The developers of StatWeather have been researching methods for long-range weather prediction since 1991. The following papers were used as the basis of the construction of the StatWeather long-range model which incorporates a proprietary pattern recognition, Bayesian networks, and machine learning algorithm. This model has evolved through ongoing tests since 2006 and is believed to be the most accurate weather forecasting paradigm available in the world today.

  • Di Narzo AF, Cocchi D. A Bayesian hierarchical approach to ensemble weather forecasting. Journal of the Royal Statistical Society: Series C. 2010; 59(3): 405-422.
  • Jianping H, Yihong Y, Shaowu W, Jifen C. An analogue-dynamical long-range numerical weather prediction system incorporating historical evolution. Quarterly Journal of the Royal Meteorological Society. 2006; 119(511):547-565
  • Mailier PJ. Can We Trust Long-Range Weather Forecasts? Management of Weather and Climate Risk in the Energy Industry. Springer; 2009. p 3-12.
  • Palmer TN. Towards the Probabilistic Earth-System Simulator: A Vision for the Future of Climate and Weather Prediction. Royal Meteorological Society Presidential Address; 2011.
  • Van Den Dool HM. A Bias in Skill in Forecasts Based on Analogues and Antilogues. American Meteorological Society. 1987; 26:1278-1281.
  • West M, Harrison J. Bayesian Forecasting and Dynamic Models, Second Edition. Springer; 1997.