scholarly journals Functional Group Identification for FTIR Spectra Using Image-Based Machine Learning Models

2021 ◽  
Author(s):  
Abigail Enders ◽  
Nicole North ◽  
Chase Fensore ◽  
Juan Velez-Alvarez ◽  
Heather Allen
Keyword(s):  
Machine Learning ◽  
Gas Phase ◽  
Functional Groups ◽  
Functional Group ◽  
Spectroscopic Method ◽  
Group Identification ◽  
Spectroscopic Technique ◽  
Ftir Spectra ◽  
Spectral Interpretation ◽  
Time Required

<p>Fourier Transform Infrared Spectroscopy (FTIR) is a ubiquitous spectroscopic technique. Spectral interpretation is a time-consuming process, but it yields important information about functional groups present in compounds and in complex substances. We develop a generalizable model via a machine learning (ML) algorithm using Convolutional Neural Networks (CNNs) to identify the presence of functional groups in gas phase FTIR spectra. The ML models will reduce the amount of time required to analyze functional groups and facilitate interpretation of FTIR spectra. Through web scraping, we acquire intensity-frequency data from 8728 gas phase organic molecules within the NIST spectral database and transform the data into images. We successfully train models for 15 of the most common organic functional groups, which we then determine via identification from previously untrained spectra. These models serve to expand the application of FTIR measurements for facile analysis of organic samples. Our approach was done such that we have broad functional group models that inference in tandem to provide full interpretation of a spectrum. We present the first implementation of ML using image-based CNNs for predicting functional groups from a spectroscopic method.</p>

scholarly journals Functional Group Identification for FTIR Spectra Using Image-Based Machine Learning Models

2021 ◽  
Author(s):  
Abigail Enders ◽  
Nicole North ◽  
Chase Fensore ◽  
Juan Velez-Alvarez ◽  
Heather Allen
Keyword(s):  
Machine Learning ◽  
Gas Phase ◽  
Functional Groups ◽  
Functional Group ◽  
Spectroscopic Method ◽  
Group Identification ◽  
Spectroscopic Technique ◽  
Ftir Spectra ◽  
Spectral Interpretation ◽  
Time Required

<p>Fourier Transform Infrared Spectroscopy (FTIR) is a ubiquitous spectroscopic technique. Spectral interpretation is a time-consuming process, but it yields important information about functional groups present in compounds and in complex substances. We develop a generalizable model via a machine learning (ML) algorithm using Convolutional Neural Networks (CNNs) to identify the presence of functional groups in gas phase FTIR spectra. The ML models will reduce the amount of time required to analyze functional groups and facilitate interpretation of FTIR spectra. Through web scraping, we acquire intensity-frequency data from 8728 gas phase organic molecules within the NIST spectral database and transform the data into images. We successfully train models for 15 of the most common organic functional groups, which we then determine via identification from previously untrained spectra. These models serve to expand the application of FTIR measurements for facile analysis of organic samples. Our approach was done such that we have broad functional group models that inference in tandem to provide full interpretation of a spectrum. We present the first implementation of ML using image-based CNNs for predicting functional groups from a spectroscopic method.</p>

Functional Group Identification for FTIR Spectra Using Image-Based Machine Learning Models

2021 ◽  
Author(s):  
Abigail A. Enders ◽  
Nicole M. North ◽  
Chase M. Fensore ◽  
Juan Velez-Alvarez ◽  
Heather C. Allen
Keyword(s):  
Machine Learning ◽  
Functional Group ◽  
Group Identification ◽  
Ftir Spectra ◽  
Learning Models ◽  
Machine Learning Models

scholarly journals Predicting the Redox Potentials of Phenazine Derivatives using DFT Assisted Machine Learning

2022 ◽  
Author(s):  
Siddharth Ghule ◽  
Soumya Dash ◽  
Sayan Bagchi ◽  
Kavita Joshi ◽  
Kumar Vanka
Keyword(s):  
Machine Learning ◽  
Energy Storage ◽  
Functional Groups ◽  
Functional Group ◽  
Storage Systems ◽  
Green Energy ◽  
Molecular Structures ◽  
Single Type ◽  
Redox Potentials ◽  
Energy Storage Systems

Here, four machine-learning models were employed to predict the redox potentials of phenazine derivatives in DME using DFT. A small dataset of 189 phenazine derivatives having only one type of functional group per molecule (20 unique groups) was used for the training. Models were validated on the external test-set containing new functional groups and diverse molecular structures and achieved reasonable accuracies (R2 > 0.57). Despite being trained on the molecules with a single type of functional group, models were able to predict the redox potentials of derivatives containing multiple and different types of functional groups with reasonable accuracy (R2 > 0.6). This type of performance for predicting redox potential from such a small and simple dataset of phenazine derivatives has never been reported before. Redox Flow Batteries (RFBs) are emerging as promising candidates for energy storage systems. However, new green and efficient materials are required for their widespread usage. We believe that the hybrid DFT-ML approach demonstrated in this report would help in accelerating the virtual screening of phenazine derivatives saving computational and experimental resources. This approach could potentially identify novel molecules for green energy storage systems such as RBF.

scholarly journals FTIR Spectra of N,N,N',N'-Tetraoctyl Diglycolamide Complex in Room Temperature Ionic Liquids

2019 ◽  
Vol 31 (8) ◽  
pp. 1866-1870
Author(s):  
R. Rama
Keyword(s):  
Ionic Liquids ◽  
Functional Groups ◽  
Metal Ion ◽  
Room Temperature ◽  
Spectroscopic Method ◽  
Vibrational Frequencies ◽  
Ftir Spectra ◽  
Room Temperature Ionic Liquids ◽  
Nitrate Ion ◽  
Different Types

