Dr. Deepak Subramani

Assistant Professor, IISc Bangalore, India

DP

About Me

My group undertakes interdisciplinary research focusing equally on method development and applications. Our contributions can be categorized into two main themes: (1) Data Science and Artificial Intelligence for Dynamic Environmental Systems; and (2) Optimal Routing of Autonomous Underwater Vehicles. We have developed and implemented new theories, numerical methods, and data-driven machine learning and artificial intelligence algorithms in both areas. Additionally, we have made stand-alone contributions to pandemic forecasting and fault detection of engineering systems (e.g., electric vehicles, space systems).

#Education #Experience #Research #Recognition #Contact

#Publications

#Opportunities

#Teaching/Skill Development

#Recording (YouTube) of Recent Lectures

#Photographs

Curriculum Vitae

News

[NEW Nov 2023] We have full time in-person open positions in Deep Learning for Ocean Modeling. Ad is here. Short-term, part-time, remote etc positions are not available.

Awarded the IISc Award for Excellence in Teaching for the Year 2022 on 5-Sept-2022.

Education

Nov. 2017

Ph.D. in Mechanical Engineering and Computational Engineering

Massachusetts Institute of Technology

Cambridge, MA

2014

S.M. in Computation for Design and Optimization

Massachusetts Institute of Technology

Cambridge, MA

2012

M.Tech and B.Tech in Mechanical Engineering

Indian Institute of Technology Madras

Chennai, Tamil Nadu, India

#Top

Work Experience

Jan 2019 - Present

Assistant Professor

Dept. of Computational and Data Sciences

Indian Institute of Science, Bengaluru

Dec. 2017 - Nov. 2018

Postdoctoral Associate

Advisor: Prof. Pierre F.J. Lermusiaux

Massachuesetts Institute of Technology

Sept. 2012 - Nov. 2017

Graduate Research Fellow

Advisor: Prof. Pierre F.J. Lermusiaux

Massachusetts Institute of Technology

Aug 2011 - June 2012

Research Assistant

Advisor: Prof. C. Balaji

Indian Institute of Technology Madras

#Top

Research Interests

Ocean Modeling

Development and applications of stochastic and deterministic primitive equation ocean modeling systems.

Computational Engineering

Development of novel numerical schemes and software systems for all our application areas using GPU and distributed computing.

Machine Learning and Deep Learning for Geosciences

Development and application of ML and DL algorithms for Ocean Modeling, Remote Sensing, Environmental Analysis, Ecology Studies, Monsoon Forecasting.

Autonomous Underwater Vehicles

Combining state of the art environmental state forecasts (ocean, atmosphere, traffic etc.) with AI/ML algorithms, PDE solutions and GPU Computing.

Data Assimilation

Combining Models and Data for Geosciences and Climate Studies.

Uncertainty Quantification

Probabilistic predictions and optimization utilizing dynamic stohcastic model order reduction schemes (e.g., Dynamically Orthogonal Field Equations)

Opportunities

Master's and Ph.D. Students

We invite students who are interested in any of the following topics: numerical solution of stochastic partial differential equations, uncertainty quantification, Bayesian and deep learning of dynamical systems, fluid dynamics of the atmosphere and oceans, and path planning of autonomous vehicles in dynamic environments.

Summer Interns

We host only the following type of summer interns: (a) Selected through the Indian Academy of Sciences Summer Research Fellows Program; (b) as part of existing collaboration with PIs; (c) candidates who demonstrate exceptional coding skills above and beyond coursework and online self learning.

JRF

Applications invited for project assistant positions in developing deep learning solutions for autonomous underwater vehicle routing. See ad here.

JRF/SRF/Post-Doctoral

Applications invited for JRF/SRF/post-doctoral positions in ocean modeling (ROMS). Required Skills: Geoscience Data Handling, Interest in running ocean models. See ad here.

General word of advice:

Generic emails stating that you have completed a particular online course does not inspire confidence in professors. It is better to share the git repository of particular projects that you worked on. Faculty around the world recieve 100s of emails from Indian students on a weekly basis and most do not read because all emails look the same. Please improve your skills and show evidence (in the form of code!) that you are skilled. Also remember when you send the same email to everyone that faculty in the same department/institute talk to each other!!!

