Mbinu mpya ya kijasusi ya bandia inaweza kusaidia kutabiri eneo la mitetemeko baada ya tetemeko la ardhi
An tetemeko la ardhi is a phenomenon caused when rock underground in the Dunia crust suddenly breaks around a geological fault line. This causes rapid release of energy which produces seismic waves which then make the ground shake and this is the sensation we fell during an earthquake. The spot where the rock breaks is called focus of the tetemeko la ardhi and place above it on ground is called ‘epicentre’. The energy released is measured as magnitude, a scale to describe how energetic was an earthquake. An earthquake of magnitude 2 is barely perceptible and can be recorded only by using sensitive specialized equipment, while earthquakes of more than magnitude 8 can cause the ground to noticeably shake very hard. An earthquake is generally followed by many aftershocks occurring by a similar mechanism and which are equally devasting and many times their intensity and severity is similar to the original earthquake. Such post-quake tremors occur generally within the first hour or a day after the main earthquake. Forecasting spatial distribution of aftershocks is very challenging.
Wanasayansi wameunda sheria za kijasusi kuelezea ukubwa na wakati wa mitetemeko ya baadaye lakini kubainisha eneo lao bado ni changamoto. Watafiti katika Chuo Kikuu cha Google na Harvard wamebuni mbinu mpya ya kutathmini matetemeko ya ardhi na kutabiri eneo la mitetemeko ya baadaye kwa kutumia teknolojia ya kijasusi katika utafiti wao uliochapishwa katika Nature. Walitumia hasa kujifunza kwa mashine - kipengele cha akili ya bandia. Katika mbinu ya kujifunza kwa mashine, mashine 'hujifunza' kutoka kwa seti ya data na baada ya kupata ujuzi huu inaweza kutumia maelezo haya kufanya ubashiri kuhusu data mpya zaidi.
Watafiti walichambua kwanza hifadhidata ya matetemeko ya ardhi kwa kutumia algoriti za kujifunza kwa kina. Kujifunza kwa kina ni aina ya hali ya juu ya kujifunza kwa mashine ambapo mitandao ya neva hujaribu na kuiga mchakato wa kufikiria wa ubongo wa mwanadamu. Kisha, walilenga kuweza utabiri aftershocks better than random guessing and try to solve the problem of ‘where’ the aftershocks will occur. Observations collected from more than 199 major earthquakes around the world were utilized consisting of around 131,000 mainshock-aftershock pairs. This information was combined with a physics-based model which describing how Ardhi would be strained and tense after an earthquake which will then trigger aftershocks. They created 5 kilometer-square grids within which system would check for an aftershock. The neural network would then form relationships between strains caused by main earthquake and the location of aftershocks. Once neural network system was well-trained in this manner, it was able to predict location of aftershocks accurately. The study was extremely challenging as it used complex real-world data of earthquakes. Researchers alternatively set up bandia na aina ya matetemeko ya ardhi 'bora' kuunda utabiri na kisha kukagua utabiri. Kuangalia matokeo ya mtandao wa neva, walijaribu kuchambua ni 'idadi gani' tofauti ambazo zinaweza kudhibiti utabiri wa mitetemeko ya baadaye. Baada ya kufanya ulinganisho wa anga, watafiti walifikia hitimisho kwamba muundo wa kawaida wa mshtuko 'unaweza kufasiriwa'. Timu inapendekeza kwamba idadi inayoitwa lahaja ya pili ya mvutano wa deviatoriki - inayoitwa J2 - inashikilia ufunguo. Kiasi hiki kinaweza kufasiriwa sana na hutumiwa mara kwa mara katika madini na nyanja zingine lakini haijawahi kutumika hapo awali kusoma matetemeko ya ardhi.
Aftershocks of earthquakes cause further injuries, damage properties and also hinder rescue efforts therefore predicting them would be life-saving for humanity. Real time forecast may not be possible at this very moment as the current AI models can deal with a particular type of aftershock and simple geological fault line only. This is important because geological fault lines have different geometry in diverse geographical location on the sayari. So, it may not be currently applicable to different type of earthquakes around the world. Nevertheless, artificial intelligence technology looks suitable for earthquakes because of n number of variables which need to considered when studying them, example strength of the shock, position of tectonic plates etc.
Mitandao ya neva imeundwa ili kuboreshwa kadri muda unavyopita, yaani kadri data inavyoingizwa kwenye mfumo, ujifunzaji zaidi hufanyika na mfumo kuboreka taratibu. Katika siku zijazo mfumo kama huo unaweza kuwa sehemu muhimu ya mifumo ya utabiri inayotumiwa na wataalam wa seism. Wapangaji wanaweza pia kutekeleza hatua za dharura kulingana na ujuzi wa tabia ya tetemeko la ardhi. Timu inataka kutumia teknolojia ya kijasusi bandia kutabiri ukubwa wa tetemeko la ardhi.
***
{Unaweza kusoma karatasi asili ya utafiti kwa kubofya kiungo cha DOI kilichotolewa hapa chini katika orodha ya (vyanzo) vilivyotajwa}
Chanzo (s)
DeVries PMR et al. 2018. Kujifunza kwa kina kuhusu mifumo ya baada ya tetemeko la ardhi kufuatia matetemeko makubwa ya ardhi. Nature560 (7720).
https://doi.org/10.1038/s41586-018-0438-y
***
