Comparing quantile regression forest and mixture density long short-term memory models for probabilistic post-processing of satellite precipitation-driven streamflow simulations
Yuhang Zhang,Aizhong Ye,Bita Analui,Phu Nguyen,Soroosh Sorooshian,Kuolin Hsu,and Yuxuan Wang
State Key Laboratory of Earth Surface Processes and Resource Ecology, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China
Department of Infrastructure Engineering, The University of Melbourne, Parkville 3010, Australia
State Key Laboratory of Earth Surface Processes and Resource Ecology, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China
Center for Hydrometeorology and Remote Sensing, Department of Civil and Environmental Engineering, University of California, Irvine, Irvine, California, CA 92697, USA
Center for Hydrometeorology and Remote Sensing, Department of Civil and Environmental Engineering, University of California, Irvine, Irvine, California, CA 92697, USA
Soroosh Sorooshian
Center for Hydrometeorology and Remote Sensing, Department of Civil and Environmental Engineering, University of California, Irvine, Irvine, California, CA 92697, USA
Kuolin Hsu
Center for Hydrometeorology and Remote Sensing, Department of Civil and Environmental Engineering, University of California, Irvine, Irvine, California, CA 92697, USA
Yuxuan Wang
College of Arts and Sciences, University of Virginia, Charlottesville, VA 22903, USA
Viewed
Total article views: 1,943 (including HTML, PDF, and XML)
HTML
PDF
XML
Total
Supplement
BibTeX
EndNote
1,409
476
58
1,943
94
39
42
HTML: 1,409
PDF: 476
XML: 58
Total: 1,943
Supplement: 94
BibTeX: 39
EndNote: 42
Views and downloads (calculated since 21 Nov 2022)
Cumulative views and downloads
(calculated since 21 Nov 2022)
Total article views: 675 (including HTML, PDF, and XML)
HTML
PDF
XML
Total
Supplement
BibTeX
EndNote
526
120
29
675
29
24
30
HTML: 526
PDF: 120
XML: 29
Total: 675
Supplement: 29
BibTeX: 24
EndNote: 30
Views and downloads (calculated since 20 Dec 2023)
Cumulative views and downloads
(calculated since 20 Dec 2023)
Total article views: 1,268 (including HTML, PDF, and XML)
HTML
PDF
XML
Total
Supplement
BibTeX
EndNote
883
356
29
1,268
65
15
12
HTML: 883
PDF: 356
XML: 29
Total: 1,268
Supplement: 65
BibTeX: 15
EndNote: 12
Views and downloads (calculated since 21 Nov 2022)
Cumulative views and downloads
(calculated since 21 Nov 2022)
Viewed (geographical distribution)
Total article views: 1,943 (including HTML, PDF, and XML)
Thereof 1,819 with geography defined
and 124 with unknown origin.
Total article views: 675 (including HTML, PDF, and XML)
Thereof 597 with geography defined
and 78 with unknown origin.
Total article views: 1,268 (including HTML, PDF, and XML)
Thereof 1,222 with geography defined
and 46 with unknown origin.
Our study shows that while the quantile regression forest (QRF) and countable mixtures of asymmetric Laplacians long short-term memory (CMAL-LSTM) models demonstrate similar proficiency in multipoint probabilistic predictions, QRF excels in smaller watersheds and CMAL-LSTM in larger ones. CMAL-LSTM performs better in single-point deterministic predictions, whereas QRF model is more efficient overall.
Our study shows that while the quantile regression forest (QRF) and countable mixtures of...