Harnessing Machine Learning and Satellite Data for Planetary-Scale Impact

Go back to programme

Harnessing Machine Learning and Satellite Data for Planetary-Scale Impact

  • Watch

    * Register (or log in) to the AI4G Neural Network to add this session to your agenda or watch the replay

    • Register

      Watch

      * Register (or log in) to the AI4G Neural Network to add this session to your agenda or watch the replay

    Remote sensing satellites capture petascale, multi-modal  data capturing our dynamic planet across space, time, and spectrum. This  rich data source holds immense potential for addressing local and  planetary-scale challenges including food insecurity, poverty, climate change, and ecosystem preservation. Fully realizing  this potential will require a new paradigm of machine learning  approaches capable of tackling the unique character of remote sensing  data. Machine learning approaches must be flexible enough to make use of the multi-modal multi-fidelity satellite data, process  meter-scale observations over planetary scales, and generalize to the  challenging diversity of remote sensing tasks. In this talk, I will  present examples of how we are developing machine learning approaches for planetary data processing including  self-supervised transformers for remote sensing data. I will also  demonstrate how treating ML research and deployment as a unified  approach instead of siloed steps leads to research advances that result in immediate societal impact, highlighting examples of how we are  partnering directly with stakeholders to deploy our innovations in areas  of critical need across the globe.

    Share this session

    Are you sure you want to remove this speaker?