Develop a domain agnostic deep learning for time series forecasting, classification, and anomaly detection framework and leverage it solve pressing problems in health, climate, agriculture, and other high impact humanitarian areas.
Develop a domain agnostic deep learning for time series forecasting, classification, and anomaly detection framework and leverage it solve pressing problems in health, climate, agriculture, and other high impact humanitarian areas.
COVID-19 County Dashboard
As explained above we have two major focuses: (1) general repository enhancements that can be applied to any time series problem and (2) vertical impact focus areas that can aim to tackle a specific issue (e.g. COVID spread, flash flood prediction…).
More
Feature | Priority | Effort | Status | Notes |
---|---|---|---|---|
Adding new time series models/loss functions |
| Leverage PyData Global Sprint | ||
Meta-data incorporation | ||||
Model Interpretability | Should add methods other than SHAP. | |||
Increasing test coverage |
| Need more unit tests of models and meta-data. | ||
Documentation and tutorials | ||||
Auto experimentation | This would be useful but requires a lot of effort. | |||
Cloud Provider Integration | ||||
Multitask learning support |
Feature | Priority | Effort | Status | Notes |
---|---|---|---|---|
COVID County Dashboard | Link to Slideshow | |||
River flow dashboard | ||||
River flow open-source | ||||
Focus Area | Priority | Effort | Status | Notes |
---|---|---|---|---|
Incorporating meta-data in TS models | ||||
Transfer learning in time series application | ||||
Focus areas