Optimization of Deep Learning Precipitation Models Using Categorical Binary Metrics

Pablo R. Larraondo*, Luigi J. Renzullo, Albert I.J.M. Van Dijk, Inaki Inza, Jose A. Lozano

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

4 Citations (Scopus)


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.
Original languageEnglish
Article numbere2019MS001909
JournalJournal of Advances in Modeling Earth Systems
Issue number5
Publication statusPublished - May 2020
Externally publishedYes


  • categorical indexes
  • machine learning
  • modeling
  • neural networks
  • precipitation verification


Dive into the research topics of 'Optimization of Deep Learning Precipitation Models Using Categorical Binary Metrics'. Together they form a unique fingerprint.

Cite this