The interaction of an octyl derivative of diglycolamide extractant complex in three different types of room temperature ionic liquids (RTILs) was studied by ATR-FTIR spectroscopic method. The shift in stretching vibrational frequencies for the functional groups (C=O and C-O) in the nitrate ion-extractant complexes and metal ion-extractant complexes in room temperature ionic liquids namely, 1-butyl-3-methylimidazolium bis(trifluoromethanesulfonyl)imide ([C4mim][NTf2], 1-butyl-1-methylpyrrolidinium bis(trifluoromethanesulfonyl)imide ([C4mpyr][NTf2]) and 1-butyl-1-methylpiperidinium bis(trifluoromethanesulfonyl)imide ([C4mpip][NTf2]) was compared. These results were also compared with that obtained for molecular diluent system, n-dodecane.

scholarly journals Identification of Freshwater Zooplankton Functional Groups Based on the Functional Traits of Species

2020 ◽  
pp. 290-306
Author(s):  
D. E. Gavrilko ◽  
G. V. Shurganova ◽  
I. A. Kudrin ◽  
B. N. Yakimov
Keyword(s):  
Cluster Analysis ◽  
Functional Groups ◽  
Functional Traits ◽  
Functional Group ◽  
Group Identification ◽  
Trophic Group ◽  
Ecological Groups ◽  
Widespread Species ◽  
Freshwater Zooplankton ◽  
Group Feeding

Information on the functional traits of the most widespread species of freshwater zooplankton (Rotifera, Cladocera, and Copepoda) in European Russia was collected and analyzed. Our database includes 355 species described by 4 traits, namely: maximum body length, trophic group, feeding type, and movement type. Cluster analysis based on Gower's functional distances shows that freshwater zooplankton can be classified into 19 groups with different ecological roles. The characteristics of each identified functional group are presented. We believe it to be fundamentally important to build a unified classification using all available data and applicable characters for all three main taxonomic groups of zooplankton. Comparison with the existing ecological zooplankton classification proposed by Yu. S. Chuikov has demonstrated a number of advantages of our approach. Several ecological groups in Yu. S. Chuikov’s classification are represented by more fractional categories in our classification. Our system of functional groups can be used in studies of the structure of zooplanktocoenoses based on direct cluster analysis and ordination or based on functional distances between samples. To calculate the functional similarity between species, one can use our database of features, which is contained in the Appendix. Analysis based on functional groups gives a better unerstanding of the structure of a community than traditional ordination, which takes into account only the taxonomic affiliation of species. The approach used for functional group identification can be useful in assessing functional diversity and identifying patterns of freshwater zooplanktocoenoses dynamics. The database of functional signs of zooplankton can be used to check the relationship of functional signs with environmental factors.

scholarly journals Statistical and machine learning models for optimizing energy in parallel applications

2019 ◽  
Vol 33 (6) ◽  
pp. 1079-1097 ◽  
Author(s):  
Mark Endrei ◽  
Chao Jin ◽  
Minh Ngoc Dinh ◽  
David Abramson ◽  
Heidi Poxon ◽  
...  
Keyword(s):  
Machine Learning ◽  
Energy Efficiency ◽  
High Performance ◽  
Large Scale ◽  
Energy Use ◽  
Parallel Applications ◽  
Learning Models ◽  
Trade Off ◽  
Time Required ◽  
Machine Learning Models

Rising power costs and constraints are driving a growing focus on the energy efficiency of high performance computing systems. The unique characteristics of a particular system and workload and their effect on performance and energy efficiency are typically difficult for application users to assess and to control. Settings for optimum performance and energy efficiency can also diverge, so we need to identify trade-off options that guide a suitable balance between energy use and performance. We present statistical and machine learning models that only require a small number of runs to make accurate Pareto-optimal trade-off predictions using parameters that users can control. We study model training and validation using several parallel kernels and more complex workloads, including Algebraic Multigrid (AMG), Large-scale Atomic Molecular Massively Parallel Simulator, and Livermore Unstructured Lagrangian Explicit Shock Hydrodynamics. We demonstrate that we can train the models using as few as 12 runs, with prediction error of less than 10%. Our AMG results identify trade-off options that provide up to 45% improvement in energy efficiency for around 10% performance loss. We reduce the sample measurement time required for AMG by 90%, from 13 h to 74 min.

scholarly journals Resilience of Epiphytic Lichens to Combined Effects of Increasing Nitrogen and Solar Radiation

2021 ◽  
Vol 7 (5) ◽  
pp. 333
Author(s):  
Lourdes Morillas ◽  
Javier Roales ◽  
Cristina Cruz ◽  
Silvana Munzi
Keyword(s):  
Global Change ◽  
Solar Radiation ◽  
Functional Groups ◽  
Physiological Response ◽  
Functional Group ◽  
Environmental Drivers ◽  
Combined Effects ◽  
Environmental Stressor ◽  
Comprehensive Understanding ◽  
Direct Sunlight

Lichens are classified into different functional groups depending on their ecological and physiological response to a given environmental stressor. However, knowledge on lichen response to the synergistic effect of multiple environmental factors is extremely scarce, although vital to get a comprehensive understanding of the effects of global change. We exposed six lichen species belonging to different functional groups to the combined effects of two nitrogen (N) doses and direct sunlight involving both high temperatures and ultraviolet (UV) radiation for 58 days. Irrespective of their functional group, all species showed a homogenous response to N with cumulative, detrimental effects and an inability to recover following sunlight, UV exposure. Moreover, solar radiation made a tolerant species more prone to N pollution’s effects. Our results draw attention to the combined effects of global change and other environmental drivers on canopy defoliation and tree death, with consequences for the protection of ecosystems.

Sign in / Sign up

Export Citation Format

Share Document