Regionalization of hydrological model parameters  using gradient boosting machine

Song, Zhihong; Xia, Jun; Wang, Gangsheng; She, Dunxian; Hu, Chen; Hong, Si

doi:https://doi.org/10.5194/hess-26-505-2022

Articles | Volume 26, issue 2

https://doi.org/10.5194/hess-26-505-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/hess-26-505-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 26, issue 2

Research article

|

31 Jan 2022

Research article |

| 31 Jan 2022

Regionalization of hydrological model parameters using gradient boosting machine

Zhihong Song, Jun Xia, Gangsheng Wang, Dunxian She, Chen Hu, and Si Hong

Download

Final revised paper (published on 31 Jan 2022)
Supplement to the final revised paper
Preprint (discussion started on 09 Aug 2021)
Supplement to the preprint

Interactive discussion

Status: closed

RC1:
'Comment on hess-2021-382', Anonymous Referee #1, 10 Oct 2021

The manuscript is interesting and clearly written. I have a single comment; in particular, what are the practical reasons for regionalizing the parameters of the hydrological model using regression algorithms, given that available data cover uniformly the region of the study; therefore regionalization is not needed in my opinion (parameters are already available).

Citation: https://doi.org/10.5194/hess-2021-382-RC1
- AC1: 'Reply on RC1', Zhihong Song, 12 Oct 2021
  
  Dear Anonymous Referee #1,
  We sincerely appreciate the referee’s positive comments on the manuscript. Please see our response to the reviewer’s concern on regionalizing the model parameters:
  Hydrologic models often rely on regionalization approaches to transfer information from small to large spatial scale (e.g., from gridcell to subbasin, watershed, and regional scale) (Beck et al., 2020; Mizukami et al., 2017), and from gauged to ungauged catchments (He et al., 2011; Hrachowitz et al., 2013; Pagliero et al., 2019; Parajka et al., 2013).
  In this study, though parameters were calibrated and available at each gridcell, the parameter values at around 450 gridcells were not reliable owning to poor model performance (i.e., KEG < 0) (Knoben et al., 2018; Koskinen et al., 2017; Sutanudjaja et al., 2018). Therefore, we only used the calibrated parameters with KGE ≥ 0 (i.e., representing better model performance) for regionalization of parameters. The model performance for 53% of these gridcells (with KGE < 0 prior to regionalization) were improved when we re-ran the model with regionalized parameters. Particularly, the KGE values in 37% of the gridcells (with KGE < 0 prior to regionalization) became positive, indicating a substantive improvement of the modeling performance.
  Even though the parameters were well calibrated and available at each gridcell, one might think whether and which topographic and edaphic properties mediate these hydrological parameters. Our machine learning (i.e., gradient boosting machine) based regionalization of parameters enables to estimate six key hydrological parameters using site-specific characteristics. Following the regionalization of parameters, our results of variable importance quantitatively indicate that the runoff generation parameters are majorly controlled by slope, saturated soil moisture content, and elevation. Moreover, the terrain attributes significantly regulate the runoff processes in relatively humid regions, while the saturated soil moisture content becomes a limiting factor in arid areas. The regionalization of parameters will improve our mechanistic understanding of the runoff generation processes and associated key hydrological parameters under different topographic and edaphic conditions.
  Thank you again for your comments.
  
