Algorithms: They’re not just for Amazon recommendations and online dating anymore. The latest application, as per the New Scientist: Battling oriental fruit flies, a species that inspires the cold sweats in anyone who makes his livelihood on a fruit orchard.
These pests are a far more serious threat than the nuisances spawned by slovenly kitchen habits. They infest at least 230 different kinds of crops. The result? Rotten, maggot-infested fruit and crop losses that can add up to billions of dollars.
Luckily, scientists in Taiwan–where the bugs are a persistent problem–are working on a solution:
In Taiwan, fruit fly populations are normally monitored using traps that are manually checked every 10 days. Cheng-Long Chuang and colleagues at the National Taiwan University in Taipei wanted to automate the counting process, so they placed infrared beams in the traps. Each trap records when the beam is broken, indicating that an oriental fruit fly has entered, attracted by a chemical designed to lure the insect. The results collected are sent via radio to a local station every 30 minutes, allowing real-time measurements of the population.
Cool, right? However, the next step sounds just a tiny bit like a Skynet for insects:
Part-funded by the Taiwanese government, the team have so far set up 240 traps on fruit farms around the country. Machine learning algorithms pool the continuous data arriving from each of these traps and predict when the local fruit fly population is about to explode.
When conditions go critical, government officials get a heads up via text message, allowing them to deploy insecticide.
We can’t help but be a little concerned at the thought of an unfriendly artificial intelligence targeting creatures that a) spread rapidly and b) wreak havoc on the environment around them. Somebody better give the Singularitarians the bad news.