Machine learning methods for empirical streamflow simulation: a comparison of model accuracy, interpretability, and uncertainty in seasonal watersheds

Shortridge, Julie E.; Guikema, Seth D.; Zaitchik, Benjamin F.

doi:10.5194/hess-20-2611-2016

Articles | Volume 20, issue 7

https://doi.org/10.5194/hess-20-2611-2016

© Author(s) 2016. This work is distributed under
the Creative Commons Attribution 3.0 License.

https://doi.org/10.5194/hess-20-2611-2016

© Author(s) 2016. This work is distributed under
the Creative Commons Attribution 3.0 License.

Articles | Volume 20, issue 7

Research article

|

04 Jul 2016

Research article |

| 04 Jul 2016

Machine learning methods for empirical streamflow simulation: a comparison of model accuracy, interpretability, and uncertainty in seasonal watersheds

Julie E. Shortridge, Seth D. Guikema, and Benjamin F. Zaitchik

Viewed

Total article views: 6,831 (including HTML, PDF, and XML)

HTML	PDF	XML	Total	Supplement	BibTeX	EndNote
3,453	3,176	202	6,831	346	186	189

HTML: 3,453
PDF: 3,176
XML: 202
Total: 6,831
Supplement: 346
BibTeX: 186
EndNote: 189

Views and downloads (calculated since 28 Oct 2015)

Month	HTML	PDF	XML	Total
Oct 2015	37	54	13	104
Nov 2015	14	25	2	41
Dec 2015	8	18	0	26
Jan 2016	23	24	0	47
Feb 2016	14	5	2	21
Mar 2016	10	1	0	11
Apr 2016	5	4	0	9
May 2016	4	2	0	6
Jun 2016	4	2	0	6
Jul 2016	127	42	6	175
Aug 2016	23	13	0	36
Sep 2016	18	8	0	26
Oct 2016	12	7	2	21
Nov 2016	12	6	0	18
Dec 2016	5	5	0	10
Jan 2017	17	10	0	27
Feb 2017	14	15	1	30
Mar 2017	20	31	2	53
Apr 2017	38	31	2	71
May 2017	33	29	3	65
Jun 2017	44	20	1	65
Jul 2017	22	18	0	40
Aug 2017	14	19	0	33
Sep 2017	9	19	0	28
Oct 2017	4	13	0	17
Nov 2017	13	25	3	41
Dec 2017	15	23	4	42
Jan 2018	7	11	0	18
Feb 2018	17	19	0	36
Mar 2018	14	16	0	30
Apr 2018	10	15	0	25
May 2018	8	21	0	29
Jun 2018	8	9	0	17
Jul 2018	10	13	0	23
Aug 2018	14	16	1	31
Sep 2018	18	25	0	43
Oct 2018	11	19	0	30
Nov 2018	19	25	0	44
Dec 2018	14	19	0	33
Jan 2019	19	74	3	96
Feb 2019	15	85	0	100
Mar 2019	11	93	0	104
Apr 2019	9	76	1	86
May 2019	15	86	2	103
Jun 2019	11	84	1	96
Jul 2019	8	45	0	53
Aug 2019	17	26	1	44
Sep 2019	15	16	1	32
Oct 2019	28	43	1	72
Nov 2019	18	35	1	54
Dec 2019	10	23	1	34
Jan 2020	15	28	1	44
Feb 2020	11	18	1	30
Mar 2020	9	22	0	31
Apr 2020	10	23	0	33
May 2020	11	21	0	32
Jun 2020	16	14	0	30
Jul 2020	24	17	10	51
Aug 2020	15	23	5	43
Sep 2020	14	23	0	37
Oct 2020	16	24	0	40
Nov 2020	17	24	0	41
Dec 2020	13	25	0	38
Jan 2021	44	37	0	81
Feb 2021	26	26	0	52
Mar 2021	27	23	1	51
Apr 2021	24	25	1	50
May 2021	24	35	0	59
Jun 2021	22	22	1	45
Jul 2021	15	16	0	31
Aug 2021	23	22	1	46
Sep 2021	26	23	1	50
Oct 2021	19	43	2	64
Nov 2021	53	41	3	97
Dec 2021	31	34	0	65
Jan 2022	40	38	3	81
Feb 2022	27	24	5	56
Mar 2022	22	19	1	42
Apr 2022	26	16	2	44
May 2022	35	20	1	56
Jun 2022	21	13	2	36
Jul 2022	29	22	1	52
Aug 2022	43	22	2	67
Sep 2022	33	42	3	78
Oct 2022	24	30	2	56
Nov 2022	41	42	1	84
Dec 2022	32	26	5	63
Jan 2023	42	39	1	82
Feb 2023	38	23	5	66
Mar 2023	63	33	17	113
Apr 2023	20	33	2	55
May 2023	57	36	3	96
Jun 2023	52	17	1	70
Jul 2023	45	21	5	71
Aug 2023	39	16	3	58
Sep 2023	41	12	1	54
Oct 2023	88	29	5	122
Nov 2023	38	9	1	48
Dec 2023	58	22	4	84
Jan 2024	29	10	2	41
Feb 2024	22	21	0	43
Mar 2024	38	31	3	72
Apr 2024	36	22	5	63
May 2024	54	21	5	80
Jun 2024	38	16	2	56
Jul 2024	45	13	5	63
Aug 2024	55	16	2	73
Sep 2024	36	17	1	54
Oct 2024	46	18	0	64
Nov 2024	41	52	2	95
Dec 2024	40	24	1	65
Jan 2025	43	27	3	73
Feb 2025	61	12	2	75
Mar 2025	70	22	0	92
Apr 2025	62	37	3	102
May 2025	38	25	2	65
Jun 2025	83	37	0	120
Jul 2025	53	33	2	88
Aug 2025	39	31	2	72
Sep 2025	81	26	0	107
Oct 2025	59	46	1	106
Nov 2025	40	43	2	85

