About
I have extensive experience going from research ideas and raw data to implementation and…
Activity
-
Weather prediction requires (1) observations, (2) data assimilation techniques and (3) a weather model for forecasting. End-to-end prediction in NWP…
Weather prediction requires (1) observations, (2) data assimilation techniques and (3) a weather model for forecasting. End-to-end prediction in NWP…
Liked by Jacob Bieker
-
I did some throughput comparisons between vanilla ViTs + mamba_out (suggested by Ross Wightman) and MambaVision. To my surprise, the ViT models are…
I did some throughput comparisons between vanilla ViTs + mamba_out (suggested by Ross Wightman) and MambaVision. To my surprise, the ViT models are…
Liked by Jacob Bieker
-
The latest FuXi weather model makes me think the days of NWP for data assimilation are numbered. https://lnkd.in/gXfgrZeh This excellent…
The latest FuXi weather model makes me think the days of NWP for data assimilation are numbered. https://lnkd.in/gXfgrZeh This excellent…
Liked by Jacob Bieker
Experience
Education
-
Leiden University
-
Masters degree in Astronomy and Data Science
Courses in neural networks, astrophysics, spacecraft systems design, detector development, statistics, and scientific communication. -
-
Activities and Societies: Society of Physics Students, Student Researcher in variety of fields, Design For America, Oregon Observation Remote Control Center
Received Stamps Leadership Scholarship, Presidential Undergraduate Research Scholar
Thesis: Using Deep Learning for FACT Source Detection - Passed with Distinction
Departmental Honors in both Physics, Computer and Information Science
Robert D. Clark Honors College
-
-
Activities and Societies: Aarhus Lacrosse, SONG Telescope, Studenthaus
Trans-Atlantic Science Student Exchange Program (TASSEP)
Studied Astronomy and Computer Science as part of my Bachelor's degree for the University of Oregon -
-
Activities and Societies: FIRST Robotics Club; Engineering Club; Theater Stage Crew; National Honors Society; Lot Whitcomb Tutor; Dean's List: 4 years; Outdoor School Camp Counselor; Starting Varsity Lacrosse Defender: 3 years; JV2 Soccer; JV Track and Field: Shotput, Javelin, Discus; JV Cross Country
Salutatorian
STEM Scholar
4.17 GPA
3 years of German - Part of German-American Partnership Program Exchange 2012
AP Biology Award
Honors Biology Award
Multimedia and Web Development Award
Licenses & Certifications
Volunteer Experience
-
GSoC Mentor
Open Climate Fix
- Present 4 months
Environment
I help mentor GSoC contributors for AI weather model development for GSoC 2024.
-
Machine Learning Researcher
International Telecommunication Union
- Present 2 years 2 months
Environment
As part of Project Resilience (https://www.itu.int/en/ITU-T/extcoop/ai-data-commons/Pages/project-resilience.aspx) I am helping to build an MVP for an AI utility to help policy makers, NGOs, academics and others act on the UN Sustainability Development Goals. Part of the Data Science track.
-
-
Tutor
Metropolitan Family Services
- 1 year 7 months
Education
Worked individually and in groups to tutor students in math, science and as part of their Engineering Club
Publications
-
Data Assimilation using ERA5, ASOS, and the U-STN model for Weather Forecasting over the UK
NeurIPS 2023 Climate Change AI Workshop
In recent years, the convergence of data-driven machine learning models with Data Assimilation (DA) offers a promising avenue for enhancing weather forecasting. This study delves into this emerging trend, presenting our methodologies and outcomes. We harnessed the UK's local ERA5 850 hPa temperature data and refined the U-STN12 global weather forecasting model, tailoring its predictions to the UK's climate nuances. From the ASOS network, we sourced t2m data, representing ground observations…
In recent years, the convergence of data-driven machine learning models with Data Assimilation (DA) offers a promising avenue for enhancing weather forecasting. This study delves into this emerging trend, presenting our methodologies and outcomes. We harnessed the UK's local ERA5 850 hPa temperature data and refined the U-STN12 global weather forecasting model, tailoring its predictions to the UK's climate nuances. From the ASOS network, we sourced t2m data, representing ground observations across the UK. We employed the advanced kriging method with a polynomial drift term for consistent spatial resolution. Furthermore, Gaussian noise was superimposed on the ERA5 T850 data, setting the stage for ensuing multi-time step virtual observations. Probing into the assimilation impacts, the ASOS t2m data was integrated with the ERA5 T850 dataset. Our insights reveal that while global forecast models can adapt to specific regions, incorporating atmospheric data in DA significantly bolsters model accuracy. Conversely, the direct assimilation of surface temperature data tends to mitigate this enhancement, tempering the model's predictive prowess.
