Yves Atchad\u00e9, Professor of Mathematics & Statistics + Computing & Data Sciences<\/figcaption><\/figure>\nAtchad\u00e9 and his team focused on Ghana in West Africa as a case study, using rainfall estimates from NASA and the Japanese space agency\u2019s Global Precipitation Measurement (GPM) mission, which has been collecting satellite observations since around 2000. They combined these with the ERA5 reanalysis dataset from the European Centre for Medium\u2011Range Weather Forecasts (ECMWF), which provides a consistent global picture of the atmosphere over recent decades.<\/p>\n
The team built a deep learning model that is specifically tuned to predict 24 hour rainfall there 12 or 30 hours ahead. Atchad\u00e9 explains: \u201cWe wanted to show that a small team, with a small model, could still match or even beat the state of the art NWP system in this region.\u201d<\/p>\n
One of the natural worries with deep learning rainfall models is that they might just \u201cmemorize\u201d past weather instead of learning real physical patterns. Atchad\u00e9\u2019s group tackled this by treating their model as a statistical model first and using regularization and careful validation to guard against overfitting. \u201cAfter we fit the model, we looked to understand what was learned by the model, and we compared that to what scientists know about rainfall formation in the area. A lot of interesting phenomena were captured by the model.\u201d<\/p>\n
At the core, the model learns that certain combinations of humidity, wind patterns, and large-scale wave features are meaningful predictors of rainfall across the region. In their Ghana experiments, the deep learning model outperforms ECMWF\u2019s own forecasts at matching observed rainfall and identifying heavy rain events, even though the model is much smaller.<\/p>\n
For Atchad\u00e9, rainfall forecasts are not just an academic exercise. \u201cIn many African countries, people still rely on predictions from Europe, not from their own institutions,\u201d he notes. \u201cIf local researchers can build models that match or surpass those, it\u2019s a way to train local scientists and to give farmers better information for planting and harvesting.\u201d<\/p>\n
He also stresses that models are inherently probabilistic. \u201cStatistical models only make probability statements, and there will always be uncertainty,\u201d he says. To manage that risk, his team utilized ensemble modeling, which means running multiple simulations or using multiple models to chart out different possible futures. \u201cThat\u2019s exactly how operational weather forecasts are presented: the storm is most likely to go this way, but it could also go that way.\u201d<\/p>\n
To explain the model to non-technical decision makers, Atchad\u00e9 keeps the language simple. \u201cWe talk about the model output,\u201d he says. \u201cWe talk about possible scenarios and the likelihood of each.\u201d Farmers want to know: is it likely to rain in the next two days, or is there a real chance of a heavy downpour that could flood my fields? The model packages the output so it\u2019s not about neural networks, but rather about risk, and what to do under each scenario.<\/p>\n
For Atchad\u00e9\u2019s lab, the rainfall work is already evolving. The next step \u201cis a super exciting thing for us,\u201d he adds. His postdoc and PhD student collaborators are now turning from daily rainfall to a bigger, more seasonal question: predicting the West African monsoon months in advance.
\n\u201cFor farmers, it is perhaps the most important prediction we can make,\u201d Atchad\u00e9 says. If the model can give them a credible forecast in March or April about the timing of the monsoon, that\u2019s far more useful than a single day\u2011ahead rainfall number.<\/p>\n
— Shriya Jonnalagadda (CDS’28), Data Science Research Communications Intern<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"Read about Professor Yves Atchad\u00e9 and his team’s work building a deep learning model that forecasts rains in West Africa using AI.<\/p>\n","protected":false},"author":25279,"featured_media":19655,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[251,5,391,244,1,373],"tags":[377,899,299,909,905],"_links":{"self":[{"href":"https:\/\/www.bu.edu\/cds-faculty\/wp-json\/wp\/v2\/posts\/19644"}],"collection":[{"href":"https:\/\/www.bu.edu\/cds-faculty\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.bu.edu\/cds-faculty\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/cds-faculty\/wp-json\/wp\/v2\/users\/25279"}],"replies":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/cds-faculty\/wp-json\/wp\/v2\/comments?post=19644"}],"version-history":[{"count":5,"href":"https:\/\/www.bu.edu\/cds-faculty\/wp-json\/wp\/v2\/posts\/19644\/revisions"}],"predecessor-version":[{"id":19760,"href":"https:\/\/www.bu.edu\/cds-faculty\/wp-json\/wp\/v2\/posts\/19644\/revisions\/19760"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/cds-faculty\/wp-json\/wp\/v2\/media\/19655"}],"wp:attachment":[{"href":"https:\/\/www.bu.edu\/cds-faculty\/wp-json\/wp\/v2\/media?parent=19644"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.bu.edu\/cds-faculty\/wp-json\/wp\/v2\/categories?post=19644"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.bu.edu\/cds-faculty\/wp-json\/wp\/v2\/tags?post=19644"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
![\"Photo](\"\/cds-faculty\/files\/2026\/03\/AdobeStock_135138020.jpeg\")
<\/p>\n![\"Headshot](\"\/cds-faculty\/files\/2026\/03\/Yves-Atchade.jpg\")