#Top

Teaching

Courses at CDS, IISc

UMC 301: Applied Data Science and Artificial intelligence (AUG Term; 2024)

DS 211: Numerical Optimization (AUG Term; 2019-2023)

DS 392: Environmental Data Analytics (JAN Term; 2020-2023)

Courses at DSBA M.Tech (Online), IISc

DA 204-O: Data Science in Practice (AUG Term 2023) - I will not be offering this course henceforth due to a rule change at IISc.

DA 202-O: Introduction to Data Science (AUG Term 2021,2022) - Will not be offered henceforth due to a rule change at IISc.

DA 224-O: Practical Machine Learning (JAN Term) - Will not be offered henceforth due to a rule change at IISc.

DA 225-O: Deep Learning (Summer Term) - Will not be offered henceforth due to a rule change at IISc.

CCE Proficience Courses, IISc

I will not be offering semester long CCE Proficience Courses from Jan 2024.

Previously, I offered a completely online semester long CCE Proficience course in Aug-Dec 2023 (Deep Neural Networks for Computer Vision and NLP), Jan-Apr 2023 (Deep Learning for Artificial Intelligence), Aug-Dec 2021 titled "Foundations of Data Science and Machine Learning" and Jan-Apr 2021 titled "Data-Driven Modeling and Optimization" at CCE, IISc as part of the Proficience Program.

IISc-TalentSprint Advanced Certification Program

Enroll for the IISc-Talent Sprint PG-Level Advanced Certification Program in Computational Data Sciences. Website: Link. I teach two modules: Foundations of Data Science (Probability, Statistics) and Machine Learning modules.

Enroll for the IISc-Talent Sprint PG-Level Advanced Certification Program in AI & MLOps. Website: Link. I teach four modules: Foundations of Machine Learning, Computer Vision, Natural Language Processing and Generative AI.

Teaching Feedback

IISc Courses Average Instructor Rating: 4.91/5 (Updated Jan 2024)

Selected Comments:

  • “Prof. Deepak is not only thorough with the subject matter, but also great at communicating and articulating his knowledge. Wonderful!”
  • “Simply love the knowledge of the professor, teaching methodology of the professor and relevant examples given”
  • “Great lecture as always. Thank you for making it interactive.”
  • Check the link for more unedited instructor feedback.

#Top

YouTube Videos of Recent Talks and Lectures

Talk about our Covid 19 Model (Ganesan and Subramani, 2021 Nature Sci. Rep.) - May 8, 2021 at EECS Symposium, IISc

Introduction to Data Science Talk

#Top

Some Snaps from Recent Events

With current group members on 5 Sept 2022

IISc Excellence in Teaching Award 5 Sept 2022

#Top

Honors/Awards

  • IISc Award for Excellence in Teaching 2022

    Awarded to faculty at IISc Bangalore for their teaching excellence based on student feedback and contribution

  • Arcot Ramachandran Young Investigator Award, 2019-2021

    Awarded to promising young assistant professors in the Division of Interdisciplinary Sciences and Engineering, IISc Bangalore

  • SNAME Award in Ocean Engineering, Dec 2017

    Awarded to the top researcher to attend conferences in Ocean Engineering, MIT

  • First Place, Graduate Science, May 2017

    Awarded at the de Florez Competition, MIT

  • Wunsch Foundation Silent Hoist & Crane Award for Outstanding Research, 2017

    Awarded annually to a graduate student in the Department of Mechanical Engineering, MIT

  • Best Presentation Award, Tata Pro Seminar, May 2017

    One among four awarded at the annual Society of Tata Fellows Induction, MIT

  • Best Live Demonstration/Prototype Award, Sept 2016

    Awarded at the Mechanical Engineering Research Symposium, MIT

  • Esteemed Presenter Award: Best Theoretical/Computational Presentation, Sept 2015

    Awarded at the Mechanical Engineering Research Symposium, MIT

  • Honourable Mention Award in Graduate Science, May 2015

    Awarded at the de Florez Design Competition, MIT

  • Best Poster Award, Mar 2015

    Awarded at the Centre for Computational Engineering Symposium, MIT

  • Runner-up Poster Award, Nov 2014

    Awarded at the Dynamic Data Driven System Sciences Conference (DyDESS) 2014

  • Highest GPA Award, 2012

    Awarded to the senior with highest GPA in Mechanical Engineering at IIT Madras

  • MITACS Globalink Scholarship

    Awarded to top 2% of juniors across Indian Universities to undertake research in Canada. Link here.

  • GE Foundation Leader Scholar 2009-11

    Awarded to roughly 200 students among 14 countries.

