Evaluation of Direct Horizontal Irradiance in China Using a Physically-Based Model and Machine Learning Methods

Abstract

Accurate estimation of direct horizontal irradiance (DHI) is a prerequisite for the design and location of concentrated solar power thermal systems. Previous studies have shown that DHI observation stations are too sparsely distributed to meet requirements, as a result of the high construction and maintenance costs of observation platforms. Satellite retrieval and reanalysis have been widely used for estimating DHI, but their accuracy needs to be further improved. In addition, numerous modelling techniques have been used for this purpose worldwide. In this study, we apply five machine learning methods: back propagation neural networks (BP), general regression neural networks (GRNN), genetic algorithm (Genetic), M5 model tree (M5Tree), multivariate adaptive regression splines (MARS); and a physically based model, Yang’s hybrid model (YHM). Daily meteorological variables, including air temperature (T), relative humidity (RH), surface pressure (SP), and sunshine duration (SD) were obtained from 839 China Meteorological Administration (CMA) stations in different climatic zones across China and were used as data inputs for the six models. DHI observations at 16 CMA radiation stations were used to validate their accuracy. The results indicate that the capability of M5Tree was superior to BP, GRNN, Genetic, MARS and YHM, with the lowest values of daily root mean square (RMSE) of 1.989 MJ m−2day−1, and the highest correlation coefficient (R = 0.956), respectively. Then, monthly and annual mean DHI during 1960–2016 were calculated to reveal the spatiotemporal variation of DHI across China, using daily meteorological data based on the M5tree model. The results indicated a significantly decreasing trend with a rate of −0.019 MJ m−2during 1960–2016, and the monthly and annual DHI values of the Tibetan Plateau are the highest, while whereas the lowest values occur in the southeastern part of the Yunnan−Guizhou Plateau, the Sichuan Basin and most of the southern Yangtze River Basin. The possible causes for spatiotemporal variation of DHI across China were investigated by discussing cloud and aerosol loading.

Systematic review of application of artificial intelligence tools in architectural, engineering and construction

“…FNN has been used for various research topics, such as contractor prequalification (Lam et al, 2001), to estimate contractors' mark-up (Liu and Ling, 2003), among others. Examples of other hybrid techniques that have been used in various disciplines/sub-disciplines are Support Vector Regressional -Particle Swarm Optimization (SVR -PSO) (Yaseen et al, 2018), SVR (Goudarzi et al, 2019), multi-gene genetic programming (MGGP) (Hodhod et al, 2018), Random Support Vector Regression (RSVR) (Zhang and Fang, 2019), ANN/simulated annealing (ANN/SA) (Majidifard et al, 2019), weights of evidence-multivariate logistic Artificial intelligence tools regression (WoE -RF) (Chen et al, 2019a) and phase space reconstruction -ANN (PSR-ANN) (Delafrouz et al, 2018).…”

Revisiting the Decadal Variability of Solar Photovoltaic Resource Potential in the Monsoon Climate Zone of East Asia Using Innovative Trend Analysis

“…Unfortunately, previous studies using the ITA technique mostly focused on the meteorological and hydrological time series, while most studies on R s tended to apply various modeling methods (Pan et al, 2013; Amrouche and Le Pivert, 2014). For example, Deo et al (2016) predicted the R s using a wavelet-coupled support vector machine, and Chen et al (2019) reconstructed a direct radiation dataset across China using different machine learning models. Few studies have examined the decadal variability of R s around the world using different trend detection techniques, although a clear understanding of the variability of R s at regional and global scales using various techniques is vitally significant due to its widespread application in the solar energy field (Kisi, 2015; Pashiardis et al, 2017).…”

Estimation of Daily Average Shortwave Solar Radiation under Clear-Sky Conditions by the Spatial Downscaling and Temporal Extrapolation of Satellite Products in Mountainous Areas

“…DSSR reflects irradiance received by a given surface, and it can be measured through empirical or physical models based on meteorological observation elements (such as sunshine duration, temperature, relative humidity, etc.) from ground sites [7][8][9][10]. Since the 1960s, satellite remote sensing has gradually become an important data source for the estimation of solar Remote Sens.…”