Science Daily June 26, 2019
Current satellite-based approaches to predict thunderstorms are usually based on the analysis of the observed brightness temperatures in different spectral channels and emit a warning if a critical threshold is reached. Researchers in Germany have developed a method using the error of two-dimensional optical flow algorithms applied to images of meteorological satellites as a feature for machine learning models. They trained different tree classifier models as well as a neural network to predict lightning. The results show a high accuracy of 96% for predictions over the next 15 minutes which slightly decreases with increasing forecast period but remains above 83% for forecasts of up to five hours. The high false positive rate of nearly 6% however needs further investigation to allow for an operational use of our approach…read more. TECHNICAL ARTICLE