Artificial intelligence is transforming the way we read, interpret, and forecast the atmosphere. In recent years, research on AI-based weather models has shown significant progress, especially in computational speed. But when it comes to the most complex variable\u2014precipitation\u2014physics continues to play a central role. <\/p>\n\n
It is in this transition space, between algorithmic innovation and the solidity of numerical models, that the new work by CIMA Research Foundation researcher Luca Monaco is positioned: \u201cExploring the viability of a machine learning-based multimodel for quantitative precipitation forecast post-processing.\u201d <\/em>A study that explores the potential of AI in the post-processing phase of NWP (Numerical Weather Prediction) forecasts 1 <\/a><\/sup>, with the goal of increasing the accuracy of rainfall estimates. <\/p>\n\n \u201cAI in this work does not replace physics, but it allows us to intervene in segments of the forecasting chain where we can truly make a difference,\u201d Monaco notes.<\/p>\n\n AI-based weather models already show high performance on low-complexity variables, but they struggle with meteorological fields characterized by high spatial and temporal variability, such as rainfall. Spatial resolution is often insufficient, precipitation patterns appear flattened, and the estimates still do not reach the quality of forecasts produced by traditional numerical models. <\/p>\n\n In fact, numerical weather prediction models continue to better identify the spatial structure of precipitation events, especially in complex areas. \u201cIf there is a strong point in physical models, it is their ability to forecast not only the location of precipitation but also its intensity,\u201d Monaco highlights. <\/p>\n\n This is where the idea behind the study originates: not to replace physical models, but to fuse their information through machine learning.<\/p>\n\n The core of the study is the construction of a machine-learning-based multimodel that combines forecasts from several physical models: COSMO-2I, COSMO-5M, IFS, and BOLAM. The goal? A single forecast that is more robust and more accurate than the individual inputs. <\/p>\n\n The evaluation was carried out on 406 precipitation events between 2018 and 2022 in Piedmont and the Aosta Valley, selected to ensure the presence of a relevant rainfall signal. The observations used come from ARPA Piemonte\u2019s Optimal Interpolation (OI) precipitation fields)2<\/a><\/sup> di ARPA Piemonte. <\/p>\n\n Special attention was dedicated to the structure of the dataset: <\/p>\n\n The results show clear improvements at low and intermediate precipitation thresholds, while performance at high thresholds is only marginally better than the benchmark, as it is strongly influenced by the resolution of the available observations. <\/p>\n\n \u201cThe quality of observations is a crucial point: without high-resolution data in formats suitable for machine learning, the potential of AI remains limited,\u201d Monaco emphasizes.<\/p>\n\n One of the most relevant aspects that emerged from the work is the potential of national centers in limited-area modeling. Large global AI models are advancing rapidly, but their level of detail is still not sufficient for many operational applications. <\/p>\n\n In this scenario, institutions such as CIMA Research Foundation possess two crucial assets: <\/p>\n\n \u201cWe have a unique data heritage and the ability to build interpretable and reliable AI models. It is a space in which we can truly make a concrete contribution to the meteorology of the future,\u201d Monaco states.<\/p>\n\n This work<\/a>, part of Monaco\u2019s PhD at Politecnico di Torino and funded by ARPA Piemonte, represents an important step in developing AI-based post-processing strategies. <\/p>\n\n \u201cWe should not be afraid of big challenges: AI is not a shortcut, but a tool that can expand what we already know how to do,\u201d concludes the researcher.<\/p>\n\n <\/p>\n Artificial intelligence is transforming the way we read, interpret, and forecast the atmosphere. In recent years, research on AI-based weather models has shown significant progress, especially in computational speed. But when it comes to the most complex variable\u2014precipitation\u2014physics continues to play a central role. It is in this transition space, between algorithmic innovation and the […]<\/p>\n","protected":false},"author":4,"featured_media":15866,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":"[{\"id\":\"901660f2-03ac-411c-b32f-b3c2d961ff24\",\"content\":\"NWP forecasts (Numerical Weather Prediction) are weather models based on the physical equations of the atmosphere. They use real observations and simulate the evolution of meteorological variables on a three-dimensional grid, providing detailed forecasts of temperature, wind, precipitation, and many other parameters. \"},{\"id\":\"b42ab651-fe43-4277-bb36-82b82a0d3a5f\",\"content\":\" OI fields are precipitation fields obtained through Optimal Interpolation (OI), a technique used to create a continuous and coherent map of precipitation starting from point measurements. \"}]"},"categories":[126],"tags":[151],"class_list":["post-15867","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-meteorology-and-climate","tag-meteorology"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.cimafoundation.org\/en\/wp-json\/wp\/v2\/posts\/15867","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.cimafoundation.org\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.cimafoundation.org\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.cimafoundation.org\/en\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/www.cimafoundation.org\/en\/wp-json\/wp\/v2\/comments?post=15867"}],"version-history":[{"count":1,"href":"https:\/\/www.cimafoundation.org\/en\/wp-json\/wp\/v2\/posts\/15867\/revisions"}],"predecessor-version":[{"id":15868,"href":"https:\/\/www.cimafoundation.org\/en\/wp-json\/wp\/v2\/posts\/15867\/revisions\/15868"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.cimafoundation.org\/en\/wp-json\/wp\/v2\/media\/15866"}],"wp:attachment":[{"href":"https:\/\/www.cimafoundation.org\/en\/wp-json\/wp\/v2\/media?parent=15867"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.cimafoundation.org\/en\/wp-json\/wp\/v2\/categories?post=15867"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.cimafoundation.org\/en\/wp-json\/wp\/v2\/tags?post=15867"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}Why Precipitation Remains a Challenge for AI<\/h2>\n\n
An AI-driven multimodel to improve rainfall forecasts<\/h2>\n\n
\n
\n
\n
AI and local meteorology: the value of national centers<\/h2>\n\n
\n
\n
Toward AI-enhanced meteorology<\/h2>\n\n