Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Feb 25, 2026

Protrusion Force Microscopy: A Method to Quantify Forces Developed by Cell Protrusions

Protrusion Force Microscopy: A Method to Quantify Forces Developed by Cell Protrusions

Published on: June 16, 2018

Feedforward neural network methodology to characterize thin films by Electrostatic Force Microscopy.

M Konomi¹, G M Sacha¹

¹Universidad Autónoma de Madrid, Campus de Cantoblanco. Madrid 28049, Spain.

Ultramicroscopy

|August 2, 2017

Summary

This study introduces a novel numerical method using neural networks to enhance thin film characterization. The approach effectively analyzes tip-sample interactions, even with incomplete or noisy experimental data.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Influence of COVID-19 confinement on students' performance in higher education.

PloS one·2020

Same author

A Model for the Characterization of the Polarizability of Thin Films Independently of the Thickness of the Film.

The journal of physical chemistry. B·2017

Same author

Artificial intelligence in nanotechnology.

Nanotechnology·2013

Same author

Fast and non-invasive conductivity determination by the dielectric response of reduced graphene oxide: an electrostatic force microscopy study.

Nanoscale·2012

Same author

Enhanced dielectric constant resolution of thin insulating films by electrostatic force microscopy.

Journal of physics. Condensed matter : an Institute of Physics journal·2012

Same author

Dipolar origin of water etching of amino acid surfaces.

Physical chemistry chemical physics : PCCP·2011

Area of Science:

Materials Science
Computational Physics
Surface Science

Background:

Accurate characterization of thin films is crucial for material science applications.
Existing numerical methods often struggle with the macroscopic shape of the tip in tip-sample interactions.
Experimental data in thin film characterization can be incomplete or affected by noise, especially at small tip-sample distances.

Purpose of the Study:

To introduce an improved numerical method for automatic thin film characterization.
To enhance the effectiveness of numerical methods by incorporating the tip's macroscopic shape.
To develop a robust method for analyzing thin films even with compromised experimental data.

Main Methods:

Combination of feedforward neural network architectures (Adaline and multilayer perceptron).

Keywords:

Electrostatic Force Microscopy Electrostatic signal simulation Evolutionary algorithms Green function Thin film classification

More Related Videos

Atomic Force Microscopy Imaging and Force Spectroscopy of Supported Lipid Bilayers

Atomic Force Microscopy Imaging and Force Spectroscopy of Supported Lipid Bilayers

Published on: July 22, 2015

Finite Element Modelling of a Cellular Electric Microenvironment

Finite Element Modelling of a Cellular Electric Microenvironment

Published on: May 18, 2021

Related Experiment Videos

Last Updated: Feb 25, 2026

Protrusion Force Microscopy: A Method to Quantify Forces Developed by Cell Protrusions

Protrusion Force Microscopy: A Method to Quantify Forces Developed by Cell Protrusions

Published on: June 16, 2018

Atomic Force Microscopy Imaging and Force Spectroscopy of Supported Lipid Bilayers

Atomic Force Microscopy Imaging and Force Spectroscopy of Supported Lipid Bilayers

Published on: July 22, 2015

Finite Element Modelling of a Cellular Electric Microenvironment

Finite Element Modelling of a Cellular Electric Microenvironment

Published on: May 18, 2021

Redefinition of Adaline architecture using Green functions from Laplace equation for charge calculation.

Adaptation of multilayer perceptron with evolutionary algorithms for training, optimizing for missing or noisy data.

Modulation of the fit function to improve network performance under adverse experimental conditions.

Main Results:

A complete training set for thin film characterization can be efficiently obtained.
The proposed method effectively calculates electrostatic charges within the tip.
The multilayer perceptron, trained with evolutionary algorithms, demonstrates high efficiency in characterizing thin films with missing or noisy data.
Successful discrimination of conductive properties from altered force curves simulating experimental noise.

Conclusions:

The novel numerical method significantly improves automatic thin film characterization.
The integration of specific neural network architectures and evolutionary algorithms offers a robust solution for handling experimental data limitations.
This approach provides a reliable means to analyze thin film properties, even under challenging experimental conditions.