Computational Science as an enabler for sustainable FEW Systems Baskar Ganapathysubramanian Iowa State University NSF FEW Workshop: Oct 12-13, 2015, ISU.

Slides:



Advertisements
Similar presentations
Econometric-Process Simulation Models for Semi-Subsistence Agricultural Systems: Application of the NUTMON Data for Machakos.
Advertisements

V Alyssa Rosemartin 1, Lee Marsh 1, Ellen Denny 1, Bruce Wilson USA National Phenology Network, Tucson, AZ; 2 - Oak Ridge National Laboratory, Oak.
1 Maximizing Drip and Micro Sprinkler Systems Efficiency through UAV (Drone), Soil Sensing Technologies & VRI.
Life and Health Sciences Summary Report. “Bench to Bedside” coverage Participants with very broad spectrum of expertise bridging all scales –From molecule.
1 Cyberinfrastructure Framework for 21st Century Science & Engineering (CF21) IRNC Kick-Off Workshop July 13,
MODIS Science Team Meeting - 18 – 20 May Routine Mapping of Land-surface Carbon, Water and Energy Fluxes at Field to Regional Scales by Fusing Multi-scale.
NSF and Environmental Cyberinfrastructure Margaret Leinen Environmental Cyberinfrastructure Workshop, NCAR 2002.
B1 -Biogeochemical ANL - Townhall V. Rao Kotamarthi.
Knowledge Management Tools Abstract More and more companies use knowledge management to leverage theis most important resource : knowledge. Knowledge.
KDD for Science Data Analysis Issues and Examples.
The Context of Forest Management & Economics, Modeling Fundamentals Lecture 1 (03/30/2015)
“Collaborative automation: water network and the virtual market of energy”, an example of Operational Efficiency improvement through Analytics Stockholm,
1 Building National Cyberinfrastructure Alan Blatecky Office of Cyberinfrastructure EPSCoR Meeting May 21,
V. Chandrasekar (CSU), Mike Daniels (NCAR), Sara Graves (UAH), Branko Kerkez (Michigan), Frank Vernon (USCD) Integrating Real-time Data into the EarthCube.
Flexibility of system to deliver water Level of control available to the irrigator e.g. ditch system on a fixed schedule vs. large capacity well supplying.
4.x Performance Technology drivers – Exascale systems will consist of complex configurations with a huge number of potentially heterogeneous components.
Last Words COSC Big Data (frameworks and environments to analyze big datasets) has become a hot topic; it is a mixture of data analysis, data mining,
Cactus Computational Frameowork Freely available, modular, environment for collaboratively developing parallel, high- performance multi-dimensional simulations.
CRESCENDO Full virtuality in design and product development within the extended enterprise Naples, 28 Nov
DOE BER Climate Modeling PI Meeting, Potomac, Maryland, May 12-14, 2014 Funding for this study was provided by the US Department of Energy, BER Program.
material assembled from the web pages at
Per Møldrup-Dalum State and University Library SCAPE Information Day State and University Library, Denmark, SCAPE Scalable Preservation Environments.
Wireless Networks Breakout Session Summary September 21, 2012.
Liam Newcombe BCS Data Centre Specialist Group Secretary Modelling Data Centre Energy Efficiency and Cost.
IPlant cyberifrastructure to support ecological modeling Presented at the Species Distribution Modeling Group at the American Museum of Natural History.
Joint Agency Workshop on California Drought Response Robert Kostecki, LBNL California Energy Commission, Sacramento, August 28, 2015.
Pascucci-1 Valerio Pascucci Director, CEDMAV Professor, SCI Institute & School of Computing Laboratory Fellow, PNNL Massive Data Management, Analysis,
Introduction to Software Engineering. Why SE? Software crisis manifested itself in several ways [1]: ◦ Project running over-time. ◦ Project running over-budget.
Update on NASA’s Sensor Web Experiments Using Simulated Doppler Wind Lidar Data S. Wood, D. Emmitt, S. Greco Simpson Weather Associates, Inc. Working Group.
