Hans Fangohr

Isaac Labrie-Boulay, Thomas Brian Winkler, Daniel Franzen et al.

One of the most important magnetic spin structure is the topologically stabilised skyrmion quasi-particle. Its interesting physical properties make them candidates for memory and efficient neuromorphic computation schemes. For the device operation, detection of the position, shape, and size of skyrmions is required and magnetic imaging is typically employed. A frequently used technique is magneto-optical Kerr microscopy where depending on the samples material composition, temperature, material growing procedures, etc., the measurements suffer from noise, low-contrast, intensity gradients, or other optical artifacts. Conventional image analysis packages require manual treatment, and a more automatic solution is required. We report a convolutional neural network specifically designed for segmentation problems to detect the position and shape of skyrmions in our measurements. The network is tuned using selected techniques to optimize predictions and in particular the number of detected classes is found to govern the performance. The results of this study shows that a well-trained network is a viable method of automating data pre-processing in magnetic microscopy. The approach is easily extendable to other spin structures and other magnetic imaging methods.

Hans Fangohr, Maximilian Albert, Matteo Franchin

We review design and development decisions and their impact for the open source code Nmag from a software engineering in computational science point of view. We summarise lessons learned and recommendations for future computational science projects. Key lessons include that encapsulating the simulation functionality in a library of a general purpose language, here Python, provides great flexibility in using the software. The choice of Python for the top-level user interface was very well received by users from the science and engineering community. The from-source installation in which required external libraries and dependencies are compiled from a tarball was remarkably robust. In places, the code is a lot more ambitious than necessary, which introduces unnecessary complexity and reduces main- tainability. Tests distributed with the package are useful, although more unit tests and continuous integration would have been desirable. The detailed documentation, together with a tutorial for the usage of the system, was perceived as one of its main strengths by the community.

Hans Fangohr, Vidar Fauske, Thomas Kluyver et al.

The Notebook validation tool nbval allows to load and execute Python code from a Jupyter notebook file. While computing outputs from the cells in the notebook, these outputs are compared with the outputs saved in the notebook file, treating each cell as a test. Deviations are reported as test failures, with various configuration options available to control the behaviour. Application use cases include the validation of notebook-based documentation, tutorials and textbooks, as well as the use of notebooks as additional unit, integration and system tests for the libraries that are used in the notebook. Nbval is implemented as a plugin for the pytest testing software.

Francisco Queiroz, Raniere Silva, Jonah Miller et al.

Scientific software often presents very particular requirements regarding usability, which is often completely overlooked in this setting. As computational science has emerged as its own discipline, distinct from theoretical and experimental science, it has put new requirements on future scientific software developments. In this paper, we discuss the background of these problems and introduce nine aspects of good usability. We also highlight best practices for each aspect with an emphasis on applications in computational science.