English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Accurate estimation of depth of contaminated zone D and the quantity of pollutant injected into a soil Q after an accidental pollution occurred in road transport is essential to asses the risk of water resources contamination. This paper presents a method for estimating D and Q after an accidental pollutant discharge at the soil surface. First a database is generated from simulated cases using a finite element model. For each case, D and Q are computed as a function of the most related parameters. Different feedforward artificial neural networks with error backpropagation are trained and tested using subsets of the database, and the ability of these networks to generalize on independent simulated data are validated on another subset of the database. Their behavior is compared and analyzed with regard to more common multilinear regression approximation tool. The proposed method is used to analyze the risk for a DNAPL pollution of groundwater resources concerned by a road project in the north of France.

Estimation de la migration d’une pollution accidentelle dans un projet routier à l’aide des réseaux de neurones artificiels