  • National Talent Scholar, 2005

    Awarded to top 0.01% of among 150,000+ applicants by Government of India through a three stage competitive exam

  • CBSE Merit Certificates, 2005 and 2007

    Awarded to top 0.01% of passed candidates in 10th grade and 12th grade national exams by Central Board of Secondary Education, India

#Top

Publications

Please see Google Scholar and CV for an updated list. Website not updated after 2021.

Papers in Peer-Reviewed Journals

    2021

  1. R. Gadi, P N. Vinayachandran and D. Subramani (2021). Data-Driven Feature Models of the Southwest Monsoon Current. Ocean Modelling. Accepted Oct 2021. Submitted PDF
  2. S. Avasarala and D. Subramani (2021). A non-Gaussian Bayesian Filter for Sequential Data Assimilationwith non-intrusive Polynomial Chaos Expansion . Int J Numer Methods Eng. 2021; 1- 26. https://doi.org/10.1002/nme.6827 Publisher Link
  3. D. Lambhate, R. Sharma, J. Clark, A. Gangopadhyay and D. Subramani (2021). W-Net: A Deep Network for Simultaneous Identification of Gulf Stream and Rings from Concurrent Satellite Images of Sea Surface Temperature and Height. IEEE Transactions on Geoscience and Remote Sensing, doi: 10.1109/TGRS.2021.3096202. Publisher Link
  4. S. Ganesan and D. Subramani (2021). Spatio-temporal predictive modeling framework for infectious disease spread Nature Scientific Reports. 11, 6741 (2021). https://doi.org/10.1038/s41598-021-86084-7 PDF
  5. Ganesan, S., Subramani, D., Anandh, T., Ghose, D. and Babu, G.R. (2021*). Ensemble Forecast of COVID-19 for Vulnerability Assessment and Policy Interventions. Submitted Sept 2021 to Nature SR. Researchsquare Preprint
  6. R. Chowdhury and D. Subramani (2021*). Optimal Path Planning of Autonomous Marine Vehicles in Stochastic Dynamic Ocean Flows using a GPU-Accelerated Algorithm. IEEE Journal of Oceanic Engineering (Sub Judice. Submitted Apr 2021, Revised Sept 2021.) Arxiv PDF
  7. 2020

  8. Mannarini, G., D.N. Subramani, P.F.J. Lermusiaux, and N. Pinardi (2020). Graph-Search and Differential Equations for Time-Optimal Vessel Route Planning in Dynamic Ocean Waves IEEE Transactions on Intelligent Transportation Systems 21(8), 3581-3593, doi:10.1109/TITS.2019.2935614 PDF
  9. 2019

  10. Subramani, D.N., and P.F.J. Lermusiaux (2019). Risk-Optimal Path Planning in Stochastic Dynamic Environments. Computer Methods in Applied Mechanics and Engineering, 353, 391–415. doi:10.1016/j.cma.2019.04.033 PDF
  11. Before 2019

  12. Subramani, D.N., Q.J. Wei and P.F.J. Lermusiaux (2018). Stochastic Time Optimal Path Planning in Uncertain Flows. Computer Methods in Applied Mechanics and Engineering, 333, pp 218-237. doi: 10.1016/j.cma.2018.01.004 PDF
  13. Subramani, D. N., P. J. Haley, Jr., and P. F. J. Lermusiaux (2017). Energy-optimal path planning in the coastal ocean, J. Geophys. Res. Oceans,122, 3981–4003, doi:10.1002/2016JC012231. PDF
  14. Sun, W., P. Tsiotras, T. Lolla, D. N. Subramani, and P. F. J. Lermusiaux (2017). Multiple-Pursuer-One-Evader Pursuit Evasion Game in Dynamic Flow Fields. Journal of Guidance, Control and Dynamics. DOI: 10.2514/1.G002125 PDF
  15. Subramani, D.N. and P.F.J. Lermusiaux (2016). Energy-optimal Path Planning by Stochastic Dynamically Orthogonal Level-Set Optimization. Ocean Modeling, 100, 57–77. DOI: 10.1016/j.ocemod.2016.01.006 PDF
  16. Subramani, D., Chandrasekar, R., Ramanujam, K.S. and C. Balaji (2014). A new ensemble-based data assimilation algorithm to improve track prediction of tropical cyclones. Natural Hazards 71: 659. doi:10.1007/s11069-013-0942-1 PDF
  17. Ramanujam, S., R. Chandrasekar, D.N. Subramani, and C. Balaji (2012) On the Effect of Non-Raining Parameters in Retrieval of Surface Rain Rate Using TRMM PR and TMI Measurements PDF

