Home > Research > Publications & Outputs > Deep Learning Integrating Scale Conversion and ...

Research

Associated organisational unit

Links

Text available via DOI:

Keywords

View graph of relations

Deep Learning Integrating Scale Conversion and Pedo‐Transfer Function to Avoid Potential Errors in Cross‐Scale Transfer

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Deep Learning Integrating Scale Conversion and Pedo‐Transfer Function to Avoid Potential Errors in Cross‐Scale Transfer. / Li, Peijun; Zha, Yuanyuan; Zhang, Yonggen et al.
In: Water Resources Research, Vol. 60, No. 3, e2023WR035543, 31.03.2024.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Li, P, Zha, Y, Zhang, Y, Michael Tso, CH, Attinger, S, Samaniego, L & Peng, J 2024, 'Deep Learning Integrating Scale Conversion and Pedo‐Transfer Function to Avoid Potential Errors in Cross‐Scale Transfer', Water Resources Research, vol. 60, no. 3, e2023WR035543. https://doi.org/10.1029/2023wr035543

APA

Li, P., Zha, Y., Zhang, Y., Michael Tso, CH., Attinger, S., Samaniego, L., & Peng, J. (2024). Deep Learning Integrating Scale Conversion and Pedo‐Transfer Function to Avoid Potential Errors in Cross‐Scale Transfer. Water Resources Research, 60(3), Article e2023WR035543. https://doi.org/10.1029/2023wr035543

Vancouver

Li P, Zha Y, Zhang Y, Michael Tso CH, Attinger S, Samaniego L et al. Deep Learning Integrating Scale Conversion and Pedo‐Transfer Function to Avoid Potential Errors in Cross‐Scale Transfer. Water Resources Research. 2024 Mar 31;60(3):e2023WR035543. Epub 2024 Mar 14. doi: 10.1029/2023wr035543

Author

Li, Peijun ; Zha, Yuanyuan ; Zhang, Yonggen et al. / Deep Learning Integrating Scale Conversion and Pedo‐Transfer Function to Avoid Potential Errors in Cross‐Scale Transfer. In: Water Resources Research. 2024 ; Vol. 60, No. 3.

Bibtex

@article{4a2d889c90eb4c7b913e80d0d2b8da30,
title = "Deep Learning Integrating Scale Conversion and Pedo‐Transfer Function to Avoid Potential Errors in Cross‐Scale Transfer",
abstract = "AbstractPedo‐transfer functions (PTFs) relate soil/landscape static properties to a wide range of model inputs (e.g., soil hydraulic parameters) that are essential to soil hydrological modeling. Combining PTFs and hydrological models is a powerful strategy allowing the use of soil/landscape static properties for the generalization of large‐scale modeling. However, since the spatial scales of soil hydraulic parameters required for model inputs and soil/landscape static properties are often not identical, cross‐scale transfer is required, which can be a significant source of errors. Here, we investigate uncertainties in cross‐scale transfer and develop an approach that avoids them. The proposed method uses the convolutional neural network (CNN) as a cross‐scale transfer approach to directly map soil/landscape static properties to soil hydraulic parameters across different spatial scales. The proposed CNN approach is applied under two different estimation strategies to invert the hydraulic parameters of a soil‐water balance model and subsequently the quality of the parameters is assessed. Both synthetical and real‐world results around the conterminous United States indicate that in general the employed end‐to‐end strategy is superior to the two‐step strategy. The CNN‐based integrated model successfully reduces potential errors in cross‐scale transfer and can be applied to other areas lacking information on hydraulic parameters or observations. The proposed method can be extended to improve parameter estimation in earth system models and enhance our understanding of key hydrological processes.",
keywords = "Water Science and Technology",
author = "Peijun Li and Yuanyuan Zha and Yonggen Zhang and {Michael Tso}, Chak‐Hau and Sabine Attinger and Luis Samaniego and Jian Peng",
year = "2024",
month = mar,
day = "31",
doi = "10.1029/2023wr035543",
language = "English",
volume = "60",
journal = "Water Resources Research",
issn = "0043-1397",
publisher = "AMER GEOPHYSICAL UNION",
number = "3",

}

RIS

TY - JOUR

T1 - Deep Learning Integrating Scale Conversion and Pedo‐Transfer Function to Avoid Potential Errors in Cross‐Scale Transfer

AU - Li, Peijun

AU - Zha, Yuanyuan

AU - Zhang, Yonggen

AU - Michael Tso, Chak‐Hau

AU - Attinger, Sabine

AU - Samaniego, Luis

AU - Peng, Jian

PY - 2024/3/31

Y1 - 2024/3/31

N2 - AbstractPedo‐transfer functions (PTFs) relate soil/landscape static properties to a wide range of model inputs (e.g., soil hydraulic parameters) that are essential to soil hydrological modeling. Combining PTFs and hydrological models is a powerful strategy allowing the use of soil/landscape static properties for the generalization of large‐scale modeling. However, since the spatial scales of soil hydraulic parameters required for model inputs and soil/landscape static properties are often not identical, cross‐scale transfer is required, which can be a significant source of errors. Here, we investigate uncertainties in cross‐scale transfer and develop an approach that avoids them. The proposed method uses the convolutional neural network (CNN) as a cross‐scale transfer approach to directly map soil/landscape static properties to soil hydraulic parameters across different spatial scales. The proposed CNN approach is applied under two different estimation strategies to invert the hydraulic parameters of a soil‐water balance model and subsequently the quality of the parameters is assessed. Both synthetical and real‐world results around the conterminous United States indicate that in general the employed end‐to‐end strategy is superior to the two‐step strategy. The CNN‐based integrated model successfully reduces potential errors in cross‐scale transfer and can be applied to other areas lacking information on hydraulic parameters or observations. The proposed method can be extended to improve parameter estimation in earth system models and enhance our understanding of key hydrological processes.

AB - AbstractPedo‐transfer functions (PTFs) relate soil/landscape static properties to a wide range of model inputs (e.g., soil hydraulic parameters) that are essential to soil hydrological modeling. Combining PTFs and hydrological models is a powerful strategy allowing the use of soil/landscape static properties for the generalization of large‐scale modeling. However, since the spatial scales of soil hydraulic parameters required for model inputs and soil/landscape static properties are often not identical, cross‐scale transfer is required, which can be a significant source of errors. Here, we investigate uncertainties in cross‐scale transfer and develop an approach that avoids them. The proposed method uses the convolutional neural network (CNN) as a cross‐scale transfer approach to directly map soil/landscape static properties to soil hydraulic parameters across different spatial scales. The proposed CNN approach is applied under two different estimation strategies to invert the hydraulic parameters of a soil‐water balance model and subsequently the quality of the parameters is assessed. Both synthetical and real‐world results around the conterminous United States indicate that in general the employed end‐to‐end strategy is superior to the two‐step strategy. The CNN‐based integrated model successfully reduces potential errors in cross‐scale transfer and can be applied to other areas lacking information on hydraulic parameters or observations. The proposed method can be extended to improve parameter estimation in earth system models and enhance our understanding of key hydrological processes.

KW - Water Science and Technology

U2 - 10.1029/2023wr035543

DO - 10.1029/2023wr035543

M3 - Journal article

VL - 60

JO - Water Resources Research

JF - Water Resources Research

SN - 0043-1397

IS - 3

M1 - e2023WR035543

ER -