News > New model helps relieve information overload
Climate is a complicated thing. While a great many scientists and commentators try breaking climate studies down into bite sized chunks for public consumption, the truth of the matter is that it's complicated, very complicated. One of the main problems is the sheer amounts of information satellites and atmospheric sensors generate. "All of the data and information that is continually collected by satellites and sensors can cause tons of problems for scientists, who simply don't have the time to analyze every pixel of every satellite image," said James Wang, professor of information sciences and technology, Penn State University in the US. Along with an international team of researchers professor Wang has developed a program that can identify and list smaller-scale ocean events. The program aims to take in this vast amount of raw data and produce lists of the occurrence and frequency of various types of oceanic events. "Our goal has been to provide a tool that would create useful information or knowledge from this large pool of data," Prof. Wang continued.
Researchers first built a database of ocean structures and then used experts to train the program to recognise and identify specific types of structures like wakes and smaller currents. The program then uses probability theories to analyze ocean changes revealed by satellite images and remote sensors and spot real environmental events. Researchers tested the technology on satellite images of sections of oceans in the Iberian Atlantic, the Mediterranean coast and near the Canary Islands. The tests included 1,000 cases of real ocean features, including 472 upwellings, 180 wakes, 10 anti-cyclonic eddies; they even included 180 previously misclassified images. The tests went well, and the best analytical method developed by the researchers accurately identified the ocean features more than 89% of the time. Just as importantly this method reduced the amount of information needed to identify a structure, making it easier to identify previously difficult to spot features.
It this level of performance is maintained the program could represent a large step forward in climate studies in which the behaviour of the oceans plays a major role. The researchers think that this new method of analysis could offer clues on subtle changes in global climate conditions. So it seems that studying the climate might be about to become just a little less complicated.