Evaluation of support vector machine for estimation of solar radiation from measured meteorological variables

Solar radiation is an essential and important variable to many models. However, it is measured at a very limited number of meteorological stations in the world. Developing method for accurate estimation of solar radiation from measured meteorological variables has been a focus and challenging task. This paper presents the method of solar radiation estimation using support vector machine (SVM). The main objective of this work is to examine the feasibility of SVM and explore its potential in solar radiation estimation. A total of 20 SVM models using different combinations of sunshine ratio, maximum and minimum air temperature, relative humidity, and atmospheric water vapor pressure as input attributes are explored using meteorological data at 15 stations in China. These models significantly outperform the empirical models with an average 14 % higher accuracy. When sunshine duration data are available, model SVM2 using sunshine ratio and air temperature range is proposed. It significantly outperforms the empirical models with an average 26 % higher accuracy. When sunshine duration data are not available, model SVM19 using maximum temperature, minimum temperature and atmospheric water vapor pressure is proposed. It significantly outperforms the temperature-based empirical models with an average of 18 % higher accuracy. The remarkable improvement indicates that the SVM method would be a promising alternative over traditional approaches for estimation of solar radiation at any locations.     

A simplified but accurate spectral solar irradiance model

Summary ¶The paper deals with the computation of solar energy available in a specific location. First, a new formula describing the relation between global solar irradiation and the duration of bright sunshine is established. The analysis of its use shows that global solar clear sky irradiance models are essential tools for daily computation of global irradiation. An integrated spectral atmospheric transmittance model is presented, it can be used to compute beam and diffuse clear sky irradiance for all applications where broadband solar energy input is needed. Since it is desirable to use simplified estimation methods for many applications, a parametric global solar irradiance model, derived from the spectral model, is also presented. This model needs only surface meteorological data as input. The influence of the averaging method used for the input parameters on the model accuracy is evaluated. Comparison of model results with the measurements shows an acceptable level of accuracy with the new model. Finally, an application of daily global solar energy computation is presented.Received May 17, 2002; revised October 14, 2002; accepted February 11, 2003 Published online September 10, 2003     

Aerosol polarized phase function and single-scattering albedo retrieved from ground-based measurements

Aerosol optical parameters, polarized phase function and single-scattering albdeo, have been retrieved from ground-based sun photometer measurements in Beijing 2003. The measured aerosol optical thickness varies from 0.12 to 0.77 with an average value of 0.39. The measured Ångström coefficient ranges from 0.75 to 1.47 with an average value of 1.21. The retrieved single-scattering albedo at 870 nm is within the 0.76–0.94 range and the average value is 0.85, suggests there are considerable aerosol absorptions in Beijing. The maximum value of retrieved polarized phase function at 870 nm ranges from 0.068 to 0.225 with an average value of 0.16, and it illustrates good correlations with the Ångström coefficient, i.e. the relative size of aerosol particles. Analyses of measurements and theoretical calculations show the polarized phase function is sensitive to aerosol size distribution and complex refractive index, especially the imaginary part of the refractive index which denotes aerosol light absorbing effects. These results suggest that the polarized phase function is an effective and unique aerosol optical parameter and is able to improve the retrieval of aerosol physical properties.     

A new approach to identify the sensitivity and importance of physical parameters combination within numerical models using the Lund–Potsdam–Jena (LPJ) model as an example

Daily global solar irradiation (R _s) is one of the main inputs in environmental modeling. Because of the lack of its measuring facilities, high-quality and long-term data are limited. In this research, R _s values were estimated based on measured sunshine duration and cloud cover of our synoptic meteorological stations in central and southern Iran during 2008, 2009, and 2011. Clear sky solar irradiation was estimated from linear regression using extraterrestrial solar irradiation as the independent variable with normalized root mean square error (NRMSE) of 4.69 %. Daily R _s was calibrated using measured sunshine duration and cloud cover data under different sky conditions during 2008 and 2009. The 2011 data were used for model validation. According to the results, in the presence of clouds, the R _s model using sunshine duration data was more accurate when compared with the model using cloud cover data (NRMSE = 11. 69 %). In both models, with increasing sky cloudiness, the accuracy decreased. In the study region, more than 92 % of sunshine durations were clear or partly cloudy, which received close to 95 % of total solar irradiation. Hence, it was possible to estimate solar irradiation with a good accuracy in most days with the measurements of sunshine duration.     

