Open Access
Water (Switzerland), volume 13, issue 12, pages 1696
How Well Can Machine Learning Models Perform without Hydrologists? Application of Rational Feature Selection to Improve Hydrological Forecasting
2
Hydroinformatics Chair Group, IHE Delft Institute for Water Education, 2611 AX Delft, The Netherlands
|
Publication type: Journal Article
Publication date: 2021-06-19
Biochemistry
Water Science and Technology
Aquatic Science
Geography, Planning and Development
Abstract
With more machine learning methods being involved in social and environmental research activities, we are addressing the role of available information for model training in model performance. We tested the abilities of several machine learning models for short-term hydrological forecasting by inferring linkages with all available predictors or only with those pre-selected by a hydrologist. The models used in this study were multivariate linear regression, the M5 model tree, multilayer perceptron (MLP) artificial neural network, and the long short-term memory (LSTM) model. We used two river catchments in contrasting runoff generation conditions to try to infer the ability of different model structures to automatically select the best predictor set from all those available in the dataset and compared models’ performance with that of a model operating on predictors prescribed by a hydrologist. Additionally, we tested how shuffling of the initial dataset improved model performance. We can conclude that in rainfall-driven catchments, the models performed generally better on a dataset prescribed by a hydrologist, while in mixed-snowmelt and baseflow-driven catchments, the automatic selection of predictors was preferable.
Citations by journals
|
1
2
3
4
|
|
|
Water (Switzerland)
|
Water (Switzerland)
4 publications, 25%
|
|
Women in the Geosciences
|
Women in the Geosciences
3 publications, 18.75%
|
|
Remote Sensing
|
Remote Sensing
1 publication, 6.25%
|
|
Environmental Modelling and Software
|
Environmental Modelling and Software
1 publication, 6.25%
|
|
Water Resources Research
|
Water Resources Research
1 publication, 6.25%
|
|
Water Resources
|
Water Resources
1 publication, 6.25%
|
|
Frontiers in Water
|
Frontiers in Water
1 publication, 6.25%
|
|
Natural Hazards and Earth System Sciences
|
Natural Hazards and Earth System Sciences
1 publication, 6.25%
|
|
Hydrology Research
|
Hydrology Research
1 publication, 6.25%
|
|
Computers and Electronics in Agriculture
|
Computers and Electronics in Agriculture
1 publication, 6.25%
|
|
1
2
3
4
|
Citations by publishers
|
1
2
3
4
5
|
|
|
Multidisciplinary Digital Publishing Institute (MDPI)
|
Multidisciplinary Digital Publishing Institute (MDPI)
5 publications, 31.25%
|
|
Wiley
|
Wiley
4 publications, 25%
|
|
Elsevier
|
Elsevier
2 publications, 12.5%
|
|
Pleiades Publishing
|
Pleiades Publishing
1 publication, 6.25%
|
|
Frontiers Media S.A.
|
Frontiers Media S.A.
1 publication, 6.25%
|
|
Copernicus
|
Copernicus
1 publication, 6.25%
|
|
IWA Publishing
|
IWA Publishing
1 publication, 6.25%
|
|
1
2
3
4
5
|
- We do not take into account publications that without a DOI.
- Statistics recalculated only for publications connected to researchers, organizations and labs registered on the platform.
- Statistics recalculated weekly.
{"yearsCitations":{"type":"bar","data":{"show":true,"labels":[2022,2023,2024],"ids":[0,0,0],"codes":[0,0,0],"imageUrls":["","",""],"datasets":[{"label":"Citations number","data":[5,9,2],"backgroundColor":["#3B82F6","#3B82F6","#3B82F6"],"percentage":["31.25","56.25","12.5"],"barThickness":null}]},"options":{"indexAxis":"x","maintainAspectRatio":true,"scales":{"y":{"ticks":{"precision":0,"autoSkip":false,"font":{"family":"Montserrat"},"color":"#000000"}},"x":{"ticks":{"stepSize":1,"precision":0,"font":{"family":"Montserrat"},"color":"#000000"}}},"plugins":{"legend":{"position":"top","labels":{"font":{"family":"Montserrat"},"color":"#000000"}},"title":{"display":true,"text":"Citations per year","font":{"size":24,"family":"Montserrat","weight":600},"color":"#000000"}}}},"journals":{"type":"bar","data":{"show":true,"labels":["Water (Switzerland)","Women in the Geosciences","Remote Sensing","Environmental Modelling and Software","Water Resources Research","Water Resources","Frontiers in Water","Natural Hazards and Earth System Sciences","Hydrology Research","Computers and Electronics in