Abstract
Air temperature forecasting has been a vital climatic factor required for different applications in many areas such as energy, industry, agriculture, health, environment, and meteorology. This study compares the performances of two static neural networks (NNs) used for the prediction of hourly ambient air temperatures in a coastal area of Turkey. Thirteen parameters from Land Surface Diagnostics and Surface Flux Diagnostics Collections from the MERRA-2 reanalysis dataset including pressure, surface specific humidity, wind speed, wind direction, air density at surface, evaporation, planetary boundary layer height, total precipitable water vapor, total precipitation, total cloud area fraction, total column ozone, greenness fraction, and leaf area index were used as input parameters for the models. Feed-Forward Neural Network (FFNN) and Cascade Forward Neural Network (CFNN) models were applied to forecast hourly ambient air temperatures at 2 m height from the surface. The results indicated that the most accurate and reliable predictions were obtained by the CFNN model with 30 neurons, while the lowest prediction performance was obtained by the FFNN model with 5 neurons. The root mean squares error (RMSE), mean absolute error (MAE) and coefficient of determination (R2) values for training (and testing) of the CFNN model with 30 neurons were 0.358 (0.376), 0.273 (0.283), and 0.997 (0.992), respectively, whereas the same parameters were 0.430 (0.447), 0.334 (0.343), and 0.996 (0.989) for the FFNN model with 5 neurons. The CFNN model had a lower RMSE and MAE, and a higher R2 than the FFNN model. These results showed that increasing the number of neurons of hidden layers from 5 to 30 provided better model performance.
Similar content being viewed by others
Data availability
The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request.
References
Abujazar MS, Fatihah S, Ibrahim IA, Kabeel AE, Sharil S (2018) Productivity modelling of a developed inclined stepped solar still system based on actual performance and using a cascaded forward neural network model. J Clean Prod 170(2018):147–159
Acı M, Avcı M (2016) Artificial neural network approach for atomic coordinate prediction of carbon nanotubes. Appl Phys A 122(631):1–14
AERONET (AErosol RObotic NETwork) (2020) https://aeronet.gsfc.nasa.gov/cgi-bin/type_one_station_ opera_v2_new?site=IMS-METU-ERDEMLI&nachal=2&level=1. Accessed: May 2020
Alkhasawneh MS, Tay LT (2018) A hybrid intelligent system integrating the cascade forward neural network with elman neural network. Arab J Sci Eng 43:6737–6749
Attoue N, Shahrour I, Younes R (2018) Smart building: use of the artificial neural network approach for indoor temperature forecasting. Energies 11(395):1–12
Badde DS, Gupta AK, Patki VK (2012) Cascade and feed forward back propagation artificial neural network models for prediction of compressive strength of ready mix concrete. IOSR J Mech Civil Eng 3(26):01–06
Beik J, Asadi M, Mirrahimi M et al (2019) An image-based computational modeling approach for prediction of temperature distribution during photothermal therapy. Appl Phys B 125(213):1–14
Bell J, Case J, Lafontaine F et al (2012) Evaluating the impacts of NASA/SPoRT daily greenness vegetation fraction on land surface model and numerical weather forecasts. Preprints. In: 16th Symp. on Integrated Observing and Assimilation Systems for the Atmosphere, Oceans, and Land Surface, New Orleans, LA, Amer. Meteor. Soc. p 247
Ben-Nakhi AE, Mahmoud MA (2004) Cooling load prediction for buildings using general regression neural networks. Energy Convers Manag 45:2127–2141
Berens P (2009) CircStat: a MATLAB toolbox for circular statistics. J Stat Softw 31(10):1–21
Bertolaccini L, Solli P, Pardolesi A, Pasini A (2017) An overview of the use of artificial neural networks in lung cancer research. J Thorac Dis 9(4):924–931
Bouketta S, Bouchahm Y (2020) Numerical evaluation of urban geometry’s control of wind movements in outdoor spaces during winter period Case of Mediterranean Climate. Renewable Energy 146(2020):1062–1069
Bre F, Gimenez JM, Fachinotti VD (2018) Prediction of wind pressure coefficients on building surfaces using artificial neural networks. Energy Buildings 158:1429–1441
Camia A, Bovio G, Aguado I, Stach N (1999) Meteorological fire danger indices and remote sensing. In Remote sensing of large wildfires. Springer, Berlin/Heidelberg, Germany, pp 39–59