Last Words DM 1. Mining Data Steams / Incremental Data Mining / Mining sensor data (e.g. modify a decision tree assuming that new examples arrive continuously,
Opportunities for Research in the Dynamics of Water Processes in the Environment at NSF Pam Stephens Directorate of Geosciences, NSF Directorate of Geosciences,
Experts in numerical algorithms and High Performance Computing services Challenges of the exponential increase in data Andrew Jones March 2010 SOS14.
1 Structure of Aalborg University Welcome to Aalborg University.
SIS Spatial Information Solutions April 23, 2005 MSU ERAC Presentation Spatial Information Solutions: A New Business Delivering Spatial Technology Research.
Machine Learning Extract from various presentations: University of Nebraska, Scott, Freund, Domingo, Hong,
1 Critical Water Information for Floods to Droughts NOAA’s Hydrology Program January 4, 2006 Responsive to Natural Disasters Forecasts for Hazard Risk.
Linking Land use, Biophysical, and Economic Models for Policy Analysis Catherine L. Kling Iowa State University October 13, 2015 Prepared for “Coupling.
Midwest Big Data Hub Edward Seidel Director, NCSA Founder Prof. of Physics, Prof of Astronomy On behalf of the Midwest Big Data Hub 1 Brian Athey Sarah.
Implementing a National Data Infrastructure: Opportunities for the BIO Community Peter McCartney Program Director Division of Biological Infrastructure.
| nectar.org.au NECTAR TRAINING Module 2 Virtual Laboratories and eResearch Tools.
System A system is a set of elements and relationships which are different from relationships of the set or its elements to other elements or sets.
NASA Earth Exchange (NEX) A collaborative supercomputing environment for global change science Earth Science Division/NASA Advanced Supercomputing (NAS)
A Social Life Network to enable farmers to meet the varying food demands Professor Gihan Wikramanayake University of Colombo School of Computing.
Optimization Techniques for Natural Resources SEFS 540 / ESRM 490 B Lecture 1 (3/30/2016)
Big Data in Indian Agriculture D. Rama Rao Director, NAARM.
Machine Learning Artificial Neural Networks MPλ ∀ Stergiou Theodoros 1.
Bhakthi Liyanage SQL Saturday Atlanta 15 July 2017
© 2016 ProsumerGrid, Inc., All Rights Reserved
Engineering (Richard D. Braatz and Umberto Ravaioli)
Inter-experimental LHC Machine Learning Working Group Activities
RDA US Science workshop Arlington VA, Aug 2014 Cees de Laat with many slides from Ed Seidel/Rob Pennington.
National Institute of Standards and Technology (NIST) Advanced Manufacturing Technology Consortia (AMTech) Program Award Number: 70NANB14H056 Development.
Scientific Computing Department
Themes in Geosciences.
Kostas Seferis, i2S Data science and e-infrastructures can help aquaculture to improve performance and sustainability!
Goodfellow: Chap 1 Introduction
Unsupervised Learning and Autoencoders
Patrick S. Schnable Department of Agronomy
Goodfellow: Chap 1 Introduction
The Importance of “Genomes to Fields”
Accelerate Your Self-Service Data Analytics
Data Warehousing and Data Mining
INNOvation in TRAINING BUSINESS ANALYSTS HAO HElEN Zhang UniVERSITY of ARIZONA
Visualizing and Understanding Convolutional Networks
Dtk-tools Benoit Raybaud, Research Software Manager.
Digital Agriculture Opportunities in Engineering
University of Wisconsin, Madison
Deep Learning for Plant Stress Phenotyping: Trends and Future Perspectives  Asheesh Kumar Singh, Baskar Ganapathysubramanian, Soumik Sarkar, Arti Singh 
THE ASSISTIVE SYSTEM SHIFALI KUMAR BISHWO GURUNG JAMES CHOU
Presentation transcript:

Computational Science as an enabler for sustainable FEW Systems Baskar Ganapathysubramanian Iowa State University NSF FEW Workshop: Oct 12-13, 2015, ISU 1

Computational Science and Engineering Group What do we do: 1)Algorithm design and software implementation 2)Application driven research: Curiosity driven group Overview of research activities related to Plant Sciences NSF FEW Workshop: Oct 12-13, 2015, ISU 2

