Modeling soil temperature based on Gaussian process regression in a semi-arid-climate, case study Ghardaia, Algeria
Tóm tắt
The renewable energy is the best energy potential to exploit, because they are economic, not pollutant and permanent. As a kind of renewable energy, geothermic which becomes more and more widely used in this field. In a geological setting regional on the effectiveness of the process solar thermal, offering a greater supply of geothermal energy, the study of Ghardaia’s case are based on data of soil temperature and especially using local meteorological data, Accurate estimates of mean daily soil temperature (MDST) are needed. In this study, we will use the capability of Gaussian process regression (GPR) for modeling MDST using 3 years of measurement (2005–2008), in a semi-arid climate. It was found that GPR-model based on mean air temperature as input, give accurate results in term of mean absolute bias error, root mean square error, relative square error, and correlation coefficient. The obtained values of these indicators are 0.0021, 0.5036, 0.0029 and 100 %, respectively, which shows that GPR is highly qualified for MDST estimation in semi-arid climate.
Tài liệu tham khảo
Bastola H, Peterson EW (2016) Heat tracing to examine seasonal groundwater flow beneath a low-gradient stream in rural central Illinois, USA. Hydrogeol J 24(1):181–194
Chan et al (2013) Nonlinear system identification with selective recursive Gaussian process models. Ind Eng Chem Res 52(51):18276–18286
Dong B et al (2005) Applying support vector machines to predict building energy consumption in tropical region. Energy Build 37(5):545–553
Guermoui et al (2013) Heart sounds analysis using wavelets responses and support vector machines. In: 2013 8th international workshop on systems, signal processing and their applications (WoSSPA). IEEE, pp 233–238
Liu Y, Gao Z (2015) Industrial melt index prediction with the ensemble anti-outlier just-in-time Gaussian process regression modeling method. J Appl Polym Sci 132(22). doi:10.1002/app.41958
Liu Y, Chen T, Chen J (2015) Auto-switch Gaussian process regression-based probabilistic soft sensors for industrial multigrade processes with transitions. Ind Eng Chem Res 54(18):5037–5047
Ni et al (2014) Non-linear calibration models for near infrared spectroscopy. Anal Chim Acta 813:1–14
Şenkal O, Kuleli T (2009) Estimation of solar radiation over Turkey using artificial neural network and satellite data. Appl Energy 86(7):1222–1228
Shamshirband et al (2015) Daily global solar radiation prediction from air temperatures using kernel extreme learning machine: a case study for Iran. J Atmos Solar Terr Phys 134:109–117
Sozen A et al (2004) Estimation of solar potential in Turkey by artificial neural networks using meteorological and geographical data. Energy Convers Manag 45(18):3033–3052
Suykens JAK, Vandewalle J (1999) Least squares support vector machine classifiers. Neural Process Lett 9(3):293–300
Vapnik VN, Vapnik V (1998) Statistical learning theory, vol 1. Wiley, New York
Wang J, Bras RL (1999) Ground heat flux estimated from surface soil temperature. J Hydrol 216(3):214–226
Wang et al (2011) Raymond Bagging for robust non-linear multivariate calibration of spectroscopy. Chemometr Intell Lab Syst 105(1):1–6
Williams CK, Rasmussen CE (2006) Gaussian processes for machine learning, vol 2. MIT Press, p 4
Yacef et al (2014) New combined models for estimating daily global solar radiation from measured air temperature in semi-arid climates: application in Ghardaia, Algeria. Energy Convers Manag 79:606–615
Yuan et al (2008) Reliable multi-objective optimization of high-speed WEDM process based on Gaussian process regression. Int J Mach Tools Manuf 48(1):47–60