Artificial neural networks for modeling time series of beach litter in the southern North Sea

Autor(en): Schulz, Marcus
Matthies, Michael
Stichwörter: ACCUMULATION; Back propagation; Beach litter category; CONTAMINATION; Environmental Sciences; Environmental Sciences & Ecology; INGESTION; Marine & Freshwater Biology; MARINE DEBRIS; Marine litter; Neural network; PLASTIC DEBRIS; POLLUTION; PREDICTION; Regression analysis; Source category; SYSTEM; Toxicology
Erscheinungsdatum: 2014
Volumen: 98
Startseite: 14
Seitenende: 20
In European marine waters, existing monitoring programs of beach litter need to be improved concerning litter items used as indicators of pollution levels, efficiency, and effectiveness. In order to ease and focus future monitoring of beach litter on few important litter items, feed-forward neural networks consisting of three layers were developed to relate single litter items to general categories of marine litter. The neural networks developed were applied to seven beaches in the southern North Sea and modeled time series of five general categories of marine litter, such as litter from fishing, shipping, and tourism. Results of regression analyses show that general categories were predicted significantly moderately to well. Measured and modeled data were in the same order of magnitude, and minima and maxima overlapped well. Neural networks were found to be eligible tools to deliver reliable predictions of marine litter with low computational effort and little input of information. (C) 2014 Elsevier Ltd. All rights reserved.
ISSN: 01411136
DOI: 10.1016/j.marenvres.2014.03.014

Show full item record

Page view(s)

Last Week
Last month
checked on Feb 26, 2024

Google ScholarTM