Predicting Effective Refractive Indices of Multimode Waveguide via Deep Learning

2021 ◽  
Author(s):  
Tianhang Yao ◽  
Tianye Huang ◽  
Yuan Xie ◽  
Zhichao Wu ◽  
Dapeng Luo ◽  
...  
Keyword(s):  
Deep Learning ◽  
Refractive Indices ◽  
Multimode Waveguide

scholarly journals A Physics-Infused Deep Learning Model for the Prediction of Refractive Indices and Its Use for the Large-Scale Screening of Organic Compound Space

2019 ◽  
Author(s):  
Mojtaba Haghighatlari ◽  
Gaurav Vishwakarma ◽  
Mohammad Atif Faiz Afzal ◽  
Johannes Hachmann
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Large Scale ◽  
Organic Molecules ◽  
Learning Model ◽  
Training Data ◽  
Refractive Indices ◽  
Learning Models ◽  
Deep Learning Model ◽  
Machine Learning Models

<div><div><div><p>We present a multitask, physics-infused deep learning model to accurately and efficiently predict refractive indices (RIs) of organic molecules, and we apply it to a library of 1.5 million compounds. We show that it outperforms earlier machine learning models by a significant margin, and that incorporating known physics into data-derived models provides valuable guardrails. Using a transfer learning approach, we augment the model to reproduce results consistent with higher-level computational chemistry training data, but with a considerably reduced number of corresponding calculations. Prediction errors of machine learning models are typically smallest for commonly observed target property values, consistent with the distribution of the training data. However, since our goal is to identify candidates with unusually large RI values, we propose a strategy to boost the performance of our model in the remoter areas of the RI distribution: We bias the model with respect to the under-represented classes of molecules that have values in the high-RI regime. By adopting a metric popular in web search engines, we evaluate our effectiveness in ranking top candidates. We confirm that the models developed in this study can reliably predict the RIs of the top 1,000 compounds, and are thus able to capture their ranking. We believe that this is the first study to develop a data-derived model that ensures the reliability of RI predictions by model augmentation in the extrapolation region on such a large scale. These results underscore the tremendous potential of machine learning in facilitating molecular (hyper)screening approaches on a massive scale and in accelerating the discovery of new compounds and materials, such as organic molecules with high-RI for applications in opto-electronics.</p></div></div></div>

scholarly journals A Physics-Infused Deep Learning Model for the Prediction of Refractive Indices and Its Use for the Large-Scale Screening of Organic Compound Space

2019 ◽  
Author(s):  
Mojtaba Haghighatlari ◽  
Gaurav Vishwakarma ◽  
Mohammad Atif Faiz Afzal ◽  
Johannes Hachmann
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Large Scale ◽  
Organic Molecules ◽  
Learning Model ◽  
Training Data ◽  
Refractive Indices ◽  
Learning Models ◽  
Deep Learning Model ◽  
Machine Learning Models

<div><div><div><p>We present a multitask, physics-infused deep learning model to accurately and efficiently predict refractive indices (RIs) of organic molecules, and we apply it to a library of 1.5 million compounds. We show that it outperforms earlier machine learning models by a significant margin, and that incorporating known physics into data-derived models provides valuable guardrails. Using a transfer learning approach, we augment the model to reproduce results consistent with higher-level computational chemistry training data, but with a considerably reduced number of corresponding calculations. Prediction errors of machine learning models are typically smallest for commonly observed target property values, consistent with the distribution of the training data. However, since our goal is to identify candidates with unusually large RI values, we propose a strategy to boost the performance of our model in the remoter areas of the RI distribution: We bias the model with respect to the under-represented classes of molecules that have values in the high-RI regime. By adopting a metric popular in web search engines, we evaluate our effectiveness in ranking top candidates. We confirm that the models developed in this study can reliably predict the RIs of the top 1,000 compounds, and are thus able to capture their ranking. We believe that this is the first study to develop a data-derived model that ensures the reliability of RI predictions by model augmentation in the extrapolation region on such a large scale. These results underscore the tremendous potential of machine learning in facilitating molecular (hyper)screening approaches on a massive scale and in accelerating the discovery of new compounds and materials, such as organic molecules with high-RI for applications in opto-electronics.</p></div></div></div>

scholarly journals Optimized Multimode Interference Fiber Based Refractometer in A Reflective Interrogation Scheme

Proceedings ◽  
2018 ◽  
Vol 2 (13) ◽  
pp. 1107
Author(s):  
Renato Bellini ◽  
Carolina V. S. Borges ◽  
Bruno Rente ◽  
Maria A. G. Martinez
Keyword(s):  
Fiber Length ◽  
Gold Film ◽  
Single Mode ◽  
Single Mode Fiber ◽  
Refractive Indices ◽  
Multimode Interference ◽  
Multimode Waveguide ◽  
Thin Gold Film ◽  
Broadband Light Source ◽  
Sensitivity Increase

A fiber based refractometer in a reflective interrogation scheme is investigated and optimized. A thin gold film was deposited on the tip of a coreless fiber section, which is spliced with a single mode fiber. The coreless fiber is a multimode waveguide, and the observed effects are due to multimode interference. To investigate and optimize the structure, the multimode part of the sensor is built with 3 different lengths: 58 mm, 29 mm and 17 mm. We use a broadband light source ranging from 1475 nm to 1650 nm and we test the sensors with liquids of varying refractive indices, from 1.333 to 1.438. Our results show that for a fixed wavelength, the sensor sensitivity is independent of the multimode fiber length, but we observed a sensitivity increase of approximately 0.7 nm/RIU for a one-nanometer increase in wavelength.

