TY - JOUR
T1 - Long-term precipitation prediction in different climate divisions of California using remotely sensed data and machine learning
AU - Majnooni, Shabnam
AU - Nikoo, Mohammad Reza
AU - Nematollahi, Banafsheh
AU - Fooladi, Mahmood
AU - Alamdari, Nasrin
AU - Al-Rawas, Ghazi
AU - Gandomi, Amir H.
N1 - Publisher Copyright:
© 2023 IAHS.
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
KW - bias correction
KW - hyperparameters
KW - long-term precipitation prediction
KW - machine learning (ML)
KW - quantile mapping (QM)
KW - satellite-based precipitation
UR - http://www.scopus.com/inward/record.url?scp=85170711838&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85170711838&partnerID=8YFLogxK
UR - https://www.mendeley.com/catalogue/1e43c03c-8e86-3a23-aa8d-acf9e25d2263/
U2 - 10.1080/02626667.2023.2248112
DO - 10.1080/02626667.2023.2248112
M3 - Article
AN - SCOPUS:85170711838
SN - 0262-6667
VL - 68
SP - 1984
EP - 2008
JO - Hydrological Sciences Journal
JF - Hydrological Sciences Journal
IS - 14
ER -