|
By Phil Williams
pwilliam@franklin.uga.edu
They’re out there, chomping away. Gypsy moths and spruce budworms can defoliate entire forests in short order. Consequently, several times a year, specially equipped airplanes and helicopters set out to deposit loads of pesticide over thousands of acres.
The good news is that careful planning and precise aerial spraying can kill the pests before they grow out of the larval stage and begin to gnaw through the forest canopy. The bad news is that there’s much room for improvement in how the pesticides are targeted on forests.
That’s why a team that includes a UGA computer scientist is, for the first time, using artificial intelligence tools called genetic algorithms to control how aerial-spraying application models do their work. The new system has been tested successfully in the lab and could be in field trials by the end of this year.
“This research is about what happens to the spray when it leaves the aircraft,” says Don Potter, a researcher with UGA’s Artificial Intelligence Center and associate professor in the department of computer science. “Our job is finding a better way to get the spray from the air to the ground.”
The project is funded by the U.S. Forest Service. The scientists on the team, in addition to Potter, came from the forest service and from a private company in Princeton, N.J.
Potter presented research on the spray modeling and application technology at the International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems in New Orleans in June, where it won Best Paper Award. A description of the work will be published this fall.
The fight against the gypsy moth and the spruce budworm is not new. Decades ago, aerial sprayers began saturating some areas of the northeast with DDT to control the rapacious forest-eating moths. Unfortunately, the considerable unintended effects of DDT included the systematic softening of bird eggshells. When federal officials banned DDT, the race was on to find another pesticide.
Scientists developed a better spray using a naturally occurring insecticide called Bacillus thuringiensis, or Bt. Because it is specific to caterpillar species, Bt is sounder ecologically--it controls gypsy moths and spruce budworms without harming other species.
At the same time, scientists and government officials were realizing that broadcast spraying wasn’t the best way to control forest pests, either. What they needed was a computer program that could take all the variables into account--wind speed, airplane altitude and humidity. A succession of such programs was developed by the U.S. Army and the forest service, each an improvement over earlier models.
“Problems still remained, though, and the forest service started to look at things in another way,” Potter explains. “The earlier simulations assume you know all the parameters--you’d input them, and the model would give you answers about how best to spray. What they needed was a system where a pilot could put in the desired spray results and then let the system figure out how best to achieve these results. It would be like listening to an expert.”
Potter and his colleagues thought the answer might lie in genetic algorithms. These computer programs are decision-making rather than just simulation models. A genetic algorithm takes the initial input from a human expert and then uses that knowledge to make extremely fine distinctions in problem-solving and to recommend the best solutions.
Though genetic algorithms had never been used in sprayer modeling before, the results so far in the laboratory have been encouraging, Potter says. The team’s spray application is called SAGA--an acronym for Spray Advisor Genetic Algorithm. The researchers combined a genetic algorithm with a slightly modified version of an earlier model to produce it.
The variables that SAGA controls include aircraft altitude, nozzle type and number, airplane characteristics, environmental characteristics such as humidity, and aircraft flight pattern. The knowledge of the expert system is embedded in such a way that the computer makes an extremely sensitive analysis of how the insecticide should best be sprayed.
According to Potter, the SAGA system generates that analysis in 30 minutes to two hours, depending on the complexity of the situation. The pilot can then feed those results into an on-board computer that would completely control all spraying from the aircraft. The result would be a precision spray taking advantage of an advanced analysis of numerous variables.
The next step will be to incorporate global-positioning satellite information into the program so that information about terrain can be added. When SAGA is finished, it will be made available to private sprayers as well as to the Forest Service where it was developed--although it would probably have to be modified for crop spraying.
“There’s no reason it shouldn’t work on crops, though,” says Potter.
|
|
