PyData Hamburg March Meetup

Hi Pythonistas
this time it's about robots and satellites .... do we need to say more? Our speakers are going to tell us two fascinating science-fact stories and how to make them real with the help of open source data analysis tools.

What you need to know to participate in remote meetups:

• Our virtual room capacity is limited to 300 attendees. So RSVP on meetup.com please and do take the time to cancel if you cannot join.
• The link to the Zoom meeting will be displayed to you on meetup.com when you RSVP. Please do not share it.
• You need to be logged in with a free Zoom account - this is an anti-troll measure.
• Please check in a few minutes before the event starts so we can support you with questions about access.

Take care, stay healthy and see you soon!

Your PyData crew

-------------------------------------------
# Networking: join at 18:15h, bring a beverage and meet other attendees sharing your interest in data science, machine learning, AI etc. - the talks will start at 18:30h

-------------------------------------------

# (Talk 1) Stefanie Stoppel & Angelie Kraft: From RGB-D images to complete point clouds

Imagine you own a household robot that cleans, cooks and does errands for you. When you tell it to go fetch your favorite coffee mug, the robot not only needs to know what that mug looks like in order to locate it in your apartment, but it should also anticipate its full 3D shape in order to grasp it and bring it to you. We are going to highlight the first steps we took in order to transfer some of these abilities to robotic grasping, by creating an end-to-end Deep Learning pipeline that takes an RGB-D image of an object as input and infers its complete 3D representation in the form of a point cloud.

Stefanie is currently pursuing a Master’s degree to become a Machine Learning Engineer. She likes automating ML workflows and cares about bias, fairness & explainability in AI.

Angelie is currently working on her Master's thesis on Bias Mitigation in Natural Language Processing. She is also co-founder of the young start-up AdaLab.ai which provides customers from research and industry with state-of-the-art ML solutions.

-------------------------------------------

# (Talk 2) Ron Hagensieker & Freddie Kalaitzis: Where are the Earth's streams flowing right now? - Dynamic hydrology maps from satellite-LiDAR fusion

The audience will learn about Very High Resolution satellite imagery and LiDAR, and the fusion of these sensor data through multi-sensor U-Nets, for the mapping of flowing networks at the continental scale, every day, stacking the times series maps over many years. The end result is a new map that could fundamentally improve how we manage our water resources around the world.

Pix2Streams reprint:
https://arxiv.org/abs/2011.07584
(accepted as a spotlight oral talk at the AI for Earth Sciences Workshop, NeurIPS 2020)

Pix2Streams demo:
https://drive.google.com/file/d/1IOXFfM1hY0QnZp1j5xQO1gviKwL2FtSP/view

Ron is a machine learning engineer and remote sensing scientist. His work in remote sensing covers a wide range in applications and methods, ranging from deforestation to naval monitoring; classic segmentation to experimental generative methods; multi-spectral to Synthetic Aperture Radar.

Freddie is a part-time Senior Research Fellow, and Theme Lead of ML for Earth Observation and Remote Sensing, in the Oxford Applied and Theoretical Machine Learning lab of Oxford University. He's also an ML & Project Lead at NASA's Frontier Development Lab (FDL), and the ML Lead of Trillium Technologies , the R&D production company behind FDL.

-------------------------------------------

PyData is a community for developers and users of open source data tools. PyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. The PyData Code of Conduct governs this meetup.