Salata Scholar Seminar Series | Daniel Crocker & Esther Rolf
Wednesday, March 20, 6:00pm - 7:00pm (EDT)
🌿 Join us for the 6th Salata Scholar Seminar Series, where we'll explore cutting-edge topics in environmental science and climate action!
Talk 1: Geospatial Machine Learning: Data-focused algorithm design, development, and evaluation
Speaker: Esther Rolf
Talk Summary:
Geospatial machine learning (geo-ML) holds great promise for consolidating data from various sources like satellite imagery and ground surveys to aid decision-making for issues such as climate change and health. However, challenges exist in creating geo-ML models due to the vast amount of data requiring efficient computing, difficulties in assessing model performance due to spatio-temporal autocorrelations, and the need to accommodate data heterogeneity from various sensors. In her talk, Esther will focus on how effectively addressing these challenges—data scale, autocorrelations, and heterogeneity—is crucial for developing robust geo-ML algorithms and evaluation methods.
Short Bio:
Esther Rolf is a postdoctoral fellow with the Harvard Data Science Initiative and the Center for Research on Computation and Society with a PhD in Computer Science at UC Berkeley. Esther's research in statistical and geospatial machine learning blends methodological and applied techniques to study and design machine learning algorithms and systems with an emphasis on usability, data-efficiency and fairness.
Talk 2: Isotopes as a Tool to Investigate Organic Aerosol Emissions and Atmospheric Oxidation Pathways
Speaker: Daniel Crocker
Talk Summary:
Human-generated pollutants impact air quality, health, and the climate, with atmospheric aerosols posing a major challenge in understanding these effects on Earth's energy balance. The research presented will explore the role of aerosols in atmospheric chemistry and climate systems using stable isotopes to identify emission sources and study their chemical interactions in the atmosphere. A new method for analyzing oxygen isotopes in organic materials will be discussed, aimed at examining oxidation processes of organic aerosols. This talk will provide a deeper understanding of the processes affecting atmospheric composition and their influence on air quality and climate in response to human and natural activities.
Short Bio:
Daniel Crocker is an atmospheric chemist with a Ph. D. from the University of California, San Diego. He was appointed as a postdoctoral fellow at Harvard University Department of Earth and Planetary Sciences, where he is developing novel methodologies for isotopic analysis of organic materials.
📅 Date: Wednesday, March 20
🕕 Time: 6pm
📍 Venue: HUCE, Seminar Room 440, 26 Oxford St., Cambridge
🍃 Refreshments will be provided.
🔗 Join our community on Slack and mailing list for the latest updates and networking opportunities:
Slack:https://join.slack.com/t/salatagraduat-fwo7660/shared_invite/zt-2d1nh442b-pk7p0teLxjBA2_lGUn0DjA
Mailing list: https://web.lists.fas.harvard.edu/mailman/lists/salata-scholars-seminar-list.lists.fas.harvard.edu/ ;
Confirmed.
We've sent a confirmation email to your email address. Be sure to check your junk folder in case you haven't received the confirmation.
🌿 Join us for the 6th Salata Scholar Seminar Series, where we'll explore cutting-edge topics in environmental science and climate action!
Talk 1: Geospatial Machine Learning: Data-focused algorithm design, development, and evaluation
Speaker: Esther Rolf
Talk Summary:
Geospatial machine learning (geo-ML) holds great promise for consolidating data from various sources like satellite imagery and ground surveys to aid decision-making for issues such as climate change and health. However, challenges exist in creating geo-ML models due to the vast amount of data requiring efficient computing, difficulties in assessing model performance due to spatio-temporal autocorrelations, and the need to accommodate data heterogeneity from various sensors. In her talk, Esther will focus on how effectively addressing these challenges—data scale, autocorrelations, and heterogeneity—is crucial for developing robust geo-ML algorithms and evaluation methods.
Short Bio:
Esther Rolf is a postdoctoral fellow with the Harvard Data Science Initiative and the Center for Research on Computation and Society with a PhD in Computer Science at UC Berkeley. Esther's research in statistical and geospatial machine learning blends methodological and applied techniques to study and design machine learning algorithms and systems with an emphasis on usability, data-efficiency and fairness.
Talk 2: Isotopes as a Tool to Investigate Organic Aerosol Emissions and Atmospheric Oxidation Pathways
Speaker: Daniel Crocker
Talk Summary:
Human-generated pollutants impact air quality, health, and the climate, with atmospheric aerosols posing a major challenge in understanding these effects on Earth's energy balance. The research presented will explore the role of aerosols in atmospheric chemistry...
---
Event details:
https://www.addevent.com/event/cH20744315
HUCE Seminar Room 440, 26 Oxford St., Cambridge, MA false MM/DD/YYYY 60 OPAQUE ataBgHfWozEYwnutbmsh62139
Confirmed.
We've sent a confirmation email to your email address. Be sure to check your junk folder in case you haven't received the confirmation.
🌿 Join us for the 6th Salata Scholar Seminar Series, where we'll explore cutting-edge topics in environmental science and climate action!
Talk 1: Geospatial Machine Learning: Data-focused algorithm design, development, and evaluation
Speaker: Esther Rolf
Talk Summary:
Geospatial machine learning (geo-ML) holds great promise for consolidating data from various sources like satellite imagery and ground surveys to aid decision-making for issues such as climate change and health. However, challenges exist in creating geo-ML models due to the vast amount of data requiring efficient computing, difficulties in assessing model performance due to spatio-temporal autocorrelations, and the need to accommodate data heterogeneity from various sensors. In her talk, Esther will focus on how effectively addressing these challenges—data scale, autocorrelations, and heterogeneity—is crucial for developing robust geo-ML algorithms and evaluation methods.
Short Bio:
Esther Rolf is a postdoctoral fellow with the Harvard Data Science Initiative and the Center for Research on Computation and Society with a PhD in Computer Science at UC Berkeley. Esther's research in statistical and geospatial machine learning blends methodological and applied techniques to study and design machine learning algorithms and systems with an emphasis on usability, data-efficiency and fairness.
Talk 2: Isotopes as a Tool to Investigate Organic Aerosol Emissions and Atmospheric Oxidation Pathways
Speaker: Daniel Crocker
Talk Summary:
Human-generated pollutants impact air quality, health, and the climate, with atmospheric aerosols posing a major challenge in understanding these effects on Earth's energy balance. The research presented will explore the role of aerosols in atmospheric chemistry...
---
Event details:
https://www.addevent.com/event/cH20744315
HUCE Seminar Room 440, 26 Oxford St., Cambridge, MA false MM/DD/YYYY 60 OPAQUE ataBgHfWozEYwnutbmsh62139
Thank you!
Your changes have been saved. Thanks for keeping us updated.
HUCE Seminar Room 440, 26 Oxford St., Cambridge, MA
Oksana Makarova, oksana_makarova@g.harvard.edu