Agriculture"],"ids":[24405,42279,22827,6214,21255,22651,28945,1418,15754,5312],"codes":[0,0,0,0,0,0,0,0,0,0],"imageUrls":["\/storage\/images\/resized\/MjH1ITP7lMYGxeqUZfkt2BnVLgjkk413jwBV97XX_medium.webp","\/storage\/images\/resized\/bRyGpdm98BkAUYiK1YFNpl5Z7hPu6Gd87gbIeuG3_medium.webp","\/storage\/images\/resized\/MjH1ITP7lMYGxeqUZfkt2BnVLgjkk413jwBV97XX_medium.webp","\/storage\/images\/resized\/GDnYOu1UpMMfMMRV6Aqle4H0YLLsraeD9IP9qScG_medium.webp","\/storage\/images\/resized\/bRyGpdm98BkAUYiK1YFNpl5Z7hPu6Gd87gbIeuG3_medium.webp","\/storage\/images\/resized\/oZgeErrVFhuDksyqFURLvYS1wtVSBWczh001igGo_medium.webp","\/storage\/images\/resized\/4QWA67eqfcfyOiA8Wk7YnqroHFqQbTsmDJUYTCTg_medium.webp","\/storage\/images\/resized\/cxBZptDQQvWgQeXj5GoTXDfgUEoGVvFgpDRctnDr_medium.webp","\/storage\/images\/resized\/uGx6c1W3cHqbKXWIuICsBj3302lg4GbPWL7ng21d_medium.webp","\/storage\/images\/resized\/GDnYOu1UpMMfMMRV6Aqle4H0YLLsraeD9IP9qScG_medium.webp"],"datasets":[{"label":"","data":[4,3,1,1,1,1,1,1,1,1],"backgroundColor":["#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6"],"percentage":[25,18.75,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25],"barThickness":13}]},"options":{"indexAxis":"y","maintainAspectRatio":false,"scales":{"y":{"ticks":{"precision":0,"autoSkip":false,"font":{"family":"Montserrat"},"color":"#000000"}},"x":{"ticks":{"stepSize":null,"precision":0,"font":{"family":"Montserrat"},"color":"#000000"}}},"plugins":{"legend":{"position":"top","labels":{"font":{"family":"Montserrat"},"color":"#000000"}},"title":{"display":true,"text":"Journals","font":{"size":24,"family":"Montserrat","weight":600},"color":"#000000"}}}},"publishers":{"type":"bar","data":{"show":true,"labels":["Multidisciplinary Digital Publishing Institute (MDPI)","Wiley","Elsevier","Pleiades Publishing","Frontiers Media S.A.","Copernicus","IWA Publishing"],"ids":[202,11,17,101,208,3207,1283],"codes":[0,0,0,0,0,0,0],"imageUrls":["\/storage\/images\/resized\/MjH1ITP7lMYGxeqUZfkt2BnVLgjkk413jwBV97XX_medium.webp","\/storage\/images\/resized\/bRyGpdm98BkAUYiK1YFNpl5Z7hPu6Gd87gbIeuG3_medium.webp","\/storage\/images\/resized\/GDnYOu1UpMMfMMRV6Aqle4H0YLLsraeD9IP9qScG_medium.webp","\/storage\/images\/resized\/oZgeErrVFhuDksyqFURLvYS1wtVSBWczh001igGo_medium.webp","\/storage\/images\/resized\/4QWA67eqfcfyOiA8Wk7YnqroHFqQbTsmDJUYTCTg_medium.webp","\/storage\/images\/resized\/cxBZptDQQvWgQeXj5GoTXDfgUEoGVvFgpDRctnDr_medium.webp","\/storage\/images\/resized\/uGx6c1W3cHqbKXWIuICsBj3302lg4GbPWL7ng21d_medium.webp"],"datasets":[{"label":"","data":[5,4,2,1,1,1,1],"backgroundColor":["#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6"],"percentage":[31.25,25,12.5,6.25,6.25,6.25,6.25],"barThickness":13}]},"options":{"indexAxis":"y","maintainAspectRatio":false,"scales":{"y":{"ticks":{"precision":0,"autoSkip":false,"font":{"family":"Montserrat"},"color":"#000000"}},"x":{"ticks":{"stepSize":null,"precision":0,"font":{"family":"Montserrat"},"color":"#000000"}}},"plugins":{"legend":{"position":"top","labels":{"font":{"family":"Montserrat"},"color":"#000000"}},"title":{"display":true,"text":"Publishers","font":{"size":24,"family":"Montserrat","weight":600},"color":"#000000"}}}}}
Metrics
Cite this
GOST |
RIS |
BibTex |
MLA
Cite this
GOST
Copy
Moreido V. M. et al. How Well Can Machine Learning Models Perform without Hydrologists? Application of Rational Feature Selection to Improve Hydrological Forecasting // Water (Switzerland). 2021. Vol. 13. No. 12. p. 1696.
GOST all authors (up to 50)
Copy
Moreido V. M., Gartsman B., Solomatine D. P., Suchilina Z. How Well Can Machine Learning Models Perform without Hydrologists? Application of Rational Feature Selection to Improve Hydrological Forecasting // Water (Switzerland). 2021. Vol. 13. No. 12. p. 1696.
Cite this
RIS
Copy
TY - JOUR
DO - 10.3390/w13121696
UR - https://doi.org/10.3390%2Fw13121696
TI - How Well Can Machine Learning Models Perform without Hydrologists? Application of Rational Feature Selection to Improve Hydrological Forecasting
T2 - Water (Switzerland)
AU - Gartsman, Boris
AU - Suchilina, Zoya
AU - Moreido, V. M.
AU - Solomatine, D. P.
PY - 2021
DA - 2021/06/19 00:00:00
PB - Multidisciplinary Digital Publishing Institute (MDPI)
SP - 1696
IS - 12
VL - 13
SN - 2073-4441
ER -
Cite this
BibTex
Copy
@article{2021_Moreido,
author = {Boris Gartsman and Zoya Suchilina and V. M. Moreido and D. P. Solomatine},
title = {How Well Can Machine Learning Models Perform without Hydrologists? Application of Rational Feature Selection to Improve Hydrological Forecasting},
journal = {Water (Switzerland)},
year = {2021},
volume = {13},
publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},
month = {jun},
url = {https://doi.org/10.3390%2Fw13121696},
number = {12},
pages = {1696},
doi = {10.3390/w13121696}
}
Cite this
MLA
Copy
Moreido, V. M., et al. “How Well Can Machine Learning Models Perform without Hydrologists? Application of Rational Feature Selection to Improve Hydrological Forecasting.” Water (Switzerland), vol. 13, no. 12, Jun. 2021, p. 1696. https://doi.org/10.3390%2Fw13121696.