Retrieving daily global solar radiation from routine climate variables

Solar radiation is an important variable for studies related to solar energy applications, meteorology, climatology, hydrology, and agricultural meteorology. However, solar radiation is not routinely measured at meteorological stations; therefore, it is often required to estimate it using other techniques such as retrieving from satellite data or estimating using other geophysical variables. Over the years, many models have been developed to estimate solar radiation from other geophysical variables such as temperature, rainfall, and sunshine duration. The aim of this study was to evaluate six of these models using data measured at four independent worldwide networks. The dataset included 13 stations from Australia, 25 stations from Germany, 12 stations from Saudi Arabia, and 48 stations from the USA. The models require either sunshine duration hours (Ångstrom) or daily range of air temperature (Bristow and Campbell, Donatelli and Bellocchi, Donatelli and Campbell, Hargreaves, and Hargreaves and Samani) as input. According to the statistical parameters, Ångstrom and Bristow and Campbell indicated a better performance than the other models. The bias and root mean square error for the Ångstrom model were less than 0.25 MJ m² day^?1 and 2.25 MJ m² day^?1, respectively, and the correlation coefficient was always greater than 95 %. Statistical analysis using Student’s t test indicated that the residuals for Ångstrom, Bristow and Campbell, Hargreaves, and Hargreaves and Samani are not statistically significant at the 5 % level. In other words, the estimated values by these models are statistically consistent with the measured data. Overall, given the simplicity and performance, the Ångstrom model is the best choice for estimating solar radiation when sunshine duration measurements are available; otherwise, Bristow and Campbell can be used to estimate solar radiation using daily range of air temperature.     

Fuzzy modelling of solar irradiation using air temperature data

Summary Fuzzy sets theory is applied to relate global solar irradiation to both the daily average and the daily amplitude of air temperature. In addition to the presentation of a new mapping technique, from the input to the output of the model, an innovative approach for the tuning of the fuzzy algorithm to fit a local meteo-climate is proposed. Since air temperature-based solar radiation models are strongly dependent on the origin location, the adaptive method presented here is designed as a tool for potential users to either increase the application area or to devise more precise local models. A critical assessment of fuzzy model performances and limitations has been conducted. Results reported here demonstrate the potential of modelling solar irradiation using fuzzy sets approach. Authors’ address: E. Tulcan-Paulescu, M. Paulescu, Physics Department, West University of Timisoara, V. Parvan 4, 300223 Timisoara, Romania.     

Temporal and spatial variations of global solar radiation over the Qinghai–Tibetan Plateau during the past 40 years

Global solar radiation is of great significance to the balance of ground surface radiation, the energy exchange between the Earth’s surface and atmosphere, and the development of weather and climate systems in various regions. In this study, the monthly global radiation recorded at 23 stations over the Qinghai–Tibetan Plateau (QTP) was utilized to estimate global solar radiation (Q) from sunshine duration and to obtain improved fits to the variation coefficients of the monthly Angström–Prescott model (APM). The modeling results were evaluated by calculating the statistical errors, including mean bias error, mean absolute error, root mean square error, and mean relative error. We demonstrate that the monthly Q values can be predicted accurately by APM over the QTP. We also assess the variations of Q values at 116 meteorological stations by APM over the QTP during 1961–2000. The analysis shows that the annual mean sunshine duration amounted to more than 3,000 h over the whole plateau, implying promising prospects for economic applications of solar energy. During the past 40 years, the mean global solar radiation has been relatively high in the western QTP, extending northward to the Inner Mongolian Plateau. Although its decadal variations in the QTP and surrounding regions were inconsistent, the anomaly values of global solar radiation were generally positive during the 1960s and 1970s, indicating that the QTP’s global solar radiation has increased during those periods. The anomaly values were negative during the 1980s and 1990s, showing that the plateau’s global solar radiation has decreased during those periods. Global solar radiation over the QTP is negatively proportional to latitude but positively proportional to altitude and relative sunshine duration. Three factors, the sunshine duration, latitude, and altitude, exert great influence on global surface radiation, of which sunshine duration is most significant. A high-variation-coefficient zone of global solar radiation occurred in the western part of the QTP but, on average, the variation coefficient of the plateau’s global solar radiation was only 0.031, suggesting that the variation in global radiation was relatively stable over the whole QTP.     

Simple new methods to estimate global solar radiation based on meteorological data in Egypt

Three simple methods to estimate global solar radiation are proposed in addition to (Solar Energy 63 (1998) 147). All were tested seasonally and at different sky conditions at seven locations in Egypt. The methods use ground-based measurements of maximum and minimum temperature, daily mean of cloud cover and extraterrestrial global radiation. Average of root mean square differences (RMSD) for a comparison between observed and estimated global radiation for all locations tested was around 10% for the new methods and 13% for Supit–Van Kappel method. The coefficient of determination R² is higher for the new methods for all tested locations. Better results were obtained when applying the new methods to different seasons. The differences in root mean square error (RMSE) between the new methods and Ångstrom–Prescott method that is based on sunshine duration data were less than 1.0 MJ m⁻² day⁻¹ at all sites. On the whole, the performance statistics demonstrate that the new methods are better when compared by Ångstrom–Prescott method.     

