Large Scale Applications of Machine Learning using Remote Sensing for Building Agriculture Solutions
March 5, 2024
March 19, 2024
Participants will become familiar with data format and quality considerations, tools, and techniques to process remote sensing imagery at large scale from publicly available satellite sources, using cloud tools such as AWS S3, Databricks, and Parquet. Additionally, participants will learn how to analyze and train machine learning models for classification using this large source of data to solve environmental problems with a focus on agriculture.
Primary Target Audience: Remote sensing scientists, practitioners, and geospatial analysts from local, regional, federal, and non-governmental organizations who use remote sensing for agricultural applications.Secondary Target Audience: Agronomists, data scientists/data engineers/ML engineers.Other Potential Participants: Any practitioners of remote sensing data.
By the end of this training attendees will be able to:
-Use recommended techniques to download and process remote sensing data from Sentinel-2 and the cropland data layer (CDL) at large scale (> 5GB) with cloud tools (Amazon Web Services [AWS];
-Simple Storage Service [S3], Databricks, Spark, Parquet);
-Filter data from both the measured (satellite images) and target (CDL) domains to serve modeling objectives based on quality factors, land classification, area of interest [AOI] overlap, and geographical location;
-Build training pipelines in TensorFlow to train machine learning algorithms on large scale remote sensing/geospatial datasets for agricultural monitoring;
-Utilize random sampling techniques to build robustness into a predictive algorithm while avoiding information leakage across training/validation/testing splits.