当前位置: X-MOL 学术J. Hydrol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Improving daily precipitation estimation in the data scarce area by merging rain gauge and TRMM data with a transfer learning framework
Journal of Hydrology ( IF 5.9 ) Pub Date : 2022-09-20 , DOI: 10.1016/j.jhydrol.2022.128455
Zhaoyu Liu , Qinli Yang , Junming Shao , Guoqing Wang , Hongyuan Liu , Xiongpeng Tang , Yunhong Xue , Linlong Bai

Merging the satellite and gauge precipitation has been proofed as an efficient approach to improve the accuracy of quantitative precipitation estimation. However, for areas with few and unevenly distributed rain gauges, accurate precipitation estimation still remains challenging. To address this problem, this paper proposes a framework to improve precipitation estimation for the data scarce area based on transfer learning. Taking the Qinghai-Tibet Plateau as a representative case study, we used two transfer learning methods (fine-tuning, domain-adversarial neural network (DANN)) to transfer precipitation fusion model from the source domain to the target domain. Results indicate that in comparison with the original TRMM data, the root mean square error (RMSE) and mean absolute error (MAE) of the merged precipitation in the Qinghai-Tibet Plateau during 2001–2005 are reduced by 27.6 % and 22.5 % by using the fine-tuning method, and reduced by 29.4 % and 21.5 % by using the DANN method, respectively. Meanwhile, the correlation coefficient (CC) is increased from 0.54 (TRMM data-rain gauge data) to 0.65 (merged data-rain gauge data). The performances of the proposed methods vary spatially, with CC decreased from southeast (0.80) to northwest (<0.40) of the study area. The DANN method performed well on different precipitation intensities, while Swish loss function can help DANN achieve better results on extreme precipitation estimation, with RMSE and MAE reduced by 2.5 % and 4.5 % respectively. The performances of the proposed methods are affected by various factors such as source domain selection and the length of study period. Findings imply that transfer learning provides new insights and new methods to improve precipitation estimation for the data scarce area, which would benefit regional water-related disaster defense and water resources management.



中文翻译:

通过将雨量计和 TRMM 数据与迁移学习框架相结合,改进数据稀缺地区的日降水量估计

将卫星降水和仪表降水相结合已被证明是提高定量降水估计精度的有效方法。然而,对于雨量计少且分布不均的地区,准确的降水量估算仍然具有挑战性。针对这一问题,本文提出了一种基于迁移学习的数据稀缺区域降水估计改进框架。以青藏高原为例,我们使用两种迁移学习方法(微调、域对抗神经网络(DANN))将降水融合模型从源域迁移到目标域。结果表明,与原始 TRMM 数据相比,2001-2005年青藏高原合并降水的均方根误差(RMSE)和平均绝对误差(MAE)通过微调分别降低了27.6%和22.5%,降低了29.4%和 21.5% 分别使用 DANN 方法。同时,相关系数(CC)从0.54(TRMM数据-雨量计数据)增加到0.65(合并数据-雨量计数据)。所提出方法的性能在空间上有所不同,CC从研究区的东南部(0.80)到西北(<0.40)降低。DANN 方法在不同降水强度上表现良好,而 Swish 损失函数可以帮助 DANN 在极端降水估计上取得更好的结果,RMSE 和 MAE 分别降低了 2.5% 和 4.5%。所提出的方法的性能受到各种因素的影响,例如源域选择和研究周期的长度。研究结果表明,迁移学习为改进数据稀缺地区的降水估计提供了新的见解和新的方法,这将有利于区域与水有关的灾害防御和水资源管理。

更新日期:2022-09-20
down
wechat
bug