Topic
Climate risk and geospatial machine learning
Climate work here runs from research into production. At IBM Research, machine learning models for long range seasonal forecasting of 2m temperature and precipitation were published at NeurIPS and EGU and deployed into IBM PAIRS Geoscope, a petabyte scale geospatial platform. In insurance, the same kind of thinking became geospatial flood and natural catastrophe risk models across more than 230,000 insured properties. The proposed doctoral research, not yet registered, continues the thread with physics informed self supervised learning for flood mapping from radar imagery.
2 work · 2 research · 2 publications · Wikidata Q3433166
Work
- Climate forecasting and geospatial ML at IBM ResearchApplied ML research at IBM Research: climate forecasting models deployed into IBM PAIRS Geoscope, published work, and a provincial COVID-19 risk dashboard.
- Insurance data science: telematics, flood risk and MLOpsLeading insurance data science at ABSA Insurance: telematics processing cut from months to under a day, flood risk across 230,000+ properties, MLOps.
Research
- Machine learning for seasonal climate forecastingIBM Research work on forecasting 2m temperature and precipitation weeks to months ahead with machine learning, published at NeurIPS 2020 CCAI and EGU 2022.
- Proposed: self supervised flood mapping from radarProposed doctoral research, not yet registered: physics informed self supervised learning for flood extent mapping from synthetic aperture radar.
Publications
- ML-based Probabilistic Prediction of 2m Temperature and Total PrecipitationProposes a daily probabilistic model that forecasts 2 m temperature and total precipitation globally, aimed at the skill gap between weather and seasonal forecasting. Physics based ensembles, climate modes and recent climatology are combined as inputs to Extreme Gradient Boosting, U-Net and Natural Gradient Boosting models. The authors report that it consistently outperforms both ECMWF 46 day forecasts and climatology. Co-authored across IBM Research in South Africa, Kenya, Brazil and the US.
- Long-Range Seasonal Forecasting of 2m-Temperature with Machine LearningTests whether two machine learning models, a convolutional and a recurrent neural network, can beat climatology when forecasting 2 m temperature up to 52 weeks ahead at six locations. The models improved on climatology up to 30 weeks lead time by correlation and up to 52 weeks by RMSE skill score, but only at some locations, and the authors note further work is needed for the models to add value in the tropics.
Related topics
Subjects that share work with this one. Those with their own page are linked.
- Geospatial machine learning
- Seasonal forecasting
- Deep learning
- Python
- Recurrent neural networks
- Remote sensing
- Apache Spark
- Data engineering
- Databricks
- Insurance
- Machine learning
- MLflow