scholarly journals Comparing molecules and solids across structural and alchemical space

2016 ◽  
Vol 18 (20) ◽  
pp. 13754-13769 ◽  
Author(s):  
Sandip De ◽  
Albert P. Bartók ◽  
Gábor Csányi ◽  
Michele Ceriotti
Keyword(s):  
Machine Learning ◽  
General Procedure ◽  
Energy Landscapes ◽  
Precise Machine

A general procedure to compare molecules and materials powers insightful representations of energy landscapes and precise machine-learning predictions of properties.

scholarly journals Quantum Chemistry Meets Machine Learning

2019 ◽  
Vol 73 (12) ◽  
pp. 983-989 ◽  
Author(s):  
Alberto Fabrizio ◽  
Benjamin Meyer ◽  
Raimon Fabregat ◽  
Clemence Corminboeuf
Keyword(s):  
Machine Learning ◽  
Statistical Learning ◽  
Quantum Chemical ◽  
Large Scale ◽  
Organic Molecules ◽  
Chemical Properties ◽  
Learning Approaches ◽  
Energy Landscapes ◽  
Free Energy Landscapes ◽  
Large Scale Screening

In this account, we demonstrate how statistical learning approaches can be leveraged across a range of different quantum chemical areas to transform the scaling, nature, and complexity of the problems that we are tackling. Selected examples illustrate the power brought by kernel-based approaches in the large-scale screening of homogeneous catalysis, the prediction of fundamental quantum chemical properties and the free-energy landscapes of flexible organic molecules. While certainly non-exhaustive, these examples provide an intriguing glimpse into our own research efforts.

scholarly journals Detection of Novel Corona Virus Using Machine Learning and Image Recognition

2020 ◽  
Vol 6 (12) ◽  
pp. 394-397
Author(s):  
Dhruv Garg and Saurabh Gautam
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Recent Past ◽  
Great Precision ◽  
The Past ◽  
Corona Virus ◽  
The World ◽  
Affected Person ◽  
Precise Machine ◽  
Self Learning

In the recent past whole of the world has come to a standstill due to a novel airborne virus. The airborne nature of this disease has made it highly contagious which has led to a great number of people being infected very fast. This requires a new method of testing that is faster and more precise. Machine Learning has allowed us to develop sophisticated self-learning models that can learn from data being fed and decide on entirely new options. In the past we have used different Machine Learning algorithm to make models on different biomedical dataset to detect various kind of acute or chronic diseases. Here we have developed a model that successfully detects severe cases of Novel corona virus affected person with great precision.

The Interplay among Molecular Structures, Crystal Symmetries and Lattice Energy Landscapes Revealed by Unsupervised Machine Learning: A Closer Look at Pyrrole Azaphenacenes

2019 ◽  
Author(s):  
Jack Yang ◽  
Nathan Li ◽  
Sean Li
Keyword(s):  
Crystal Structure ◽  
Machine Learning ◽  
Crystal Engineering ◽  
Crystal Packing ◽  
Similarity Index ◽  
Lattice Energy ◽  
Molecular Structures ◽  
Machine Learning Techniques ◽  
Specific Reference ◽  
Energy Landscapes

The ability to perform large-scale crystal structure predictions (CSP) have significantly advanced the synthesis of functional molecular solids by designs. In our recent work [Chem. Mater., 30, 4361 (2018)], we demonstrated our latest developments in organic CSPs by screening a set of 28 pyrrole azaphenacene isomers which led to one new molecule with higher thermodynamic stability and carrier mobilities in its crystalline form, compared to the one reported experimentally. Hereby, using the lattice energy landscapes for pyrrole azaphenacenes as examples, we applied machine-learning techniques to statistically reveal in more details, on how molecular symmetry and Z' values translate to the crystal packing landscapes, which in terms affect the coverage of landscape through quasi-random crystal structure samplings. A recurring theme in crystal engineering is to identify the probabilities of targeting isostructures to a specific reference crystal upon chemical functionalisations. For this, we propose here a global similarity index in conjunction with the Energy-Density Isostructurality (EDI) map to analyse the lattice energy landscapes for halogen substituted pyrrole azaphenacenes. A continue effort in the field is to accelerate CSPs for sampling a much wider chemical space for high-throughput material screenings, we propose a potential solution to this challenge drawn upon this study. Our work will hopefully stimulate the crystal engineering community in adapting a more statistically-oriented approach in understanding crystal packing of organic molecules in the age of digitisation.

