Abstract
Machine learning has experienced great success in many applications. Precipitation is a hard meteorological variable to predict, but it has a strong impact on society. Here, a machine-learning technique—a formulation of gradient-boosted trees—is applied to climate seasonal precipitation prediction over South America. The Optuna framework, based on Bayesian optimization, was employed to determine the optimal hyperparameters for the gradient-boosting scheme. A comparison between seasonal precipitation forecasting among the numerical atmospheric models used by the National Institute for Space Research (INPE, Brazil) as an operational procedure for weather/climate forecasting, gradient boosting, and deep-learning techniques is made regarding observation, with some showing better performance for the boosting scheme.
Highlights
Development (COPDT), Av. dos Astronautas, 1758, São José dos Campos 12227-010, SP, Brazil; Abstract: Machine learning has experienced great success in many applications
The results of the climate precipitation prediction process using the machine-learning models developed in XGBoost and TensorFlow [11,24]
The results of the forecast process using the XGB model are compared with the seasonal prediction by the numerical atmospheric model BAM and deep learning (TF model) [11]
Summary
Development (COPDT), Av. dos Astronautas, 1758, São José dos Campos 12227-010, SP, Brazil; Abstract: Machine learning has experienced great success in many applications. A comparison between seasonal precipitation forecasting among the numerical atmospheric models used by the National Institute for Space Research (INPE, Brazil) as an operational procedure for weather/climate forecasting, gradient boosting, and deep-learning techniques is made regarding observation, with some showing better performance for the boosting scheme. One key issue for many applications of weather forecasting is the precipitation field This is the most difficult meteorological variable to predict due to high time and space variability. Machine-learning algorithms have been employed in a variety of areas, recording tremendous success for image processing, data classification, time series prediction, and pattern recognition. These data-driven tools have been employed in atmospheric sciences, where huge and heterogeneous databases are available. For weather and climate forecasting, one advantage of employing machine learning is the computational effort reduction [6]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
