音頻科普:海豚能用回聲定位
?Something Clicks for Dolphin Identification海豚能用回聲定位
Machine-learning algorithms teased seven distinct dolphin clicking patterns from a library of more than 50 million clicks, identifying one species by sound alone.
機器學(xué)習算法梳理出了海豚超過(guò)五千萬(wàn)種拍擊中的七種模式,僅從聲音就能判別種群。
撰文/播音 Christopher Intagliata?克里斯托福?因塔爾利亞他
翻譯?張心茹
審校?張清越
?
Light doesn't travel well underwater. So dolphins and other toothed whales navigate like bats, using echolocating clicks. <>
光在水中不能良好地傳播,因此海豚和其他齒鯨像蝙蝠一樣利用拍擊的回聲定位導航。
"They're like lasers of sound they produce out of their forehead, and they bounce them off things the same way bats do, to interpret their environment."
“他們從前額發(fā)出的聲音像激光,像蝙蝠發(fā)出的聲音一樣在周?chē)瓷?,以此?lái)了解四周的環(huán)境”
Kait Frasier is an oceanographer at the Scripps Institution of Oceanography. And her studies of underwater clicks include tossing computers, worth $100,000 dollars each, over the side of a ship, into the Gulf of Mexico.
凱特?弗萊瑟是斯克里普斯海洋學(xué)研究所(Scripps Institution of Oceanography)的一名海洋學(xué)家。她對水下拍擊的研究動(dòng)用了每臺價(jià)值十萬(wàn)美元的計算機,她把計算機安裝在船的側面,伸入墨西哥灣的海域里。
"It just feels so wrong. But a year later you go back, you send out this little ping signal, it goes, doo doo doo doo doo, and that goes out to the instrument and it drops its weights and floats to the surface. And it's this magical moment, like 'I never thought we'd get that back.'"
“一開(kāi)始感覺(jué)很不好。但一年后回來(lái),發(fā)射輕微的信號后,嘟 嘟 嘟 ,這些聲音傳入儀器,它失重,浮出水面。這是一個(gè)神奇的時(shí)刻,我從未想過(guò)我們會(huì )看到它們回來(lái)?!?/span>
The waterproof computers have underwater microphones attached…. So when they float back up, they're loaded with a symphony of underwater sounds. Including more than 50 million clicks. <> And by the way that sample was slowed down by half, and lowered an octave.
這些防水電腦附帶有水下麥克風(fēng)……所以當它們浮起時(shí),它們錄滿(mǎn)了水下聲音組成的交響曲。包括了五千萬(wàn)中拍擊聲《拍擊交響樂(lè )》同時(shí)這些樣品減慢一半速度,降了八度。
Frasier used to comb through that audio, staring at the signals, trying to differentiate one from the other. "Yeah, more than i would like to spend my time sifting through."
弗萊瑟曾經(jīng)梳理這些音頻,觀(guān)察這些信號,試圖區分它們。“我不想把時(shí)間都花在整理它們上?!?/span>
So she set machine learning algorithms at the data instead… which sifted out seven distinct clicking patterns. And the algorithms were able to identify one species—called Risso's dolphin—by sound alone. ?The results are in the journal PLOS Computational Biology. [Kaitlin E. Frasier et al., Automated classification of dolphin echolocation click types from the Gulf of Mexico]
所以她轉而對數據設置了機器學(xué)習算法……篩選了七種不同的拍擊模式。這個(gè)算法可以?xún)H通過(guò)聲音識別其中一個(gè)物種,里索海豚(Risso's dolphin)。這些結果收錄于PLOS計算生物學(xué)雜志[Kaitlin E. Frasier et al., Automated classification of dolphin echolocation click types from the Gulf of Mexico]
Traditional marine mammal surveys scan surface waters from a boat, and extrapolate from there. But this tech might offer an alternative. "Instead of going out on a boat you put this instrument out, and it does this passive acoustic listening for a year, or many years in a row, and you can use that to get better time series of these animals over a long period of time."
If it can figure out how to tease out more individual species types, this survey method might really click.
傳統的海洋哺乳動(dòng)物研究只從船上搜索海面,然后根據水面結果推斷。但這種技術(shù)或許提供了一種新思路。“除了駕船出海,你可以攜帶這個(gè)設備,它可以被動(dòng)接收一年的音頻信號,也可以是多年,然后你可以用它了解更長(cháng)時(shí)間跨度內的動(dòng)物行為時(shí)間?!比绻芙鉀Q如何梳理出更多的物種類(lèi)型,這種研究方法將會(huì )真正“聲”動(dòng)學(xué)界。
—Christopher Intagliata
原文鏈接:https://www.scientificamerican.com/podcast/episode/something-clicks-for-dolphin-identification/
關(guān)注【深圳科普】微信公眾號,在對話(huà)框:
回復【最新活動(dòng)】,了解近期科普活動(dòng)
回復【科普行】,了解最新深圳科普行活動(dòng)
回復【研學(xué)營(yíng)】,了解最新科普研學(xué)營(yíng)
回復【科普課堂】,了解最新科普課堂
回復【科普書(shū)籍】,了解最新科普書(shū)籍
回復【團體定制】,了解最新團體定制活動(dòng)
回復【科普基地】,了解深圳科普基地詳情
回復【觀(guān)鳥(niǎo)知識】,學(xué)習觀(guān)鳥(niǎo)相關(guān)科普知識
回復【博物學(xué)院】,了解更多博物學(xué)院活動(dòng)詳情
?