A multi-modal machine learning approach to detect extreme rainfall events in Sicily

Abstract

In 2021 almost 300 mm of rain, nearly half of the average annual rainfall, fell near Catania (Sicily Island, Italy). Such events took place in just a few hours, with dramatic consequences on the environmental, social, economic, and health systems of the region. These phenomena are now very common in various countries all around the world: this is the reason why, detecting local extreme rainfall events is a crucial prerequisite for planning actions, able to reverse possibly intensified dramatic future scenarios. In this paper, the Affinity Propagation algorithm, a clustering algorithm grounded on machine learning, was applied, to the best of our knowledge, for the first time, to detect extreme rainfall areas in Sicily. This was possible by using a high-frequency, large dataset we collected, ranging from 2009 to 2021 which we named RSE (the Rainfall Sicily Extreme dataset). Weather indicators were then been employed to validate the results, thus confirming the presence of recent anomalous rainfall events in eastern Sicily. We believe that easy-to-use and multi-modal data science techniques, such as the one proposed in this study, could give rise to significant improvements in policy-making for successfully contrasting climate change.

Precision agriculture for wine production: A machine learning approach to link weather conditions and wine quality

“…Focusing on the vegetative growth and ripening of the fruits of the vine, the main factors to be measured for the quality of wine products are the temperature, light radiation and rainfall of the territory under analysis. Among the climatic factors, the air temperature plays a decisive role on the overall ripening of the grapes and in particular on the aromas and flavors, with important repercussions on the characteristics of the wines [47] , [50] , [14] , [49] . In our analysis, we focused solely on the temperature variable, as it represents the culmination of numerous climatic influences.…”

A machine learning approach to assess Sustainable Development Goals food performances: The Italian case

“…Such phenomena could damage crop production by affecting plant functions like photosynthesis, and heavy precipitations, which could lead to water redistribution and soil erosion. A connection between climate change and the occurrence of these extreme events is reported and clearly shown in studies as for instance [ 6 ]. It is in fact clear that the vulnerability of the agricultural sector is a matter of global concern, as it jeopardizes the production and availability of food due to irreversible shifts in weather patterns.…”

“…Machine Learning and Artificial Intelligence methods have been widely used in the literature in order to deeper the understanding of interdisciplinary and complex phenomena such as climate change, food production, bioinformatics and other complex citizen science phenomena and economics [ 6 , 15 – 20 ]. For instance in [ 21 ], the authors studied the performances of the Italian agrifood market from a new, and very important point of view, a subset of the Sustainable Development Goals [ 22 , 23 ], which were put in place by the United Nations in 2014 [ 24 ], considering the agrifood market and the sustainability aspects, and it is composed of indicators belonging to SDG02: Zero Hunger, SDG12: Responsible Consumption and Production, and SDG13: Climate Change [ 25 ].…”

Efficacy of Machine Learning in Simulating Precipitation and Its Extremes Over the Capital Cities in North Indian States

“…Traditional modeling approaches struggle to capture the complex interplay of factors shaping precipitation patterns, including climate change, topography, and atmospheric dynamics [31][32][33] . In response, integrating machine learning (ML) techniques has emerged as a promising avenue for understanding precipitation [34][35][36][37] and extreme precipitation [38][39][40][41] variability and enhancing forecasting accuracy leveraging large meteorological datasets and computational power to improve predictive capabilities amid climate change uncertainties [34][35][36] .…”