UPP Alumni Profile: Pascal Caraccioli-Salinas

Get to know Pascal

Who were your USGS supervisor and PSU advisor? 

Stanley Mordesnky (smordensky@usgs.gov ) and John Lipor (lipor@pdx.edu ).

Provide a link to your project website, publication, or presentation (if applicable).

• Separating signals in elevation data improves supervised machine learning predictions for hydrothermal favorability.
• Improving Supervised Machine Learning Predictions for Hydrothermal Favorability by Separating Signals in Elevation Data.
• Don’t Let Negatives Hold You Back: Accounting for Underlying Physics and Natural Distributions of Hydrothermal Systems When Selecting Negative Training Sites Leads to Better Machine Learning Predictions.

What were your primary responsibilities/roles of your research position? 

My role was to conduct independent research on geothermal machine learning. It implied writing scripts on python, data analysis and interpretation and paper writing. 

What did you learn from this experience? 

This experienced confirm my passion for science and allowed me to pursue a PhD at the school of my top choice.

What aspects of your project did you enjoyed the most?

Doing the science, interpreting the data. I also enjoyed interacting with my advisor. 

What are you doing now?

I'm pursuing a PhD in Geological Sciences at Cornell.

Which PSU courses have been the most useful to you in your job(s) since graduation? 

Multilevel methods and Large Data Algorithms (Mth 371). 

Are there any courses you now wish you had taken at PSU, based on your job requirements? 

Partial differential equations, signal processing, fluid mechanics, stochastic fluid mechanics.