.
| Workshop Information | |
|---|---|
| Dates | Sept. 3 - October 29, 2024 |
| When | Tuesdays 2-3 pm Arizona Time |
| Where | Hybrid at Weaver Science-Engineering Library Room 212 & Zoom |
Worshop Registration [Feeback Form] Youtube Playlist
Step out of conventional GIS frameworks and discover the latest trends in geospatial data science where open tools, cloud technologies, and the proliferation of sensor data are innovating earth observation and environmental monitoring.
Emphasizing open science and reproducible methods, this immersive hands-on workshop series will:
- Show you how to harness cloud computing platforms
- Demonstrate Deep Learning workflows for remoteley sensed imagery
- Introduce you to cloud-native formats
- Help you build geospatial analysis pipelines
Each workshop session is designed to be a discrete lesson where students will walk away with specific knowledge on a tool and resources to explore deeper. Our goal is to demystify vocabulary and show you how to use these tools with straight forward examples. We hope to cover material that is not currently being taught in credited classes at U of A.
The series is FREE and open to all University of Arizona personnel and is tailored for graduate students, postdocs, and early career faculty looking to expand their geospatial skills. Please register here for the workshop
We welcome students and professionals from any field of study across the university. A variety of skill levels are also welcome, though each lesson will assume the audience has limited experience on the topic. Basic knowledge of scripting languages (python/R) and some prior geospatial experience will be helpful. Some of the lessons will include gentle live coding, but the focus will be on the big picture of what the code is doing. Jupyter notebooks with pre-written python code will be provided for several of the lessons.
| Date | Topic | Description |
|---|---|---|
| 09/03/24 | Cyverse Geospatial | Join us to explore Cyverse, a one-of-a-kind cloud computing and storage platform designed for Open Science and a powerful tool for geospatial data analysis. Learn how Cyverse can be leveraged to help you store, analyze, and share data for your geospatial research. Attendees will also learn how to get free access to Planet satellite imagery and free use of photogrammetry software Agisoft Metashape. |
| 09/10/24 | Google Earth Engine | Join us as we introduce Google Earth Engine, a revolutionary cloud-based platform for planetary-scale environmental data analysis. This workshop will show you how to access the platform, the basics of how to navigate the software, and tips for leveraging the massive data catalog. We will show you code examples, app examples, and point you to resources on how to learn more about the powerful tool. This is a must-know tool for geospatial data analysts! |
| 09/17/24 | Deep Learning for Aerial Imagery: DeepForest | Have you wanted to get into geospatial deep learning but aren't sure how? This session demonstrates the use of the python library DeepForest for detecting trees (or birds) in high-resolution aerial imagery. DeepForest uses the powerful deep learning framework Pytorch, but reduces the complexity for researchers more focused on forestry and ecology. Using python code in a jupyter notebook, we will demonstrate workflows to run existing tree detection models, as well as how to fine-tune a model for your area of interest. An existed account with Cyverse is necessary to follow along in the jupyter notebook. |
| 09/24/24 | Deep Learning for Aerial Imagery: Detecto | In this session we will continue with deep learning object detection and show you a python library called Detecto that can help you train a CNN model to identify any object you wish in imagery. |
| 10/01/24 | Cloud Native Formats: Cloud Optimized Geotiffs | As geospatial datasets proliferate and expand in size, the distribution model of downloading all data to your local machine is starting to break down. Come learn about Cloud-Native geospatial formats that empower us to stream data across the web. Whether you want analyze heavy data or share your data with the world, understanding cloud-native concepts will up your geospatial data skills. This session will introduce cloud optimized geotiffs (COGs) and provide you with python code to get started. |
| 10/08/24 | Cloud Native Formats: Cloud Optimized Point Clouds | This session will continue on the topic of cloud-native formats and focus specifically on cloud-optimized point clouds (COPC). Point cloud formats such as .las for LiDAR and photogrammetry are often heavy and difficult to move around the web. But once we convert it to a cloud-optimized format, we can easily share data out to visualize in a web browser or for analysis in a jupyter notebook. We will show you how to create, share, and work with COPC data. |
| 10/15/24 | Containerized Pipelines | How you ever downloaded someone else's code and it wouldn't run on you machine? You are not alone! Reproducible analysis code is a significant problem and a serious drag on Open Science and building on each other's work. Fortunately, there are software technologies that can help us out. In this session, we will cover the basics of software containers (i.e., Docker) and then show you how they can be sequenced to form reproducible analysis pipelines. As an example, we will process drone imagery using OpenDroneMap, and analyze drone point clouds using PDAL. |
| 10/22/24 | Geospatial Data APIs | Geospatial datasets can increasingly be searched for and downloaded through scripting languages. For those looking to automate data download and scale their data analysis beyond point-and-click computing, we will show you how to use data Applications Programming Interfaces (APIs). The focus of the session will be acquiring Planet satellite imagery in a python environment. |
| 10/29/24 | SpatioTemporal Asset Catalogs | As geospatial datasets proliferate across the web, they are often isolated, difficult to discover, and lack consistent metadata. To overcome these challenges many geospatial companies and government agencies are adopting the use of SpatioTemporal Asset Catalogs (STAC). STAC consists of a standard metadata format (geojson) for describing the spatial and temporal characteristics of geospatial data. It also consists of a standard API which makes it easier to programmatically access and use the data. Come learn how this technology works and help us build an open and global catalog of geospatial data! |
The series is expert-led by educators at the University of Arizona Data Science Institute and Cyverse.
Jeffrey Gillan Ph.D, is a research data scientist with Cyverse and has 15 years of experience in geospatial science. His remote sensing expertise includes drone-based photogrammetry, LiDAR, and hyperspectral image analysis.
Dr. Gillan is available for consulations and collaborations if you are looking to incorporate geospatial data science in your research or grant proposal.
In addition to the live workshops, all of the lesson content will be openly available in the Github repository wiki https://github.com/ua-datalab/Geospatial_Workshops/wiki
UArizona DataLab, Data Science Institute, University of Arizona, 2024.
