STEPS: A Tool to Forecast Meteorological Variables on a Short Time Scale

R. Shrivastava

¹ Radiation Safety Systems Division, Bhabha Atomic Research Centre, Mumbai - 400 085, India

^a[email protected], ^b[email protected], ^c[email protected]

*Corresponding Author: R. Shrivastava, Email: [email protected]

Accurate prediction of meteorological variables like air temperature is important in various sectors like agriculture, forecast of energy demand, climate change, transportation etc. Air temperature forecasts are also crucial in determination of heat and cold waves. Across the globe as demand for solar energy is increasing, there is a need for precise forecasts of solar radiation too. In recent times, machine learning methods are becoming popular in weather forecasting. This study describes the development of Short Term Prediction System (STEPS), a model based on Auto Regressive Integrated Moving Average (ARIMA) technique suitable for prediction of hourly values of meteorological variables like air temperature, relative humidity, solar and net radiation with a lead time of three days. The model has been validated at a single point using two years of meteorological measurements. At a lead time of one day, mean absolute error in air temperature forecast is less than 2 °C and for relative humidity is less than 11 % throughout the year and. For solar and net radiation at the same lead time, respective mean absolute errors are less than 30 W m-2 during non-monsoon season and approximately 75 W m-2 during monsoon season. Hence, model results indicate that the forecasting proficiency is comparable to traditional Numerical Weather Prediction (NWP) model at a fraction of computational cost and time. 

Short term, meteorological variables, ARIMA, machine learning, time series forecasting

R. Shrivastava, Indumathi S. Iyer and Anmol Batra (2025). STEPS: A Tool to Forecast Meteorological Variables on a Short Time Scale. Journal of Artificial Intelligence and Systems, 7, 76–88. https://doi.org/10.33969/AIS.2025070105.

[1] P. Chen, A. Niu, D. Liu, W. Jiang and B. Ma, "Time Series Forecasting of Temperatures using SARIMA: An Example from Nanjing," in IOP Conf. Series: Materials Science and Engineering, 2018. 

[2] M. Murat, I. Malinowska, M. Gos and J. Krzyszczak, "Forecasting daily meteorological time series using ARIMA and regression models," International Agrophysics, vol. 32, pp. 253-264, 2018. 

[3] H. Astsatryan, H. Grigoryan, A. Poghosyan, R. Abrahamyan, S. Asmaryan, V. Muradyan, G. Tepanosyan, Y. Guigoz and G. Giuliani, "Air temperature forecasting using artificial neural network for Ararat valley," Earth Science Informatics, vol. 14, p. 711–722, 2021. 

[4] K. Abhishek, M. Singh, S. Ghosh and A. Anand, "Weather forecasting model using Artificial Neural Network," Procedia Technology, vol. 4, pp. 311-318, 2012. 

[5] S. Baboo and I. Shereef, "An Efficient Weather Forecasting System using Artificial Neural Network," International Journal of Environmental Science and Development, vol. 1, no. 4, pp. 321-326, 2010. 

[6] L. Fara, A. Diaconu, D. Craciunescu and S. Fara, "Forecasting of Energy Production for Photovoltaic Systems Based on ARIMA and ANN Advanced Models," International Journal of Photoenergy, 2021. 

[7] H. Ettayyebi and K. Himdi, "Artificial Neural Network for Forecasting One Day Ahead of Global Solar Irradiance," in The Second International Conference on Smart Applications and Data Analysis for Smart Cities, 2018. 

[8] M. Alsharif, M. K. Younes and J. Kim, "Time Series ARIMA Model for Prediction of Daily and Monthly Average Global Solar Radiation: The Case Study of Seoul, South Korea," Symmetry, vol. 11, pp. 240-256, 2019. 

[9] E. Chodakowska, J. Nazarko, L. Nazarko, H. Rabayah, R. Abendeh and R. Alawneh, "ARIMA Models in Solar Radiation Forecasting in Different Geographic Locations," Energies, vol. 16, pp. 5029-5042, 2023. 

[10] N. Junhuathon and K. Chayakulkheeree, "Comparative Study of Short-Term Photovoltaic Power Generation Forecasting Methods.," in Proceedings of the 2021 International Conference on Power, Energy and Innovations (ICPEI), Nakhon Ratchasima, 2021. 

[11] Y. Jiang, L. Zheng and X. Ding, "Ultra-Short-Term Prediction of Photovoltaic Output Based on an LSTM-ARMA Combined Model Driven by EEMD," J. Renew. Sustain. Energy 2021, vol. 13, pp. 046103-046116, 2021. 

[12] S. Mughal, Y. Sood and R. Jarial, "Design and Optimization of Photovoltaic System with a Week Ahead Power Forecast Using Autoregressive Artificial Neural Networks," Mater. Today Proc., vol. 52, p. 834–841, 2022. 

[13] J. Rogier and N. Mohamudally, "Forecasting Photovoltaic Power Generation via an IoT Network Using Nonlinear Autoregressive Neural Network," Procedia Comput. Sci., vol. 151, p. 643–650, 2019. 

[14] S. Boubaker, S. Kamel, L. Kolsi and O. Kahouli, "Forecasting of One-Day-Ahead Global Horizontal Irradiation Using Block-Oriented Models Combined with a Swarm Intelligence Approach," Nat. Resour. Res., vol. 30, pp. 1-26, 2021. 

[15] R. Basmadjian, A. Shaafieyoun and S. Julka, "Day-Ahead Forecasting of the Percentage of Renewables Based on Time-Series Statistical Methods," Energies, vol. 14, p. 7443, 2021. 

[16] G. Reikard, "Predicting Solar Radiation at High Resolutions: A Comparison of Time Series Forecasts," Sol. Energy, vol. 83, pp. 342-249, 2009. 

[17] M. Alomar, F. Khaleel, M. Aljumaily, A. Masood, S. Razali, M. AlSaadi, N. Ansari and M. Hameed, "Data-driven models for atmospheric air temperature forecasting at a continental climate region," PLOS One, vol. 17, no. 11, pp. 1-31, 2022.

[18]  G. Box, G. Jenkins, G. Reinsel and G. Ljung, Time Series Analysis Forecasting and Control (Fifth Edition), New Jersey: John Wiley and Sons, 2016. 

[19]  L. Carbonell, G. Mastrapa, Y. Rodriguez, L. Escudero, M. Gacita, A. Morlot, I. Montejo, E. Ruiz and S. Rivas, "Assessment of the Weather Research and Forecasting model implementation in Cuba addressed to diagnostic air quality," Atmos Poll Res, vol. 4, pp. 64-4, 2013. 

[20] R. Borge, V. Alexandrov, J. Vas, J. Lumbreras and E. Rodri´guez, "A comprehensive sensitivity analysis of the WRF model for air quality applications over the Iberian Peninsula," Atmospheric Environment, vol. 42, pp. 8560-8574, 2008. 

[21] G. Chicco, V. Cocina, P. Leo, F. Spertino and A. Pavan, "Error Assessment of Solar Irradiance Forecasts and AC Power from Energy Conversion Model in Grid-Connected Photovoltaic Systems," Energies, vol. 9, no. 8, pp. 1-27, 2016. 

[22] O. Ojo, B. Adeyemi and D. Oluleye, "Artificial neural network models for prediction of net radiation over a tropical region," Neural Computing and Applications, vol. 33, no. 12, pp. 6865-6877, 2020.