Presented By O’Reilly and Intel AI
Put AI to work
Sep 4-5, 2018: Training
Sep 5-7, 2018: Tutorials & Conference
San Francisco, CA

AI for Earth: Using machine learning to monitor, model, and manage natural resources

Jennifer Marsman (Microsoft)
4:00pm-4:40pm Friday, September 7, 2018
Secondary topics:  Computer Vision
Average rating: *****
(5.00, 2 ratings)

Who is this presentation for?

  • Everyone will find value in this session.

What you'll learn

  • Understand real problems in the conservation space and how machine learning is helping to solve them

Description

Microsoft has pledged $50 million over the next five years to the recently formed AI for Earth team, which helps NGOs apply AI to challenges in conservation biology and environmental science. AI for Earth awards grants including funding for cloud computing and support from dedicated data scientists and software engineers. It also aims to address the most common requests of grantees by producing general-purpose solutions, for which the team publicly shares its training data, code, and models. Over the past few months, AI for Earth has made its AI technologies available to more than 35 organizations in more than 10 countries and organized multiday workshops to ensure that grantees are able to fully use the tools provided.

Jennifer Marsman outlines Microsoft’s objectives for AI for Earth and highlights recent successes. These include:

  • Project Premonition, a collaboration between Microsoft and researchers at Johns Hopkins University and the University of Pittsburgh that seeks to estimate relative abundances of insect species based on classification of their wing beat frequency and collect individuals from target blood-sucking species to test for the presence of human pathogens.
  • Systematic Poacher Detector (SPOT), which uses nocturnal drone imagery to detect the presence of poachers in Botswanan natural parks in near real time, allowing them to be removed shortly after arrival and before daybreak/hunting begins.
  • FarmBeats, which combines drone imagery and in-soil nutrient and water sensors to monitor crop health and identify areas in need of special treatments, such as irrigation and fertilization.
  • A partnership with iNaturalist, in which information on sightings of specific species is collected from users of the company’s popular mobile app, who provide photographs and solicit crowdsourced labels. Neural networks trained to classify this data can also be applied to imagery from stationary, motion-triggered cameras (“camera traps”) by a variety of conservation efforts, including the Snow Leopard Trust.
Photo of Jennifer Marsman

Jennifer Marsman

Microsoft

Jennifer Marsman is the principal software engineer for Microsoft’s AI for Earth Group, where she uses data science, machine learning, and artificial intelligence to aid with clean water, agriculture, biodiversity, and climate change. She has been featured in Bloomberg for her work using EEG and machine learning to perform lie detection. Previously, Jennifer was a software developer in Microsoft’s Natural Interactive Services Division, where she authored two patents related to search and data mining algorithms. She has also held positions with Ford Motor Company, National Instruments, and Soar Technology. Since 2016, Jennifer has been recognized as one of the top 100 most influential individuals in artificial intelligence and machine learning by Onalytica, reaching the #2 slot in 2018, and in 2009 was chosen as the “techie whose innovation will have the biggest impact” by X-OLOGY for her work with GiveCamps, a weekend-long event where developers code for charity. She has also received many honors from Microsoft, including the Best in Role award for technical evangelism, Central Region Top Contributor Award, Heartland District Top Contributor Award, DPE Community Evangelist Award, CPE Champion Award, MSUS Diversity and Inclusion Award, Gold Club, and Platinum Club. Jennifer is a frequent speaker at software development conferences around the world. She holds a bachelor’s degree in computer engineering and a master’s degree in computer science and engineering from the University of Michigan in Ann Arbor, where she specialized in artificial intelligence and computational theory. To learn more, check out her blog.