Climate Change Data Portal
| DOI | 10.1002/qj.4759 |
| Deep-learning-based downscaling of precipitation in the middle reaches of the Yellow River using residual-based CNNs | |
| 发表日期 | 2024 |
| ISSN | 0035-9009 |
| EISSN | 1477-870X |
| 英文摘要 | The middle reaches of the Yellow River (MRYR), located in northern China, are the transition zone between semi-arid and semi-humid climates. As one of the climate-sensitive regions in China, MRYR has a fragile ecological environment and serious soil loss, which leads to geological disasters such as landslides, collapses, and mudslides caused by extreme precipitation. However, scarceness of high-resolution precipitation data over MRYR limits assessment of the environmental impacts caused by climate change, especially for extreme precipitation. In this article, we design a Residual-in-Residual Dense Block based Network (RRDBNet) model for the statistical downscaling of precipitation in MRYR, and compare the proposed RRDBNet with a generalized linear regression model (GLM) and two popular deep-learning-based models. The multi-level residuals and dense connectivity strategies introduced in RRDBNet help it to learn more abstract features and complex nonlinear relationships among climate variables to improve downscaling performance. The results show that the proposed RRDBNet has good performance in precipitation simulations, which can reproduce the spatial-temporal characteristics of high-resolution precipitation well. RRDBNet reduces the root-mean-squared error (RMSE) by 19% and improves the Pearson correlation coefficient (CC) by 6% relative to GLM for climatology mean precipitation. Especially, RRDBNet has substantial improvements in extreme precipitation compared with other models. It reduces RMSE by 58% (79%) and improves CC by 38% (145%) relative to GLM for R95P (R99P), where R95P and R99P represent extreme precipitation and very extreme precipitation, respectively. For the probability density function of daily precipitation, it is further demonstrated that RRDBNet performs better as regards extreme precipitation frequency. Our results suggest that statistical downscaling based on RRDBNet may be an effective tool for historical and future climate simulations from global climate models. A Residual-in-Residual Dense Block based Network (RRDBNet) model is designed for the statistical downscaling of regional precipitation. The evaluation shows that RRDBNet has substantial improvements in precipitation and extreme precipitation compared with other two deep-learning models. For probability density function of daily precipitation, it is further demonstrated that RRDBNet performs better as regards extreme precipitation frequency. Our results suggest that statistical downscaling based on RRDBNet may be an effective tool for historical and future climate simulations from global climate models. image |
| 英文关键词 | deep learning; extreme precipitation; Residual-in-Residual Dense Block; statistical downscaling; Yellow River middle reaches |
| 语种 | 英语 |
| WOS研究方向 | Meteorology & Atmospheric Sciences |
| WOS类目 | Meteorology & Atmospheric Sciences |
| WOS记录号 | WOS:001237438900001 |
| 来源期刊 | QUARTERLY JOURNAL OF THE ROYAL METEOROLOGICAL SOCIETY
 |
| 文献类型 | 期刊论文 |
| 条目标识符 | http://gcip.llas.ac.cn/handle/2XKMVOVA/292256 |
| 作者单位 | Xi'an Shiyou University; Chinese Academy of Sciences; Institute of Earth Environment, CAS |
| 推荐引用方式 GB/T 7714 | . Deep-learning-based downscaling of precipitation in the middle reaches of the Yellow River using residual-based CNNs[J],2024. |
| APA | (2024).Deep-learning-based downscaling of precipitation in the middle reaches of the Yellow River using residual-based CNNs.QUARTERLY JOURNAL OF THE ROYAL METEOROLOGICAL SOCIETY. |
| MLA | "Deep-learning-based downscaling of precipitation in the middle reaches of the Yellow River using residual-based CNNs".QUARTERLY JOURNAL OF THE ROYAL METEOROLOGICAL SOCIETY (2024). |
| 条目包含的文件 | 条目无相关文件。 | |||||
| 个性服务 |
| 推荐该条目 |
| 保存到收藏夹 |
| 导出为Endnote文件 |
| 谷歌学术 |
| 谷歌学术中相似的文章 |
| 百度学术 |
| 百度学术中相似的文章 |
| 必应学术 |
| 必应学术中相似的文章 |
| 相关权益政策 |
| 暂无数据 |
| 收藏/分享 |
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。
