Deep learning for stochastic precipitation generation – deep SPG v1.0
<p>We present a deep-neural-network-based single-site stochastic precipitation generator (SPG), capable of producing realistic time series of daily and hourly precipitation. The neural network outputs a wet-day probability and precipitation distributions in the form of a mixture model. The SPG...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2023-07-01
|
| Series: | Geoscientific Model Development |
| Online Access: | https://gmd.copernicus.org/articles/16/3785/2023/gmd-16-3785-2023.pdf |
| _version_ | 1797783260130967552 |
|---|---|
| author | L. J. Bird M. G. W. Walker G. E. Bodeker I. H. Campbell G. Liu S. J. Sam J. Lewis S. M. Rosier |
| author_facet | L. J. Bird M. G. W. Walker G. E. Bodeker I. H. Campbell G. Liu S. J. Sam J. Lewis S. M. Rosier |
| author_sort | L. J. Bird |
| collection | DOAJ |
| description | <p>We present a deep-neural-network-based single-site stochastic precipitation generator (SPG), capable of producing realistic time series of daily and hourly precipitation. The neural network outputs a wet-day probability and precipitation distributions in the form of a mixture model. The SPG was tested in four different locations in New Zealand, and we found it accurately reproduced the precipitation depth, the autocorrelations seen in the original data, the observed dry-spell lengths, and the seasonality in precipitation. We present two versions of the hourly and daily SPGs: (i) a stationary version of the SPG that assumes that the statistics of the precipitation are time independent and (ii) a non-stationary version that captures the secular drift in precipitation statistics resulting from climate change. The latter was developed to be applicable to climate change impact studies, especially studies reliant on SPG projections of future precipitation. We highlight many of the pitfalls associated with the training of a non-stationary SPG on observations alone and offer an alternative method that replicates the secular drift in precipitation seen in a large-ensemble regional climate model. The SPG runs several orders of magnitude faster than a typical regional climate model and permits the generation of very large ensembles of realistic precipitation time series under many climate change scenarios. These ensembles will also contain many extreme events not seen in the historical record.</p> |
| first_indexed | 2024-03-13T00:23:31Z |
| format | Article |
| id | doaj.art-be22c4d753644193b39c6ae6aa8f27e4 |
| institution | Directory Open Access Journal |
| issn | 1991-959X 1991-9603 |
| language | English |
| last_indexed | 2024-03-13T00:23:31Z |
| publishDate | 2023-07-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Geoscientific Model Development |
| spelling | doaj.art-be22c4d753644193b39c6ae6aa8f27e42023-07-11T10:09:15ZengCopernicus PublicationsGeoscientific Model Development1991-959X1991-96032023-07-01163785380810.5194/gmd-16-3785-2023Deep learning for stochastic precipitation generation – deep SPG v1.0L. J. Bird0M. G. W. Walker1G. E. Bodeker2I. H. Campbell3G. Liu4S. J. Sam5J. Lewis6S. M. Rosier7Bodeker Scientific, Alexandra, New ZealandBodeker Scientific, Alexandra, New ZealandBodeker Scientific, Alexandra, New ZealandBodeker Scientific, Alexandra, New ZealandBodeker Scientific, Alexandra, New ZealandBodeker Scientific, Alexandra, New ZealandClimate & Energy College, The University of Melbourne, Parkville, Victoria, AustraliaNational Institute of Water and Atmospheric Research, Wellington, New Zealand<p>We present a deep-neural-network-based single-site stochastic precipitation generator (SPG), capable of producing realistic time series of daily and hourly precipitation. The neural network outputs a wet-day probability and precipitation distributions in the form of a mixture model. The SPG was tested in four different locations in New Zealand, and we found it accurately reproduced the precipitation depth, the autocorrelations seen in the original data, the observed dry-spell lengths, and the seasonality in precipitation. We present two versions of the hourly and daily SPGs: (i) a stationary version of the SPG that assumes that the statistics of the precipitation are time independent and (ii) a non-stationary version that captures the secular drift in precipitation statistics resulting from climate change. The latter was developed to be applicable to climate change impact studies, especially studies reliant on SPG projections of future precipitation. We highlight many of the pitfalls associated with the training of a non-stationary SPG on observations alone and offer an alternative method that replicates the secular drift in precipitation seen in a large-ensemble regional climate model. The SPG runs several orders of magnitude faster than a typical regional climate model and permits the generation of very large ensembles of realistic precipitation time series under many climate change scenarios. These ensembles will also contain many extreme events not seen in the historical record.</p>https://gmd.copernicus.org/articles/16/3785/2023/gmd-16-3785-2023.pdf |
| spellingShingle | L. J. Bird M. G. W. Walker G. E. Bodeker I. H. Campbell G. Liu S. J. Sam J. Lewis S. M. Rosier Deep learning for stochastic precipitation generation – deep SPG v1.0 Geoscientific Model Development |
| title | Deep learning for stochastic precipitation generation – deep SPG v1.0 |
| title_full | Deep learning for stochastic precipitation generation – deep SPG v1.0 |
| title_fullStr | Deep learning for stochastic precipitation generation – deep SPG v1.0 |
| title_full_unstemmed | Deep learning for stochastic precipitation generation – deep SPG v1.0 |
| title_short | Deep learning for stochastic precipitation generation – deep SPG v1.0 |
| title_sort | deep learning for stochastic precipitation generation deep spg v1 0 |
| url | https://gmd.copernicus.org/articles/16/3785/2023/gmd-16-3785-2023.pdf |
| work_keys_str_mv | AT ljbird deeplearningforstochasticprecipitationgenerationdeepspgv10 AT mgwwalker deeplearningforstochasticprecipitationgenerationdeepspgv10 AT gebodeker deeplearningforstochasticprecipitationgenerationdeepspgv10 AT ihcampbell deeplearningforstochasticprecipitationgenerationdeepspgv10 AT gliu deeplearningforstochasticprecipitationgenerationdeepspgv10 AT sjsam deeplearningforstochasticprecipitationgenerationdeepspgv10 AT jlewis deeplearningforstochasticprecipitationgenerationdeepspgv10 AT smrosier deeplearningforstochasticprecipitationgenerationdeepspgv10 |