xi's moments
Home | Technology

AI map launched to predict waterlogged areas

By ZHANG YANGFEI | chinadaily.com.cn | Updated: 2018-05-31 20:20

A Chinese map app added a new function for predicting and marking waterlogged areas in real time by launching a new version on Thursday. The predictions for waterlogged areas will be accurate, fast and cover the whole country soon, the product manager Li Qiang said.

The new version of the app - the Amap -- will initially cover information on waterlogged areas in 17 cities and is expected to cover the entire nation by mid-June before the flood season.

It will also be able to send weather alerts to users and will automatically avoid waterlogged roads while planning routes.

The new version was jointly developed with China Meteorological Administration. It has created a template to analyze a massive amount of data on traffic and meteorological information, which will help to predict and mark waterlogged areas in real time on the app.

Li said the updated map will also enhance interaction with its users to improve accuracy. Users near a marked waterlogged area could rate it on the map regarding whether the prediction is correct or not.

According to Li, the previous map could only report waterlogged areas after they formed, which could not prevent pedestrians or cars from being stuck in the water or even drowning.

"There's a difference between monitoring and predicting," said Chen Yonghai, the vice-president of Amap. "Only predicting can help our users have a safer and better trip."

"People often think that a map is just for locating things and finding directions, but we want to blend more dynamic information into it to give our users a more real and three-dimensional experience," he added.

Global Edition
BACK TO THE TOP
Copyright 1995 - . All rights reserved. The content (including but not limited to text, photo, multimedia information, etc) published in this site belongs to China Daily Information Co (CDIC). Without written authorization from CDIC, such content shall not be republished or used in any form. Note: Browsers with 1024*768 or higher resolution are suggested for this site.
License for publishing multimedia online 0108263

Registration Number: 130349