RUNOFF ESTIMATION BASED ON HYBRID-PHYSICS-DATA MODEL
Runoff estimations play an important role in water resource planning and management. Existing hydrological models can be divided into physical models and data-driven models. Although the physical model contains certain physical knowledge and can be well generalized to new scenarios, the application...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Copernicus Publications
2022-05-01
|
Series: | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
Online Access: | https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/V-3-2022/347/2022/isprs-annals-V-3-2022-347-2022.pdf |
_version_ | 1811246840122703872 |
---|---|
author | C. Zhang H. Xue G. Dong H. Jing S. He |
author_facet | C. Zhang H. Xue G. Dong H. Jing S. He |
author_sort | C. Zhang |
collection | DOAJ |
description | Runoff estimations play an important role in water resource planning and management. Existing hydrological models can be divided into physical models and data-driven models. Although the physical model contains certain physical knowledge and can be well generalized to new scenarios, the application of physical models is limited by the high professional knowledge requirements, difficulty in obtaining data and high computational costs. The data-driven model can fit the observed data well, but the estimation may not be physically consistent. In this letter, we propose a hybrid physical data (HPD) model combining physical model and deep learning model for runoff estimation. The model uses the output of a physical hydrological model together with the driving factors as another input of the neural network to estimate the monthly runoff of the upper Heihe River Basin in China. We show that the use of the HPD model improves the quality of runoff estimation, and results in high R<sup>2</sup>, NSE values of 0.969, and a low RMSE value of 9.645. It is indicated that the new model had an excellent learning capability to simulate runoff and flexible ability to extract complex relevant information; At the same time, the estimation capacity of peak runoff is optimized. |
first_indexed | 2024-04-12T14:59:12Z |
format | Article |
id | doaj.art-bc93b71a8dc84958968ca33424ffcc6b |
institution | Directory Open Access Journal |
issn | 2194-9042 2194-9050 |
language | English |
last_indexed | 2024-04-12T14:59:12Z |
publishDate | 2022-05-01 |
publisher | Copernicus Publications |
record_format | Article |
series | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
spelling | doaj.art-bc93b71a8dc84958968ca33424ffcc6b2022-12-22T03:28:07ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502022-05-01V-3-202234735210.5194/isprs-annals-V-3-2022-347-2022RUNOFF ESTIMATION BASED ON HYBRID-PHYSICS-DATA MODELC. Zhang0H. Xue1G. Dong2H. Jing3S. He4The School of Surveying and Land Information Engineering, Henan Polytechnic University, ChinaThe School of Surveying and Land Information Engineering, Henan Polytechnic University, ChinaYellow River Institute of Hydraulic Research, Heihe River Resources and Ecological Protection Research Center, ChinaThe School of Surveying and Land Information Engineering, Henan Polytechnic University, ChinaThe School of Surveying and Land Information Engineering, Henan Polytechnic University, ChinaRunoff estimations play an important role in water resource planning and management. Existing hydrological models can be divided into physical models and data-driven models. Although the physical model contains certain physical knowledge and can be well generalized to new scenarios, the application of physical models is limited by the high professional knowledge requirements, difficulty in obtaining data and high computational costs. The data-driven model can fit the observed data well, but the estimation may not be physically consistent. In this letter, we propose a hybrid physical data (HPD) model combining physical model and deep learning model for runoff estimation. The model uses the output of a physical hydrological model together with the driving factors as another input of the neural network to estimate the monthly runoff of the upper Heihe River Basin in China. We show that the use of the HPD model improves the quality of runoff estimation, and results in high R<sup>2</sup>, NSE values of 0.969, and a low RMSE value of 9.645. It is indicated that the new model had an excellent learning capability to simulate runoff and flexible ability to extract complex relevant information; At the same time, the estimation capacity of peak runoff is optimized.https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/V-3-2022/347/2022/isprs-annals-V-3-2022-347-2022.pdf |
spellingShingle | C. Zhang H. Xue G. Dong H. Jing S. He RUNOFF ESTIMATION BASED ON HYBRID-PHYSICS-DATA MODEL ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
title | RUNOFF ESTIMATION BASED ON HYBRID-PHYSICS-DATA MODEL |
title_full | RUNOFF ESTIMATION BASED ON HYBRID-PHYSICS-DATA MODEL |
title_fullStr | RUNOFF ESTIMATION BASED ON HYBRID-PHYSICS-DATA MODEL |
title_full_unstemmed | RUNOFF ESTIMATION BASED ON HYBRID-PHYSICS-DATA MODEL |
title_short | RUNOFF ESTIMATION BASED ON HYBRID-PHYSICS-DATA MODEL |
title_sort | runoff estimation based on hybrid physics data model |
url | https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/V-3-2022/347/2022/isprs-annals-V-3-2022-347-2022.pdf |
work_keys_str_mv | AT czhang runoffestimationbasedonhybridphysicsdatamodel AT hxue runoffestimationbasedonhybridphysicsdatamodel AT gdong runoffestimationbasedonhybridphysicsdatamodel AT hjing runoffestimationbasedonhybridphysicsdatamodel AT she runoffestimationbasedonhybridphysicsdatamodel |