Precise estimation of hourly global solar radiation for micrometeorological analysis by using data classification and hourly sunshine

We have developed a method for estimating hourly global solar radiation (GSR) from hourly sunshine duration data. This procedure requires only hourly sunshine duration as the input data and utilizes hourly precipitation and daily snow cover as auxiliary data to classify time intervals into six cases according to weather conditions. To obtain hourly GSR using a simple algebraic form, a quadratic function of the solar elevation angle and the sunshine duration ratio is used. Daily GSR is given by a sum of hourly GSRs. We evaluated the performance of the newly developed method using data obtained at 67 meteorological stations and found that the estimated GSR is highly consistent with that observed. Hourly and daily root-mean-square misfits are approximately 0.2 MJ/m²/h (~55 W/m²) and 1.4 to 1.5 MJ/m²/day (~16 to 17 W/m²), respectively. Our classification of weather conditions is effective for reducing estimation errors, especially under cloudy skies. Since the sunshine duration is observed at more meteorological stations than GSR, the proposed new method is a powerful tool for obtaining solar radiation with hourly resolution and a dense geographical distribution. One of the proposed methods, GSRgrn, can be applicable to hourly GSR estimations at different observation sites by setting local parameters (the precipitable water, surface albedo, and atmospheric turbidity) suitable to the sites. The hourly GSR can be applied for various micrometeorological studies, such as the heat budget of crop fields.     

锡林浩特市太阳辐射变化及相关气象要素分析

利用1990—2010年锡林浩特气象站太阳总辐射、日照时数、日照百分率、降水量、气温以及总云量的观测资料,运用5a滑动平均及最小二乘原理等方法,分析了锡林浩特市1990—2010年来的总辐射变化规律,并分析了气温、降水、日照、云量等的变化以及与太阳总辐射的相关关系。研究结果表明,锡林浩特市太阳总辐射呈现波动增加的趋势,但四季太阳辐射量在近21a的年际波动略有不同。相关要素分析表明,太阳总辐射与日照时数和夏季、秋季气温有很显著的正相关关系,与降水量和春季、夏季的总云量呈负相关关系。     

Estimating solar radiation as a function of air temperature using Fourier series

Summary Due to the periodicity of variations in solar radiation and air temperature their dimensionless values are expanded in Fourier series. Fourier coefficients were determined using data recorded by weather stations in various Egyptian cities. In terms of ambient air temperature, these coefficients are used to calculate solar radiation for specific geographic locations near to weather stations for which solar radiation data are unavailable.Estimates of solar radiation calculated by means of Fourier coefficients are compared with observed solar radiation data based on the number of hours of sunshine for the stations where there were records of sunshine duration. The comparison shows a good agreement between estimated and observed.With 10 Figures     

几种水平面太阳总辐射量计算模型的对比分析

利用中国区域1961-1999年39 a间98个常规气象观测数据,建立6个模型分别以天文辐射、干洁大气总辐射和湿洁大气总辐射为起始数据,进行太阳辐射日总量的模拟,对比分析了6个水平面太阳总辐射量计算模型的性能.结果表明:在三种起始数据中,干洁大气总辐射和湿洁大气总辐射均能较好地体现宏观地势对太阳辐射空间分布的影响,以湿洁大气总辐射为起始数据的计算模型拟合精度相对较高.对6个水平面太阳总辐射量计算模型的对比分析发现:2个以日照百分率为主导因子,气温日较差为修正项的综合模型拟合误差最小,精度最高;经典的日照百分率模型次之,但其模型系数最稳定可靠;3个气温日较差模型拟合效果最差.最终选用经验系数稳定、拟合精度较高的日照百分率模型,制作了2001年中国水平面太阳辐射日总量空间分布图.     

Assessing the distribution of solar irradiation in Mbarara, Uganda

Summary Existing literature lacks information on formulation and performance assessment of diffuse solar radiation models in the Eastern African region yet this region has a high potential for the utilization of solar energy. The objective of this paper is to assess the performance of seventeen diffuse solar irradiation empirical correlations, at Kampala, Uganda. The best performing correlations were determined using the ranking method. The normalized absolute mean bias error and root mean square error were computed and utilized in the ranking process. The results indicated that the correlations relating diffuse transmittance with relative sunshine duration are more reliable for diffuse solar radiation predictions at least in the Uganda environment. These models are expressed in terms of first, second and third order polynomials of the relative sunshine duration and are particularly recommended for their simplicity and worldwide applicability.     

