For just a moment, think of the immense amount of data generated by Earth-observing systems. The sheer volume often makes it impractical for humans alone to perform the analysis, and accordingly, many groups are turning to artificial intelligence (AI) and machine learning (ML) algorithms to support their analysis. We'll hear from Development Seed and EOS about how they are using AI and ML to unlock the power of this planetary-scale data that is becoming increasingly more accessible in the cloud. From open-source libraries and human-in-the loop initial processing passes, to fully automated pipelines, we'll examine the new capacity for analysis now possible with technology.
6. - ‘Fully automated’ machine
learning pipeline;
- Semi-automated machine
learning that will require our
professional mappers’ QA and
map objects.
7. Urchn
Tracking cities from space
‘Fully automated’ machine
learning pipelines backup
Urchn.
- Segmentation: for
detecting building
footprint and road
network.
- Object detection for
individual building
count.
11. Mapping high-voltage
grids in Pakistan,
Nigeria and Zambia
Semi-automated machine
learning that requires our
professional mappers’ QA
and mapping objects.
- Image classification
based supervised
machine learning
approaches.
13. - ‘Fully automated’ machine
learning pipeline;
- Semi-automated machine
learning that will require our
professional mappers’ QA and
mapping objects.
14. - ‘Fully automated’ machine
learning pipeline;
- Semi-automated machine
learning that will require our
professional mappers’ QA and
mapping objects.
How we did it
16. 2. Spot Instance of AWS deep
learning AMI (don’t forgot to
turn on CloudWatch)
17. We open source our machine learning tools and
pipelines:
1. Satellite machine learning training data generation: Label Maker, Skynet-data;
2. Open source machine learning pipelines:
● Image classification:
High-voltage grids
AWS SageMaker case study
ResNet with AWS
● Image segmentation: Skynet
● Object detection: Tensorflow object detection
And we will open source have more tools and pipelines, stay tune!