天氣預(yù)報(bào)現(xiàn)在可以更加準(zhǔn)確了。

時(shí)間：2022-04-09 16:21:01 | 來(lái)源：行業(yè)動(dòng)態(tài)

時(shí)間：2022-04-09 16:21:01 來(lái)源：行業(yè)動(dòng)態(tài)

時(shí)下五天的預(yù)測(cè)有90%的準(zhǔn)確性，與25年前三天預(yù)測(cè)的準(zhǔn)確度相同。短期預(yù)測(cè)（也就是說(shuō)以小時(shí)為時(shí)間跨度的當(dāng)下預(yù)測(cè)）則更具挑戰(zhàn)性，主要是由于地面的微觀變化。DeepMind和?？巳卮髮W(xué)的科學(xué)家們與英國(guó)氣象局合作，利用人工智能建立了一個(gè)當(dāng)下預(yù)測(cè)系統(tǒng)，該系統(tǒng)可望克服這些挑戰(zhàn)做出更準(zhǔn)確的短期預(yù)測(cè)，包括對(duì)重大風(fēng)暴和洪水的預(yù)測(cè)。另外一項(xiàng)研究是研究建模的效率以及人工智能如何分析過(guò)去的天氣模式對(duì)未來(lái)事件更有效和更準(zhǔn)確地預(yù)測(cè)。

My focus of work and the area of AI that I am particularly interested in is its application to predict the potential impact from weather events. The outcomes of weather as opposed to the weather itself.

筆者的工作重點(diǎn)（以及我特別感興趣的人工智能領(lǐng)域）是人工智能在預(yù)測(cè)來(lái)自天氣事件的潛在影響方面的應(yīng)用，相對(duì)于天氣本身而言，更多的涉及到天氣所產(chǎn)生的結(jié)果。

For example, using AI in the utility sector to predict potential outages. Historical outage data is collected on a specific utility location, or region, and allows a computer to generate predictions for future needs based on forecasted weather conditions. It understands how infrastructure has responded to past storms including learning differences in network hardening, realizing the age of individual infrastructure components and maintenance practices. These datasets will yield a baseline of potential outages from upcoming storms. We can apply the same approach with municipalities. Understanding variables such as the citys infrastructure, topography, and evacuation routes, along with historical weather data, we can help cities have better insight into potential areas of impact and risk of public or infrastructure safety.

例如，公共事業(yè)部門利用人工智能預(yù)測(cè)可能出現(xiàn)的停電。一個(gè)特定的公用事業(yè)地點(diǎn)或地區(qū)的歷史停電數(shù)據(jù)收集了以后可以允許計(jì)算機(jī)根據(jù)預(yù)測(cè)的天氣狀況生成對(duì)未來(lái)需求的預(yù)測(cè)。這些歷史數(shù)據(jù)涵括了基礎(chǔ)設(shè)施應(yīng)對(duì)過(guò)去的風(fēng)暴的知識(shí)，包括學(xué)習(xí)加固網(wǎng)絡(luò)的差異，實(shí)現(xiàn)個(gè)別基礎(chǔ)設(shè)施組件的年齡和維護(hù)的做法。這些數(shù)據(jù)集可以生成未來(lái)可能到來(lái)的風(fēng)暴導(dǎo)致的停電基線數(shù)據(jù)。市政區(qū)管理層次上也可以采用同樣的方法。我們對(duì)于城市的基礎(chǔ)設(shè)施、地形和疏散路線等變量以及歷史氣象數(shù)據(jù)的了解，可以幫助城市更好地洞察潛在的影響領(lǐng)域和公共或基礎(chǔ)設(shè)施安全的風(fēng)險(xiǎn)。

And, while we talk about advanced technology and insights, I think it is important to note that the human element is still crucial to the process. A recent Wired article citied studies that found forecasts by human forecasters were more accurate than AI forecasts.

而且，在我們談?wù)撓冗M(jìn)的技術(shù)和洞察力的同時(shí)，筆者認(rèn)為人的因素在這個(gè)過(guò)程中仍然至關(guān)重要。最近《連線》雜志的一篇文章提到一些研究結(jié)果，這些研究發(fā)現(xiàn)人類預(yù)報(bào)員的預(yù)測(cè)比人工智能的預(yù)測(cè)更準(zhǔn)確。

Another area that requires human intervention is the increasing need for risk communicators. These are meteorologists who take the forecast further and convey the risk or impact to a business, municipality or public. I have heard several comments that when AI is more trustworthy it will be as simple as toggling weather preferences to have accurate, meaningful weather data on demand. While I agree that we will have progressively better data and forecasts, I believe this will also increase the need for human experts to evaluate, interpret and communicate the data and the risk and impact in a way that makes sense to those who must make nimble, informed decisions to protect people, infrastructure, and businesses assets. The bigger question shouldnt be human or AI forecasts, but rather how can meteorologists use improved AI to help decision makers make the best decisions for their stakeholders.

另一個(gè)需要人為干預(yù)的領(lǐng)域是風(fēng)險(xiǎn)溝通者的增長(zhǎng)需求。風(fēng)險(xiǎn)溝通者是一群特殊的氣象學(xué)家，他們?cè)陬A(yù)測(cè)的基礎(chǔ)上更進(jìn)了一步，將風(fēng)險(xiǎn)或影響傳達(dá)給企業(yè)、市政當(dāng)局或公眾。我聽(tīng)到過(guò)一些評(píng)論指，在人工智能更值得信賴后就可以簡(jiǎn)單地切換天氣偏好按需求獲得準(zhǔn)確、有意義的天氣數(shù)據(jù)。我們將擁有逐步改善的數(shù)據(jù)和預(yù)測(cè)，這一點(diǎn)我同意，但我相信這也將增加對(duì)人類專家的需求，以達(dá)到評(píng)估、解釋和溝通數(shù)據(jù)（以及風(fēng)險(xiǎn)和影響）的目的，所用到的方式是有意義的，可以幫助那些必須做出靈活、明智決定以保護(hù)人民、基礎(chǔ)設(shè)施和企業(yè)資產(chǎn)的人。更大的問(wèn)題并不是人類預(yù)測(cè)還是人工智能預(yù)測(cè)，而是氣象學(xué)家如何利用改進(jìn)的人工智能幫助決策者為他們的利益相關(guān)者做出最佳決定。