scholarly journals Pitfalls of simulation-based machine learning in optoelectronic device design

2020 ◽  
Author(s):  
Joachim Piprek
Keyword(s):  
Machine Learning ◽  
Design Optimization ◽  
Light Emitting Diode ◽  
Optoelectronic Device ◽  
Point Of View ◽  
Device Physics ◽  
Learning Approaches ◽  
Device Design ◽  
Light Emitting ◽  
Simulation Based

Focusing on GaN-based light-emitting diode (LED) design optimization, this paper evaluates simulation-based machine learning approaches from a device physics point of view. Strategies are suggested for achieving more realistic results.

scholarly journals Pitfalls of simulation-based machine learning in optoelectronic device design

2020 ◽  
Author(s):  
Joachim Piprek
Keyword(s):  
Machine Learning ◽  
Design Optimization ◽  
Light Emitting Diode ◽  
Optoelectronic Device ◽  
Point Of View ◽  
Device Physics ◽  
Learning Approaches ◽  
Device Design ◽  
Light Emitting ◽  
Simulation Based

Focusing on GaN-based light-emitting diode (LED) design optimization, this paper evaluates simulation-based machine learning approaches from a device physics point of view. Strategies are suggested for achieving more realistic results.

scholarly journals Simulation-based Machine Learning for Optoelectronic Device Design: Perspectives, Problems, and Prospects

2021 ◽  
Author(s):  
Joachim Piprek
Keyword(s):  
Machine Learning ◽  
Numerical Simulation ◽  
Real World ◽  
Computational Analysis ◽  
Light Emitting Diode ◽  
Optoelectronic Device ◽  
Point Of View ◽  
Light Emitting ◽  
Simulation Based ◽  
Link Theory

Abstract Numerical simulation and machine learning represent opposite approaches to computational analysis of the real world, deductive vs. inductive. However, both methods suffer from various uncertainties and even their combination often fails to link theory and reality. Focusing on GaN-based light-emitting diode (LED) design optimization, this paper evaluates examples of simulation-based machine learning from a physics point of view. Strategies are suggested for achieving more realistic predictions.

scholarly journals OXIGÊNIO NO CONTEXTO DA COVID-19: O QUE SABEMOS SOBRE A MOLÉCULA QUE RESPIRAMOS E O PAPEL CENTRAL DA QUÍMICA

Química Nova ◽  
2021 ◽  
Author(s):  
Bruna Cerqueira ◽  
Bruna Silva ◽  
Rafael Campos ◽  
Lourenço Santana ◽  
Wilson Lopes ◽  
...  
Keyword(s):  
Light Emitting Diode ◽  
Chemical Characterization ◽  
Point Of View ◽  
Oxygen Production ◽  
Oxygen Saturation Level ◽  
Light Emitting ◽  
Physical Chemical ◽  
Oxygen Cycle ◽  
Oxygen Concentrator

OXYGEN IN THE COVID-19 CONTEXT: WHAT WE KNOW ABOUT THE MOLECULE WE BREATHE AND THE CENTRAL ROLE OF CHEMISTRY. In this work, the role of chemistry in the coronavirus disease 2019 (COVID-19) pandemic is highlighted through the medical oxygen supply crises in Brazil, as an example of oxygen utility in health. Starting from oxygen chemical characterization, the oxygen cycle in nature is discussed to show how oxygen is formed through photosynthesis, followed by the description of the industrial oxygen production from atmospheric air, including physical-chemical aspects. The use of medical oxygen concentrator is presented and how this device works from the chemical point of view. Besides, the noninvasive and painless oximetry is described in terms of how oxygen saturation level in blood is measured using LED - light emitting diode.

scholarly journals Machine-Learning Assisted Prediction of Spectral Power Distribution for Full-Spectrum White Light-Emitting Diode

2020 ◽  
Vol 12 (1) ◽  
pp. 1-18 ◽  
Author(s):  
Jiajie Fan ◽  
Yutong Li ◽  
Irena Fryc ◽  
Cheng Qian ◽  
Xuejun Fan ◽  
...  
Keyword(s):  
Machine Learning ◽  
White Light ◽  
Power Distribution ◽  
Spectral Power ◽  
Light Emitting Diode ◽  
Full Spectrum ◽  
Light Emitting ◽  
Spectral Power Distribution

scholarly journals Measurements for non-intrusive load monitoring through machine learning approaches

ACTA IMEKO ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 90
Author(s):  
Giovanni Bucci ◽  
Fabrizio Ciancetta ◽  
Edoardo Fiorucci ◽  
Simone Mari ◽  
Andrea Fioravanti
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
Point Of View ◽  
Machine Learning Algorithms ◽  
Management Service ◽  
Learning Approaches ◽  
Load Monitoring ◽  
Long Time ◽  
Processing Techniques ◽  
Energy Companies