-
Discovering Effective Policies for Land-Use Planning [Best Pathway to Impact]
NeurIPS 2023 Climate Change AI Workshop
How areas of land are allocated for different uses, such as forests, urban, and agriculture, has a large effect on carbon balance, and therefore climate change. Based on available historical data on changes in land use and a simulation of carbon emissions/absorption, a surrogate model can be learned that makes it possible to evaluate the different options available to decision-makers efficiently. An evolutionary search process can then be used to discover effective land-use policies for…
How areas of land are allocated for different uses, such as forests, urban, and agriculture, has a large effect on carbon balance, and therefore climate change. Based on available historical data on changes in land use and a simulation of carbon emissions/absorption, a surrogate model can be learned that makes it possible to evaluate the different options available to decision-makers efficiently. An evolutionary search process can then be used to discover effective land-use policies for specific locations. Such a system was built on the Project Resilience platform and evaluated with the Land-Use Harmonization dataset and the BLUE simulator. It generates Pareto fronts that trade off carbon impact and amount of change customized to different locations, thus providing a potentially useful tool for land-use planning.
-
Advances in solar forecasting: Computer vision with deep learning
Advances in Applied Energy
Renewable energy forecasting is crucial for integrating variable energy sources into the grid. It allows power systems to address the intermittency of the energy supply at different spatiotemporal scales. To anticipate the future impact of cloud displacements on the energy generated by solar facilities, conventional modeling methods rely on numerical weather prediction or physical models, which have difficulties in assimilating cloud information and learning systematic biases. Augmenting…
Renewable energy forecasting is crucial for integrating variable energy sources into the grid. It allows power systems to address the intermittency of the energy supply at different spatiotemporal scales. To anticipate the future impact of cloud displacements on the energy generated by solar facilities, conventional modeling methods rely on numerical weather prediction or physical models, which have difficulties in assimilating cloud information and learning systematic biases. Augmenting computer vision with machine learning overcomes some of these limitations by fusing real-time cloud cover observations with surface measurements acquired from multiple sources. This Review summarizes recent progress in solar forecasting from multisensor Earth observations with a focus on deep learning, which provides the necessary theoretical framework to develop architectures capable of extracting relevant information from data generated by ground-level sky cameras, satellites, weather stations, and sensor networks. Overall, machine learning has the potential to significantly improve the accuracy and robustness of solar energy meteorology; however, more research is necessary to realize this potential and address its limitations.
-
Comparing the carbon costs and benefits of low-resource solar nowcasting
NeurIPS 2022 Workshop on Tackling Climate Change with Machine Learning
Mitigating emissions in line with climate goals requires the rapid integration of low carbon energy sources, such as solar photovoltaics (PV) into the electricity grid. However, the energy produced from solar PV fluctuates due to clouds obscuring the sun's energy. Solar PV yield nowcasting is used to help anticipate peaks and troughs in demand to support grid integration. This paper compares multiple low-resource approaches to nowcasting solar PV yield. To do so, we use a dataset of UK…
Mitigating emissions in line with climate goals requires the rapid integration of low carbon energy sources, such as solar photovoltaics (PV) into the electricity grid. However, the energy produced from solar PV fluctuates due to clouds obscuring the sun's energy. Solar PV yield nowcasting is used to help anticipate peaks and troughs in demand to support grid integration. This paper compares multiple low-resource approaches to nowcasting solar PV yield. To do so, we use a dataset of UK satellite imagery and solar PV energy readings over a 1 to 4-hour time range. Our work investigates the performance of multiple nowcasting models. The paper also estimates the carbon emissions generated and averted by deploying models such as these, and finds that short-term PV forecasting may have a benefit several orders of magnitude greater than its carbon cost and that this benefit holds for small models that could be deployable in low-resource settings around the globe.
