Premium
A GENETIC ALGORITHM TO REDUCE STREAM CHANNEL CROSS SECTION DATA 1
Author(s) -
Berenbrock Charles
Publication year - 2006
Publication title -
jawra journal of the american water resources association
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.957
H-Index - 105
eISSN - 1752-1688
pISSN - 1093-474X
DOI - 10.1111/j.1752-1688.2006.tb03845.x
Subject(s) - genetic algorithm , cross section (physics) , section (typography) , genetic data , algorithm , data point , computer science , channel (broadcasting) , cross sectional data , software , data mining , statistics , mathematics , machine learning , telecommunications , population , physics , quantum mechanics , programming language , operating system , demography , sociology
A genetic algorithm (GA) was used to reduce cross section data for a hypothetical example consisting of 41 data points and for 10 cross sections on the Kootenai River. The number of data points for the Kootenai River cross sections ranged from about 500 to more than 2,500. The GA was applied to reduce the number of data points to a manageable dataset because most models and other software require fewer than 100 data points for management, manipulation, and analysis. Results indicated that the program successfully reduced the data. Fitness values from the genetic algorithm were lower (better) than those in a previous study that used standard procedures of reducing the cross section data. On average, fitnesses were 29 percent lower, and several were about 50 percent lower. Results also showed that cross sections produced by the genetic algorithm were representative of the original section and that near‐optimal results could be obtained in a single run, even for large problems. Other data also can be reduced in a method similar to that for cross section data.