Air Temperature Forecasting Using Machine Learning Techniques: A Review

Efforts to understand the influence of historical climate change, at global and regional levels, have been increasing over the past decade. In particular, the estimates of air temperatures have been considered as a key factor in climate impact studies on agricultural, ecological, environmental, and industrial sectors. Accurate temperature prediction helps to safeguard life and property, playing an important role in planning activities for the government, industry, and the public. The primary aim of this study is to review the different machine learning strategies for temperature forecasting, available in the literature, presenting their advantages and disadvantages and identifying research gaps. This survey shows that Machine Learning techniques can help to accurately predict temperatures based on a set of input features, which can include the previous values of temperature, relative humidity, solar radiation, rain and wind speed measurements, among others. The review reveals that Deep Learning strategies report smaller errors (Mean Square Error = 0.0017 °K) compared with traditional Artificial Neural Networks architectures, for 1 step-ahead at regional scale. At the global scale, Support Vector Machines are preferred based on their good compromise between simplicity and accuracy. In addition, the accuracy of the methods described in this work is found to be dependent on inputs combination, architecture, and learning algorithms. Finally, further research areas in temperature forecasting are outlined.

[1]  David M. Livingstone,et al.  Forecasting Groundwater Temperature with Linear Regression Models Using Historical Data , 2015, Ground water.

[2]  A. A. Argiriou,et al.  Use of neural networks for tropospheric ozone time series approximation and forecasting ? a review , 2007 .

[3]  Zohrab Samani,et al.  Estimating solar radiation and evapotranspiration using minimum climatological data , 2000 .

[4]  O. Kisi,et al.  Prediction of long‐term monthly air temperature using geographical inputs , 2014 .

[5]  Nikolaos Kourentzes,et al.  Validation and forecasting accuracy in models of climate change , 2011 .

[6]  Abdullatif Ben-Nakhi,et al.  Cooling load prediction for buildings using general regression neural networks , 2004 .

[7]  T. Wigley,et al.  Global temperature variations between 1861 and 1984 , 1986, Nature.

[8]  Zongben Xu,et al.  Three improved neural network models for air quality forecasting , 2003 .

[9]  Pradeep Hewage,et al.  Deep learning-based effective fine-grained weather forecasting model , 2020, Pattern Analysis and Applications.

[10]  Gerrit Hoogenboom,et al.  Support vector regression with reduced training sets for air temperature prediction: a comparison with artificial neural networks , 2011, Neural Computing and Applications.

[11]  J. L. Balenzategui,et al.  Estimation of photovoltaic module yearly temperature and performance based on Nominal Operation Cell Temperature calculations , 2004 .

[12]  Mahboubeh Afzali,et al.  The potential of artificial neural network technique in daily and monthly ambient air temperature prediction , 2012 .

[13]  Demetris Koutsoyiannis,et al.  Univariate Time Series Forecasting of Temperature and Precipitation with a Focus on Machine Learning Algorithms: a Multiple-Case Study from Greece , 2018, Water Resources Management.

[14]  Mehmet Bilgili,et al.  Prediction of Long-term Monthly Temperature and Rainfall in Turkey , 2009 .

[15]  António E. Ruano,et al.  Prediction of building's temperature using neural networks models , 2006 .

[16]  Emmanuel Sirimal Silva,et al.  Predicting global temperature anomaly: A definitive investigation using an ensemble of twelve competing forecasting models , 2018, Physica A: Statistical Mechanics and its Applications.

[17]  Michele Meroni,et al.  Revisiting the concept of a symmetric index of agreement for continuous datasets , 2016, Scientific Reports.

[18]  Paresh Chandra Deka,et al.  Effects of Data Pre-processing on the Prediction Accuracy of Artificial Neural Network Model in Hydrological Time Series , 2016 .

[19]  Yun-fei Qiu,et al.  Temperature Forecast Based on SVM Optimized by PSO Algorithm , 2010, 2010 International Conference on Intelligent Computing and Cognitive Informatics.

[20]  Á. Pardo,et al.  Temperature and seasonality influences on Spanish electricity load , 2002 .

[21]  Sancho Salcedo-Sanz,et al.  Prediction of daily maximum temperature using a support vector regression algorithm , 2011 .

[22]  Rob J Hyndman,et al.  Another look at measures of forecast accuracy , 2006 .

[23]  Ajith Abraham,et al.  An ensemble of neural networks for weather forecasting , 2004, Neural Computing & Applications.

[24]  Babak Nadjar Araabi,et al.  Prediction of Climate Change Induced Temperature Rise in Regional Scale Using Neural Network , 2012 .

[25]  Giovanni Bovio,et al.  Meteorological fire danger indices and remote sensing , 1999 .

[26]  Y. Radhika,et al.  Atmospheric Temperature Prediction using Support Vector Machines , 2009 .

[27]  Terry C. K. Lee,et al.  Evidence of Decadal Climate Prediction Skill Resulting from Changes in Anthropogenic Forcing , 2006 .

[28]  Adel Mellit,et al.  Artificial Intelligence technique for modelling and forecasting of solar radiation data: a review , 2008, Int. J. Artif. Intell. Soft Comput..

[29]  Aris Tsangrassoulis,et al.  On the energy consumption in residential buildings , 2002 .

[30]  Antonello Pasini,et al.  A neural network model for visibility nowcasting from surface observations: Results and sensitivity to physical input variables , 2001 .

[31]  R. E. Abdel-Aal,et al.  Hourly temperature forecasting using abductive networks , 2004, Eng. Appl. Artif. Intell..

