Long-term precipitation prediction in different climate divisions of California using remotely sensed data and machine learning

Majnooni, S; Nikoo, MR; Nematollahi, B; Fooladi, M; Alamdari, N; Al-Rawas, G; Gandomi, AH

Long-term precipitation prediction in different climate divisions of California using remotely sensed data and machine learning

Majnooni, S Nikoo, MR Nematollahi, B Fooladi, M Alamdari, N Al-Rawas, G Gandomi, AH

Permalink

Publisher:: TAYLOR & FRANCIS LTD
Publication Type:: Journal Article
Citation:: Hydrological Sciences Journal, 2023, 68, (14), pp. 1984-2008
Issue Date:: 2023-01-01

Closed Access

	Filename	Description	Size
	Long-term precipitation prediction in different climate divisions of California using remotely sensed data and machine learning.pdf	Accepted version	30.09 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Majnooni, S
dc.contributor.author	Nikoo, MR
dc.contributor.author	Nematollahi, B
dc.contributor.author	Fooladi, M
dc.contributor.author	Alamdari, N
dc.contributor.author	Al-Rawas, G
dc.contributor.author	Gandomi, AH
dc.date.accessioned	2024-04-29T03:14:50Z
dc.date.available	2024-04-29T03:14:50Z
dc.date.issued	2023-01-01
dc.identifier.citation	Hydrological Sciences Journal, 2023, 68, (14), pp. 1984-2008
dc.identifier.issn	0262-6667
dc.identifier.issn	2150-3435
dc.identifier.uri	http://hdl.handle.net/10453/178444
dc.description.abstract	This study presented a novel paradigm for forecasting 12-step-ahead monthly precipitation at 126 California gauge stations. First, the satellite-based precipitation time series from Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS), TerraClimate, ECMWF Reanalysis V5 (ERA5), and Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks-Climate Data Record (PERSIANN-CDR) products were bias-corrected using historical precipitation data. Four methods were tested, and quantile mapping (QM) was the best. After pre-processing data, 19 machine-learning models were developed. random forest, Extreme Gradient Boosting (XGBoost), extreme gradient boosting, support vector machine, multi-layer perceptron, and K-nearest-neighbours were chosen as the best models based on Complex Proportional Assessment (COPRAS) measurement. After hyperparameter adjustment, the Bayesian back-propagation regularization algorithm fused the results. The superior models’ predictions were considered inputs, and the target’s initial step was labeled. The next 11 steps at each station followed this approach, and the fusion models accurately predicted all steps. The 12th step’s average Nash-Sutcliffe efficiency (NSE), mean square error (MSE), coefficient of determination (R2), correlation coefficient (R) were 0.937, 52.136, 0.880, and 0.869, respectively, demonstrating the framework’s effectiveness at high forecasting horizons to help policymakers manage water resources.
dc.language	English
dc.publisher	TAYLOR & FRANCIS LTD
dc.relation.ispartof	Hydrological Sciences Journal
dc.relation.isbasedon	10.1080/02626667.2023.2248112
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0406 Physical Geography and Environmental Geoscience, 0905 Civil Engineering, 0907 Environmental Engineering
dc.subject.classification	Environmental Engineering
dc.subject.classification	3707 Hydrology
dc.subject.classification	3709 Physical geography and environmental geoscience
dc.subject.classification	4005 Civil engineering
dc.title	Long-term precipitation prediction in different climate divisions of California using remotely sensed data and machine learning
dc.type	Journal Article
utslib.citation.volume	68
utslib.for	0406 Physical Geography and Environmental Geoscience
utslib.for	0905 Civil Engineering
utslib.for	0907 Environmental Engineering
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access	*
dc.date.updated	2024-04-29T03:14:45Z
pubs.issue	14
pubs.publication-status	Published
pubs.volume	68
utslib.citation.issue	14

Abstract:

This study presented a novel paradigm for forecasting 12-step-ahead monthly precipitation at 126 California gauge stations. First, the satellite-based precipitation time series from Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS), TerraClimate, ECMWF Reanalysis V5 (ERA5), and Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks-Climate Data Record (PERSIANN-CDR) products were bias-corrected using historical precipitation data. Four methods were tested, and quantile mapping (QM) was the best. After pre-processing data, 19 machine-learning models were developed. random forest, Extreme Gradient Boosting (XGBoost), extreme gradient boosting, support vector machine, multi-layer perceptron, and K-nearest-neighbours were chosen as the best models based on Complex Proportional Assessment (COPRAS) measurement. After hyperparameter adjustment, the Bayesian back-propagation regularization algorithm fused the results. The superior models’ predictions were considered inputs, and the target’s initial step was labeled. The next 11 steps at each station followed this approach, and the fusion models accurately predicted all steps. The 12th step’s average Nash-Sutcliffe efficiency (NSE), mean square error (MSE), coefficient of determination (R2), correlation coefficient (R) were 0.937, 52.136, 0.880, and 0.869, respectively, demonstrating the framework’s effectiveness at high forecasting horizons to help policymakers manage water resources.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/178444