logo
科言猫学术研究的AI总结
language
手机端手机端
  • Phone Feature微信小程序
简体中文简体中文
notice消息通知
博客博客
delete
arrow
返回

Improved streamflow simulations in hydrologically diverse basins using physically-informed deep learning models

delete2025-02-24
delete0
PRE
AI
B
Bhanu Magotra
M
Manabendra Saharia *
C
C. T. Dhanya
DOI：10.1080/02626667.2025.2458545delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
物理信息深度学习模型，特别是长短期记忆（LSTM）网络，在大规模径流模拟中显示出潜力。然而，对深度学习模型中物理信息相对贡献的深入理解一直缺失。我们使用印度次大陆水文多样性区域220个流域的大型样本测试平台，通过基于各种静态流域属性和模拟地表状态的组合的多种LSTM模型变体，量化了逐步添加物理信息对模型性能的影响。我们发现，使用流域地球物理学作为附加输入训练的LSTM模型在样本内流域全国中位 Kling-Gupta 效率（KGE）方面优于基础LSTM模型，将KGE从0.32提高到0.60。此外，该模型在样本外流域中保留了显著的预测能力，表明预训练的LSTM模型可以成为数据稀缺区域径流预测的有力工具。
Keyword:
LSTM
deep learning
streamflow
physically-informed models
large-sample hydrology

期刊

Hydrological Sciences Journal 封面图
Hydrological Sciences Journal
IF:
2.5
论文数:
407
被引数:
8.8K

机构

I
Indian Inst Technol Delhi
学者数:
646
论文数: 312
被引数: 85
引用论文

引用论文

Learning long-term dependencies with gradient descent is difficult使用梯度下降学习长期依赖关系是困难的
errIEEE Transactions on Neural Networks
IF0
err1994-03-01
err0
PREAI
errY. Bengio; P. Simard; P. Frasconi
err分享
err收藏
A recurrent neural networks approach using indices of low-frequency climatic variability to forecast regional annual runoff
errHydrological Processes
IF0
err2000-01-01
err0
PREAI
errPaulin Coulibaly; Fran�ois Anctil; Peter Rasmussen; Bernard Bob�e
err分享
err收藏
A novel smoothing-based long short-term memory framework for short-to medium-range flood forecasting
errHydrological Sciences Journal
IF0
err2023-02-24
err0
PREAI
errAmina Khatun; Chandranath Chatterjee; Gaurav Sahu; Bhabagrahi Sahoo
err分享
err收藏
Development of a new high spatial resolution (0.25° × 0.25°) long period (1901-2010) daily gridded rainfall data set over India and its comparison with existing data sets over the region
errMAUSAM
IF0
err2014-01-01
err0
errOAAI
errD.S Pai; M Rajeevan; O.P Sreejith; B. Mukhopadhyay; N.S Satbha
err分享
err收藏
Implementation of Noah land surface model advances in the National Centers for Environmental Prediction operational mesoscale Eta model
errJOURNAL OF GEOPHYSICAL RESEARCH-ATMOSPHERES
IF3.4
err2003-11-29
err2.8K
errOAAI
errEk, MB; Mitchell, KE; Lin, Y; Rogers, E; Grunmann, P; Koren, V; Gayno, G; Tarpley, JD
err分享
err收藏
A Review on Hydrological Models
errAquatic Procedia
IF0
err2015-01-01
err0
errOAAI
errGayathri K. Devia; B.P. Ganasri; G.S. Dwarakish
err分享
err收藏
Value of process understanding in the era of machine learning: A case for recession flow prediction
errJOURNAL OF HYDROLOGY
IF6.3
err2023-11-01
err4
PREAI
errIstalkar, Prashant; Kadu, Akshay; Biswal, Basudev
err分享
err收藏
Long Short-Term Memory长短期记忆
errNeural Computation
IF0
err1997-11-01
err0
PREAI
errSepp Hochreiter; Jürgen Schmidhuber
err分享
err收藏
What Role Does Hydrological Science Play in the Age of Machine Learning?水文科学在机器学习时代扮演什么角色？
errWater Resources Research
IF0
err2021-03-24
err0
errOAAI
errGrey S. Nearing; Frederik Kratzert; Alden Keefe Sampson; Craig S. Pelissier; Daniel Klotz; Jonathan M. Frame; Cristina Prieto; Hoshin V. Gupta
err分享
err收藏
A high‐accuracy map of global terrain elevations
errGeophysical Research Letters
IF0
err2017-06-14
err0
errOAAI
errDai Yamazaki; Daiki Ikeshima; Ryunosuke Tawatari; Tomohiro Yamaguchi; Fiachra O'Loughlin; Jeffery C. Neal; Christopher C. Sampson; Shinjiro Kanae; Paul D. Bates
err分享
err收藏
学者 查看更多内容