Cervone.
What are the big problems you hope this research solves?
Weather forecasts are crucial for renewable energy production forecasts, like wind and photovoltaic solar energy. I hope my research would ultimately contribute to the ongoing penetration of renewable energy into the electricity grid.
The reliance on fossil fuels for power generation is not sustainable for meeting the increasing demand of a growing global economy and population. However, while in abundance, renewable energy, like wind and solar, is volatile and the harvest of such energy sources is subject to a largely different source of uncertainty. For example, weather conditions and geographic locations both have an impact on the predictability of energy availability.
My research aims to reduce this uncertainty by using ensemble forecasts and machine learning, improving our status quo forecast quality. I hope to bring my contribution to this “green” movement by using my skills on data analysis, machine learning, and high-performance computing.
What is your elevator pitch for your research?
My research focuses on improving predictions of renewable energy generation from sources like wind and photovoltaic solar.
Day-ahead forecasts of wind and solar availability specifically has market values because the information helps to schedule and coordinate power generation from different sources. The more accurate we can predict wind and solar availability, the more we can rely on renewable sources and less on fossil fuel natural gas.
Specifically, I use ensemble forecasts and machine learning to accomplish better forecasts. Ensembles provide probability information that quantifies the forecast uncertainty. Machine learning models can encode non-linear relationship that is otherwise hard to capture. My research is computationally intensive because it relies on a large repository of both observed and simulation data.
What – or who – are your dream collaborations and collaborators in other fields or disciplines?
National Center for Atmospheric Research (NCAR) has always be a dream collaboration. It has the top research in atmospheric and climate sciences.
What types of interdisciplinary collaborations would you like to build in the future?
I have always seen myself at the intersection of GIScience, Atmospheric Science, and Computer Science. My research has mostly involved renewable energy forecast and I believe it is a great topic to build upon using my education and skills from the three fields. Wind and solar heavily depends on weather conditions, and therefore, accurate weather forecast is the first step towards better energy production forecast. Running weather models and energy performance simulations are computationally expensive. Therefore, knowledge on high-performance computing and supercomputers is desired. Finally, the problem has a geospatial component, meaning location matters. Specifically, any optimization of energy production would have an important component regarding its location and the surrounding environment. I hope to build interdisciplinary collaboration from these aspects.
What’s your favorite sound?
Well. There are actually two if I may. I’m a guitar player so I definitely want to mention the pluck of guitar strings.
Another sound is the spinning fan of my computer. Because that typically means my program is up and running, and no errors have (yet) interrupted the process.
If you had unlimited money, what projects would you take on?
What’s your advice for would-be scientists?
Doing research might seem lonely and hidden because you are likely to be the one person who understand the topic with such great depth and detail. But in reality, it can be interactive and socialized. Understanding the commonality is important because in recent days, problems at hand are global and interdisciplinary, and they require interdisciplinary solutions.
What profession other than your own would you enjoy?
Being in a rock band.
Favorite hobbies/pastimes that have nothing to do with your professional work?
Playing the guitar.
What’s in your Spotifiy (or other app) playlist?
I set up my own music library and streaming services (https://weiming-hu.github.io/) via the open-source platform Nextcloud.
- Featured Researcher: Nick Tusay
- Multi-institutional team to use AI to evaluate social, behavioral science claims
- 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
- Algorithm aims to alert consumers before they use illicit online pharmacies
- Scientists tap AI betting agents to help solve research reproducibility concerns
- Deep learning may help doctors choose better lung cancer treatments
- Using cues and actions to help people get along with artificial intelligence