The Experts below are selected from a list of 321 Experts worldwide ranked by ideXlab platform
Deti Xie - One of the best experts on this subject based on the ideXlab platform.
-
Estimation of monthly solar radiation from measured temperatures using support vector machines – A case study
Renewable Energy, 2011Co-Authors: Jilong Chen, Hong-bin Liu, Deti XieAbstract:Abstract Solar radiation is the principal and fundamental energy for many physical, chemical and biological processes. However, it is measured at a very limited number of meteorological stations in the world. This paper presented the methods of monthly mean daily solar radiation estimation using support vector machines (SVMs), which is a relatively new machine learning algorithm based on the statistical learning theory. The main objective of this paper was to examine the feasibility of SVMs in estimating monthly solar radiation using air temperatures. Measured long-term monthly air temperatures including maximum and minimum temperatures (Tmax and Tmin, respectively) were gathered and analyzed at Chongqing meteorological station, China. Seven combinations of air temperatures, namely, (1) Tmax, (2) Tmin, (3) Tmax − Tmin, (4) Tmax and Tmin, (5) Tmax and Tmax − Tmin, (6) Tmin and Tmax − Tmin, and (7) Tmax, Tmin, and Tmax − Tmin, were served as input features for SVM models. Three equations including linear, polynomial, and radial basis function were used as kernel functions. The performances were evaluated using root mean square error (RMSE), relative root mean square error (RRMSE), Nash-Sutcliffe (NSE), and determination coefficient (R2). The developed SVM models were also compared with several empirical temperature-based models. Comparison analyses showed that the newly developed SVM model using Tmax and Tmin with polynomial kernel function performed better than other SVM models and empirical methods with highest NSE of 0.999, R2 of 0.969, lowest RMSE of 0.833 MJ m−2 and RRMSE of 9.00%. The results showed that the SVM methodology may be a promising alternative to the traditional approaches for predicting solar radiation where the records of air temperatures are available.
-
estimation of monthly solar radiation from measured temperatures using support vector machines a case study
Renewable Energy, 2011Co-Authors: Jilong Chen, Hong-bin Liu, Deti XieAbstract:Abstract Solar radiation is the principal and fundamental energy for many physical, chemical and biological processes. However, it is measured at a very limited number of meteorological stations in the world. This paper presented the methods of monthly mean daily solar radiation estimation using support vector machines (SVMs), which is a relatively new machine learning algorithm based on the statistical learning theory. The main objective of this paper was to examine the feasibility of SVMs in estimating monthly solar radiation using air temperatures. Measured long-term monthly air temperatures including maximum and minimum temperatures (Tmax and Tmin, respectively) were gathered and analyzed at Chongqing meteorological station, China. Seven combinations of air temperatures, namely, (1) Tmax, (2) Tmin, (3) Tmax − Tmin, (4) Tmax and Tmin, (5) Tmax and Tmax − Tmin, (6) Tmin and Tmax − Tmin, and (7) Tmax, Tmin, and Tmax − Tmin, were served as input features for SVM models. Three equations including linear, polynomial, and radial basis function were used as kernel functions. The performances were evaluated using root mean square error (RMSE), relative root mean square error (RRMSE), Nash-Sutcliffe (NSE), and determination coefficient (R2). The developed SVM models were also compared with several empirical temperature-based models. Comparison analyses showed that the newly developed SVM model using Tmax and Tmin with polynomial kernel function performed better than other SVM models and empirical methods with highest NSE of 0.999, R2 of 0.969, lowest RMSE of 0.833 MJ m−2 and RRMSE of 9.00%. The results showed that the SVM methodology may be a promising alternative to the traditional approaches for predicting solar radiation where the records of air temperatures are available.
Jilong Chen - One of the best experts on this subject based on the ideXlab platform.
-
Estimation of monthly solar radiation from measured temperatures using support vector machines – A case study
Renewable Energy, 2011Co-Authors: Jilong Chen, Hong-bin Liu, Deti XieAbstract:Abstract Solar radiation is the principal and fundamental energy for many physical, chemical and biological processes. However, it is measured at a very limited number of meteorological stations in the world. This paper presented the methods of monthly mean daily solar radiation estimation using support vector machines (SVMs), which is a relatively new machine learning algorithm based on the statistical learning theory. The main objective of this paper was to examine the feasibility of SVMs in estimating monthly solar radiation using air temperatures. Measured long-term monthly air temperatures including maximum and minimum temperatures (Tmax and Tmin, respectively) were gathered and analyzed at Chongqing meteorological station, China. Seven combinations of air temperatures, namely, (1) Tmax, (2) Tmin, (3) Tmax − Tmin, (4) Tmax and Tmin, (5) Tmax and Tmax − Tmin, (6) Tmin and Tmax − Tmin, and (7) Tmax, Tmin, and Tmax − Tmin, were served as input features for SVM models. Three equations including linear, polynomial, and radial basis function were used as kernel functions. The performances were evaluated using root mean square error (RMSE), relative root mean square error (RRMSE), Nash-Sutcliffe (NSE), and determination coefficient (R2). The developed SVM models were also compared with several empirical temperature-based models. Comparison analyses showed that the newly developed SVM model using Tmax and Tmin with polynomial kernel function performed better than other SVM models and empirical methods with highest NSE of 0.999, R2 of 0.969, lowest RMSE of 0.833 MJ m−2 and RRMSE of 9.00%. The results showed that the SVM methodology may be a promising alternative to the traditional approaches for predicting solar radiation where the records of air temperatures are available.