The spindle stage: A powerful optical tool

1988 ◽  
Vol 46 ◽  
pp. 52-53
Author(s):  
Mickey E. Gunter ◽  
F. Donald Bloss
Keyword(s):  
Significant Error ◽  
Optical Data ◽  
Refractive Indices ◽  
Axis Of Rotation ◽  
Polarizing Microscope ◽  
Microscope Stage

A single, reasonably homogeneous, nonopaque 30-to-300 μm crystal, mounted on a spindle stage and studied by immersion methods under a polarizing microscope, yields optical data frequently sufficient to identify and characterize a substance unequivocally. The data obtainable include (1) the orientation of the crystal's principal vibration axes and (2) its principal refractive indices, to within 0.0002 if desired, for light vibrating along these principal vibration axes. Spindle stages tend to be simple and relatively inexpensive, some costing less than $50. They permit rotation of the crystal about a single axis which is parallel to the microscope stage. This spindle or S-axis is thus perpendicular to the M-axis, namely the microscope stage's axis of rotation.A spindle stage excels when studying anisotropic crystals. It orients uniaxial crystals within minutes and biaxial crystals almost as quickly so that their principal refractive indices - ɛ and ω (uniaxial); α, β and γ (biaxial) - can be determined without significant error from crystal misorientation.

Light microscopy of ceramics

1993 ◽  
Vol 51 ◽  
pp. 908-909
Author(s):  
Walter C. McCrone
Keyword(s):  
Refractive Index ◽  
Light Microscopy ◽  
Light Microscope ◽  
Polarized Light ◽  
Refractive Indices ◽  
Complete Coverage ◽  
The Subject ◽  
Lower Refractive Index

An excellent chapter on this subject by V.D. Fréchette appeared in a book edited by L.L. Hench and R.W. Gould in 1971 (1). That chapter with the references cited there provides a very complete coverage of the subject. I will add a more complete coverage of an important polarized light microscope (PLM) technique developed more recently (2). Dispersion staining is based on refractive index and its variation with wavelength (dispersion of index). A particle of, say almandite, a garnet, has refractive indices of nF = 1.789 nm, nD = 1.780 nm and nC = 1.775 nm. A Cargille refractive index liquid having nD = 1.780 nm will have nF = 1.810 and nC = 1.768 nm. Almandite grains will disappear in that liquid when observed with a beam of 589 nm light (D-line), but it will have a lower refractive index than that liquid with 486 nm light (F-line), and a higher index than that liquid with 656 nm light (C-line).

Deep Learning

2009 ◽  
Author(s):  
Stellan Ohlsson
Keyword(s):  
Deep Learning

On electronic polarizabilities and refractive indices in SbSI crystal

1983 ◽  
Vol 44 (12) ◽  
pp. 349-359
Author(s):  
Wataru Kinase ◽  
Tadataka Morishita ◽  
Yutaka Hiyama ◽  
Tomoo Maeda
Keyword(s):  
Refractive Indices

Intelligence artificielle : le futur de l’Orthodontie ?

2019 ◽  
Vol 53 (3) ◽  
pp. 281-294
Author(s):  
Jean-Michel Foucart ◽  
Augustin Chavanne ◽  
Jérôme Bourriau
Keyword(s):  
Big Data ◽  
Deep Learning ◽  
Intelligence Artificielle ◽  
Set Up

Nombreux sont les apports envisagés de l’Intelligence Artificielle (IA) en médecine. En orthodontie, plusieurs solutions automatisées sont disponibles depuis quelques années en imagerie par rayons X (analyse céphalométrique automatisée, analyse automatisée des voies aériennes) ou depuis quelques mois (analyse automatique des modèles numériques, set-up automatisé; CS Model +, Carestream Dental™). L’objectif de cette étude, en deux parties, est d’évaluer la fiabilité de l’analyse automatisée des modèles tant au niveau de leur numérisation que de leur segmentation. La comparaison des résultats d’analyse des modèles obtenus automatiquement et par l’intermédiaire de plusieurs orthodontistes démontre la fiabilité de l’analyse automatique; l’erreur de mesure oscillant, in fine, entre 0,08 et 1,04 mm, ce qui est non significatif et comparable avec les erreurs de mesures inter-observateurs rapportées dans la littérature. Ces résultats ouvrent ainsi de nouvelles perspectives quand à l’apport de l’IA en Orthodontie qui, basée sur le deep learning et le big data, devrait permettre, à moyen terme, d’évoluer vers une orthodontie plus préventive et plus prédictive.

Sign in / Sign up

Export Citation Format

Share Document