-
Automated Radio Source Component Association and Cross-Identification for LoTSS
European Astronomical Society Meeting 2020
-
The Evolution of Bulge-Dominated Field Galaxies from z~1 to the Present
The Astrophysical Journal
-
Life in Low Density Enviroments - Field Galaxies from Z-1.0 to the Present
International Astronomical Union Poster
Manuscript ID: IAU-15-S319-0355
Other authors -
Projects
-
Meme Machine
Worked with three other students to develop a user interface and backend for a chat encryption and image manipulation program for the final project for CIS 330, C/C++ and Unix class.
-
CHYMERA Visualization
- Present
Worked on developing 3d visualizations for the CHYMERA accretion disk and supernovae simulations using VisIT and Silo.
-
Gene Sequencing Barcode Generator
Created a program to generate unique barcodes for use in T-cell Receptor sequencing and other gene sequencing projects, with an emphasis on Illumina sequencing machines.
-
T-cell Receptor Sequence Normalization and Analysis
Worked on normalizing TCR sequence data for researchers part of the Stand Up 2 Cancer pancreatic cancer team.
Normalized data based on spiked reads, created data visualizations based off the genetic reads. -
Data Visulization for Genomics Data
I worked on creating software to create visulizations of genomics data from the Brenden Colson Center and the Stand Up 2 Cancer groups.
-
Research Experience for Undergraudates Utility
- Present
A Django web-based interface created to make administration, application, and generally the whole process of running a Research Experience for Undergraduates (REU) program easier and more user friendly.
-
Adding support for importing Corless Genetic data into Beacon database
I added support for importing the CSV files that Corless creates into the Beacon SQLite database. Beacon is a project by the Global Alliance For Genomics and Health to test the willingness of institutions to share their genomics data. More information is available here: http://genomicsandhealth.org/work-products-demonstration-projects/beacon-project-0
-
Insights - Personal Data Analysis
- Present
I am building a series of Python and R scripts to take data from Google Takeout, Facebook data download, Linkedin Data export, along with local photos, and live data from various services, combine all the data in a SQLite database, and then run analysis on that data.
-
Stand Up 2 Cancer Data Analysis
Worked as part of the Computational Biology department at OHSU on creating scripts and programs in R to help with data collection and analysis for researchers part of the Stand Up 2 Cancer Dream Team.
-
Gemini/Hubble Space Telescope Galaxy Cluster Project Data Analysis
Currently working on analyzing and visualizing data from field galaxies as part of the Galaxy Cluster Project.
-
Venture Dept. Labs Telescope Competition
Participated in the hackathon to make a project that conveys an astronomical idea or concept in an easy to understand, unique, digital way. Created the website over the course of two days.
-
CHYMERA Computational Fluid Dynamics Simulations
- Present
The goal is to develop computational fluid dynamics simulations for Rossby Wave Instabilities and Supernovae simulations.
-
Camera Control For Myo
- Present
An Android app taking advantage of Thalmic Lab's Myo Armband to control an Android camera through gestures and muscle movements.
-
General User Interface for Control of Robotic Dome
- Present
Built a general user interface to control the dome of the robotic telescope the University of Oregon runs as part of the Pine Mountain Observatory in Eastern Oregon.
-
Using Deep Learning for FACT Source Detection
-
This project was originally used for the thesis requirement for the Robert D. Clark Honors College, Department of Physics, and Department of Computer Science at the University of Oregon. It was successfully defended in May 2018 and I passed with distinction.
This project focuses on using convolutional neural networks to perform analysis of air shower events for the First G-APD Cherenkov Telescope (FACT), located in the Canary Islands. -
ATLAS Luminosity Data Visualization
-
Developed visualizations with ROOT of data from the ATLAS LUCID and BCM detectors
-
STEM Scholar Capstone Project: Exoplanets Android App
-
For a senior capstone project, I worked on and developed and Android application to take data from the Open Exoplanet Catalogue and display it on Android devices.
