A novel approach for detecting error measurements in a network of automatic weather stations
Abstract
In the present work, a novel methodology for error detection in automatic weather stations has been implemented. Time series acquired from two highly correlated stations with a station under analysis are utilised to obtain a 24-h air temperature forecast that allows to know if a station register erroneous measurements. Four models to obtain a reliable forecast have been analysed, auto-regressive integrated moving average, Long Short-Term Memory (LSTM), LSTM stacked and a convolutional LSTM model with uncertainty error reduction. The analysis carried out exhibits a significant success with the methodology for three stations reaching error values between 0.98∘C and 1.50∘C and correlation coefficients between 0.72 and 0.81.