This course aims to provide a succinct overview of the emerging discipline of Materials Informatics at the intersection of materials science, computational science, and information science. Attention is drawn to specific opportunities afforded by this new field in accelerating materials development and deployment efforts. A particular emphasis is placed on materials exhibiting hierarchical internal structures spanning multiple length/structure scales and the impediments involved in establishing invertible process-structure-property (PSP) linkages for these materials. More specifically, it is argued that modern data sciences (including advanced statistics, dimensionality reduction, and formulation of metamodels) and innovative cyberinfrastructure tools (including integration platforms, databases, and customized tools for enhancement of collaborations among cross-disciplinary team members) are likely to play a critical and pivotal role in addressing the above challenges.
LR
Great initiative of creating this course! If you're curious about the idea of combining materials science and data science, this course is for you. Enjoy!
RR
Machine learning part and its application to material science was interesting but informative contents like material dev eco system and whole week 1 was more informative than logical
RV
A good summary of the present challenges and need for Active learning and advanced ways of material development by leveraging the data and physics
BB
the course is nice and useful, but is very tough. You require a good knowledge of statistics, computation, and material science to make it through it.
GT
Excellent experience. It engages my knowledge broadly about Data Science in Materials. Thank you
MQ
Really helpful. It provides what I was wandering about.Their work is appriciated.
DB
A perfect course if one wants to pursue a research career in material science with an engineering background.
PS
It includes ausam information in structured manner to learn the subject easily.
MR
This course effectively bridged the gap between materials science and data-driven methodologies, introducing advanced techniques for managing and analyzing complex materials data.
AS
Got an overview about how materials data is analysed. This course helps us in understanding the need of data sciences for accelerating material development.
PC
It is a great way to combine both the branches, Material sciences, and data science. I completely loved this certification. Looking forward to learning more.
SG
I take this opportunity to express sincere gratitude to Dr Surya Kalidindi. Thank you COURSERA yet again.
Showing: 20 of 87
Too much introduction, not much actual useful stuff. Too much mathematically without well illustrated examples.
Useful introduction to vocabulary and concepts in the field, but can't help but feel the pacing and scope of the course takes an abrupt switch at times.
I think it's wonderful course, but I did not have enough real practical skills from it (in my opinion). Thank you very much to the instructors for this course!
An excellent introduction to Material informatics. I highly recommend to any beginners to get started with learning informatics regarding materials.
This is a great starter course for materials informatics. It covers a good amount of topics and uses a nice case study to reinforce digital representation of data, spatial correlations, principal component analysis, and regression. I really liked the examples of pyMKS. My only suggestions is it would have been nice to have more hands-ons use of pyMKS and sci-kit learn. This could have been accomplished through a course project or homeworks.
This course discussed one particular issue in materials informatics. I hoped to see several other informatics-based techniques to solve problems in materials innovation.
Excellent course if you are looking to understand how to design high performance materials leveraging current advances in data sciences.
Very well delivered by Dr. Surya Kalidindi and Prof McDowell. Reference to the book on the subject by Dr. Kalidindi supplemented by web search was useful.
Need to put the new skills acquired, in practice at work, where I see a huge potential.
Thanks Georgia Tech!!
Very valuable course for materials modelling enthusiast. It provides me the firm grounding and preparation for my future research work in this material modeling. This course is a fine balance of technical knowledge, its implementation and the practical approaches one needs to adopt to effectively use this knowledge of materials modeling in real world. (Anupam Purwar)
Very informative course. Cover many concepts of data science as well as the Material design field.
I would recommend this course to the people who want to stay in their core field while utilizing modern-day techniques such as machine learning and data science in their work.
Machine learning part and its application to material science was interesting but informative contents like material dev eco system and whole week 1 was more informative than logical
The course was overall good but some of the course content is outdated (installing PyMKS) please look into this matter.
Great introduction of the why and how of materials informatics!
Some topics were very lightly touched while some of them were outright skipped. For example the instructor said the topic of leave one out cross validation was done earlier while it wasn't. Overall I was an insightful course for those who want to link Material Science and Computation/Modelling but the caveat is a lot of external reading is suggested and I would suggest you might have a basic data science/Linear algebra knowledge for PCA analysis and Spatial Correlations along with python for pyMKS system.
Not bad, but it would be better with a bit of hands-on practice.
The course gives a "good" overview of some techniques but is way too descriptive, way too theoretical. There is no progressive (computational) practice. The major flaws of this course are: 1)no handouts of the slides provided, 2) reference to papers are not clickable URL's, 3) PyMKS runs in Python 2.7 (not 3.4) with many modules deprecated. Running this PyMks is therefore not easy at all and bugged with the environments. Once you get in the course is just about replicating some logic without going in-depth of the potential of this tool. As well , what are more up to date tools to be used? 5) instructors are not really good at teaching , 6) there is no active learners community at this period (november 2019)
It took until the last 15 minutes of week 5 to get to the actual data science...
Too much talk about general idea. Lack of practice to learn skills
The course has been very helpful in forming a basic understanding of data sciences application in Materials Engineering. Also it motivated me to explore even more, study and adopt these skills in my research.
In my opinion, a few more lectures on PyMKS applications in the last week would be of more help.
I strongly recommend setting up an advanced followup of this course with deeper analysis and some hands-on practice.
My heartfelt thanks to Prof. Kalidindi for this initiative.
I am in the process of transitioning from a purely design position to a professional materials engineer for a 3D house printing company. This course was a great fundamental introduction to materials processing history all the way to current high-end cyberinfrastructure like e-collaborative data pipelines, open-source machine learning libraries in python used to make cutting edge material breakthroughs today.
This course is very informative and relevant for Material Engineering students like me to incorporate Data Science and modern technology to speed up research on the discovery of new materials. This course has also provided useful computational tools such as Pymks. Pymks enable use to compute the 2 point spatial correlation and visualization does help in the analysis of the material's structure properties.