Variations and trends in global solar radiation for Turkey

Summary Since measured solar radiation data in Turkey have rather high random errors, sunshine duration data covering the period from 1960 through 1994 from 34 stations in Turkey were taken to derive estimates of monthly mean global solar radiation by a quadratic correlation. The least square linear regression method was applied for trend analysis. Significant negative trends of the annual means were observed with 71 percent of the stations A 3.44 percent decrease in global solar radiation was observed over the last 35 years in Turkey. The decrease in solar radiation is an indication of increased air pollution, as statistical parameters show that Turkey is rapidly expanding economically, and thus air quality has deteriorated correspondingly.With 3 Figures     

1960~2000年黄河流域太阳总辐射气候变化规律研究

运用数据集群技术，在黄河流域建立了用日照百分率拟合太阳总辐射的不同时空尺度估算式，对比分析了不同数据集群下总辐射的拟合精度。利用逆距离加权插值法，将获得的黄河流域及其周边35个日射站1~12月总辐射拟合的经验系数进行空间内插，获得了黄河流域1~12月总辐射拟合经验系数的空间分布。结合黄河流域及其周边164个常规气象站日照百分率观测资料，对黄河流域1960~2000年太阳总辐射进行了计算，分析了其气候变化的时空分布规律。结果表明:黄河流域近年来太阳总辐射呈下降趋势，在季节上主要表现在夏季和冬季。     

济南的城市发展对气候的影响

研究了济南城市的发展对局地气候的影响，发现济南城郊气温差值，降水日数差值有逐渐增大的趋势，而市区日照时数，太阳直接辐射量，总辐射量有明显减小的趋势，天空散射辐射量增加趋势明显。     

宝坻太阳辐射资料可用性研究

应用典型的辐射资料质量检验方法、辐射数据变化特征分析、人工与器测日照对比分析及太阳总辐射与相关辐射要素间的统计分析对天津市宝坻国家级基本气象站站内的太阳辐射观测系统试运行期间的辐射观测数据进行了质量分析,结果表明,试运行期间数据到报情况理想,总、散射辐射观测数据的BSRN的质量检验合格率为100%,直接辐射合格率为85%,净辐射通过了仪器阀值质量检验;太阳辐射值及变化特征符合理论实际;人工与器测日照时数具有很好的线性相关性(R2=0.96),总辐射与日照时数及散射辐射之间的线性变化与历史经验结论吻合。总体来看,宝坻太阳辐射系统观测数据可用性较高,能够满足日常业务需求。     

Estimating sunshine duration from other climatic data by artificial neural network for ET0 estimation in an arid environment

Sunshine duration data are desirable for calculating daily solar radiation (R _s) and subsequent reference evapotranspiration (ET₀) using the Penman–Monteith (PM) method. In the absence of measured R _s data, the Ångström equation has been recommended by the Food and Agriculture Organization (FAO) of the United Nations. This equation requires actual sunshine duration that is not commonly observed at many weather stations. This paper examines the potential for the use of artificial neural networks (ANNs) to estimate sunshine duration based on air temperature and humidity data under arid environment. This is important because these data are commonly available parameters. The impact of the estimated sunshine duration on estimation of R _s and ET₀ was also conducted. The four weather stations selected for this study are located in Sistan and Baluchestan Province (southeast of Iran). The study demonstrated that modelling of sunshine duration through the use of ANN technique made acceptable estimates. Models were compared using the determination coefficient (R ²), the root mean square error (RMSE) and the mean bias error (MBE). Average R ², RMSE and MBE for the comparison between measured and estimated sunshine duration were calculated resulting 0.81, 6.3 % and 0.1 %, respectively. Our analyses also demonstrate that the difference between the measured and estimated sunshine duration has less effect on the estimated R _s and ET₀ by using Ångström and FAO-PM equations, respectively.     

2001-2012年北京市空气污染指数节气分布及其与气象要素的关系

利用2001年1月1日-2012年12月31日北京市空气污染指数资料和地面气象观测数据,对北京市API的节气变化特征及其与气象因子在节气尺度上的相关关系进行统计分析。结果表明：2001-2012年北京市春季和冬季分别以清明和小雪节气API最高,空气质量最差;立秋节气API最低,空气质量最好。春分至霜降节气空气首要污染物是PM₁₀,SO₂作为首要污染物出现在立冬~大寒和立春~惊蛰节气,小寒达到最大。温度、风速和相对湿度是影响北京空气质量主要气象因子,立春~谷雨主要受气压影响,立冬~大寒受相对湿度和日照时数影响较大,立夏~霜降与平均气温和最低气温显著相关,风速主要影响春秋节气。