Martha Morrissey

Martha is a Machine Learning Engineer at Development Seed. Outside of work Martha enjoys cycling, running, and taking her cat on walks.

The speaker's profile picture


Al Accelerated Human-in-the-Loop Land Use and Land Cover Mapping
Martha Morrissey, Caleb Robinson

PEARL, the Planetary Computer Land Cover Mapping Platform, uses state of the art ML and AI technologies to drastically reduce the time required to produce an accurate land cover map. Scientists and mappers get access to pre-trained, high performing starter models, and high resolution imagery (e.g. NAIP) hosted on Microsoft Azure. The land cover mapping tool manages the infrastructure for running inference at scale, visualizes model predictions, shows the model’s per class performance, allows for adding new training classes, and allows users to retrain the model. The tool helps harness the power of expert human mappers and scientists through immediate model evaluation metrics, easy retraining cycles and instant user feedback within the UI.

Scaling AI to map every school on the planet
Zhuang-Fang NaNa Yi, Martha Morrissey

UNICEF's Giga Initiative endeavors to map every school on the Planet. Knowing the location of schools is the first step to accelerate connectivity, online learning, and initiatives for children and their communities, and drive economic stimulus, particularly in lower-income countries. Development Seed is working with the UNICEF Office of Innovation to enable rapid school mapping from space across Asia, Africa, and South America with AI. In seven months of development and implementation, we added 23,100 unmapped schools to the map in Kenya, Rwanda, Sierra Leone, Niger, Honduras, Ghana, Kazakhstan, and Uzbekistan.
To accomplish this we built an end-to-end scalable AI model pipeline that scans high-resolution satellite imagery from Maxar, applies our highly refined algorithm for identifying buildings that are likely to be schools, and flags those schools for human review by our talented Data Team. You can view our interactive maps of schools before and after the project for all countries we mapped, and examples of unmapped schools we found through the project.
Scanning high-resolution imagery of large sections of the planet is a massive undertaking. Accomplishing an effort of this scale gave us the opportunity to make improvements to our scalable AI tool (will be open-sourced soon), from efficient model training and experiments with Kubeflow on Google Kubernetes Engine, fast model inference with ML-Enabler, and data curation tools. We are proud to contribute these advances with AI for Good communities through advancing open datasets and open source libraries.

Use Cases and Applications