APPLICATION OF SELF-ORGANIZING MAP (SOM) ANALYSIS FOR ESTIMATING BICYCLE SHARING: A NEW PERSPECTIVE

Meteorology may be key to forecasting whether people will use it or not (depending on city studied), but so date, the predictions made have generated some controversy because they been analyzed using non-linear analysis. The objective of this study is analyse relationship between time spent València bike sharing service (SBC) as a means active transport and weather. A self-organising map analysis (SOM) was performed generate profiles (clusters) days SBC meteorological factors non-parametric compare different generated. results showed 8 days, which obtained multiple significant differences. These show that, although there are variables with greater weight than others for estimating SBC, their always linear combination them needed rigor in predictions. In has observed order predict high should warm if humidity low moderate, temperature limited high, virtually no precipitation average wind speed. On other hand, estimate use, characterized by relative humidity, these precipitation, temperatures would taken into account. conclusion, analyses such SOM proves an effective tool relation meteorology. Keywords: Active transport, bike-sharing, SOM, meteorology, non-lineal analyses.