Find in Library

Short-term quantitative precipitation forecast is a challenging topic in meteorology, as the number of severe meteorological phenomena is increasing in most regions of the world. Weather radar data is of utmost importance to meteorologists for issuing short-term weather forecast and warnings of severe weather phenomena. We are proposing <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><mi>u</mi><mi>t</mi><mi>o</mi><mi>N</mi><mi>o</mi><mi>w</mi><mi>P</mi></mrow></semantics></math></inline-formula>, a binary classification model intended for precipitation nowcasting based on weather radar reflectivity prediction. Specifically, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><mi>u</mi><mi>t</mi><mi>o</mi><mi>N</mi><mi>o</mi><mi>w</mi><mi>P</mi></mrow></semantics></math></inline-formula> uses two convolutional autoencoders, being trained on radar data collected on both stratiform and convective weather conditions for learning to predict whether the radar reflectivity values will be above or below a certain threshold. <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><mi>u</mi><mi>t</mi><mi>o</mi><mi>N</mi><mi>o</mi><mi>w</mi><mi>P</mi></mrow></semantics></math></inline-formula> is intended to be a proof of concept that autoencoders are useful in distinguishing between convective and stratiform precipitation. Real radar data provided by the Romanian National Meteorological Administration and the Norwegian Meteorological Institute is used for evaluating the effectiveness of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><mi>u</mi><mi>t</mi><mi>o</mi><mi>N</mi><mi>o</mi><mi>w</mi><mi>P</mi></mrow></semantics></math></inline-formula>. Results showed that <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><mi>u</mi><mi>t</mi><mi>o</mi><mi>N</mi><mi>o</mi><mi>w</mi><mi>P</mi></mrow></semantics></math></inline-formula> surpassed other binary classifiers used in the supervised learning literature in terms of probability of detection and negative predictive value, highlighting its predictive performance.