Proceedings of Peer-Reviewed Conferences

    2021

  1. Anjali, P. and Subramani, D.N., 2021. Inter and Intra-Annual Spatio-Temporal Variability of Habitat Suitability for Asian Elephants in India: A Random Forest Model-based Analysis. Accepted to IEEE InGARSS 2021. Arxiv PDF

    2020

  2. Lambhate, D. and D. N. Subramani, 2020 Super-Resolution of Sea Surface Temperature Satellite Images. Global Oceans 2020: Singapore – U.S. Gulf Coast, 2020, pp. 1-7, doi: 10.1109/IEEECONF38699.2020.9389030. Publisher Link
  3. Chowdhury, R., and D.N. Subramani, 2020 Physics-Driven Machine Learning for Time-Optimal Path Planning in Stochastic Dynamic Flows. In: Darema F., Blasch E., Ravela S., Aved A. (eds) Dynamic Data Driven Applications Systems. DDDAS 2020. Lecture Notes in Computer Science, vol 12312. Springer, Cham. https://doi.org/10.1007/978-3-030-61725-7_34 Publisher Link
  4. 2019 and Earlier

  5. Gupta, A., Haley, P.J., Subramani, D.N. and Lermusiaux, P.F.J., 2019. Fish modeling and Bayesian learning for the Lakshadweep Islands. In OCEANS 2019 MTS/IEEE SEATTLE (pp. 1-10). IEEE. PDF
  6. Ferris, D.L, D.N. Subramani, C.S. Kulkarni, P.J. Haley and P.F.J. Lermusiaux, 2018. Time-Optimal Multi-Waypoint Mission Planning in Dynamic Environments. OCEANS 2018 MTS/IEEE Charleston, 2018, pp. 1-8, doi: 10.1109/OCEANS.2018.8604683.PDF.
  7. Dutt, A., D.N. Subramani, C.S. Kulkarni, and P.F.J. Lermusiaux, 2018. Clustering of Massive Ensemble of Vehicle Trajectories in Strong, Dynamic and Uncertain Ocean Flows. In: Oceans '18 MTS/IEEE Charleston, 22-25 October 2018. doi:10.1109/oceans.2018.8604634 PDF
  8. Subramani, D. N., P. F. J. Lermusiaux, P.J. Haley, Jr., C. Mirabito, S. Jana, C. S. Kulkarni, A. Girard, D. Wickman, J. Edwards, J. Smith, 2017. Time-Optimal Path Planning: Real-Time Sea Exercises. In: Oceans '17 MTS/IEEE Aberdeen, 19-22 June 2017, In press.PDF
  9. Subramani, D. N., Lolla, T., Haley Jr., P. J., Lermusiaux, P. F. J., 2015. A stochastic optimization method for energy-based path planning. In: Ravela, S., Sandu, A. (Eds.), DyDESS 2014. Vol. 8964 of LNCS. Springer, pp. 347-358. PDF
  10. Mirabito, C., D.N. Subramani, T. Lolla, P.J. Haley, Jr., A. Jain, P.F.J. Lermusiaux, C. Li, D.K.P. Yue, Y. Liu, F.S. Hover,N. Pulsone, J. Edwards, K.E. Railey, and G. Shaw, 2017. Autonomy for Surface Ship Interception.In: Oceans '17 MTS/IEEE Aberdeen, 19-22 June 2017, In Press. PDF
  11. Edwards, J., J. Smith, A. Girard, D. Wickman, P.F.J. Lermusiaux, D.N. Subramani, P.J. Haley, Jr., C. Mirabito, C.S. Kulkarni, and,S. Jana, 2017. Data-driven Learning and Modeling of AUV Operational Characteristics for Optimal Path Planning. In: Oceans '17 MTS/IEEE Aberdeen, 19-22 June 2017, In Press.PDF
  12. Sun, W., P. Tsiotras, T. Lolla, D. N. Subramani, and P. F. J. Lermusiaux, 2017. Pursuit-Evasion Games in Dynamic Flow Fields via Reachability Set Analysis. 2017 American Control Conference. In press.PDF

#Top

Contact

Address
CDS 321, Nilgiri Marg,
Indian Institute of Science, Bengaluru 560012
Mobile Number
plus nine one, zero eight zero two two five three two zero five eight
Email
deepakns [at] iisc [dot] ac [dot] in

#Top