Training

A large component of the AAR-HPC project is the sharing of knowledge with the development and delivery of training. MSU faculty and staff developed a variety of online and in-person training courses for USDA-ARS scientists covering a range of geospatial, biologic, and data science topics.

Training Workshop Summaries

Developing a UAS Program:
Designed to help researchers launch an effective UAS program, this workshop covers planning, registration, certifications, mission planning, and data management. Ideal for those considering UAS integration into their research.

UAS Missions, Operations, and Planning:
Offers an overview for sUAS pilots on aircraft types, regulations, mission planning, flight skills, and reporting. Helps build a safe and efficient UAS program for research data collection.

Data Wrangling: UAS Data Processing Overview:
Introduces common UAS sensors and provides a step-by-step demo of photogrammetry workflows using Agisoft Metashape and Pix4D to produce georeferenced, reflectance-corrected orthomosaics.

Introduction to Atlas:
An introductory session on USDA’s Atlas supercomputer, this course explains high-performance computing basics, research applications, and how to access and use Atlas for scientific workflows.

Blockchain Networks:
Covers the fundamentals of blockchain technology, including cryptographic principles, network types, and applications in data security and decision-making transparency.

Introduction to Image Processing and Classical Machine Learning: Hands-on workshop using Python and Jupyter notebooks to explore image representation, processing, and classification using classical machine learning techniques. Includes introductory deep learning content.

Advanced Topics in Deep Learning: Expands on deep learning methods for image segmentation, object detection, and spatio-temporal analysis. Participants explore and modify neural network architectures through hands-on coding exercises.

Python Getting Started:
Designed for absolute beginners to learn to prepare their computers with a suitable environment for doing work with Python along with the opportunity to do some basic data wrangling.

Python Learn by Doing:
Course is designed for intermediate learners and focuses on real-world data analysis using Python. Participants will work with geospatial, image, and tabular datasets while learning computational, statistical, and machine learning techniques applicable across various research domains.