Challenge
Earth observation (EO) data from satellites, planes & UAVs are essential to climate change action, however the volume, velocity & variety of EO data inhibit its discovery, which also requires time and expertise. There is no central repository for open EO data & tools; most are proprietary & costly. Internet speed, software, storage, analytic capabilities, human resource limitations, & cost pose additional barriers to utilizing these ostensibly “free” data.
Description
The platform simplifies discovery and use of geospatial data to strengthen climate change research. Essential data (weather, soil composition, crop suitability, population, and hydrology) is updated daily and weekly from orbiting instruments. Users benefit from open-source machine-learning tools that facilitate rapid data analysis (e.g., land-cover changes, climate disasters). These data are fundamental to climate risk mitigation planning, and required for Green Climate Fund applications.
Outcomes
Radiant MLHub launched in 2019 as a resource for a community of practice, giving data scientists benchmarks they can use to train and validate their models and improve its performance. In Oct 2020, we have 14 training datasets and 1,255 subscribers.
