“ETRI’s AI for making a better tomorrow” Episode 1 – Spatiotemporal Algal Bloom Prediction using Deep Learning
In this episode of AI for Good Perspectives, key experts from ETRI discuss their goal to build a real-time algal bloom control system, using ML-based prediction to help with decision making on early algae suppression.
IN THIS EPISODE, WE WILL DISCUSS…
(1) Extreme data imbalance: Input datasets are inherently very skewed since algal blooms are rarely observed. How can we train ML models from extremely imbalanced water quality data?
(2) Broad target data: The target area for this project is too broad to collect all datasets. How can we estimate chlorophyll-a concentration for all target areas?
This AI for Good Perspectives episode is part our “ETRI’s AI for making a better tomorrow” series.
WHAT IS AI FOR GOOD PERSPECTIVES?
AI for Good Perspectives are interviews, viewpoints and presentations from the AI for Good community, moderated by professional journalists and available on demand.
Speakers, Panelists and Moderators
MIRAN CHOIPrincipal ResearcherETRIDr. Miran Choi is a Principal Researcher and Standardization Specialist at ETRI. She is a Rapporteur of Q24/SG16, Human Factors Group. She is an editor of ITU-T F.746.3 and its series on Intelligent Question Answering System Standards. She is interested in Standardization of AI related fields, specifically Natural Language Processing and Machine Translation.
JIYONG KIMPrincipal Researcher, Managing Director of Smart Data Research SectionETRIJiyong Kim is currently leading the project “Space-time complex analysis technology for blue-green algae prediction”. He is the managing director of smart data research section at Electronics and Telecommunications Research Institute(ETRI). He received the M.S. degree from Seoul National University, Korea, in 1997. His research topics include big data analysis, machine learning and IoT.