NOMAD Summer
A hands-on course on tools for novel-materials discovery
September 25-29, 2017, Berlin

NOMAD summer tuturials


Since most hands-on sessions will be web-based, we advise the participants to make an account on NOMAD to access the services within a personal workspace, and keep their work after the NOMAD school. To create an account go to and click on the green “Login” in the gray bar, or follow the instructions in the API tutorial.

1. Advanced Graphics

An extensive tutorial on the remote-visualization classes is provided in printed form. Alternatively it can be downloaded from For connecting to the remote visualization service, please use this URL and replace SESSION by the name of the session that has been assigned to you.

2. NOMAD Encyclopedia

With this tutorial you will familiarize with the NOMAD Encyclopedia, its application program interface (API), and the custom-made 3D viewer.

3. High-throughput Calculations & Data Quality

The Atomic Simulation Environment and genetic algorithms: This tutorial gives an introduction to the genetic algorithm (GA) in the Atomic Simulation Environment (ASE) and how it can be used to facilitate high-throughput calculations. In the tutorial we will determine the convex hull of a binary metal slab and in the process get to know different variants of the GA, so that afterwards we will know how to best setup the GA for an optimization problem with a large phase space. In order to run the tutorial in the computer lab, you need to run the following command on the command line:

$ export PYTHONPATH=/users/ext/nomad20/.local/lib/python3.4/site-packages:$PYTHONPATH

Then download and unzip this archive. You then need to run the jupyter notebook pointing to the notebook in the folder you unzipped:

$ jupyter-notebook ga_convex_hull_ase.ipynb

Tutorial on the GA implementation in ASE

4. Data Analytics I: Overview and Structure Prediction

Predicting energy differences between crystal structures: (Meta-)stability of octet-binary compounds: This tutorial shows how to find descriptive parameters (short formulas) that predict the crystal structure (here, rocksalt (RS), zincblende (ZB), CsCl, NiAs or CrB), using the example of octet binary compounds. It is based on the algorithm Sure Independence Screening followed by L0 minimization (SIS+L0), that enables to search for optimal descriptor by scanning huge feature spaces. Link to the tutorial

Hands-on Workshop Density-Functional Theory and Beyond: Compressed sensing for identifying descriptors: Fully fledged tutorial for understanding both the methodology and the data stream of the first tutorial. Link to the tutorial

5. Data Analytics II: Cluster Expansion & Thermodynamics

The tutorials can be accessed by clicking on the “Dashboard” tab in Once there, open the shared notebook clusterX-x1.bkr for the example of a surface AlNa alloy or clusterX-x2.bkr for the example of a binary SiGe alloy.

6. Data Analytics III: Materials Properties Prediction

NOMAD - Subgroup Discovery Toolkit: Subgroup discovery (SGD) is a data mining technique that allows for the discovery of structure in data. It reveals subsets in a given dataset that have unusual or exceptional properties and characterizes such revealed subsets with a natural-language style description. Link to the tutorial

The face of crystals: Insightful Classification using Deep Learning: This tutorial enables users to interactively reproduce the main results of the manuscript: Ziletti, D. Kumar, M. Scheffler, and L. M. Ghiringhelli: The face of crystals: Insightful Classification using Deep Learning. It is also possible to explore different settings, and thus create new results using the deep-learning-based methodology introduced in the manuscript. Link to the tutorial;Link to the preprint

7. Data Analytics IV: Kernel Methods

Complexity tool estimator for accurate forces learning: Monocrystalline Silicon example.: The goal of this tutorial is to show a possible application of kernel methods for forces prediction using nomad data and nomad infrastructure. This example is for classical MD data. The user can access the tutorial by:

Learning atomic charges: In this tutorial, we will use Gaussian process regression, GPR (or equivalently, Kernel Ridge Regression, KRR) to train and predict charges of atoms in small organic molecules. This tutorial is accessible from:

Classification of grain boundaries in Fe: In this tutorial we will be using a machine learning method (clustering) to analyse results of Grain Boundary (GB) calculations of alpha-iron. This tutorial is accessible from: