talk-data.com

In this episode, we talk with Daniel, an astrophysicist turned machine learning engineer and AI ambassador. Daniel shares his journey bridging astronomy and data science, how he leveraged live courses and public knowledge sharing to grow his skills, and his experiences working on cutting-edge radio astronomy projects and AI deployments. He also discusses practical advice for beginners in data and astronomy, and insights on career growth through community and continuous learning.TIMECODES00:00 Lunar eclipse story and Daniel’s astronomy career04:12 Electromagnetic spectrum and MEERKAT data explained10:39 Data analysis and positional cross-correlation challenges15:25 Physics behind radio star detection and observation limits16:35 Radio astronomy’s advantage and machine learning potential20:37 Radio astronomy progress and Daniel’s ML journey26:00 Python tools and experience with ZoomCamps31:26 Intel internship and exploring LLMs41:04 Sharing progress and course projects with orchestration tools44:49 Setting up Airflow 3.0 and building data pipelines47:39 AI startups, training resources, and NVIDIA courses50:20 Student access to education, NVIDIA experience, and beginner astronomy programs57:59 Skills, projects, and career advice for beginners59:19 Starting with data science or engineering1:00:07 Course sponsorship, data tools, and learning resourcesConnect with Daniel Linkedin -   / egbodaniel   Connect with DataTalks.Club: Join the community - https://datatalks.club/slack.htmlSubscribe to our Google calendar to have all our events in your calendar - https://calendar.google.com/calendar/...Check other upcoming events - https://lu.ma/dtc-eventsGitHub: https://github.com/DataTalksClubLinkedIn -   / datatalks-club   Twitter -   / datatalksclub   Website - https://datatalks.club/

​In this episode, we’re joined by Daniel Egbo, an astrophysicist turned ML engineer and AI ambassador (Arize, Tavily). Daniel will talk about the moment he decided to try data science and ML and what he transferred from astronomy.

​We’ll delve into how he selects resources, stays motivated during self-learning, and overcomes obstacles.

​We plan to cover:

• ​Why Daniel decided to try data science and ML and skills from astronomy that helped
• ​How he chooses learning resources in a noisy landscape
• ​What keeps him motivated and the first steps when he feels stuck
• ​Building a career from Africa/remotely
• ​Daniel’s experience with ML Zoomcamp

​ ​About the speaker

​Daniel Egbo is an astrophysicist turned machine learning engineer and AI ambassador (Arize, Tavily). A PhD candidate at the University of Cape Town, he builds end-to-end ML and LLM applications with a focus on reliability and learning in public. His work spans knowledge-retrieval assistants, practical evaluation, and applying data science to astronomy. ​

Join our slack: https://datatalks.club/slack.html

Please join Charlottesville Data Science for the talk Ditch the Anxiety, Make Bold Moves, and Design Your Meaningful Tech Career by seasoned data science leader Kim Scott! We'll be gathering in person at Vault Virginia on the Downtown Mall.

→ Are you signed up for the Charlottesville Data Science Substack? If not, please consider subscribing at https://news.cvilleds.org. It's free, and it's the primary way we share announcements and event updates with the data science, AI, and machine learning community in Charlottesville and Central Virginia. ←

About the talk

For tech professionals who pride themselves on superior analytical thinking, it can be hard to admit that we’re, collectively speaking, quite emotionally dysregulated these days. With AI hype-mongering threatening livelihoods and massive government and big tech layoffs, I’m witnessing many colleagues going through an existential career crisis. There’s a lot of tactical advice out there for which new tech skills to develop, how to create a stunning personal brand, and so on. But frankly, tactics alone won't calm your nerves or get you where you want to go in the long run.

How do I know this? I’ve spent decades as a high-achieving career woman, with an impressive career taking me from astronomy to data science to product management, working in academia, corporate, and startups, and holding multiple leadership roles. At least…that’s what you can see from the outside. Internally, I was suffering from anxiety, trying (and failing) to maintain a persona I thought was necessary for success, and acting in ways that went against my core values. Fast forward to today, where I spend little time worrying, show up authentically, and have the self-efficacy to know I’m capable of shaping the career and life I want to live.

In this talk, I’ll start by discussing some of the common challenges tech professionals face today that are leading to an increase in anxiety, burnout, and disillusionment, including rapid technology changes, job insecurity, and challenging workplace cultures. Next, I’ll share the story of my own professional journey in data science, with a backstage pass to the not-so-pretty side. Along the way, I’ll teach how concepts and exercises in emotional agility, thought models, and coaching helped me develop the awareness, self-compassion, and self-love to break the anxiety cycle, manage challenging situations with a lot more ease, and finally make bold decisions that benefit me and align with my values. I’ll end with some practical tools and mindset shifts that can help you stay calm, collected, and able to direct your energy to what matters most. Even if everyone else is freaking out.