Honors & Awards
-
DAAD RISE Germany Scholar
Deutscher Akademischer Austauschdienst
Research Scholarship to work in a Germany University for the summer.
-
Dean's List Winter Term 2016
University of Oregon Honors College
-
Dean's List Fall Term
University of Oregon
-
ACM Division 1 Northwest Regional Competition
Association for Computing Machinery
My team from the University of Oregon got 2nd place at the Oregon site, and 21st overall, for the Division 1 ACM Regional competition for the Pacific Northwest.
-
Venture Labs: Telescope Competition First Place
Venture Department, Emerald Media Group
Created a website to promote scientific literacy, especially in astronomy, that was unique and was experienced through a screen. Viewable at www.gravitysdance.com, the site will be used with high school students, incoming freshman, and other undergraduate students to promote interest in the sciences and science literacy.
-
Dean's List for Fall Term
Univeristy of Oregon Robert D. Clark Honors College
-
Stamps Leadership Scholarship
University of Oregon and Samps Foundation
The Stamps Family Charitable Foundation partners with visionary colleges and universities, including the University of Oregon, to award multi-year scholarships that enable extraordinary educational opportunities. The Stamps Family Foundation's mission is to build a nationally prestigious merit-based scholarship program that supports exceptional students as they become leaders throughout society.
Stamps Scholars are driven and talented individuals with proven leadership skills who are…The Stamps Family Charitable Foundation partners with visionary colleges and universities, including the University of Oregon, to award multi-year scholarships that enable extraordinary educational opportunities. The Stamps Family Foundation's mission is to build a nationally prestigious merit-based scholarship program that supports exceptional students as they become leaders throughout society.
Stamps Scholars are driven and talented individuals with proven leadership skills who are supported by multi-year awards to work toward their long-term goals.
Languages
-
English
Native or bilingual proficiency
-
German
Elementary proficiency
Organizations
-
Design For America
-
- PresentI worked on developing sustainable footwear for Eugene homeless residents. I went through the entire design process and worked with product designers, manufacturers, and green chemists.
-
Summer Program For Undergraduate Research (SPUR)
Web Developer
- Present -
Oregon Observation Remote Control Center
Software Developer
- Present -
American Astronomical Society
-
More activity by Jacob
-
You want to push the limits of what is possible with machine learning in Earth system modeling? Join us at ECMWF for the WeatherGenerator project, a…
You want to push the limits of what is possible with machine learning in Earth system modeling? Join us at ECMWF for the WeatherGenerator project, a…
Liked by Jacob Bieker
-
The Nvidia Pruning and Distillation paper is a technical masterpiece. LLMs like Llama 3.1 405B and NVIDIA Nemotron-4 340B excel in many tasks but…
The Nvidia Pruning and Distillation paper is a technical masterpiece. LLMs like Llama 3.1 405B and NVIDIA Nemotron-4 340B excel in many tasks but…
Liked by Jacob Bieker
-
We have now seen the first results from all 4 EarthCARE’s instruments: and let me tell you, they are truly promising! The latest ones to come in…
We have now seen the first results from all 4 EarthCARE’s instruments: and let me tell you, they are truly promising! The latest ones to come in…
Liked by Jacob Bieker
-
So: interested in running a data driven global weather prediction model, which uses multiple inputs (more than ERA5), at a higher resolution (0.1…
So: interested in running a data driven global weather prediction model, which uses multiple inputs (more than ERA5), at a higher resolution (0.1…