Using Machine Learning for processing Big Data of Copernicus Satellite Sensors at the Example of the TROPOMI / Sentinel-5 Precursor and Sentinel-4 Cloud Product

2020 ◽  
Author(s):  
Fabian Romahn ◽  
Athina Argyrouli ◽  
Ronny Lutz ◽  
Diego Loyola ◽  
Victor Molina Garcia
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Neural Networks ◽  
General Procedure ◽  
Training Data ◽  
Machine Learning Techniques ◽  
Critical Parameters ◽  
Observation Data ◽  
Computational Performance ◽  
Retrieval Algorithms

<p>The satellites of the Copernicus program show the increasing relevance of properly handling the huge amount of Earth observation data, nowadays common in remote sensing. This is further challenging if the processed data has to be provided in near real time (NRT), like the cloud product from TROPOMI / Sentinel-5<!-- The slash has spaces before “TROPOMI” and after “Sentinel-5”, which is inconsistent with the lack of spaces in the title. --> Precursor (S5P) or the upcoming Sentinel-4 (S4) mission.</p><p>In order to solve the inverse problems that arise in the retrieval of cloud products, as well as in similar remote sensing problems, usually complex radiative transfer models (RTMs) are used. These are very accurate, however also computationally very expensive and therefore often not feasible in combination with NRT requirements. With the recent significant breakthroughs in machine learning, easier application through better software and more powerful hardware, the methods of this field have become very interesting as a way to improve the classical remote sensing algorithms.</p><p>In this presentation we show how artificial neural networks (ANNs) can be used to replace the original RTM in the ROCINN (Retrieval Of Cloud Information using Neural Networks) algorithm with sufficient accuracy while increasing the computational performance at the same time by several orders of magnitude.</p><p>We developed a general procedure which consists of smart sampling, generation and scaling of the training data, as well as training, validation and finally deployment of the ANN into the operational processor. In order to minimize manual work, the procedure is highly automated and uses latest technologies such as TensorFlow. It is applicable for any kind of RTMs and thus can be used for many retrieval algorithms like it is already done for ROCINN in S5P and will be soon for ROCINN in the context of S4. Regarding the final performance of the generated ANN, there are several critical parameters which have a high impact (e.g. the structure of the ANN). These will be evaluated in detail. Furthermore, we also show general limitations of ANNs in comparison with RTMs, how this can lead to unexpected side effects and ways to cope with these issues.</p><p>With the example of ROCINN, as part of the operational S5P and upcoming S4 cloud product, we show the great potential of machine learning techniques in improving the performance of classical retrieval algorithms and thus increasing their capability to deal with much larger data quantities. However, we also highlight the importance of a proper configuration and possible limitations.</p>

scholarly journals Energy landscapes for machine learning

2017 ◽  
Vol 19 (20) ◽  
pp. 12585-12603 ◽  
Author(s):  
Andrew J. Ballard ◽  
Ritankar Das ◽  
Stefano Martiniani ◽  
Dhagash Mehta ◽  
Levent Sagun ◽  
...  
Keyword(s):  
Machine Learning ◽  
Energy Landscapes ◽  
Molecular Science

The energy landscapes framework developed in molecular science provides new insight in the field of machine learning.

A03 Precise machine-learning suggests that neuronal death in HD is mainly driven by the loss of homeostatic responses

2021 ◽  
Author(s):  
Lucile Mégret ◽  
Barbara Gris ◽  
Satish Sasidharan Nair ◽  
Jasmin Cevost ◽  
Mary Wertz ◽  
...  
Keyword(s):  
Machine Learning ◽  
Neuronal Death ◽  
Precise Machine

Machine learning of ab-initio energy landscapes for crystal structure predictions

2019 ◽  
Vol 158 ◽  
pp. 414-419 ◽  
Author(s):  
Shreyas Honrao ◽  
Bryan E. Anthonio ◽  
Rohit Ramanathan ◽  
Joshua J. Gabriel ◽  
Richard G. Hennig
Keyword(s):  
Crystal Structure ◽  
Machine Learning ◽  
Ab Initio ◽  
Energy Landscapes

scholarly journals Energy landscapes for a machine learning application to series data

2016 ◽  
Vol 144 (12) ◽  
pp. 124119 ◽  
Author(s):  
Andrew J. Ballard ◽  
Jacob D. Stevenson ◽  
Ritankar Das ◽  
David J. Wales
Keyword(s):  
Machine Learning ◽  
Series Data ◽  
Energy Landscapes
Sign in / Sign up

Export Citation Format

Share Document