Teaching

This course provides a comprehensive introduction to statistical methods and data analysis, beginning with fundamental statistical inference techniques for making informed decisions based on data. It then expands to environmental and energy data analysis, covering time-series, spatial, and spatio-temporal datasets. Students will learn modern analytical techniques and tools to handle, visualize, and interpret complex datasets. By integrating foundational statistical concepts with practical applications, this course equips students with the skills necessary to analyze real-world environmental and energy challenges effectively.

This course offers an introduction to deep learning techniques for analyzing environmental big data. It covers basic concepts and progresses to advanced architectures like Convolutional (CNNs) and Recurrent Neural Networks (RNNs). Students will learn to collect, preprocess, and analyze large-scale environmental datasets, including remote sensing and hydrological data. Key topics include flood prediction, drought assessment, wildfire detection, and the use of global satellite images with land surface models for real-world applications. Emphasis is placed on integrating remote sensing with hydrological models for water resource management. By course end, students will produce a manuscript applying deep learning to environmental challenges.

In this workshop, you will learn to assess water quality using advanced remote sensing techniques and machine learning models, focusing on the Korean Peninsula. Leveraging NASA Sentinel-2 satellite data, we will explore the principles of remote sensing, data preprocessing, and feature extraction. You will gain hands-on experience in applying machine learning algorithms to analyze and predict water quality parameters such as Chlorophyll-a concentration. By the end of the workshop, you will be equipped with the skills to utilize satellite imagery and machine learning for environmental monitoring and water quality management.

This course is designed to simplify the complex world of data analysis. It starts by teaching the basics of statistical inference, making smart guesses and decisions based on data. It then shifts to big data analysis, exploring how to handle, analyze, and draw conclusions from large datasets using modern techniques and tools. This course is ideal for anyone looking to make informed decisions using data, blending foundational statistical concepts with practical big data applications in a clear, straightforward manner.

This course delves into machine learning and data mining techniques tailored for environmental challenges, using data from ground observations, satellites, and models. Covering both supervised and unsupervised methods, students will learn to analyze and interpret complex environmental data through hands-on exercises and projects. By the end, participants will possess the skills to apply these techniques to real-world environmental issues and contribute to resource preservation.

In the world of programming, one of the most common scenarios we encounter is having to optimize code that's running too slowly. This can be particularly challenging when working with large datasets or complex algorithms. Today, we're going to look at a practical example of how to optimize Python code to make it run faster.

Causal Language' in Scientific Research: A Guide for Graduate Students.