[32]  Li Li,et al.  Prediction of Temperature Time Series Based on Wavelet Transform and Support Vector Machine , 2012, J. Comput..

[33]  H. K. Cigizoglu,et al.  Forecast of daily mean, maximum and minimum temperature time series by three artificial neural network methods , 2008 .

[34]  Matthew Newman,et al.  An Empirical Benchmark for Decadal Forecasts of Global Surface Temperature Anomalies , 2012 .

[35]  R. Tol.  Estimates of the Damage Costs of Climate Change. Part 1: Benchmark Estimates , 2002 .

[36]  Shafiqur Rehman,et al.  Application of neural networks for the prediction of hourly mean surface temperatures in Saudi Arabia , 2002 .

[37]  B. Saavedra-Moreno,et al.  Monthly prediction of air temperature in Australia and New Zealand with machine learning algorithms , 2016, Theoretical and Applied Climatology.

[38]  A. Pasini,et al.  Neural network modelling for the analysis of forcings/temperatures relationships at different scales in the climate system , 2006 .

[39]  Ayushi Rastogi,et al.  Pattern analysis approach for prediction using Wavelet Neural Networks , 2011, 2011 Seventh International Conference on Natural Computation.

[40]  Ajith Abraham,et al.  Weather analysis using ensemble of connectionist learning paradigms , 2007, Appl. Soft Comput..

[41]  Adamu I. Abubakar,et al.  Utilising key climate element variability for the prediction of future climate change using a support vector machine model , 2016 .

[42]  F. Joos,et al.  Probabilistic climate change projections using neural networks , 2003 .

[43]  Soteris A. Kalogirou,et al.  Artificial neural networks in renewable energy systems applications: a review , 2001 .

[44]  Nikhil R. Pal,et al.  SOFM-MLP: a hybrid neural network for atmospheric temperature prediction , 2003, IEEE Trans. Geosci. Remote. Sens..

[45]  A. Massi Pavan,et al.  Least squares support vector machine for short-term prediction of meteorological time series , 2012, Theoretical and Applied Climatology.

[46]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[47]  R. W. McClendon,et al.  Artificial neural networks for automated year-round temperature prediction , 2009 .

[48]  Tobias Günther,et al.  Visualization of Neural Network Predictions for Weather Forecasting , 2019, Comput. Graph. Forum.

[49]  F. Giorgi,et al.  Climate change due to greenhouse effects in China as simulated by a regional climate model , 2001 .

[50]  Sushil J. Louis,et al.  Forecasting the weather of Nevada: A deep learning approach , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[51]  Stephen Cusack,et al.  Improved Surface Temperature Prediction for the Coming Decade from a Global Climate Model , 2007, Science.

[52]  S. S. De,et al.  Artificial Neural Network Based Prediction of Maximum and Minimum Temperature in the Summer Monsoon Months over India , 2009 .

[53]  Fred L. Collopy,et al.  Error Measures for Generalizing About Forecasting Methods: Empirical Comparisons , 1992 .

[54]  Mark New,et al.  Surface air temperature and its changes over the past 150 years , 1999 .

[55]  Cécile Penland,et al.  Prediction of Nino 3 sea surface temperatures using linear inverse modeling , 1993 .

[56]  İlker Bekir Topçu,et al.  Prediction of compressive strength of concrete containing fly ash using artificial neural networks and fuzzy logic , 2008 .

[57]  Imre M. Jánosi,et al.  Nonlinear correlations of daily temperature records over land , 2006 .

[58]  Xuebin Zhang,et al.  Characteristics of Daily and Extreme Temperatures over Canada , 2001 .

[59]  P. Stott,et al.  Origins and estimates of uncertainty in predictions of twenty-first century temperature rise , 2002, Nature.

[60]  Jesús M. Zamarreño,et al.  A Short-Term Temperature Forecaster Based on a Novel Radial Basis Functions Neural Network , 2001, Int. J. Neural Syst..

[61]  Munindar P. Singh,et al.  Weather Forecasting Model using Artificial Neural Network , 2012 .

[62]  J. Garibaldi,et al.  A new accuracy measure based on bounded relative error for time series forecasting , 2017, PloS one.

[63]  Song Li,et al.  An ensemble approach for short-term load forecasting by extreme learning machine , 2016 .

[64]  Chia-Nan Ko,et al.  Short-term load forecasting using SVR (support vector regression)-based radial basis function neural network with dual extended Kalman filter , 2013 .

[65]  Sancho Salcedo-Sanz,et al.  Accurate local very short-term temperature prediction based on synoptic situation Support Vector Regression banks , 2012 .

[66]  Cécile Penland,et al.  Prediction of Tropical Atlantic Sea Surface Temperatures Using Linear Inverse Modeling , 1998 .

[67]  Mustafa Gölcü,et al.  Daily means ambient temperature prediction using artificial neural network method: A case study of Turkey , 2009 .

[68]  Holger R. Maier,et al.  Neural networks for the prediction and forecasting of water resource variables: a review of modelling issues and applications , 2000, Environ. Model. Softw..

[69]  Johan A. K. Suykens,et al.  Black-box modeling for temperature prediction in weather forecasting , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[70]  Swati Agarwal,et al.  Temperature Prediction using Wavelet Neural Network , 2012 .

[71]  E. Sarachik,et al.  Empirically Derived Markov Models and Prediction of Tropical Pacific Sea Surface Temperature Anomalies , 2000 .