Generalized reference evapotranspiration models with limited climatic data based on random forest and gene expression programming in Guangxi, China

Created by W.Langdon from gp-bibliography.bib Revision:1.8120

@Article{Wang:2019:AWM,

• author = "Sheng Wang and Jinjiao Lian and Yuzhong Peng and Baoqing Hu and Hongsong Chen",
• title = "Generalized reference evapotranspiration models with limited climatic data based on random forest and gene expression programming in {Guangxi, China}",
• journal = "Agricultural Water Management",
• year = "2019",
• volume = "221",
• pages = "220--230",
• month = "20 " # jul,
• keywords = "genetic algorithms, genetic programming, gene expression programming, water resources, climate change impact, variable importance, karst region",
• identifier = "RePEc:eee:agiwat:v:221:y:2019:i:c:p:220-230",
• oai = "oai:RePEc:eee:agiwat:v:221:y:2019:i:c:p:220-230",
• URL = "https://www.sciencedirect.com/science/article/pii/S0378377419305499",
• DOI = "doi:10.1016/j.agwat.2019.03.027",
• abstract = "Accurate estimation of reference evapotranspiration (ET0) is very important in hydrological cycle research, and is essential in agricultural water management and allocation. The application of the standard model (FAO-56 Penman-Monteith) to estimate ET0 is restricted due to the absence of required meteorological data. Although many machine learning algorithms have been applied in modelling ET0 with fewer meteorological variables, most of the models are trained and tested using data from the same station, their performances outside the training station are not evaluated. This study aims to investigate generalisation ability of the random forest (RF) algorithm in modelling ET0 with different input combinations (refer to different circumstances in missing data), and compares this algorithm with the gene-expression programming (GEP) method using the data from 24 weather stations in a karst region of southwest China. The ET0 estimated by the FAO-56 Penman-Monteith model was used as a reference to evaluate the derived RF-based and GEP-based models, and the coefficient of determination (R2), Nash-Sutcliffe coefficiency of efficiency (NSCE), root of mean squared error (RMSE), and percent bias (PBIAS) were used as evaluation criteria. The results revealed that the derived RF-based generalisation ET0 models are successfully applied in modelling ET0 with complete and incomplete meteorological variables (R2, NSCE, RMSE and PBIAS ranged from 0.637 to 0.987, 0.626 to 0.986, 0.107 to 0.563 mm day{$-$}1, and {$-$}2.916 percent to 1.571 percent, respectively), and seven RF-based models corresponding to different incomplete data circumstances are proposed. The GEP-based generalisation ET0 models are also proposed, and they produced promising results (R2, NSCE, RMSE and PBIAS ranged from 0.639 to 0.944, 0.636 to 0.942, 0.222 to 0.555 mm day{$-$}1, and {$-$}1.98 percent to 0.248 percent, respectively). Although the RF-based ET0 models performed slightly better than the GEP-based models, the GEP approach has the ability to give explicit expressions between the dependent and independent variables, which is more convenient for irrigators with minimal computer skills. Therefore, we recommend applying the RF-based models in water balance research, and the GEP-based models in agricultural irrigation practice. Moreover, the models performance decreased with periods due to climate change impact on ET0. At last, both of the two methods have the ability to assess the importance of predictors, the order of the importance of meteorological variables on ET0 in Guangxi is: sunshine duration, air temperature, relative humidity, and wind speed.",

}

Genetic Programming entries for Sheng Wang Jinjiao Lian Yu-zhong Peng Baoqing Hu Hongsong Chen

Citations