  References
  Beck, H.E., Pan, M., Lin, P., Seibert, J., Dijk, A.I.J.M., and Wood, E.F.: Global Fully Distributed Parameter Regionalization Based on Observed Streamflow From 4,229 Headwater Catchments, Journal of Geophysical Research: Atmospheres, 125(17), 10.1029/2019JD031485, 2020
  He, Y., Bárdossy, A., and Zehe, E.: A review of regionalisation for continuous streamflow simulation, Hydrol. Earth Syst. Sc., 15(11), 3539-3553, 10.5194/hess-15-3539-2011, 2011
  Hrachowitz, M., Savenije, H.H.G., Blöschl, G., McDonnell, J.J., Sivapalan, M., Pomeroy, J.W., Arheimer, B., Blume, T., Clark, M.P., Ehret, U., Fenicia, F., Freer, J.E., Gelfan, A., Gupta, H.V., Hughes, D.A., Hut, R.W., Montanari, A., Pande, S., Tetzlaff, D., Troch, P.A., Uhlenbrook, S., Wagener, T., Winsemius, H.C., Woods, R.A., Zehe, E., and Cudennec, C.: A decade of Predictions in Ungauged Basins (PUB)—a review, Hydrological Sciences Journal, 58(6), 1198-1255, 10.1080/02626667.2013.803183, 2013
  Knoben, W.J.M., Woods, R.A., and Freer, J.E.: A Quantitative Hydrological Climate Classification Evaluated With Independent Streamflow Data, Water Resour. Res., 54(7), 5088-5109, https://doi.org/10.1029/2018WR022913, 2018
  Koskinen, M., Tahvanainen, T., Sarkkola, S., Menberu, M.W., Laurén, A., Sallantaus, T., Marttila, H., Ronkanen, A., Parviainen, M., Tolvanen, A., Koivusalo, H., and Nieminen, M.: Restoration of nutrient-rich forestry-drained peatlands poses a risk for high exports of dissolved organic carbon, nitrogen, and phosphorus, Sci. Total Environ., 586, 858-869, https://doi.org/10.1016/j.scitotenv.2017.02.065, 2017
  Mizukami, N., Clark, M.P., Newman, A.J., Wood, A.W., Gutmann, E.D., Nijssen, B., Rakovec, O., and Samaniego, L.: Towards seamless large-domain parameter estimation for hydrologic models, Water Resour. Res., 53(9), 8020-8040, 10.1002/2017WR020401, 2017
  Pagliero, L., Bouraoui, F., Diels, J., Willems, P., and McIntyre, N.: Investigating regionalization techniques for large-scale hydrological modelling, J. Hydrol., 570, 220-235, 10.1016/j.jhydrol.2018.12.071, 2019
  Parajka, J., Viglione, A., Rogger, M., Salinas, J.L., Sivapalan, M., and Blöschl, G.: Comparative assessment of predictions in ungauged basins – Part 1: Runoff-hydrograph studies, Hydrol. Earth Syst. Sc., 17(5), 1783-1795, 10.5194/hess-17-1783-2013, 2013
  Sutanudjaja, E.H., van Beek, R., Wanders, N., Wada, Y., Bosmans, J.H.C., Drost, N., van der Ent, R.J., de Graaf, I.E.M., Hoch, J.M., de Jong, K., Karssenberg, D., López López, P., Peßenteiner, S., Schmitz, O., Straatsma, M.W., Vannametee, E., Wisser, D., and Bierkens, M.F.P.: PCR-GLOBWB 2: a 5 arcmin global hydrological and water resources model, Geosci Model Dev, 11(6), 2429-2453, 10.5194/gmd-11-2429-2018, 2018
  
  Citation: https://doi.org/10.5194/hess-2021-382-AC1
RC2:
'Comment on hess-2021-382', Anonymous Referee #2, 22 Nov 2021

This discussion paper examines the use of gradient boosting machine learning to model the dependency of model parameters and estimate model parameters for four climate regions in China. The study also enhances the DTVGM model by incorporating the Penman-Monteith-Leuning (PML) equation. The discussion paper is well-presented, the study design is nicely conceived, and the results and discussion are presented fairly, with references to supporting figures, tables or cited literature, where appropriate.

I only have minor comments to enhance what is already a high quality manuscript.

(1) In several places, the model is referred to as the “China-wide hydrological model” (see L105). This is somewhat confusing. Is this a formal name for the hydrological model? If so, I would expect to see a citation after the phrase to reference the use of this name. If this is not the formal name, it may be more helpful to say “We ran a hydrological model developed by Beck et al (2020), for country of China in a spatially distributed…” In Section 2.1, the title could be changed to “Application of the hydrological model across China.”

(2) In my reading, there was some confusion about how you were able to compute evaluation metrics for all 15,640 grid cells (see Figure 5 for example). If you know the “truth” for runoff and ET at every grid cell, then why do you need a regionalization model?

(3) Also in Figure 5, it would be helpful to show the comparison of the model performance with and without the PML addition so that one can see in quantifiable terms how the addition of the equation improves the calibration and validation performance.

(4) Section 2.4: You provide an excellent description of the evaluation criteria; however, in your use of the Taylor skill score, could you clarify how the skill is determined for model parameters when you cannot know the true value of the parameters? L207-209 were somewhat confusing. This could be my lack of familiarity with the TSS, but it may be helpful to look over those lines to see if you could improve the explanation there.

(5) In the figure captions, some of the acronyms are spelled out, while others are not. It may be best to spell out all abbreviated words and their abbreviations in the captions so the reader does not have to refer back to the text.

Citation: https://doi.org/10.5194/hess-2021-382-RC2
- AC2: 'Reply on RC2', Zhihong Song, 24 Nov 2021
  
  Dear Anonymous Referee #2,
  We really appreciate your valuable suggestions and comments which can help us improve the quality of our manuscript. We have addressed the comments point-by-point. Please check the attached replies. The manuscript will be modified accordingly.
  
  Citation: https://doi.org/10.5194/hess-2021-382-AC2

Peer review completion

AR: Author's response | RR: Referee report | ED: Editor decision

ED: Publish subject to minor revisions (further review by editor) (12 Dec 2021) by Stacey Archfield

AR by Zhihong Song on behalf of the Authors (13 Dec 2021) Author's response Author's tracked changes Manuscript

ED: Publish as is (03 Jan 2022) by Stacey Archfield

Short summary

We performed a machine learning approach to regionalize the parameters of a China-wide hydrological model by linking six model parameters with 10 physical attributes (terrain and soil properties). The results show the superiority of machine-learning-based regionalization approach compared with the traditional linear regression method in ungauged regions. We also obtained the relative importance of attributes against model parameters.