Cumulative views and downloads (calculated since 28 Oct 2015)

Month	HTML	PDF	XML	Total
Oct 2015	37	54	13	104
Nov 2015	14	25	2	41
Dec 2015	8	18	0	26
Jan 2016	23	24	0	47
Feb 2016	14	5	2	21
Mar 2016	10	1	0	11
Apr 2016	5	4	0	9
May 2016	4	2	0	6
Jun 2016	4	2	0	6
Jul 2016	127	42	6	175
Aug 2016	23	13	0	36
Sep 2016	18	8	0	26
Oct 2016	12	7	2	21
Nov 2016	12	6	0	18
Dec 2016	5	5	0	10
Jan 2017	17	10	0	27
Feb 2017	14	15	1	30
Mar 2017	20	31	2	53
Apr 2017	38	31	2	71
May 2017	33	29	3	65
Jun 2017	44	20	1	65
Jul 2017	22	18	0	40
Aug 2017	14	19	0	33
Sep 2017	9	19	0	28
Oct 2017	4	13	0	17
Nov 2017	13	25	3	41
Dec 2017	15	23	4	42
Jan 2018	7	11	0	18
Feb 2018	17	19	0	36
Mar 2018	14	16	0	30
Apr 2018	10	15	0	25
May 2018	8	21	0	29
Jun 2018	8	9	0	17
Jul 2018	10	13	0	23
Aug 2018	14	16	1	31
Sep 2018	18	25	0	43
Oct 2018	11	19	0	30
Nov 2018	19	25	0	44
Dec 2018	14	19	0	33
Jan 2019	19	74	3	96
Feb 2019	15	85	0	100
Mar 2019	11	93	0	104
Apr 2019	9	76	1	86
May 2019	15	86	2	103
Jun 2019	11	84	1	96
Jul 2019	8	45	0	53
Aug 2019	17	26	1	44
Sep 2019	15	16	1	32
Oct 2019	28	43	1	72
Nov 2019	18	35	1	54
Dec 2019	10	23	1	34
Jan 2020	15	28	1	44
Feb 2020	11	18	1	30
Mar 2020	9	22	0	31
Apr 2020	10	23	0	33
May 2020	11	21	0	32
Jun 2020	16	14	0	30
Jul 2020	24	17	10	51
Aug 2020	15	23	5	43
Sep 2020	14	23	0	37
Oct 2020	16	24	0	40
Nov 2020	17	24	0	41
Dec 2020	13	25	0	38
Jan 2021	44	37	0	81
Feb 2021	26	26	0	52
Mar 2021	27	23	1	51
Apr 2021	24	25	1	50
May 2021	24	35	0	59
Jun 2021	22	22	1	45
Jul 2021	15	16	0	31
Aug 2021	23	22	1	46
Sep 2021	26	23	1	50
Oct 2021	19	43	2	64
Nov 2021	53	41	3	97
Dec 2021	31	34	0	65
Jan 2022	40	38	3	81
Feb 2022	27	24	5	56
Mar 2022	22	19	1	42
Apr 2022	26	16	2	44
May 2022	35	20	1	56
Jun 2022	21	13	2	36
Jul 2022	29	22	1	52
Aug 2022	43	22	2	67
Sep 2022	33	42	3	78
Oct 2022	24	30	2	56
Nov 2022	41	42	1	84
Dec 2022	32	26	5	63
Jan 2023	42	39	1	82
Feb 2023	38	23	5	66
Mar 2023	63	33	17	113
Apr 2023	20	33	2	55
May 2023	57	36	3	96
Jun 2023	52	17	1	70
Jul 2023	45	21	5	71
Aug 2023	39	16	3	58
Sep 2023	41	12	1	54
Oct 2023	88	29	5	122
Nov 2023	38	9	1	48
Dec 2023	58	22	4	84
Jan 2024	29	10	2	41
Feb 2024	22	21	0	43
Mar 2024	38	31	3	72
Apr 2024	36	22	5	63
May 2024	54	21	5	80
Jun 2024	38	16	2	56
Jul 2024	45	13	5	63
Aug 2024	55	16	2	73
Sep 2024	36	17	1	54
Oct 2024	46	18	0	64
Nov 2024	41	52	2	95
Dec 2024	40	24	1	65
Jan 2025	43	27	3	73
Feb 2025	61	12	2	75
Mar 2025	70	22	0	92
Apr 2025	62	37	3	102
May 2025	38	25	2	65
Jun 2025	83	37	0	120
Jul 2025	53	33	2	88
Aug 2025	39	31	2	72
Sep 2025	81	26	0	107
Oct 2025	59	46	1	106
Nov 2025	40	43	2	85

Latest update: 26 Nov 2025

Short summary

This paper compares six methods for data-driven rainfall–runoff simulation in terms of predictive accuracy, error structure, interpretability, and uncertainty. We demonstrate that autocorrelation in model errors can result in biased estimates of important values and show how certain model structures can be more easily interpreted to yield insights on physical watershed function. Finally, we explore how model structure can impact uncertainty in climate change sensitivity estimates.