{"id":638824,"date":"2024-09-19T14:31:00","date_gmt":"2024-09-19T11:31:00","guid":{"rendered":"https:\/\/en.buradabiliyorum.com\/brightband-sees-a-bright-and-open-source-future-for-ai-powered-weather-forecasting\/"},"modified":"2024-09-19T14:31:00","modified_gmt":"2024-09-19T11:31:00","slug":"brightband-sees-a-bright-and-open-source-future-for-ai-powered-weather-forecasting","status":"publish","type":"post","link":"https:\/\/buradabiliyorum.com\/en\/brightband-sees-a-bright-and-open-source-future-for-ai-powered-weather-forecasting\/","title":{"rendered":"#Brightband sees a bright (and open-source) future for AI-powered weather forecasting"},"content":{"rendered":"
\n

With an explosion of weather and climate data that the last generation of tools can\u2019t handle, is AI the future of forecasting? <\/p>\n

Research certainly suggests so, and a newly funded startup called Brightband <\/a>is taking a shot at turning machine learning forecast models into both a business and open source standard.<\/p>\n

Today\u2019s weather prediction and climate monitoring techniques are rooted in statistical and numerical models that are going on decades old. That doesn\u2019t mean they\u2019re bad or wrong \u2014 just not particularly efficient. These physics-based models are the kind of thing you set aside a few weeks on a supercomputer for.<\/p>\n

But AI has a knack for pulling patterns out of large bodies of data, and research has shown that, when AI is trained on years of weather patterns and observations around the world, it can predict upcoming events with surprising accuracy. <\/p>\n

So why isn\u2019t it being used all over the place?<\/p>\n

\u201cThe reason there\u2019s this gap is that the government finds it hard to attract top talent, as do weather companies, while for these tech companies, weather is not their core industry. They don\u2019t go deep into the domain and work with the players to give them the tools they need,\u201d explained Julian Green, CEO and co-founder of Brightband (formerly known as OpenEarthAI). \u201cWe think a startup brings great AI people, great data people, and great weather people together. There\u2019s a real opportunity to operationalize AI and make it available to everyone.\u201d<\/p>\n

The startup is in the process of designing its own model trained on years of weather observation data, but Daniel Rothenberg, co-founder and head of data and weather, was quick to note that they\u2019re \u201cstanding on the shoulders of giants.\u201d<\/p>\n

\u201cThe big physics-based models are monsters,\u201d he said. \u201cBut AI is the beneficiary of those models \u2014 the first leap was taking advantage of them, finding that the models really can learn those patterns. We\u2019re building on top of that and extending it. We\u2019re shooting for state of the art: as good or better than the available global weather forecasting.\u201d<\/p>\n

It would also be orders of magnitude faster, Green noted. \u201cThat\u2019s sort of the core disruption: it\u2019s faster and cheaper,\u201d making it more suitable to custom and fast-moving use cases.<\/p>\n

\u201cPeople have very specific needs across different industries,\u201d Green went on. \u201cEnergy companies need to be able to predict the supply of renewables from wind and sun, and demand for heating and cooling; transportation companies need to avoid extreme weather; agriculture needs to plan weeks out to hire people to seed, water, fertilize, or harvest.\u201d<\/p>\n

Interestingly, the company is committing to releasing its models for anyone to use<\/a>.<\/p>\n

\u201cOur goal is to open source the basic forecasting capability, not just the model but the data you use to train it, and the metrics you use to evaluate it, bus model is to layer on top, paid-for services for more specific capabilities,\u201d Green said.<\/p>\n

Part of doing so means including (and processing, and releasing) lots of data that has been skipped over in favor of pre-processed databases.<\/p>\n

\u201cThere\u2019s petabytes upon petabytes of historical data from weather balloons and satellites that are ignored because they\u2019re hard to work with,\u201d said Rothenberg; but as with most AI models, the more data the better, and a carefully curated variety can significantly improve the quality of their output. \u201cWe really feel that building a community around this is going to accelerate the things we can do in terms of understanding the atmosphere and doing it at scale.\u201d<\/p>\n

I suggested that this seemed almost like they were doing what the National Weather Service (which provides tons of observational data and forecasts for free as a public service) and other agencies would do if they could.<\/p>\n

Green demurred, saying they work closely with those agencies and that they are indeed the keepers of a trove of important data \u2014 it just isn\u2019t necessarily the kind of fast, portable data that a highly responsive consumer-facing company needs. He said they see this as a continuation of the international collaboration on weather data.<\/p>\n

As for where they actually are in building the product: \u201cIt\u2019s relatively early,\u201d Green admitted. \u201cWe\u2019ve been working on this for a few months, nothing is live today but we hope to have a model by the end of 2025 that takes in observations [i.e. satellite or local radar imagery] and produces a forecast for them.\u201d<\/p>\n

Brightband is structured as a public benefit corporation, but that\u2019s \u201cprimarily signaling,\u201d Green said. \u201cWe\u2019re trying to lay out our mission transparently, pinning our cause to the mast and saying \u2018this is what we\u2019re interested in doing.\u2019 I think the 10 million we raised is testament to the fact that we\u2019re able to attract capital.\u201d<\/p>\n

A PBC in this case basically means the board has to balance shareholder interests with those of the stated mission in certain circumstances, but doesn\u2019t limit profits or anything like that.<\/p>\n

Expect a weather-related product before a climate one \u2014 but neither has a hard timeline except for the end-of-year show-and-tell.<\/p>\n

Brightband\u2019s $10 million series<\/a> A round was led by Prelude Venture, with participation from Starshot Capital, Garage Capital, Future Back Ventures, Preston-Werner Ventures, CLAI Ventures, Adrien Treuille, and Cal Henderson.<\/p>\n<\/div>\n

If you liked the article, do not forget to share it with your friends. Follow us on\u00a0Google News<\/a><\/span>\u00a0too, click on the star and choose us from your favorites.<\/span><\/strong><\/p><\/blockquote>\n

\n

If you want to read more like this article, you can visit our Technology<\/a><\/span> category.<\/strong><\/p>\n<\/blockquote>\n

Source<\/a><\/span><\/p>\n","protected":false},"excerpt":{"rendered":"

With an explosion of weather and climate data that the last generation of tools can\u2019t handle, is AI the future of forecasting? Research certainly suggests so, and a newly funded startup called Brightband is taking a shot at turning machine learning forecast models into both a business and open source standard. Today\u2019s weather prediction and…<\/p>\n","protected":false},"author":1,"featured_media":638825,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/techcrunch.com\/wp-content\/uploads\/2024\/02\/cloud-computing-2024.jpg?resize=1200,675","fifu_image_alt":"","footnotes":""},"categories":[18],"tags":[77337,151908,74839,70917,45849],"class_list":["post-638824","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-technology","tag-ai","tag-brightband","tag-fundraising","tag-startups","tag-weather"],"_links":{"self":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts\/638824","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/comments?post=638824"}],"version-history":[{"count":0,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts\/638824\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media\/638825"}],"wp:attachment":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media?parent=638824"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/categories?post=638824"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/tags?post=638824"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}