-
estimation of monthly solar radiation from measured temperatures using support vector machines a case study
Renewable Energy, 2011Co-Authors: Jilong Chen, Hong-bin Liu, Deti XieAbstract:Abstract Solar radiation is the principal and fundamental energy for many physical, chemical and biological processes. However, it is measured at a very limited number of meteorological stations in the world. This paper presented the methods of monthly mean daily solar radiation estimation using support vector machines (SVMs), which is a relatively new machine learning algorithm based on the statistical learning theory. The main objective of this paper was to examine the feasibility of SVMs in estimating monthly solar radiation using air temperatures. Measured long-term monthly air temperatures including maximum and minimum temperatures (Tmax and Tmin, respectively) were gathered and analyzed at Chongqing meteorological station, China. Seven combinations of air temperatures, namely, (1) Tmax, (2) Tmin, (3) Tmax − Tmin, (4) Tmax and Tmin, (5) Tmax and Tmax − Tmin, (6) Tmin and Tmax − Tmin, and (7) Tmax, Tmin, and Tmax − Tmin, were served as input features for SVM models. Three equations including linear, polynomial, and radial basis function were used as kernel functions. The performances were evaluated using root mean square error (RMSE), relative root mean square error (RRMSE), Nash-Sutcliffe (NSE), and determination coefficient (R2). The developed SVM models were also compared with several empirical temperature-based models. Comparison analyses showed that the newly developed SVM model using Tmax and Tmin with polynomial kernel function performed better than other SVM models and empirical methods with highest NSE of 0.999, R2 of 0.969, lowest RMSE of 0.833 MJ m−2 and RRMSE of 9.00%. The results showed that the SVM methodology may be a promising alternative to the traditional approaches for predicting solar radiation where the records of air temperatures are available.
Hong-bin Liu - One of the best experts on this subject based on the ideXlab platform.
-
Estimation of monthly solar radiation from measured temperatures using support vector machines – A case study
Renewable Energy, 2011Co-Authors: Jilong Chen, Hong-bin Liu, Deti XieAbstract:Abstract Solar radiation is the principal and fundamental energy for many physical, chemical and biological processes. However, it is measured at a very limited number of meteorological stations in the world. This paper presented the methods of monthly mean daily solar radiation estimation using support vector machines (SVMs), which is a relatively new machine learning algorithm based on the statistical learning theory. The main objective of this paper was to examine the feasibility of SVMs in estimating monthly solar radiation using air temperatures. Measured long-term monthly air temperatures including maximum and minimum temperatures (Tmax and Tmin, respectively) were gathered and analyzed at Chongqing meteorological station, China. Seven combinations of air temperatures, namely, (1) Tmax, (2) Tmin, (3) Tmax − Tmin, (4) Tmax and Tmin, (5) Tmax and Tmax − Tmin, (6) Tmin and Tmax − Tmin, and (7) Tmax, Tmin, and Tmax − Tmin, were served as input features for SVM models. Three equations including linear, polynomial, and radial basis function were used as kernel functions. The performances were evaluated using root mean square error (RMSE), relative root mean square error (RRMSE), Nash-Sutcliffe (NSE), and determination coefficient (R2). The developed SVM models were also compared with several empirical temperature-based models. Comparison analyses showed that the newly developed SVM model using Tmax and Tmin with polynomial kernel function performed better than other SVM models and empirical methods with highest NSE of 0.999, R2 of 0.969, lowest RMSE of 0.833 MJ m−2 and RRMSE of 9.00%. The results showed that the SVM methodology may be a promising alternative to the traditional approaches for predicting solar radiation where the records of air temperatures are available.
