DeepMind AI Zai Iya Hasashen Yanayi Mai Kyau

Deepmind AI

Meteorology a matsayin kimiyya yana ci gaba godiya ga ci gaban fasaha. A halin yanzu, akwai shirye -shiryen kwamfuta da yawa waɗanda ke iya yin hasashen kai tsaye lokacin da inda za a yi ruwan sama. Kamfanin da Deepmind ya haɓaka haɓakar ɗan adam wanda ke iya yin hasashen kusan daidai lokacin da inda za a yi ruwan sama. Wannan kamfani ya yi aiki tare da masanan yanayi na Burtaniya don ƙirƙirar ƙirar da ta fi dacewa don yin tsinkayen ɗan gajeren lokaci fiye da tsarin yanzu.

A cikin wannan labarin za mu gaya muku duk abin da kuke buƙatar sani game da jakar Robleda, fasahar hasashen yanayi na kamfanin DeepMind.

Hasashen yanayi

zurfin tunani

DeepMind, wani kamfani ne na leken asiri na London, ya ci gaba da aikinsa na amfani da zurfin ilmantarwa ga matsalolin kimiyya masu wahala. DeepMind ya haɓaka kayan aikin ilmantarwa mai zurfi da ake kira DGMR tare da haɗin gwiwar Ofishin Sadarwa na Ƙasar Burtaniya, wanda zai iya yin hasashen yiwuwar yiwuwar ruwan sama a cikin mintuna 90 masu zuwa. Yana ɗaya daga cikin mawuyacin ƙalubale a hasashen yanayi.

Idan aka kwatanta da kayan aikin da ake da su, da yawa masana sun yi imanin cewa hasashen DGMR shine mafi kyau akan abubuwa da yawa, gami da hasashen wurin, kewayo, motsi da tsananin ruwan sama, 89% na lokacin. Sabuwar kayan aikin DeepMind yana buɗe sabon maɓalli a cikin ilimin halitta wanda masana kimiyya ke ƙoƙarin warwarewa shekaru da yawa.

Koyaya, har ma da ƙaramin ci gaba a cikin tsinkaya yana da mahimmanci. Hasashen ruwan sama, musamman ruwan sama mai ƙarfi, yana da mahimmanci ga masana'antu da yawa, daga ayyukan waje zuwa sabis na jirgin sama da gaggawa. Amma samun daidai yana da wahala. Tabbatar da yawan ruwa a sararin sama da lokacin da kuma inda zai faɗi ya dogara da yawancin yanayin yanayin yanayi, kamar canjin zafin jiki, samuwar girgije, da iska. Duk waɗannan abubuwan suna da sarkakiya cikin su, amma sun fi rikitarwa idan aka haɗa su.

Mafi kyawun fasahar hasashen da ake samu yana amfani da adadi mai yawa na kwaikwayon kwamfuta na kimiyyar sararin samaniya. Waɗannan sun dace da tsinkaye na dogon lokaci, amma ba su da kyau sosai don yin hasashen abin da zai faru a sa'a mai zuwa. Wannan shi ake kira hasashen gaggawa.

Ci gaban DeepMind

ci gaban hasashen yanayi

An samar da dabarun ilmantarwa mai zurfi na baya, amma waɗannan fasahohin galibi suna aiki da kyau ta wata fuska, kamar tsinkayar wuri, da kuma kashe wani, kamar ƙarfin tsinkaya. Bayanan radar don ruwan sama mai ƙarfi wanda ke taimakawa hango ruwan sama nan da nan ya kasance babban ƙalubale ga masanan yanayi.

Ƙungiyar DeepMind ta yi amfani da bayanan radar don horar da AI. Kasashe da yankuna da yawa suna yawan buga hotuna na ma'aunin radar wanda ke bin diddigin girgije da motsi cikin yini. Misali, a Burtaniya, ana sanya sabbin karatu kowane minti biyar. Ta hanyar haɗa waɗannan hotunan tare, zaku iya samun bidiyon dakatarwar motsi na zamani wanda ke nuna yadda yanayin ruwan sama na ƙasa ke canzawa.

Masu binciken suna aika wannan bayanan zuwa cibiyar sadarwa mai zurfin kama da GAN, wanda shine AI wanda aka horar da shi wanda zai iya samar da sabbin samfuran bayanai waɗanda suke da kama da ainihin bayanan da ake amfani da su a cikin horo. An yi amfani da GAN wajen samar da fuskokin karya, ciki har da Rembrandt na karya. A wannan yanayin, DGMR (wanda ke nufin "Tsarin Rain Rain Raini") ya koya don ƙirƙirar hotunan radar ƙarya waɗanda ke ci gaba da ainihin jerin ma'auni.

