Summer Internship

• Internship duration: approximately 400 hours during November 2024 - February 2025 (dates are flexible)

• Location: preferably Wellington or Alexandra, but we are open to remote working for the right candidate

• Remuneration: $24.50 per hour

About the Project

We are looking for a summer intern to contribute to the research project "DeepWeather: Using artificial intelligence to improve weather forecasts", which is a 2.5 year $1M project funded by MBIE's Endeavour Smart Ideas fund.

Bodeker Scientific is leading the project, and the project team comprises team members from MetService, British Antarctic Survey, University of Waikato, He Oranga Trust, and RedSky AI, with expertise from across NZ, UK, and USA.

In DeepWeather, we are applying artificial intelligence methods to develop a new way of generating weather forecasts, producing high-resolution forecasts at a fraction of current costs. A neural network (NN) is being trained to learn how to generate weather at hyperlocal scales (several 100m) given data from a lower resolution numerical weather prediction (NWP) model. While the initial training may be computationally expensive, once trained, the NN can be applied to any NWP forecast to fill in the missing detail inside each grid-cell, at negligible cost. This cost reduction means that we can generate higher resolution forecasts than are currently available, and process many more forecasts to produce probabilistic risk assessments of rare but highly damaging events.

If successful, our fused-NN-NWP model will be incorporated into MetService’s NWP chain, delivering new hyperlocal weather forecasts, enhancing the ability of emergency managers to save lives and protect property, and industries to manage risks and minimise losses. The need for such forecasts will only increase as the frequency and severity of extreme weather events increase under climate change.

Your Role

You will participate in the development and validation of machine learning (ML) models created for the DeepWeather project, helping with the following tasks:

• Research and develop validation methods which correlate well with physical consistency and high-fidelity outputs.

• Compare models to each other and available dynamical weather forecasts.

• Enforce physics constraints into ML models to produce physically-realistic weather forecasts.

• Incorporate ensemble forecasting methods into the ML models.

• Document code and abide by open-source software best practices.

• Be a contributing author to publications.

Skills/Attributes

• Degree in computer science, data science, information and computer engineering, or equivalent.

• Adept in Python programming.

• Some working knowledge of artificial intelligence with a focus on deep-learning.

• Well-developed written and verbal communication skills.

• Self-motivated and works well in a team.

• Experience in computing in the cloud would be advantageous.

How to Apply

To apply for this summer internship opportunity, please email the following to annabel@bodekerscientific.com by 30 September 2024 midnight:

1. CV

2. Cover letter explaining why you're interested in this internship, and highlighting your experience and skills relevant to the role

3. Examples of code you've written (preferrably in Python), or a link to any GitHub repositories of your code

If you have any questions, please contact annabel@bodekerscientific.com