Liked by Jacob Bieker
-
Excited to announce the public code release of Aurora - a foundation model for atmospheric forecasting! 🌍 ⛅ Code: https://lnkd.in/dsaGx_hr Docs:…
Excited to announce the public code release of Aurora - a foundation model for atmospheric forecasting! 🌍 ⛅ Code: https://lnkd.in/dsaGx_hr Docs:…
Liked by Jacob Bieker
-
My good friends at Ducky are hiring a founding engineer. If you’re interested in helping companies better enable their customers by empowering…
My good friends at Ducky are hiring a founding engineer. If you’re interested in helping companies better enable their customers by empowering…
Liked by Jacob Bieker
-
Accelerating Weather Prediction with AI. The Triple Point® is back after a month "off" and excited to share the latest episode! A lot has changed…
Accelerating Weather Prediction with AI. The Triple Point® is back after a month "off" and excited to share the latest episode! A lot has changed…
Liked by Jacob Bieker
-
With every year that passes, the impacts of climate change become increasingly evident around the world. Now, more than ever, is an exciting time to…
With every year that passes, the impacts of climate change become increasingly evident around the world. Now, more than ever, is an exciting time to…
Liked by Jacob Bieker
-
Excited to share this new research led by Jaideep Pathak on autoregressive AI for km-scale atmospheric prediction. Exciting to see the first glimmers…
Excited to share this new research led by Jaideep Pathak on autoregressive AI for km-scale atmospheric prediction. Exciting to see the first glimmers…
Liked by Jacob Bieker
-
Looking forward to reading the latest AI weather research from #NVIDIAResearch https://nvda.ws/3SQUeCb. It’s nice to see diffusion gaining…
Looking forward to reading the latest AI weather research from #NVIDIAResearch https://nvda.ws/3SQUeCb. It’s nice to see diffusion gaining…
Liked by Jacob Bieker
-
🚀 𝗔𝘄𝗲𝘀𝗼𝗺𝗲 𝗪𝗲𝗮𝘁𝗵𝗲𝗿 𝗙𝗼𝗿𝗲𝗰𝗮𝘀𝘁𝗶𝗻𝗴 𝘄𝗶𝘁𝗵 𝗢𝗽𝗲𝗻-𝗦𝗼𝘂𝗿𝗰𝗲 𝗔𝗜 🌦️ Exciting developments in the world of AI-driven…
🚀 𝗔𝘄𝗲𝘀𝗼𝗺𝗲 𝗪𝗲𝗮𝘁𝗵𝗲𝗿 𝗙𝗼𝗿𝗲𝗰𝗮𝘀𝘁𝗶𝗻𝗴 𝘄𝗶𝘁𝗵 𝗢𝗽𝗲𝗻-𝗦𝗼𝘂𝗿𝗰𝗲 𝗔𝗜 🌦️ Exciting developments in the world of AI-driven…
Liked by Jacob Bieker
-
Today I announce my resignation as TransitionZero's CTO. In my almost two years leading TransitionZero's technical team, we grew the organisation…
Today I announce my resignation as TransitionZero's CTO. In my almost two years leading TransitionZero's technical team, we grew the organisation…
Liked by Jacob Bieker
-
📣 🔍 New FAQ out on the EU's Corporate Sustainability Reporting Directive (CSRD)! As companies prepare for the first year of reporting under the…
📣 🔍 New FAQ out on the EU's Corporate Sustainability Reporting Directive (CSRD)! As companies prepare for the first year of reporting under the…
Liked by Jacob Bieker
-
A personal update aimed at my friends and colleagues in the oceanography and climate research community. I have officially left Columbia University…
A personal update aimed at my friends and colleagues in the oceanography and climate research community. I have officially left Columbia University…
Liked by Jacob Bieker
-
Earth’s future climate simulated at 9 km global resolution, A team of scientists from the IBS Center for Climate Physics in South Korea and the…
Earth’s future climate simulated at 9 km global resolution, A team of scientists from the IBS Center for Climate Physics in South Korea and the…
Liked by Jacob Bieker
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore MoreOthers named Jacob Bieker
-
Jacob Bieker
Maintenance Technician at Evansville Vanderburgh Public Library
-
Jake Bieker
Mortgage/Consumer Loan Officer at First Kansas Bank
-
Jacob Von Bieker
Avionics Technician at Canadian Armed Forces | Forces armées canadiennes
-
Jacob Von Bieker
--
4 others named Jacob Bieker are on LinkedIn
See others named Jacob Bieker