Approximate life cycle assessment of product concepts using multiple regression analysis and artificial neural networks

2003 ◽  
Vol 17 (12) ◽  
pp. 1969-1976 ◽  
Author(s):  
Ji Hyung Park ◽  
Kwang-Kyu Seo
Keyword(s):  
Neural Networks ◽  
Regression Analysis ◽  
Artificial Neural Networks ◽  
Life Cycle Assessment ◽  
Life Cycle ◽  
Multiple Regression Analysis ◽  
Multiple Regression ◽  
Artificial Neural ◽  
Product Concepts

scholarly journals Life Cycle Assessment of Seabass (Dicentrarchus labrax) Produced in Offshore Fish Farms: Variability and Multiple Regression Analysis

2019 ◽  
Vol 11 (13) ◽  
pp. 3523 ◽  
Author(s):  
Benjamín García García ◽  
Caridad Rosique Jiménez ◽  
Felipe Aguado-Giménez ◽  
José García García
Keyword(s):  
Regression Analysis ◽  
Life Cycle Assessment ◽  
Life Cycle ◽  
Multiple Regression Analysis ◽  
Multiple Regression ◽  
Environmental Impacts ◽  
Dicentrarchus Labrax ◽  
Regression Coefficients ◽  
Feeding System ◽  
Fish Farms

Equations were developed through multiple regression analysis (MRA) to explain the variability of potential environmental impacts (PEIs) estimated by life cycle assessment (LCA). The case studied refers to the production of seabass in basic offshore fish farms. Contribution analysis showed that the components of the system which most influence the potential environmental impacts are the feed (54% of the overall impact) and the fuel consumed by vessels operating in the farm (23%). Feed and fuel varied widely from one fish farm to another due to different factors, such as the efficiency of the feeding system used in each of them, or the distance from the harbor to the farm. Therefore, a number of scenarios (13) were simulated with different values of both factors and the results of the PEI were fitted by MRA to the model: PEI = a + b × Feed + c × Fuel. For all the PEIs, the regression coefficients were significant (p < 0.05) and R2 was 1. These equations allow us to estimate simply and quickly very different scenarios that reflect the reality of different farms at the present time, but also future scenarios based on the implementation of technologies that will decrease both feed and fuel consumption.

Sign in / Sign up

Export Citation Format

Share Document