How to find us

Please enter the building using the side door on 3rd Street SE, right across 3rd Street from the Front Porch Music School, then take the stairs or elevator to the first floor. We'll be gathering in the Great Hall and Gallery area.

Please join Charlottesville Data Science for our first event since PyData Virginia 2025! Arthur Adams, a postdoctoral researcher in astronomy at the University of Virginia, will present the talk Code and the Art of Modeling Exoplanet Atmospheres. We'll be gathering in person at Vault Virginia on the Downtown Mall.

→ Are you signed up for the Charlottesville Data Science Substack? If not, please consider subscribing at https://news.cvilleds.org. It's free, and it's the primary way we share announcements and event updates with the data science, AI, and machine learning community in Charlottesville and Central Virginia. ←

About the talk

With the launch of the James Webb Space Telescope, major advances are being made in astronomy — especially in the characterization of extrasolar planets (“exoplanets”). With this rapid influx of unprecedented data, there has been an excitement in revisiting how we develop and adapt software, including machine learning and AI, to do science. In this talk, Arthur will provide a look at some tools in Python that many researchers currently use to model exoplanet atmospheres, discuss how he and his colleagues build collaborations to do more effective scientific inquiry, and offer a perspective on what tools are often under-appreciated to scaffold their push toward an increasingly ML/AI-supported field of research. He also wants to learn from the wider data science community how we can further improve our efforts!

The talk is intended as an overview and does not require much previous knowledge. However, it may be most engaging for those who:

1. Have a working knowledge of common Python design principles and software packages such as pandas and xarray, and
2. Are interested in a modestly technical look at current data analysis practices in exoplanet astronomy.

Extensive subject-matter knowledge is not needed; in fact, one of Arthur's goals is to expose these ideas to and get feedback from a wider audience with enthusiasm for science!

Arthur will also give a sneak peek of an early build of Potluck, an experimental project that models atmospheres, which is inspired by the ideas and challenges in the exoplanet modeling community. This code will be publicly available (as many in our field are) to all who are interested.

How to find us

Please enter the building using the side door on 3rd Street SE, right across 3rd Street from the Front Porch Music School, then take the stairs or elevator to the first floor. We'll be gathering in the Great Hall and Gallery area.

PyData Pittsburgh is excited to host our first event of 2025: Machine Learning in Astronomy. Join us on Tuesday, February 25, as Ashod Khederlarian, a 4th-year Ph.D. student at the University of Pittsburgh, shares state-of-the-art Machine Learning techniques being used to analyze vast astronomical datasets.

We have an exciting venue for this event—the Allegheny Observatory has graciously agreed to not only host the talk but also offer a free private tour exclusively for the PyData Pittsburgh group after the presentation! Don’t miss this opportunity to learn about cutting-edge AI applications in astronomy while exploring one of Pittsburgh’s most fascinating scientific landmarks.

Note: Attendance for this event is limited. Please RSVP only if you are committed to attending. Thank you.

About the talk:

Astronomy is an observational science. To understand the history and evolution of our universe and everything in it, our only option is to observe the night sky and test our theories against the observations. Current and next-generation observatories, such as the Dark Energy Spectroscopic Instrument, the Rubin Observatory, the Roman Space Telescope, and the Euclid Space Telescope will collect light coming from billions of galaxies and stars, resulting in 10s of terabytes of data per night. Most of this complex, high-dimensional data will not be seen by the naked eye, making data science and Machine Learning (ML) tools essential for analyzing them.

In this talk, Ashod will highlight how state-of-the-art ML techniques are being used in Astronomy. Particularly, he will focus on his work at the University of Pittsburgh on using simple neural networks to add realistic properties to galaxy simulations, using deep convolutional neural networks to make 3D maps of the universe, and using dimensionality reduction techniques to visualize high-dimensional datasets.

About the observatory:

The Allegheny Observatory is one of the major historic astronomical research institutions of the world. A short presentation about the institution will be shown followed by a walking tour of the building finally ending up at the 13" Fitz-Clark refractor.

Times: 7pm, Doors Open 7:30pm, Machine Learning in Astronomy Talk 8:30pm, Observatory Tour

Getting to the observatory:

Address: 159 Riverview Ave, Pittsburgh, PA 15214

If you are coming up 279 from Pittsburgh, take exit 3, Hazlett St. Turn left on East street. Continue north on East St. DO NOT turn left on Milroy. Your mapping program will reroute you: Continue on and bear left to stay on East street at the 4th light. Make a sharp left turn onto Perrysville Ave. Continue on to make a right turn at Riverview Ave.

You can park on the righthand side of the one way road that loops around the observatory, or in the parking lot for the nearby dog park. Enter through the main doors and proceed to the event room.

