Confluence Retirement

In an effort to consolidate USGS hosted Wikis, the myUSGS Confluence service is targeted for retirement on January 28, 2022. The official USGS Wiki and collaboration space is now SharePoint. Please migrate existing spaces and content to the SharePoint platform and remove it from Confluence at your earliest convenience. If you need any additional information or have any concerns about this change, please contact myusgs@usgs.gov. Thank you for your prompt attention to this matter.
Skip to end of metadata
Go to start of metadata

You are viewing an old version of this page. View the current version.

Compare with Current View Page History

« Previous Version 13 Next »

Meeting summaries and links in reverse chronological order.

2019 November 12 - AI/ML in USGS enabled by Tallgrass: classifying golden eagle behavior using telemetry


Log in to access this month's recording and slides.


Abstract: This presentation provides an overview of how we use a recurrent autoencoder neural network to encode sequential Californiagolden eagle telemetry data. The encoding is followed by an unsupervisedclustering technique, Deep Embedded Clustering (DEC), to iteratively clusterthe data into a chosen number of behavior classes. We apply the method tosimulated movement data sets and telemetry data for a Golden Eagle. The DECachieves better unsupervised clustering accuracy scores for the simulated datasets as compared to the baseline K-means clustering result.

Speaker Bio: Natalya Rapstine is a Computer Scientist at Advanced ResearchComputing group, specializing in computational data science, statistics, andmachine learning applications for advancement of science at the U.S. GeologicalSurvey. She received a M.S. in Statistics from Colorado School of Mines.

2019 October 8 - Radiant MLHub: A Repository for Machine Learning Ready Geospatial Training Data

Abstract:  Satellite observations provide invaluable data across different spatio-temporal scales. These data enable us to build models for applications such as land cover classification, agricultural monitoring, surface water mapping, biodiversity monitoring, among others. Meanwhile, machine learning (ML) techniques can be utilized to advance these applications, and develop faster, more efficient and scalable models. These techniques learn from training datasets that are generated from image annotation or ground reference observations. However, to develop accurate ML-based models, and be able to validate their accuracy, we need to use benchmark training datasets that are representative of the diversity of the target variable, and openly accessible to all researchers and developers. 
       To address this requirement, Radiant Earth Foundation has established Radiant MLHub to foster sharing of geospatial training data for different thematic applications. Radiant MLHub is hosted on the cloud and users will be able to search for different training datasets, and quickly ingest them into their pipelines using an API. To increase interoperability of training datasets generated by different institutions, Radiant MLHub has adopted the SpatioTemporal Asset Catalog (STAC) as the standard for data cataloging. 
        In this presentation, I will review the architecture of Radiant MLHub, its API access and the STAC definition for training data. Next, I will present two applications on using ML models for LC classification from multi-spectral data and surface water detection from Synthetic Aperture (SAR) data. 

Speaker bio: Hamed Alemohammad is the Chief Data Scientist at Radiant Earth Foundation, leading the development of Radiant MLHub as an opensource cloud native commons for Machine Learning applications using Earth Observations. He has extensive expertise in machine learning, remote sensing and imagery techniques particularly in developing new algorithms for multi-spectral satellite and airborne based observations. He also serves as an elected member of the American Geophysical Union’s technical committee on remote sensing. Prior to joining Radiant Earth, he was a Research Scientist at Columbia University. Hamed received his PhD in Civil and Environmental Engineering from MIT in 2014.

2019 September 10 - An Application of Google’s Tensorflow for a Cannabis Production Inventory in Northern California

2019 August 13 - Continuous streamflow and nearshore wave monitoring from time-lapse cameras using deep neural networks.

  • Daniel Buscombe (Northern Arizona University) described a proof-of-concept study into designing and implementing a single deep learning framework that can be used for both stream gaging and wave gauging from appropriate time-series of imagery.
  • Recording for 2019-08-13 Part 1 
  • Recording for 2019-08-13 Part 2 

2019 June 11 - Strategic Science Planning at USGS

  • Pete Doucette provided a review of recent Strategic Science Planning at USGS. This included thoughts captured from the 21st Century Science Update
    Workshop at NCTC, and the CDI Workshop in Boulder, CO, held May and June 2019.
  • Recording for 2019-06-11

2019 May 14 - XGBoost in Continuous Change Detection and Classification (CCDC); Deep learning to quantify benthic habitat

  • Announcements (Pete Doucette)
    • Pete and other members of an AI/ML focus group presented to the USGS Executive Leadership Team at the end of March. Associate Directors are enthusiastic about incorporating AI/ML into their mission area research.
    • Don't forget the CDI workshop is happening June 4-7, 2019 in Boulder Colorado, tomorrow, May 15 is the last day for registration. Virtual participation links will be posted on the Workshop Page by the week before the workshop.
    • The AI/ML group leads are still interested in collecting an inventory of your AI/ML projects to share with interested USGS leadership. You can fill out the form here.
  • XGBoost in Continuous Change Detection and Classification (CCDC) - Chris Barber, USGS EROS
  • Deep learning to quantify benthic habitat - Peter Esselman, USGS Great Lakes Science Center
  • Recording for 2019-05-14

2019 April 9 - no meeting

2019 March 12 - Infrastructure for Deep Learning at the USGS; AI for Ecosystem Services


2019 February 12 - Innovation Center Opportunities and AI and Land Imaging


2018 December 11 - Inaugural Meeting


  • No labels