-
estimation of monthly solar radiation from measured temperatures using support vector machines a case study
Renewable Energy, 2011Co-Authors: Jilong Chen, Hong-bin Liu, Deti XieAbstract:Abstract Solar radiation is the principal and fundamental energy for many physical, chemical and biological processes. However, it is measured at a very limited number of meteorological stations in the world. This paper presented the methods of monthly mean daily solar radiation estimation using support vector machines (SVMs), which is a relatively new machine learning algorithm based on the statistical learning theory. The main objective of this paper was to examine the feasibility of SVMs in estimating monthly solar radiation using air temperatures. Measured long-term monthly air temperatures including maximum and minimum temperatures (Tmax and Tmin, respectively) were gathered and analyzed at Chongqing meteorological station, China. Seven combinations of air temperatures, namely, (1) Tmax, (2) Tmin, (3) Tmax − Tmin, (4) Tmax and Tmin, (5) Tmax and Tmax − Tmin, (6) Tmin and Tmax − Tmin, and (7) Tmax, Tmin, and Tmax − Tmin, were served as input features for SVM models. Three equations including linear, polynomial, and radial basis function were used as kernel functions. The performances were evaluated using root mean square error (RMSE), relative root mean square error (RRMSE), Nash-Sutcliffe (NSE), and determination coefficient (R2). The developed SVM models were also compared with several empirical temperature-based models. Comparison analyses showed that the newly developed SVM model using Tmax and Tmin with polynomial kernel function performed better than other SVM models and empirical methods with highest NSE of 0.999, R2 of 0.969, lowest RMSE of 0.833 MJ m−2 and RRMSE of 9.00%. The results showed that the SVM methodology may be a promising alternative to the traditional approaches for predicting solar radiation where the records of air temperatures are available.
Vijay P Singh - One of the best experts on this subject based on the ideXlab platform.
-
trends in temperature diurnal temperature range and sunshine duration in northeast india
International Journal of Climatology, 2011Co-Authors: Deepak Jhajharia, Vijay P SinghAbstract:Trends in maximum (Tmax), minimum (Tmin) and mean (Tmean) temperatures; diurnal temperature range (DTR = Tmax − Tmin); and sunshine duration at eight sites in Northeast (NE) India were investigated. Three sites observed decreasing trends in DTR corresponding to annual, seasonal (pre-monsoon and monsoon) and monthly (September) time scales. On the other hand, DTR increases were also observed at other three sites in monsoon and post-monsoon seasons as well as in the months of June, October and December. The sites showing DTR decreases (increases) witnessed either increasing trends in Tmin (Tmax) or decreasing trends in Tmax (Tmin), with Tmax (Tmin) showing either no trend or increasing at a smaller rate than Tmin (Tmax). Temperature remained practically trendless in winter and pre-monsoon seasons over NE India. However, temperature increases were observed in monsoon and post-monsoon seasons. Decreasing trends in sunshine duration were observed mainly on annual, seasonal (winter and pre-monsoon) and monthly (January, February and March) time scales. Concomitant decreases in sunshine duration may be one of the potential causes of the observed DTR decreases over NE India. Copyright © 2010 Royal Meteorological Society
Michael Begert - One of the best experts on this subject based on the ideXlab platform.
-
Effects of large-scale atmospheric flow and sunshine duration on the evolution of minimum and maximum temperature in Switzerland
Theoretical and Applied Climatology, 2019Co-Authors: Simon C. Scherrer, Michael BegertAbstract:The evolution of mean annual minimum (Tmin) and maximum temperature (TMAX) on the Swiss Plateau shows distinct differences over the last 150 years. Tmin increased relatively steadily by about 3 °C. TMAX increased by only 1.5 °C with substantial decadal variability and hardly any increase until about 1940. However, in the most recent decades, TMAX trends are somewhat larger than Tmin trends. While most aspects of the Tmin evolution can be well explained by the global forcing and the modifying effects of the large-scale atmospheric flow alone, local sunshine duration (SD) information is crucial to explain major features of the TMAX series and the differences between Tmin and TMAX since about 1950. SD shows no clear trend until 1950, a decline from 1950 to 1980 and an increase since 1980 resembling the global dimming and brightening signal. TMAX is strongly influenced by SD and the TMAX evolution can be well reconstructed with local Tmin and SD. Strong TMAX declines are found from 1950 to the 1970s. Tmin shows no trend in this period. Between 1980 and about 2005, both Tmin and TMAX show strong increases caused by the greenhouse gas forcing, decreasing aerosols and probably also decreasing cloud cover. Since about 2005, the increases are weaker. The brightening has weakened and the warming effect of the continuously growing greenhouse gas forcing has additionally been reduced by cooling effects caused by large-scale atmospheric flow anomalies. The reasons for the considerable differences in the Tmin and TMAX evolution prior to 1950 remain unknown and further investigations are needed to shed more light on this disparity.
