In the marble halls of a luxury hotel, the main experts are discussing a new approach to an ancient problem: how to make it rain in the EAA, the rich Gulf State that is found in one of the largest deserts in the world.
Decades of work and millions of dollars have been plowed to facilitate the endless drought in the eau rich in oil, whose mainly expatrified population rises without flinching due to a dry and hostile climate and summer heat.
Despite the best efforts of the United Arab Emirates, the rain is still rare.
But in the Rain Rain International Forum in Abu Dhabi, the officials maintained a new hope: to take advantage of artificial intelligence to expel more humidity than often clouds.
Among the initiatives is an AI system to improve cloud planting, the practice of using plans to shoot salt or other chemicals in clouds to increase rain.
“It is quite finished,” said Luca Delle Monache, deputy director of the Western Climate Center and water ends at the San Diego Scripps Oceanography Institution of the University of California.
“We are making the final touches.”
However, Delle Monache admitted that AI was not a “silver bullet” for the EAU, which like other countries have followed the planting of clouds for decades.
Sowing in the cloud works by increasing the size of the drops, which then falls like rain. It is estimated that rain will increase by 10-15 percent, said Delle Monache.
But it only works with certain types of fans of clusters, and can even suppress the rain if it is not done correctly.
“You have to do it in the right place at the right time. That is why we use artificial intelligence, ”he added.
Prayers, applause
The three -year project, financed with $ 1.5 million of the EAU rain improvement program, feeds satellite, radar and meteorological data in an algorithm that predicts where clouds will be formed in the next six hours.
It promises to advance in the current method where cloud flights are led by experts who study satellite images.
Hundreds of those flights occur annually in the EAU.
With only about 100 millimeters (3.9 inches) of annual rainfall, the almost 10 million people of the EAU depend mainly on desalted water, with plants that produce approximately 14 percent of the total world, according to official figures.
The population is foreign of 90 percent and has increased almost 30 times since the foundation of the EAU in 1971.
People concentrate on the big cities of Dubai, Abu Dhabi and Sharjah, shelters that embrace the coast of the vast interior of the Arab desert.
However, the country still needs groundwater, replaced by rain and encouraged by a series of dams, for agriculture and industry.
Although Eau officials say that rain has increased, downpours are still so unusual that it is known that children in school explode in applause and applaud the classroom windows for a better view.
The rain, even the artificial variety, is exotic enough to be a leisure attraction: on Raining Street in Dubai, visitors pay 300 Dirhams ($ 81) to walk in the false drizzle.
Asking for prayers for rain is a long -standing practice of the gulf ruling families.
The memorable exception was last April, when the strongest records in record closed the main international air center of Dubai and flooded roads, paralyzing the city for days.
‘Very niche’ area ‘
Looking for solutions, the EAU in 2017 began to celebrate the Rain Forum, which has now seen seven editions. His rain improvement program has delivered $ 22.5 million in subsidies for a decade.
“When it comes to cloud seeds, this program here is the best in the world,” said Delle Monache in the forum, held near the Presidential Palace and next to the ADNOC headquarters, the state oil firm.
“It is a very niche area in atmospheric science. There are few experts in the world and now they are almost all here. “
The algorithm of his team was not the only use of AI in the discussion.
Marouane Temimi, an associated professor at the Stevens Institute of Technology in New Jersey, described a system developed by the United States that uses automatic learning to track the path and impact of storms in real time.
However, Temimi, like Delle Monache, was also cautious about AI solutions, warning that there were clear limits.
The lack of detailed data on the composition of the cloud, a common problem, since the monitoring team is expensive, hinders precise predictions even with AI, Temimi said.
“I would say that we still have some work to do just because we have data, but not enough data to train models correctly,” he told AFP.
The enthusiasm for AI was also attenuated by Loic Fauchon, president of the World Government, Commercial, UN Government and other groups.
“Be careful. Try to find the correct balance between artificial intelligence and human intelligence,” he told the conference.
“Do not go too fast to artificial intelligence. Humanity is probably the best [option]. “