Chattopadhyay S, Jhajharia D, Chattopadhyay G (2011) Univariate modelling of monthly maximum temperature time series over northeast India: neural network versus Yule-Walker equation based approach. Meteorol Appl 18:70–82
Chen S-M, Hwang J-R (2000) Temperature prediction using fuzzy time series. IEEE Trans Syst Man Cybern Part B 30(2):263–275
Dang R, Li H, Liu Z et al (2016) Statistical analysis of relationship between daytime Lidar-Derived planetary boundary layer height and relevant atmospheric variables in the semiarid region in Northwest China. Adv Meteorology 2016(5375918):1–13
Dombaycı ÖA, Gölcü M (2009) Daily means ambient temperature prediction using artificial neural network method: a case study of Turkey. Renewable Energy 34(4):1158–1161
Downs TD, Mardia KV (2002) Circular regression. Biometrika 89:689–697
Elbita A, Qahwaji R, Ipson S, Sharif MS, Ghanchi F (2014) Preparation of 2D sequences of corneal images for 3D model building. Comput Methods Programs Biomed 114(2):194–205
Erdemir D, Ayata T (2017) Prediction of temperature decreasing on a green roof by using artificial neural network. Appl Therm Eng 112:1317–1325
Ganesh SS, Arulmozhivarman P, Tatavarti VSNR (2018) Prediction of PM2.5 using an ensemble of artificial neural networks and regression models. J Amb Intel Hum Comp. https://doi.org/10.1007/s12652-018-0801-8
Garcia MA, Balenzategui J (2004) Estimation of photovoltaic module yearly temperature and performance based on nominal operation cell temperature calculations. Renew Energy 29:1997–2010
Hardalaç F, Basaranoglu M, Yüksel M, Kutbay U et al (2015) The rate of mucosal healing by azathioprine therapy and prediction by artificial systems. Turk J Gastroenterol 26:315–321
Hedayat A, Davilu H, Barfrosh AA, Sepanloo K (2009) Estimation of research reactor core parameters using cascade feed forward artificial neural networks. Prog Nucl Energy 51(6–7):709–718
Jammalamdaka SR, SenGupta A (2001) Topics in circular statistics. World Scientific, New York
Karaca Y (2016) Case study on artificial neural networks and applications. Appl Math Sci 10(45):2225–2237
Kazem HA, Chaichan MT (2015) Effect of humidity on photovoltaic performance based on experimental study. Int J Appl Eng Res 10(23):43572–43577
Kloog I, Nordio F, Coull BA, Schwartz J (2014) Predicting spatiotemporal mean air temperature using MODIS satellite surface temperature measurements across the Northeastern USA. Remote Sens Environ 150(2014):132–139
Kumar GS, Rajasekhar K (2017) Performance analysis of Levenberg-Marquardt and Steepest Descent algorithms based ANN to predict compressive strength of SIFCON using manufactured sand. Eng Sci Technol Int J 20(2017):1396–1405
Lazzús JA, Vega-Jorquera P, Salfate I et al (2020) Variability and forecasting of air temperature in Elqui Valley (Chile). Earth Sci Inform 13:1411–1425
Lee S, Lee YS, Son Y (2020) Forecasting daily temperatures with different time interval data using deep neural networks. Appl Sci 10:1609
Lu E, Tu J (2021) Relative importance of surface air temperature and density to interannual variations in monthly surface atmospheric pressure. Int J Climatol 41(S1):E819–E831
Mardia KV, Jupp PE (2000) Directional statistics. John Wiley & Sons
Matuszko D, Węglarczyk S (2013) Effect of cloudiness on long-term variability in air temperature in Krakow. Int J Climatol 34:145–154
Mba L, Meukam P, Kemajou A (2016) Application of artificial neural network for predicting hourly indoor air temperature and relative humidity in modern building in humid region. Energy Buildings 121:32–42
Memon RA, Leung DYC, Liu CH (2010) Effects of building aspect ratio and wind speed on air temperatures in urban-like street canyons. Build Environ 45(1):176–188
Mirgol B, Nazari M (2018) Possible scenarios of winter wheat yield reduction of Dryland Qazvin Province, Iran, based on prediction of temperature and precipitation till the end of the century. Climate 6(78):1–14
Narad S, Chavan P (2016) Cascade forward back-propagation neural network based group authentication using (n, n) secret sharing scheme. Procedia Comp Sci 78:185–191
NASA (National Aeronautics and Space Administration) (2020) Goddard Space Flight Center. https://gmao.gsfc.nasa.gov/reanalysis/MERRA-2/, Accessed: May 2020
Nassif WG, Jasim FH, Al-Taai OT (2021) Analysis of air temperature, relative humidity and evaporation over Iraq using ECMWF reanalysis. Indian J Ecology 48(2):446–452
