From b94dd840d97bd447af2dd09b96cac4cb3531e9f1 Mon Sep 17 00:00:00 2001 From: The Open Journals editorial robot <89919391+editorialbot@users.noreply.github.com> Date: Fri, 16 Aug 2024 08:50:57 +0100 Subject: [PATCH] Creating 10.21105.joss.06912.jats --- .../paper.jats/10.21105.joss.06912.jats | 319 ++++++++++++++++++ 1 file changed, 319 insertions(+) create mode 100644 joss.06912/paper.jats/10.21105.joss.06912.jats diff --git a/joss.06912/paper.jats/10.21105.joss.06912.jats b/joss.06912/paper.jats/10.21105.joss.06912.jats new file mode 100644 index 0000000000..522bec8772 --- /dev/null +++ b/joss.06912/paper.jats/10.21105.joss.06912.jats @@ -0,0 +1,319 @@ + + +
+ + + + +Journal of Open Source Software +JOSS + +2475-9066 + +Open Journals + + + +6912 +10.21105/joss.06912 + +f3dasm: Framework for Data-Driven Design and Analysis of +Structures and Materials + + + +https://orcid.org/0000-0003-3602-0452 + +van der Schelling +M. P. + + + + +https://orcid.org/0000-0001-5956-3877 + +Ferreira +B. P. + + + + +https://orcid.org/0000-0002-6216-0355 + +Bessa +M. A. + + +* + + + +Materials Science & Engineering, Delft University of +Technology, the Netherlands + + + + +School of Engineering, Brown University, United States of +America + + + + +* E-mail: + + +31 +5 +2024 + +9 +100 +6912 + +Authors of papers retain copyright and release the +work under a Creative Commons Attribution 4.0 International License (CC +BY 4.0) +2022 +The article authors + +Authors of papers retain copyright and release the work under +a Creative Commons Attribution 4.0 International License (CC BY +4.0) + + + +Python +data-driven +materials +framework +machine learning + + + + + + Summary +

f3dasm + (Framework for Data-driven Design and Analysis of Structures and + Materials) is a Python project that provides a general and + user-friendly data-driven framework for researchers and practitioners + working on the design and analysis of materials and structures. The + package aims to streamline the data-driven process and make it easier + to replicate research articles in this field, as well as share new + work with the community.

+ +

Logo of + f3dasm. +

+ + + + + Statement of need +

In the last decades, advancements in computational resources have + accelerated novel inverse design approaches for structures and + materials. In particular, data-driven methods leveraging machine + learning techniques play a major role in shaping our design processes + today.

+

Constructing a large material response database poses practical + challenges, such as proper data management, efficient parallel + computing, and integration with third-party software. Because most + applied fields remain conservative when it comes to openly sharing + databases and software, a lot of research time is instead being + allocated to implement common procedures that would be otherwise + readily available. This lack of shared practices also leads to + compatibility issues for benchmarking and replication of results by + violating the FAIR principles.

+

In this work we introduce an interface for researchers and + practitioners working on the design and analysis of materials and + structures. The package is called + f3dasm + (Framework for Data-driven Design and Analysis of Structures and + Materials). This work generalizes the original closed-source framework + proposed by Bessa and co-workers + (Bessa + et al., 2017), making it more flexible and adaptable to + different applications, namely by allowing the integration of + different choices of software packages needed in the different steps + of the data-driven process:

+ + +

design of experiments, in which input variables + describing the microstructure, properties and external conditions + of the system are determined and sampled;

+ + +

data generation, typically through computational + analyses, resulting in the creation of a material response + database + (Ferreira + et al., 2023);

+ + +

machine learning, in which a surrogate model is + trained to fit experimental findings;

+ + +

optimization, where we try to iteratively improve + the design.

+ + +

[fig:data-driven-process] + provides an illustration of the stages in the data-driven process.

+ +

Illustration of the f3dasm + data-driven process. +

+ + +

f3dasm + is an + open-source + Python package compatible with Python 3.8 or later. The + library includes a suite of benchmark functions, optimization + algorithms, and sampling strategies to serve as default + implementations. Furthermore, + f3dasm + offers automatic data management for experiments, easy integration + with high-performance computing systems, and compatibility with the + hydra configuration manager. Comprehensive + online + documentation is also available to assist users and + developers of the framework.

+

In a similar scope, it is worth mentioning the projects + simmate + (Sundberg + et al., 2022) and + strucscan, + as they provide tools for the management of materials science + simulation and databases. However, these projects focus on the + generation and retrieval of materials properties and do not include + machine learning or optimization interfaces. In recent years, numerous + optimization frameworks have been developed to facilitate data-driven + design. + Optuna + is a hyperparameter optimization framework that combines a variety of + optimization algorithms with dynamically constructed search space + (Akiba + et al., 2019) and + pygmo + provides unified interfaces for parallel global optimization + (Biscani + & Izzo, 2020). Interfaces to these and many other + optimization frameworks have been integrated into a separate package + f3dasm_optimize, + and can be used in conjunction with + f3dasm.

+ + + Acknowledgements +

We would express our gratitude to Jiaxiang Yi for his contributions + to writing an interface with the ABAQUS simulation software and to + Deepesh Toshniwal for providing valuable feedback.

+ + + + + + + + + BessaMiguel + BostanabadR. + LiuZ. + HuA. + ApleyDaniel W. + BrinsonC. + ChenW. + LiuWing Kam + + A framework for data-driven analysis of materials under uncertainty: Countering the curse of dimensionality + Computer Methods in Applied Mechanics and Engineering + 2017 + 320 + April + 10.1016/j.cma.2017.03.037 + 633 + 667 + + + + + + SundbergJack D. + BenjaminSiona S. + McRaeLauren M. + WarrenScott C. + + Simmate: A framework for materials science + Journal of Open Source Software + The Open Journal + 2022 + 7 + 75 + https://doi.org/10.21105/joss.04364 + 10.21105/joss.04364 + 4364 + + + + + + + BiscaniFrancesco + IzzoDario + + A parallel global multiobjective framework for optimization: pagmo + Journal of Open Source Software + The Open Journal + 2020 + 5 + 53 + https://doi.org/10.21105/joss.02338 + 10.21105/joss.02338 + 2338 + + + + + + + AkibaTakuya + SanoShotaro + YanaseToshihiko + OhtaTakeru + KoyamaMasanori + + Optuna: A next-generation hyperparameter optimization framework + Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining + 2019 + https://doi.org/10.1145/3292500.3330701 + 10.1145/3292500.3330701 + 2623 + 2631 + + + + + + FerreiraBernardo P. + PiresF. M. Andrade + BessaMiguel A. + + CRATE: A python package to perform fast material simulations + Journal of Open Source Software + The Open Journal + 2023 + 8 + 87 + https://doi.org/10.21105/joss.05594 + 10.21105/joss.05594 + 5594 + + + + + +