Virtual Speaker Series: Data Science Tools in Action

Abstract: The rapid growth of geospatial data and the increasing demand for open-source solutions have significantly reshaped the field of geospatial data science. This presentation delves into the development and practical applications of open-source Python packages tailored for geospatial analysis. We will showcase powerful libraries such as Geemap, Leafmap, and SAMGeo, and GeoAI, which simplify complex workflows in data processing, visualization, and analysis. These tools empower researchers, developers, and organizations to harness the full potential of spatial data, driving innovation and collaboration in geospatial data science and GeoAI.

Bio: Dr. Qiusheng Wu is an Associate Professor and the Director of Graduate Studies in the Department of Geography & Sustainability at the University of Tennessee, Knoxville. He also serves as an Amazon Scholar. Dr. Wu’s research focuses on geospatial data science and open-source software development, with an emphasis on leveraging big geospatial data and cloud computing to study environmental change, particularly surface water and wetland inundation dynamics. He is the creator of several widely used open-source Python packages, including geemap, leafmap, segment-geospatial, and geoai, which support advanced geospatial analysis and interactive visualization. His open-source work is available at https://github.com/opengeos.

Focus of research: Geospatial Data Science, open source software development, and cloud computing.

Abstract: One of the challenges in traditional time series analysis is scalability. Most of the analysis methods were designed to handle a single time series at a time. In this workshop, we will explore methods for analyzing time series at scale. We will demonstrate how to apply unsupervised methods such as cluster analysis and PCA to analyze and extract insights from multiple time series simultaneously. This workshop is based on Prof. Rob J Hyndman's paper about feature-based time series analysis.

Bio: Rami Krispin is a data science and engineering manager who mainly focuses on time series analysis, forecasting, and MLOps applications. He is passionate about open source, working with data, machine learning, and putting stuff into production. He creates content about MLOps and recently released a course - Data Pipeline Automation with GitHub Actions Using R and Python, on LinkedIn Learning, and is the author of Hands-On Time Series Analysis with R.

Focus of research: Time series analysis and forecasting

Abstract: Learn to communicate your data-driven insights with clarity and impact. In this hands-on seminar, you'll use R to build effective and elegant visualizations tailored to the type and structure of your data. Whether you're analyzing structured datasets, text, or experimental results, you'll gain practical skills for choosing and creating the right graphic for the job. We will cover a range of visualization techniques, including: Text and Sentiment Analysis: Word clouds, frequency plots, sentiment bar charts, and comparison clouds to visualize language patterns and emotional tone. Regression and Statistical Models: Coefficient plots, diagnostic plots, and effect displays to interpret and communicate model results. Categorical, Numerical, and Time-Series Data: Histograms, boxplots, bar charts, and line graphs to explore and compare distributions and trends.

Bio: Dr. Fernandez’s research focuses on a wide range of risky behavior and mental health topics with a special focus on suicide and substance abuse, including opioid-related healthcare utilization. Dr. Fernandez has over 20 articles appearing in well-respected journals such as the the International Economic Review, The Journal of Economic Education, Journal of Business Venturing, Journal of Economic Perspectives, Journal of Economic Behavior and Organization, and Health Service Research Journal. He has appeared in over 100 local, regional, and national media interviews including NPR’s Planet Money and the Indicator.

Dr. Fernandez is a faculty scholar at the Commonwealth Institute of Kentucky, a member of the Statutory Committee Consensus Forecasting Group for the State of Kentucky, the former President of the American Society of Hispanic Economists, of the Co-Chair of the Committee on Status of Minority Groups in the Economics Profession of the American Economic Association, and the chair of the Economics Department at the University of Louisville.

Research focus: Health economics

Abstract: In this talk, Dr. Ge shares his journey integrating AI into data science workflows — from the early experimentation with ChatGPT to the latest advances in fully automated platforms like Google’s Data Science Agents. He highlights how AI tools have transformed the way we code, analyze data, and build models. Dr. Ge announced the launch of Datably.ai, a new AI-powered platform developed by his startup to help users explore and interpret data efficiently via human-AI collaboration.

Bio: Dr. Ge teaches bioinformatics and data science at South Dakota State University. His research group developed iDEP and ShinyGO, two widely used tools for the analysis and visualization of genomics data. In 2022, he wrote RTutor.ai, the first data analytics platform powered by large language models (LLMs). He later founded Orditus LLC, an AI startup dedicated to making data accessible to everyone.

Focus of research: 

• AI-powered data analytics
• Bioinformatics