If you arrive at the front door and it is closed, please knock or buzz the bell. Thanks!

To use a handicapped-accessible ramp, park in the back of the observatory, use the ramp to the back door and ring the doorbell to the left of the door.

We are very happy to announce that we are organizing the 12th edition of the Eindhoven Data Community meetup. This time we will be back at one of our favourite locations, the Skybar in Microlab!

This meetup will be all about on how to make impact using Machine Learning. First, Maria Vechtomova, MLOps Tech Lead at Ahold Delhaize, will talk about how to standardize the processes around ML model deployment in order to significantly reduce time to production. Second, Yke Rusticus, ML engineer at Xebia Data, will tell more about how Vattenfall leverages data and AI to help customers get a grip on their energy consumption and help them become more sustainable one step at a time.

Leveraging data and AI to help customers become more sustainable one step at a time. Vattenfall's mission is to enable fossil free living in one generation. With gas prices rising and the effect of global warming becoming more apparent, more people are realising that we must act now. But where do you start? In this session, we will share how Vattenfall leverages data and AI to help customers get a grip on their energy consumption and help them become more sustainable one step at a time.

MLOps as a product 10 years ago, the first corporate companies started investing in data science. By now, most have multiple machine learning models running in production, but productionalizing new models takes longer than companies would like it to. The goal of MLOps is to standardize the processes around machine learning model deployment and significantly reduce time to production. In large organizations, this quickly pays off. Maria Vechtomova believes that MLOps should be viewed as a product, and therefore managed as a product. In her talk, she will walk through the components of an MLOps platform (such as MLOps infrastructure, reusable deployment pipelines and governance) and the composition of the ideal MLOps product team.

Program

• 17:00 – 18:00 🍕 Food
• 18:00 – 18:10 🎤 Welcome
• 18:10 – 19:00 🎤 Yke Rusticus - Leveraging data and AI to help customers become more sustainable one step at a time.
• 19:00 – 19:15 ⏸️ Break
• 19:15 – 20:00 🎤 Maria Vechtomova - MLOps as a product
• 20:00-21:00 🥤 Drinks

Speaker 1: Yke Rusticus Yke is a Machine Learning Engineer at Xebia Data with a background in astronomy and artificial intelligence. In the industry, he learned that models and algorithms often do not get past the experimentation phase, leading him to specialise in MLOps to bridge the gap between experimentation and production. As a professional in this field, Yke has developed ML platforms and use cases across different cloud providers, and is passionate about sharing his knowledge through tutorials and trainings.

Speaker 2: Maria Vechtomova Maria is a Lead ML Engineer at Ahold Delhaize, bridging the gap between data scientists infra and IT teams at different brands and focusing on standardization of ML model deployments across all the brands of Ahold Delhaize. Maria believes that a model only starts living when it is in production. For this reason, last seven years, she focused on MLOps. Together with Basak and Raphael, running Marvelous MLOps. For more info, follow Marvelous MLOps on Substack: https://marvelousmlops.substack.com

We talked about:

Daynan’s background Astronomy vs cosmology Applications of data science and machine learning in astronomy Determining signal vs noise What the data looks like in astronomy Determining the features of an object in space Ground truth for space objects Why water is an important resource in the space economy Other useful resources that can be found in asteroids Sources of asteroids The data team at an asteroid mining company Open datasets for hobbyists Mission and hardware design for asteroid mining Partnerships and hires

Links: 

LinkedIn: https://www.linkedin.com/in/daynan/ We're looking for a Sr Data Engineer: https://boards.eu.greenhouse.io/karmanplus/jobs/4027128101?gh_jid=4027128101 Minor Planet Center: https://minorplanetcenter.net/- JPL Horizons has a nice set of APIs for accessing data related to small bodies (including asteroids): https://ssd.jpl.nasa.gov/api.html ESA has NEODyS: https://newton.spacedys.com/neodys   IRSA catalog that contains image and catalog data related to the WISE/NEOWISE data (and other infrared platforms): https://irsa.ipac.caltech.edu/frontpage/ NASA also has an archive of data collected from their various missions, including a node related to small bodies: https://pds-smallbodies.astro.umd.edu/ Sub-node directly related to asteroids: https://sbn.psi.edu/pds/ Size, Mass, and Density of Asteroids (SiMDA) is a nice catalog of observed asteroid attributes (and an indication of how small our sample size is!): https://astro.kretlow.de/?SiMDA The source survey data, several are useful for asteroids: Pan-STARRS (https://outerspace.stsci.edu/display/PANSTARRS)

MLOps Zoomcamp: https://github.com/DataTalksClub/mlops-zoomcamp

Join DataTalks.Club: https://datatalks.club/slack.html

Our events: https://datatalks.club/events.html