AIRLINK 80.55 Increased By ▲ 1.14 (1.44%)
BOP 5.28 Decreased By ▼ -0.05 (-0.94%)
CNERGY 4.39 Increased By ▲ 0.01 (0.23%)
DFML 34.79 Increased By ▲ 1.60 (4.82%)
DGKC 76.90 Increased By ▲ 0.03 (0.04%)
FCCL 20.65 Increased By ▲ 0.12 (0.58%)
FFBL 33.50 Increased By ▲ 2.10 (6.69%)
FFL 9.75 Decreased By ▼ -0.10 (-1.02%)
GGL 10.20 Decreased By ▼ -0.05 (-0.49%)
HBL 118.45 Increased By ▲ 0.52 (0.44%)
HUBC 135.60 Increased By ▲ 1.50 (1.12%)
HUMNL 7.04 Increased By ▲ 0.04 (0.57%)
KEL 4.67 No Change ▼ 0.00 (0%)
KOSM 4.70 Decreased By ▼ -0.04 (-0.84%)
MLCF 37.60 Increased By ▲ 0.16 (0.43%)
OGDC 137.00 Increased By ▲ 0.30 (0.22%)
PAEL 23.04 Decreased By ▼ -0.11 (-0.48%)
PIAA 27.17 Increased By ▲ 0.62 (2.34%)
PIBTL 6.91 Decreased By ▼ -0.09 (-1.29%)
PPL 113.40 Decreased By ▼ -0.35 (-0.31%)
PRL 27.49 Decreased By ▼ -0.03 (-0.11%)
PTC 14.75 No Change ▼ 0.00 (0%)
SEARL 57.00 Decreased By ▼ -0.20 (-0.35%)
SNGP 66.67 Decreased By ▼ -0.83 (-1.23%)
SSGC 11.05 Decreased By ▼ -0.04 (-0.36%)
TELE 9.27 Increased By ▲ 0.04 (0.43%)
TPLP 11.58 Increased By ▲ 0.02 (0.17%)
TRG 71.92 Decreased By ▼ -0.18 (-0.25%)
UNITY 25.60 Increased By ▲ 0.78 (3.14%)
WTL 1.36 Decreased By ▼ -0.04 (-2.86%)
BR100 7,590 Increased By 64.4 (0.86%)
BR30 24,769 Increased By 119.8 (0.49%)
KSE100 72,447 Increased By 475.5 (0.66%)
KSE30 23,926 Increased By 177.4 (0.75%)

SEOUL: Google Inc. could greatly improve the prediction of earthquake aftershocks by using machine learning, a type of artificial intelligence (AI) technology, a scientist from the company said on Tuesday.

In earthquakes, an initial mainshock is typically followed by a series of smaller aftershocks. Forecasting the locations of these aftershocks has become important as they can significantly hamper recovery efforts.

Martin Wattenberg, a senior staff research scientist at Google's People + AI Research initiative (PAIR), has joined hands with a team of researchers from Harvard University to see if they can apply machine learning to explain where aftershocks might occur.

"We applied machine learning algorithms to analyze a database of earthquakes from around the world to try to predict where aftershocks might occur," the scientist told reporters in Seoul by a video conference, adding that the system improved the precision rate to six percent from the previous three percent.

The researchers' neural network system trained on more than 131,000 earthquakes and could predict the locations of aftershocks in an independent test data set of more than 30,000 earthquakes, more accurately than the classic Coulomb method.

Wattenberg said this machine-learning-driven system provides improved forecasts of aftershock locations and identifies physical quantities that may control earthquake triggering during the most active part of the seismic cycle.

"It's still a low precision ... it's not accurate enough for practical use but it's an exciting first step," Wattenberg said. "This is a real improvement, but to be clear, not yet strong enough for practical use."

The scientist said the machine learning-based forecasts may one day help emergency and rescue services, and even inform evacuation plans.

PAIR is a team of AI researchers with the focus on the "human side" of AI, including the relationship between users and technology, Google said. The goal is not just to publish research papers but also releasing open source tools for researchers and other experts to use.

Copyright APP (Associated Press of Pakistan), 2018
 

Comments

Comments are closed.