Data Science to Help Society

In this module, we will learn how to apply data science for the good of society. We introduce two examples, one for COVID-19, the other for hydrology.

COVID 101, Climate Change and their Technologies

General Material

Python Language

Need to add material here

Using Google CoLab and Jupyter notebooks

For questions on software, please mail Fugang Wang
- Fugang can also give you help on python including introductory material if you need extra
5 notebooks from Google
Introduction to Machine Learning Using TensorFlow (pptx)
Introduction to using Colab from IU class E534 with videos and note (google docs) This unit includes 3 videos
- How to create a colab notebook (mp4)
- How to create a simple program (mp4)
- How to do benchmark (mp4)
Deep Learning for MNIST The docs are located alongside the video at
- Introduction to MNIST
- This teaches how to do deep learning on a handwriting example from NIST which is used in many textbooks
- In the latter part of the document, a homework description is given. That can be ignored!
- There are 5 videos
  1. DNN MNIST Introduction (mp4)
  2. DNN MNIST import section (mp4)
    - Running into import errors starting at the keras.models line in the code
  3. DNN MNIST data preprocessing (mp4)
  4. DNN MNIST model definition (mp4)
  5. DNN MNIST final presentation (mp4)
Jupyter notebook on Google Colab for COVID-19 data analysis ipynb

Follow-up on Discussion of AI remaking Industry worldwide

Class on AI First Engineering with 35 videos describing technologies and particular industries Commerce, Mobility, Banking, Health, Space, Energy in detail (youtube playlist)
Introductory Video (one of 35) discussing the Transformation - Industries invented and remade through AI (youtube)
Some online videos on deep learning
- Introduction to AI First Engineering (youtube)

Examples of Applications of Deep Learning (youtube)

Optimization -- a key in Statistics, AI and Deep Learning (youtube)

Learn the Deep Learning important words and parts (youtube)

Deep Learning and Imaging: It's first great success (youtube)

Covid Material

Covid Biology Starting point

Medical Student COVID-19 Curriculum - COVID-19 Curriculum Module 1 and then module 2

Compucell3D Modelling material

Download
Manual
List of NanoHub Tools
For help please ask Juliano Ferrari Gianlupi

Interactive Two-Part Virtual Miniworkshop on Open-Source CompuCell3D

Multiscale, Virtual-Tissue Spatio-Temporal Simulations of COVID-19 Infection, Viral Spread and Immune Response and Treatment Regimes** VTcovid19Symp

Part I: Will be presented twice:
First Presentation June 11th, 2020, 2PM-5PM EST (6 PM- 9PM GMT)
Second Presentation June 12th, 9AM - 12 noon EST (1 PM - 4 PM GMT)
Part II: Will be presented twice:
First Presentation June 18th, 2020, 2PM-5PM EST (6 PM- 9PM GMT)
Second Presentation June 19th, 9AM - 12 noon EST (1 PM - 4 PM GMT)

Topics in Covid 101

Biology¹ and Harvard medical school material above
Epidemiology²
Public Health: Social Distancing and Policies³
HPC⁴
Data Science ⁵^,⁶^,⁷
Modeling ⁸^,⁹

Climate Change Material

Topics in Climate Change (Russell Hofmann)

This also needs Colab and deep learning background
A cursory and easy to understand review of climate issues in terms of AI: Tackling Climate Change with Machine Learning
For application in extreme weather event prediction, an area where traditional modelling methods have always struggled:
- Interpretable Deep Learning for Spatial Analysis of Severe Hailstorms¹⁰
AI4ESS Summer School: Anyone who is interested in using Machine learning for climate science research I highly recommend you register for the Artificial Intelligence for Earth System Science summer school & interactive workshops which conveniently runs June 22^nd^ to 26^th^. Prior Experience with tensorflow/keras via google co-lab should be all the introductory skill needed to follow along. Register ASAP. https://www2.cisl.ucar.edu/events/summer-school/ai4ess/2020/artificial-intelligence-earth-system-science-ai4ess-summer-school
Kaggle Climate Change Climate Change Forecast - SARIMA Model with classic time series methods
Plotting satellite data Notebook (ipynb)
Accessing UCAR data (docx)
Hydrology with RNN and LSTM’s (more than 20 PDF’s)

