University of Miami
Post Doctoral Associate - Improving Subseasonal Precipitation Forecasts
University of Miami, Miami, Florida, United States, 33101
Post Doctoral Associate - Improving Subseasonal Precipitation Forecasts with Machine Learning
The University of Miami Rosenstiel School of Marine, Atmospheric, and Earth Science is seeking to hire a Post Doctoral Associate to work at the intersection of atmospheric science and machine learning to improve subseasonal precipitation forecasts. The postdoc will be working to develop a real-time forecasting tool to improve U.S. Week 3-4 precipitation forecasts with innovative data science methods to provide uncertainty quantification. Machine learning will be applied to identify when, where, and why forecasts can be considered forecasts-of-opportunity. This position seeks candidates with a background in atmospheric and climate science, particularly on subseasonal timescales, and experience using machine learning methods. The postdoc will be advised by Dr. Marybeth Arcodia and includes collaborative efforts with Dr. Emily Becker and the NOAA Climate Prediction Center. Key Responsibilities Train neural networks and quantify uncertainty to evaluate predictability Perform explainable AI (XAI) related research to determine areas of enhanced predictability Work closely with collaborators to design the machine-learning based forecasting tool to be used by Climate Prediction Center forecasters Visit the Climate Prediction Center to foster collaboration and promote successful development of the forecasting tool, with the potential for transition to operations Publish findings in peer-reviewed academic journals and present findings at scientific workshops and conferences Required Qualifications Minimum educational qualification is a Ph.D. or equivalent in fields including but not limited to Atmospheric or Climate Science, Environmental Science, Data Science, or other related fields Strong capabilities and demonstrated experience working with large climate datasets, high performance computing, and machine learning Demonstrated experience working both independently and collaboratively Publication record in peer-reviewed academic journals performing high-quality research Strong written and oral communication skills Desire to work both independently and in a diverse team setting with collaborators and graduate students Preferred Qualifications Demonstrated research experience on the topics of explainable machine learning, particularly applied to climate science problems Demonstrated research experience with subseasonal forecasting or predictability Start Date/Appointment Term : Fall 2025. The position is for one year with the possibility for extension. Required Application Materials : Cover letter, 2 page (max) statement of research experiences and interests that address the required and preferred job qualifications and curriculum vitae. The University of Miami is an Equal Opportunity Employer - Females/Minorities/Protected Veterans/Individuals with Disabilities are encouraged to apply. Applicants and employees are protected from discrimination based on certain categories protected by Federal law. Click here for additional information.
The University of Miami Rosenstiel School of Marine, Atmospheric, and Earth Science is seeking to hire a Post Doctoral Associate to work at the intersection of atmospheric science and machine learning to improve subseasonal precipitation forecasts. The postdoc will be working to develop a real-time forecasting tool to improve U.S. Week 3-4 precipitation forecasts with innovative data science methods to provide uncertainty quantification. Machine learning will be applied to identify when, where, and why forecasts can be considered forecasts-of-opportunity. This position seeks candidates with a background in atmospheric and climate science, particularly on subseasonal timescales, and experience using machine learning methods. The postdoc will be advised by Dr. Marybeth Arcodia and includes collaborative efforts with Dr. Emily Becker and the NOAA Climate Prediction Center. Key Responsibilities Train neural networks and quantify uncertainty to evaluate predictability Perform explainable AI (XAI) related research to determine areas of enhanced predictability Work closely with collaborators to design the machine-learning based forecasting tool to be used by Climate Prediction Center forecasters Visit the Climate Prediction Center to foster collaboration and promote successful development of the forecasting tool, with the potential for transition to operations Publish findings in peer-reviewed academic journals and present findings at scientific workshops and conferences Required Qualifications Minimum educational qualification is a Ph.D. or equivalent in fields including but not limited to Atmospheric or Climate Science, Environmental Science, Data Science, or other related fields Strong capabilities and demonstrated experience working with large climate datasets, high performance computing, and machine learning Demonstrated experience working both independently and collaboratively Publication record in peer-reviewed academic journals performing high-quality research Strong written and oral communication skills Desire to work both independently and in a diverse team setting with collaborators and graduate students Preferred Qualifications Demonstrated research experience on the topics of explainable machine learning, particularly applied to climate science problems Demonstrated research experience with subseasonal forecasting or predictability Start Date/Appointment Term : Fall 2025. The position is for one year with the possibility for extension. Required Application Materials : Cover letter, 2 page (max) statement of research experiences and interests that address the required and preferred job qualifications and curriculum vitae. The University of Miami is an Equal Opportunity Employer - Females/Minorities/Protected Veterans/Individuals with Disabilities are encouraged to apply. Applicants and employees are protected from discrimination based on certain categories protected by Federal law. Click here for additional information.