A L I V E

Autonomy, Learning, Information and Vision for Earth, Planets, Climate and Life

 CAOS

CRISES

SLOOP

FluX

  

 

Cooperative Autonomous Observing Systems (caos.mit.edu):

A new class of autonomous field instruments using unmanned systems for mapping and monitoring. A key characteristic is that they operate in a system dynamics and optimation loop coupling model prediction, uncertainty quantification, estimation, sensing, planning and control. Some projects in this space are:

  • Planet in a Bottle: Coupled Physical Numerical Laboratories : Laboratories that couple models and data in the study of fluids. 
  • Fluid SLAM: Simultaneous Localization and Mapping of Coherent Atmospheric Structures: Plumes and Shallow Clouds
  • Wings Over Wildlife: Autnomous observatories of individuals and groups of animals in their ecosystems.
  • Stratoro: Autonomous Stratospheric Observatory for Natural Hazards and Climate
  • Dynamic Data Driven Glacier Observatory
  • Informative Nuclear Explosion Monitoring
  • Learning Small Planet Detectors from Transiting Exoplanet Lightcurves

Climate Risk and Environmental Sustainability (crises.mit.edu)

Our interdisciplinary project develops methods for risk assessment (including uncertainty quantification), and mitigation. The approaches we take draw from statistical signal processing, physically-based models, machine learning and economics and have many other applications in   and site or basic specific risk assessment (windrisktech.com).

SLOOP: Individual Animal Identification for Conservation (sloop.mit.edu) 

Building an accurate ecological information system depends on an keep accurate inventory of individuals. We bring vision-based methods to individual animal identification, or Animal Biometrics. Sloop pioneered the use of local features with relevance feedback from crowds for individual identification. It remains one of the largest systems for individual identification. Among many firsts: adaptation of generic visual features into specific animal identification strategies; boosted retrieval and learning from relevance feedback using experts and crowds; large-scale conservation application. Other features include RESTful architecture, rapid-distributed closure, randomized representations, hybrid shape-context, and scale-cascaded deformation invariance. 

  • Wings Over Wildlife: Autnomous observatories of individuals and groups of animals in their ecosystems.
     

FLuid imaging eXperiments (flux.mit.edu):  Discover new techniques to image and understand fluid behavior in the laboratory and in the field.

  • Learning Small Planet Detectors from Transiting Exoplanet Lightcurves
  • Synthetic Aperture Imaging of Bubbly Flows. Check out Lightfield imaging of bubbles! 
  • Planet-in-a-Bottle Project: The use of coupled physical-numerical systems to study geophysical fluids in the laboratory, demonstrated in this differentially-heated, rotating fluid experiment. 
  • Particle Tracking: The classic multi-subject tracking problem extended to particles in a fluid.