Feature extraction: Data for crop models Spatial coverage (Dimensions of field) Temporal Coverage (Crop Cycle) Data for validation/input/calibration Data deluge due to sensor advances and data collection improvements Heterogeneous, multi length and time scale data Noisy, gappy data Need to extract traits used for various ‘down stream’ tasks Have to do this in an automated, high throughput, and efficient way Similar issues faced by other disciplines: Astronomy, Particle physics, Driverless automobiles, security and defense applications Machine learning approaches very promising NSF FEW Workshop: Oct 12-13, 2015, ISU 3

Machine Learning Goal of ML is to generalize beyond training data Pattern recognition, perception and control tasks Very difficult to manually encode all features From opsrules.com MNIST dataset TIMIT dataset Breakthrough in learning algorithms. Prominent examples include ‘deep networks’ NVIDIA cuDNN website More data, Better computing infrastructure NSF FEW Workshop: Oct 12-13, 2015, ISU 4

Learning feature labels in scenes: Convolution networks From Le Cun group, Hinton group, Ng group Machine Learning Examples NSF FEW Workshop: Oct 12-13, 2015, ISU 5

From Le Cun group, Hinton group, Ng group Machine Learning Examples Learning a hierarchy of features: Feature extractions using auto-encoders, sparse encoders, Deep Belief networks, Deep Neural Networks NSF FEW Workshop: Oct 12-13, 2015, ISU 6

Basic hypothesis: Use high throughput phenotyping to enable extraction of detailed characteristics of tassels. Challenges: Identification of tassel locations, followed by extraction of tassel features of close to a million images! ML: Agricultural Examples P. Schnable

Basic hypothesis: Use high throughput phenotyping to understand features affecting (a)biotic stress tolerance A. Singh Standard Area Diagram Example Application: Iron Deficiency Chrolosis (IDC) IDC: Inability of plants to absorb iron from soil Current Methods are Visual: -Time consuming -Labor Intensive -Reliability/Consistency issues ML tools for rapid identification. Deploy as apps ML: Agricultural Examples S. Sarkar

ML for Yield Prediction Goal: 1) Collect and curate dataset of economic, agricultural, meteorological, and crop management traits that is used to make predictions. 2) Develop and deploy suite of statistical and ML tools on data 3) Create a workflow that will enable the larger community to utilize data and test methods Yield forecasting: Combination of knowledge-based computer programs (that simulate plant-weather-soil-management interactions) along with soil and environment data and targeted surveys. D. Hayes Companies such as Climate Corp and other big data firms may now be able to beat the USDA at yield forecasting, leading to detrimental asymmetric markets. A publicly available high quality yield prediction tool will enable the producers to make informed decisions thereby ensuring a symmetrical market. S. Sarkar D. Nettleton NSF FEW Workshop: Oct 12-13, 2015, ISU 9

D. Attinger M. Gilbert Simple physiological model of adult maize plant. Validated in field by Matthew Gilbert (UC Davis) Several field-testable traits: stomatal conductance, root, stem, leaf conductance. Input: Hourly weather data. Outputs: Water use, Photosynthetic yield Optimization: Trait identification for productivity Software engineering Code optimization  Integrate with parallel optimization framework  Deploy on HPC systems

Optimization: Trait identification for productivity Pareto front with more than 3 million configurations tested. Ran on XSEDE TACC and local HPC resources (unpublished, 2015). Explored traits that perform under well irrigated vs drought conditions. NSF FEW Workshop: Oct 12-13, 2015, ISU 11

Concluding Observations 1)Leverage (rapid) machine learning developments 2)Learn from progress/best practices in other fields 3)Fast ML models as surrogate models for exploration, uncertainty quantification 4)Visualization and data management become important 5)Data exchange/sharing/interoperability protocols have to be set. 6)Critical to incorporate software engineering practices into the workflow (code reuse, modularity). 7)Need sustained support for software development and maintenance 8)Need to be ready for next generation cyber infrastructure 9)Community based approach?