Ozdemir E, Tuna Tuygun G, Elbir T (2020) Application of aerosol classification methods based on AERONET version 3 product over eastern Mediterranean and Black Sea. Atmos Pollut Res 11:2226–2243
Potocnik P, Vidrih B, Kitanovski A et al (2019) Neural network, ARX, and extreme learning machine models for the short-term prediction of temperature in buildings. Build Simul 12:1077–1093
Pwasong A, Sathasivam S (2016) A new hybrid quadratic regression and cascade forward backpropagation neural network. Neurocomputing 182:197–209
Raible CC, Bischof G, Fraedrich K et al (1999) Statistical single-station short-term forecasting of temperature and probability of precipitation: area interpolation and NWP combination. Weather Forecast 14(2):203–214
Rajendra P, Murthy KVN, Subbarao A et al (2019) Use of ANN models in the prediction of meteorological data. Model Earth Syst Environ 5:1051–1058
Rajini NH, Bhavani R (2013) Computer aided detection of ischemic stroke using segmentation and texture features. Measurement 46(6):1865–1874
Roy DS (2020) Forecasting the air temperature at a weather station using deep neural networks. Procedia Comp Sci 178:38–46
Salcedo-Sanz S, Deo RC, Carro-Calvo L et al (2016) Monthly prediction of air temperature in Australia and New Zealand with machine learning algorithms. Theor Appl Climatol 125:13–25
Schneider A, Schuh A, Maetzel FK et al (2008) Weather-induced ischemia and arrhythmia in patients undergoing cardiac rehabilitation: another difference between men and women. Int J Biometeorol 52:535–547
Shin KH, Jung JW, Chang KH et al (2021) Dynamical prediction of two meteorological factors using the deep neural network and the long short-term memory. 1:22
Takeuchi Y, Endo Y, Murakami S (2008) High correlation between winter precipitation and air temperature in heavy-snowfall areas in Japan. Ann Glaciol 49:7–10
Tengeleng S, Armand N (2014) Performance of using cascade forward back propagation neural networks for estimating rain parameters with rain drop size distribution. Atmosphere 5(2):454–472
Tran TTK, Bateni SM, Ki SJ, Vosoughifar HA (2021) Review of neural networks for air temperature forecasting. Water 13(9):1294. https://doi.org/10.3390/w13091294
Tuna Tuygun G, Elbir T (2020) Long-term temporal analysis of the columnar and surface aerosol relationship with planetary boundary layer height at a southern coastal site of Turkey. Atmos Pollut Res 11:2259–2269
Ustaoglu B, Cigizoglu HK, Karaca M (2008) Forecast of daily mean, maximum and minimum temperature time series by three artificial neural network methods. Met Apps 15:431–445
Vaidya M, Matsagar S, Mandavkar M et al (2019) Intelligent traffic monitoring system using IOT. Int J Sci Res Eng Trends 5(3):756–760
Wang S, Kim S, Peiris TB (2018) An improved meta-analysis for analyzing cylindrical-type time series data with applications to forecasting problem in environmental study. J Appl Stat 45(3):474–486
Warsito B, Santoso R, Suparti YH (2018) Cascade forward neural network for time series prediction. J Phys: Conf Ser 1025(2018):1–8
Xing L, Li L, Gong J, Ren C et al (2018) Daily soil temperatures predictions for various climates in United States using data-driven model. Energy 160:430–440
Yang J, Ma J (2019) Feed-forward neural network training using sparse representation. Expert Syst Appl 116:255–264
Yuan X, Chen C, Yuan Y et al (2015) Short-term wind power prediction based on LSSVM–GSA model. Energy Convers Manage 101:393–401
Zhao Z, Qin J, He Z et al (2020) Combining forward with recurrent neural networks for hourly air quality prediction in Northwest of China. Environ Sci Pollut Res. https://doi.org/10.1007/s11356-020-08948-1
Acknowledgements
We are thankful to all of our students (Gizem Tuna Tuygun, Selin Karslioglu, and Elif Tezcan) at the Dokuz Eylul University for downloading data from MERRA-2.
Author information
Authors and Affiliations
Corresponding author
Additional information
Responsible Editor: Silvia Trini Castelli.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Gündoğdu, S., Elbir, T. Application of feed forward and cascade forward neural network models for prediction of hourly ambient air temperature based on MERRA-2 reanalysis data in a coastal area of Turkey. Meteorol Atmos Phys 133, 1481–1493 (2021). https://doi.org/10.1007/s00703-021-00821-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00703-021-00821-1