人工智能在對(duì)非洲象進(jìn)行統(tǒng)計(jì)中發(fā)揮了關(guān)鍵作用

人工智能在對(duì)非洲象進(jìn)行統(tǒng)計(jì)中發(fā)揮了關(guān)鍵作用

There are two kinds of elephants in Africa: the forest elephant and the savanna elephant (above), photographed this past spring in Liwonde National Park in Malawi. The Great Elephant Census found that Africa's savanna elephant population decreased by about a third in the seven years between 2007 and 2014.

非洲有兩種大象:森林象和草原象(上圖)，這是今年春天在馬拉維利旺德國家公園拍攝的。大象普查發(fā)現(xiàn)，在2007年至2014年的七年間，非洲草原大象的數(shù)量減少了約三分之一。

A few years ago, Paul Allen, the co-founder of Microsoft, published the results of something called the Great Elephant Census, which counted all the savanna elephants in Africa. What it found rocked the conservation world: In the seven years between 2007 and 2014, Africa's savanna elephant population decreased by about a third and was on track to disappear completely from some African countries in as few as 10 years.

幾年前，微軟的聯(lián)合創(chuàng)始人保羅·艾倫公布了一項(xiàng)名為“大象普查”的調(diào)查結(jié)果，這個(gè)調(diào)查統(tǒng)計(jì)了所有草原大象的數(shù)量。它的發(fā)現(xiàn)震驚了自然保護(hù)界:在2007年至2014年的七年間，非洲草原大象的數(shù)量減少了約三分之一，而且在短短10年內(nèi)就會(huì)從一些非洲國家完全消失。

To reverse that trend, researchers landed on a technology: artificial intelligence. AI's ability to find regularity in enormous volumes of information is demystifying not just elephant behavior but human behavior — specifically poacher behavior — too.

為了扭轉(zhuǎn)這一趨勢，研究人員開發(fā)了一種技術(shù)：人工智能。人工智能在海量信息中發(fā)現(xiàn)規(guī)律的能力不僅揭開了大象行為的神秘面紗，也揭開了人類行為，特別是偷獵者行為的神秘面紗。

"AI can process huge amounts of information to tell us where the elephants are, how many there are," said Cornell University researcher Peter Wrege. "And ideally tell us what they are doing."

“人工智能可以處理大量的信息，告訴我們大象在哪里，有多少大象，”康奈爾大學(xué)的研究員彼得·瑞格說。“最好告訴我們他們?cè)谧鍪裁础?rdquo;

There are two kinds of elephants in Africa: savanna elephants, which were counted by Allen's census, and forest elephants, which the census couldn't account for because that elephant lives beneath a thick rainforest canopy.

非洲有兩種大象:草原象(由艾倫的普查統(tǒng)計(jì)得到)和森林象(由于大象生活在濃密的雨林樹冠下，無法普查這兩種大象的數(shù)量)。

Even at the level of the jungle, Wrege says, losing a forest elephant is easy to do. "Sometimes you see them, let's say, 15 meters [16 yards] away from you and then they move 5 meters into the forest and you can't see them," he said. "Somehow they just disappear."

瑞格說，即使在叢林中，失去一頭森林象也很容易。他說:“有時(shí)候在離你15米(16碼)遠(yuǎn)的地方看到它們，然后它們往森林里移動(dòng)了5米，你就看不到它們了。”“它們不知怎么就消失了。”

Researchers at Cornell University have been studying the forest elephant for years, trying to figure out — like Allen did with the savanna elephant — how many there are and how fast they are being killed. Given how stealthy the forest elephants are, Wrege began to think that rather than look for them, maybe he should try something a little different: Maybe he should listen for them.

康奈爾大學(xué)的研究人員多年來一直在研究森林象，就像艾倫研究草原象一樣，試圖弄清楚它們的數(shù)量和被捕殺的速度?？紤]到森林里的大象是多么的隱蔽，瑞格開始思考與其尋找它們，不如嘗試一些不同的方法:也許他應(yīng)該傾聽它們的聲音。

To do this, Wrege had 50 custom audio recorders made. He divided the rainforest into a grid and headed to Central Africa. His team hung the custom recorders every 23 feet to 30 feet in the treetops, just a little higher than an elephant could reach with its trunk while standing on its hind legs. Three months later, they would return to the forest, locate the recorders, change the batteries, put in new audio cards, and start all over again.

為此，瑞格定制了50臺(tái)錄音機(jī)。他將雨林分成網(wǎng)格狀，然后前往中非。他的團(tuán)隊(duì)在樹梢上每隔23到30英尺懸掛一個(gè)定制的記錄器，這個(gè)高度僅比大象用后腿站立時(shí)用鼻子所能到達(dá)的高度高一點(diǎn)。三個(gè)月后，他們回到森林，找到錄音機(jī)，換電池，放上新的聲卡，再次重復(fù)之前的步驟。

As the months wore on, the recorders were collecting hundreds of thousands of hours of jungle sounds, more than any team of graduate students could realistically listen to — which meant Wrege had another problem: How could he sort through all these recordings to find the elephant voices he wanted?

幾個(gè)月過去了，錄音機(jī)收集了數(shù)十萬小時(shí)的叢林聲音，比任何一個(gè)研究生小組實(shí)際能聽到的都要多——這意味著瑞格還有另一個(gè)問題:他如何才能從這些錄音中找出他想要的大象的聲音呢?

The computer scientist Josephine Wolff, who is now a professor at the Fletcher School at Tufts University. "At a party with a lot of background noise, the human brain can focus on a specific person's voice and amplify that above all the other voices. AI can do the same thing."

計(jì)算機(jī)科學(xué)家約瑟芬·沃爾夫現(xiàn)在是塔夫茨大學(xué)弗萊徹學(xué)院的教授。“在一個(gè)有很多噪音的聚會(huì)上，人類的大腦可以專注于一個(gè)特定的人的聲音，并將其放大到所有其他聲音之上。人工智能也能做到這一點(diǎn)。”

It is particularly good at working with images, so Wrege ran the audio through a software program that turned the recordings he had collected into spectrograms. He then had a company in Santa Cruz, Calif., build him a neural network that could sort through the cacophony of jungle sounds and find elephants.

它特別擅長處理圖像，因此瑞格通過一個(gè)軟件程序運(yùn)行音頻，該程序?qū)⑺占匿浺艮D(zhuǎn)換成聲譜圖。后來，他在加州圣克魯斯有一家公司，這家公司為他建立了一個(gè)神經(jīng)網(wǎng)絡(luò)，可以從叢林里的各種雜音中找出大象。