The topic of non-intrusive load monitoring (NILM) has seen a significant increase in research interest over the past decade, which has led to a significant increase in the performance of these systems. Nowadays, NILM systems are used in numerous applications, in particular by energy companies that provide users with an advanced management service of different consumption. These systems are mainly based on artificial intelligence algorithms that allow the disaggregation of energy by processing the absorbed power signal over more or less long time intervals (generally from fractions of an hour up to 24 h). Less attention was paid to the search for solutions that allow non-intrusive monitoring of the load in (almost) real time, that is, systems that make it possible to determine the variations in loads in extremely short times (seconds or fractions of a second). This paper proposes possible approaches for non-intrusive load monitoring systems operating in real time, analysing them from the point of view of measurement. The measurement and post-processing techniques used are illustrated and the results discussed. In addition, the work discusses the use of the results obtained to train machine learning algorithms that allow you to convert the measurement results into useful information for the user.

Research Into Irradiation Conditions With Led Phyto-Irradiators in Cucumber Plants Cultivating by Photoculture Technology

2021 ◽  
pp. 56-61
Author(s):  
Alexander E. Kurshev ◽  
Sergey D. Bogatyrev ◽  
Olga E. Zheleznikova ◽  
Kirill A. Chmil
Keyword(s):  
Light Emitting Diode ◽  
Methodological Approach ◽  
Experimental Studies ◽  
Point Of View ◽  
Practical Significance ◽  
State University ◽  
Light Emitting ◽  
White Leds ◽  
Biochemical Processes ◽  
Growing Seasons

The article presents the results of two full vegetation growing seasons for Svyatogor F1 cucumber plants sort in photoculture conditions. The studies were carried out on an experimental research hydroponic installation (ERHI) under photosynthetically active photon irradiance EPPFD = (250 ± 10) μmol/s·m2. In the experiment, we used phyto-irradiators (PI) with high-pressure sodium lamps (HPSL) of the DNaZ type, as well as light emitting diode (LED) phyto-irradiators of the combined spectrum. A methodological approach to photobiological research (PBR) in the artificial climate laboratory at the Ogarev Mordovia State University was developed, which allowed us to determine the effect of the radiation of the LED PI combined spectrum on the productivity of cucumber plants under photoculture conditions. On the basis of the conducted experimental studies, it was found that the quality of seedlings grown under a phyto-irradiator with a HPSL of the DNaZ type is better than under a LED PI of the combined spectrum. From the point of view of the productivity of cucumber plants of this variety, the spectrum created by the radiation of white LEDs and radiation of LEDs with peak wavelengths λ = 660 nm and λ = 730 nm turned out to be more favourable. It was revealed that radiation, acting on the photoreceptors of a plant and thus triggering cascades of physiological and biochemical processes, can cause its ambiguous reaction. The practical significance of the results obtained was shown.

scholarly journals A Physics-Informed, Machine Learning Emulator of a 2D Surface Water Model: What Temporal Networks and Simulation-Based Inference Can Help Us Learn about Hydrologic Processes

Water ◽  
2021 ◽  
Vol 13 (24) ◽  
pp. 3633
Author(s):  
Reed M. Maxwell ◽  
Laura E. Condon ◽  
Peter Melchior
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Water Depth ◽  
Current Model ◽  
Time Dependent ◽  
Water Model ◽  
Learning Approaches ◽  
Simulation Based ◽  
3D Cnn ◽  
Learning Architectures

While machine learning approaches are rapidly being applied to hydrologic problems, physics-informed approaches are still relatively rare. Many successful deep-learning applications have focused on point estimates of streamflow trained on stream gauge observations over time. While these approaches show promise for some applications, there is a need for distributed approaches that can produce accurate two-dimensional results of model states, such as ponded water depth. Here, we demonstrate a 2D emulator of the Tilted V catchment benchmark problem with solutions provided by the integrated hydrology model ParFlow. This emulator model can use 2D Convolution Neural Network (CNN), 3D CNN, and U-Net machine learning architectures and produces time-dependent spatial maps of ponded water depth from which hydrographs and other hydrologic quantities of interest may be derived. A comparison of different deep learning architectures and hyperparameters is presented with particular focus on approaches such as 3D CNN (that have a time-dependent learning component) and 2D CNN and U-Net approaches (that use only the current model state to predict the next state in time). In addition to testing model performance, we also use a simplified simulation based inference approach to evaluate the ability to calibrate the emulator to randomly selected simulations and the match between ML calibrated input parameters and underlying physics-based simulation.

Sign in / Sign up

Export Citation Format

Share Document