References

Y. M. Bar-On, A. I. Flamholz, R. Phillips, and R. Milo, “SARS-CoV-2 (COVID-19) by the numbers,” arXiv [q-bio.OT], 28-Mar-2020. http://arxiv.org/abs/2003.12886 ↩︎
Jiangzhuo Chen, Simon Levin, Stephen Eubank, Henning Mortveit, Srinivasan Venkatramanan, Anil Vullikanti, and Madhav Marathe, “Networked Epidemiology for COVID-19,” Siam News, vol. 53, no. 05, Jun. 2020. https://sinews.siam.org/Details-Page/networked-epidemiology-for-covid-19 ↩︎
A. Adiga, L. Wang, A. Sadilek, A. Tendulkar, S. Venkatramanan, A. Vullikanti, G. Aggarwal, A. Talekar, X. Ben, J. Chen, B. Lewis, S. Swarup, M. Tambe, and M. Marathe, “Interplay of global multi-scale human mobility, social distancing, government interventions, and COVID-19 dynamics,” medRxiv - Public and Global Health, 07-Jun-2020. http://dx.doi.org/10.1101/2020.06.05.20123760 ↩︎
D. Machi, P. Bhattacharya, S. Hoops, J. Chen, H. Mortveit, S. Venkatramanan, B. Lewis, M. Wilson, A. Fadikar, T. Maiden, C. L. Barrett, and M. V. Marathe, “Scalable Epidemiological Workflows to Support COVID-19 Planning and Response,” May 2020. ↩︎
Luca Magri and Nguyen Anh Khoa Doan, “First-principles Machine Learning for COVID-19 Modeling,” Siam News, vol. 53, no. 5, Jun. 2020. https://sinews.siam.org/Details-Page/first-principles-machine-learning-for-covid-19-modeling ↩︎
[Robert Marsland and Pankaj Mehta, “Data-driven modeling reveals a universal dynamic underlying the COVID-19 pandemic under social distancing,” arXiv [q-bio.PE], 21-Apr-2020. http://arxiv.org/abs/2004.10666 ↩︎
Geoffrey Fox, “Deep Learning Based Time Evolution.”. http://dsc.soic.indiana.edu/publications/Summary-DeepLearningBasedTimeEvolution.pdf. ↩︎
T. J. Sego, J. O. Aponte-Serrano, J. F. Gianlupi, S. Heaps, K. Breithaupt, L. Brusch, J. M. Osborne, E. M. Quardokus, and J. A. Glazier, “A Modular Framework for Multiscale Spatial Modeling of Viral Infection and Immune Response in Epithelial Tissue,” BioRxiv, 2020. https://www.biorxiv.org/content/10.1101/2020.04.27.064139v2.abstract ↩︎
Yafei Wang, Gary An, Andrew Becker, Chase Cockrell, Nicholson Collier, Morgan Craig, Courtney L. Davis, James Faeder, Ashlee N. Ford Versypt, Juliano F. Gianlupi, James A. Glazier, Randy Heiland, Thomas Hillen, Mohammad Aminul Islam, Adrianne Jenner, Bing Liu, Penelope A Morel, Aarthi Narayanan, Jonathan Ozik, Padmini Rangamani, Jason Edward Shoemaker, Amber M. Smith, Paul Macklin, “Rapid community-driven development of a SARS-CoV-2 tissue simulator,” BioRxiv, 2020. https://www.biorxiv.org/content/10.1101/2020.04.02.019075v2.abstract ↩︎
Gagne II, D. J., S. E. Haupt, D. W. Nychka, and G. Thompson, 2019: Interpretable Deep Learning for Spatial Analysis of Severe Hailstorms. Mon. Wea. Rev., 147, 2827–2845, https://doi.org/10.1175/MWR-D-18-0316.1 ↩︎