Seeing the Earth from the Cloud: How Machine Learning is Changing the Way we See the World
Deep learning is the world-leading computer vision technology for recognizing everyday objects in Internet images, but we are just at the beginning of what this technology can achieve. Neuroscience-inspired algorithms can understand datasets beyond human levels of comprehension, analyzing images collected at frequencies of light invisible to the naked eye, and over scales of space and time that span entire planets and decades. Descartes Labs has applied machine learning to satellite imagery, creating systems that are enabling a revolution in our understanding of the global environment and the changes happening all around us, with profound implications for management of natural resources, and for understanding the challenges of urbanization.
Dr. Steven P. Brumby is Co-Founder and CTO of Descartes Labs, a venture-backed start-up based in Los Alamos NM and San Francisco CA focused on monitoring and predicting global agriculture using deep learning technology and satellite imagery. Previous to Descartes Labs, Steven was a Senior Research Scientist at Los Alamos National Laboratory (LANL) Information Sciences Group (CCS-3) working on development of novel sparse-coding and deep-learning algorithms for video, image and signals analysis. He received his Ph.D. in Theoretical Physics at the University of Melbourne (Australia) in 1997. He is a co-inventor of LANL’s award-winning GENIE image analysis algorithm (R&D100 Award 2002, Federal Laboratory Consortium Technology Transfer Award 2011). He was Principal Investigator of LANL’s Video Analysis and Search Technology (VAST) project, leading a team of 16 scientists developing neuroscience-inspired sparse deep-learning models of computer vision for high performance computing (HPC) and cloud platforms, applied to real-world problems.