Methods and systems for climate forecasting using artificial neural networks
US11231522B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Oct 26, 2020 |
| Grant date | Jan 25, 2022 |
| Priority date | — |
| Expiry date | Oct 26, 2040 |
Classification
- Technology area (CPC Y)Emerging Cross-Sectional Technologies
- CPC primaryY02A90/10
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods and systems for generating a neural network (NN)-based climate forecasting model are disclosed. The methods and systems perform steps of generating a multi-model ensemble of global climate simulation data by combining simulation data from at least two global climate simulation models; pre-processing the multi-model ensemble of global climate simulation data; training the NN-based climate forecasting model on the pre-processed multi-model ensemble of global climate simulation data; and validating the NN-based climate forecasting model using observational historical climate data. Embodiments of the present invention enable accurate climate forecasting without the need to run new dynamical global climate simulations on supercomputers. Also disclosed are benefits of the new methods, and alternative embodiments of implementation.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.