Gwajin DeepMind AI

hasashen yanayi

Shakir Mohamed, wanda ya jagoranci binciken a DeepMind, ya ce wannan daidai yake da kallon 'yan fim daga fim da hasashen abin da zai biyo baya. Don gwada wannan hanyar, ƙungiyar ta tambayi masanan yanayi 56 daga Ofishin Hasashen Jiragen Sama (waɗanda ba su da hannu a cikin aikin) don zurfafa zurfafa abubuwan kwaikwayo na zahiri da saitin abokan hamayya.

Kashi 89% na mutane sun ce sun fi son sakamakon da DGMR ya bayar. Algorithms na koyon injin gabaɗaya suna ƙoƙarin haɓakawa don sauƙi gwargwadon yadda tsinkayar ku ke da kyau. Koyaya, hasashen yanayi yana da fannoni daban -daban. Wataƙila hasashen ya sami tsananin ruwan sama a daidai wurin, ko wasu hasashen sun sami madaidaicin haɗin ƙarfi amma a inda bai dace ba, da sauransu.

DeepMind ya ce zai fitar da tsarin dukkan sunadaran da kimiyya ta sani. Kamfanin ya yi amfani da furotin ɗinsa na AlphaFold mai lanƙwasa hankali na wucin gadi don samar da tsari don kariyar ɗan adam, har ma da yisti, kuda 'ya'yan itace da beraye.

Haɗin gwiwar tsakanin DeepMind da Met Office kyakkyawan misali ne na aiki tare da masu amfani na ƙarshe don kammala ci gaban AI. Babu shakka wannan kyakkyawar shawara ce, amma galibi ba ta faruwa. Ƙungiyar ta yi aiki a kan aikin na tsawon shekaru da yawa kuma bayanai daga ƙwararru daga Ofishin Jakadancin sun tsara aikin. Suman Ravuri, masanin kimiyyar bincike a DeepMind, ya ce: "Yana inganta ci gaban samfurinmu ta wata hanya ta daban fiye da yadda muke aiwatarwa." "In ba haka ba, da mun ƙirƙiri abin ƙira wanda ba zai zama da amfani musamman a ƙarshe ba."

DeepMind kuma yana ɗokin nuna cewa AI ɗin sa yana da aikace -aikace masu amfani. Ga Shakir, DGMR da AlphaFold sashi ne na labarin guda ɗaya: kamfanin yana amfani da shekarunsu na ƙwarewar warware wasanin gwada ilimi. Wataƙila mafi mahimmancin ƙarshe anan shine cewa DeepMind ya fara jera matsalolin kimiyya na zahiri.

Ci gaba a hasashen yanayi

Dole ne a tallafa wa hasashen yanayi ta hanyar haɓaka fasaha yayin da muke kara kusantowa da cikakken fahimtar yadda yanayin mu ke aiki. Sau da yawa ɗan adam da lissafin sa na iya fuskantar kuskuren gama gari wanda za a iya guje masa tare da haɓaka haɓakar ɗan adam.

Hasashen yanayi yana da mahimmanci don zama ɗan adam tunda zamu iya cin moriyar abubuwa da yawa albarkatun ruwa mafi inganci da gujewa wasu bala'o'i a cikin hadari da ruwan sama mai ƙarfi. A saboda wannan dalili, masanan yanayi na ƙara yarda da haɓaka ayyukan fasaha na wucin gadi don hasashen ruwan sama.

Ina fatan cewa tare da wannan bayanin zaku iya ƙarin koyo game da aikin DeepMind da halayensa.


Abubuwan da ke cikin labarin suna bin ka'idodinmu na ka'idojin edita. Don yin rahoton kuskure danna a nan.

Kasance na farko don yin sharhi

Bar tsokaci

Your email address ba za a buga. Bukata filayen suna alama da *

*

*

  1. Mai alhakin bayanan: Miguel Ángel Gatón
  2. Dalilin bayanan: Gudanar da SPAM, gudanar da sharhi.
  3. Halacci: Yarda da yarda
  4. Sadarwar bayanan: Ba za a sanar da wasu bayanan ga wasu kamfanoni ba sai ta hanyar wajibcin doka.
  5. Ajiye bayanai: Bayanin yanar gizo wanda Occentus Networks (EU) suka dauki nauyi
  6. Hakkoki: A kowane lokaci zaka iyakance, dawo da share bayanan ka.