Optimization of Deep Learning Precipitation Models Using Categorical Binary Metrics
In one sentence. Differentiable versions of probability of detection and false alarm rate let neural precipitation forecasts be trained directly on categorical skill scores.
Abstract
Abstract This work introduces a methodology for optimizing neural network models using a combination of continuous and categorical binary indices in the context of precipitation forecasting. Probability of detection and false alarm rate are popular metrics used in the verification of precipitation models. However, machine learning models trained using gradient descent cannot be optimized based on these metrics, as they are not differentiable. We propose an alternative formulation for these categorical indices that are differentiable and we demonstrate how they can be used to optimize the skill of precipitation neural network models defined as a multiobjective optimization problem. To our knowledge, this is the first proposal of a methodology for optimizing weather neural network models based on categorical indices.
Labels
- Topic
- Post-processing & calibration
- Type
- New model or method
- Method
- Classical ML (trees, GP, linear, kernels)
- Time scale
- 6 h–3 days
- Domain
- Regional
- Data
- Other
- Status
- Research
- Identifiers
- DOI:10.1029/2019ms001909 OpenAlex:W3019495891
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.