Rainy Day Prediction Model with Climate Covariates Using Artificial Neural Network MLP, Pilot Area: Central Italy

Abstract

The reconstruction of daily precipitation data is a much-debated topic of great practical use, especially when weather stations have missing data. Missing data are particularly numerous if rain gauges are poorly maintained by their owner institutions and if they are located in inaccessible areas.In this context, an attempt was made to assess the possibility of reconstructing daily rainfall data from other climatic variables other than the rainfall itself, namely atmospheric pressure, relative humidity and prevailing wind direction.The pilot area for the study was identified in Central Italy, especially on the Adriatic side, and 119 weather stations were considered.The parameters of atmospheric pressure, humidity and prevailing wind direction were reconstructed at all weather stations on a daily basis by means of various models, in order to obtain almost continuous values rain gauge by rain gauge. The results obtained using neural networks to reconstruct daily precipitation revealed a lack of correlation for the prevailing wind direction, while correlation is significant for humidity and atmospheric pressure, although they explain only 10–20% of the total precipitation variance. At the same time, it was verified by binary logistic regression that it is certainly easier to understand when it will or will not rain without determining the amount. In this case, in fact, the model achieves an accuracy of about 80 percent in identifying rainy and non-rainy days from the aforementioned climatic parameters. In addition, the modelling was also verified on all rain gauges at the same time and this showed reliability comparable to an arithmetic average of the individual models, thus showing that the neural network model fails to prepare a model that performs better from learning even in the case of many thousands of data (over 400,000). This shows that the relationships between precipitation, relative humidity and atmospheric pressure are predominantly local in nature without being able to give rise to broader generalisations.

Triple coupling random forest approach for bias correction of ensemble precipitation data derived from Earth system models for Divandareh‐Bijar Basin (Western Iran)

“…According to Figures 8 and 9 the EN‐Single‐RF alters the distribution of simulated precipitation, while EN‐RF accurately simulates the statistical distribution. This difference can be attributed to EN‐Single‐RF predicting many non‐zero precipitation values for dry days, affecting the variance of daily precipitation (Gentilucci & Pambianchi, 2022). This difference shows that the near‐zero values predicted by EN‐Single‐RF for dry days altered the probability distribution of daily precipitation.…”

Hidden in snow: Selected aspects of chemical composition of an urban snow cover (Kielce, SE Poland)

“…Changes in the Earth's climate, apart from the increase in global air temperature, affect the snow cover [Pant et al 2023]. Its thickness, as well as the number of days with snow, is declining in many regions of Europe [Olefs et al 2020, Gentilucci et al 2023, Stucchi et al 2023, Szyga-Pluta 2021. Analysis of the data from IMGW, Human pressure on air quality effects an increase in the amount of anthropogenic substances (suspended matter, hydrocarbons, metals) in precipitation [Douglas, Sturm 2004, Fonseca-Salazar et al 2023, Kashulina et al 2014, Opekunova et al 2021].…”

Analysis of Snow Cover in the Sibillini Mountains in Central Italy

“…Snow cover data are often subject to rather large gaps, in some cases recorded manually and only in rare cases automatically with snow measuring weather stations, so that data reconstructions are often necessary [10,11]. In addition, satellite survey data are not always reliable, both in terms of quantity and in terms of the presence or absence of the snow event, so major calibrations with weather stations are necessary, which do not always lead to acceptable results [12][13][14]. In particular, products such as IMERG, MERRA-2, or ERA sometimes show a certain underestimation of the snowpack, which makes these instruments unreliable for the purposes of a detailed analysis of snow depths [15,16].…”