PPT - SSTD 2011

Report
KwangSoo Yang, Shashi Shekhar
Jing Dai, Sambit Sahu, and Milind Naphade
Department of Computer Science, University of Minnesota
IBM T.J. Watson Research Hawthorne
The importance of water
Water is one of our most important natural resources and water scarcity
may be the most underestimated resource issue facing the world today.
Source:
World Meteorological Organisation (WMO), Geneva, 1996;
Global Environment Outlook 2000 (GEO),
UNEP, Earthscan, London, 1999.
By 2025 about 3 billion people could face water scarcity due to the climate change,
population growth, and increasing demand for water per capita.
- United Nations, The Millennium Project
Water scarcity
Distribution of precipitation is varying in space and time.
High rate of evaporation from surface water resource
Water quality
- Leakage of saline or contaminated water from the land surface
- Water contamination by sewage effluent.
Example) Water Pollution
Water scarcity is not only an issue of enough water but also of access to safe
water.
Developing intelligent water resource management systems is necessary to
remedy the problem.
Current water management
Hand grab sampling
• Crumbling infrastructure
• Leaks and theft in agriculture area
• Few sensors
(home water meter and plant meter)
Water Theft
• Hidden water network
(underground water and buried pipelines)
Water sensors
One technology to remedy this problem is to implement fully integrated systems
which allow monitoring, analyzing, controlling, and optimizing of all aspects of
water flows.
Smarter Water Management
IBM Smarter Planet emphasizes smarter water management for planning,
developing, distributing, and managing optimal use of limited water resources.
Measuring, Monitoring, Modeling, and Managing
Sensing
Metering
Real Time
Data Integration
Real Time
+ Historical data
Data Modeling
+ Analytics
Visualization
+ Decisions
Source: IBM Smarter Water Management
A lot of data are needed to fully understand, model, and predict how water
flows around the planet.
Spatio-Temporal Network (STN)
Water network flow is represented and analyzed as spatio-temporal
network datasets.
Minnesota river network
source: http://geology.com/
Ground water network
source: http://me.water.usgs.gov
Water pipe network
source: Wikipedia
Spatio-temporal network databases (STNDB) will likely be a key component of
smarter water management since effectiveness of decision depends on the quality of
information
Challenges for STN of water networks
The key issue is the quality of dataset to fully understand, model,
and predict water flows in the network.
1. STN datasets not fully observable
- underground natural flows
- buried pipes may shift
2. Assess of STN datasets requires a novel semantics.
ex) Lagrangian reference frame
3. Heterogeneity of real-world STN datasets
Hidden STN
Water Network Tomography
Example) Water Cooling System
The internal structure and status of the cooling
system may not be directly observable due to
radioactive emissions from the damaged
nuclear reactors.
Water Cooling System / Nuclear reactor
source: http://www.firstpr.com.au/jncrisis/
Network tomography is one solution to understand the internal characteristic
of the network using end-to-end measurements, without needing the
cooperation of internal nodes.
infer
Given end-to-end
measurements
topology/connectivity
flow delay or bottleneck
identify
monitor
water loss
Hidden STN
Water Network Tomography
Y1
1
1
0
0
X1
Y2
0
0
1
1
X2
1
0
1
0
X3
=
Y3
Y1
X1
X2
Y2
X3
X4
Y3
Y4
Y4
0
0
0
1
X4
Origin-destination (OD) water network flow
Input
Output
: Given nodes X and Y,
flows at nodes Y
: Estimate A
Objective
: Minimize the error
Constraints
: Incorporate the temporal and spatial dependence
: Sparse matrix
: Tracer data
Y=AX
Ex) Cost matrix
Flow matrix
Connectivity matrix
OD matrix contains several components, including origin, destination,
and barrier information (e.g., max flow, amount of resistance, speed, direction)
N measured data
N2 hidden data
Hardness • under-constrained
• under-determined
STN Non-stationarity
Water supply and consumption patterns change over time
Water
network
supply
demand
Flow distribution in water networks is not i.i.d.
Time varying factors
Ex) Time varying water Consumption
Climate change
Event
Geography
Drought
Contamination
Population
Temperature
Leakage
Factories/Farms
Precipitation
Disaster
Pools
STN Non-stationarity
Spatial location + network connectivity + time-varying property
Datasets grows massively while the density of the datasets becomes sparse.
Example) Water leakage detection system
Historical and real-time datasets
• Inappropriate pressure levels
and flows
• High risk areas in networks
• Burst/corroded pipes
Water networks
ex) sink, branch points, and water mains
Monitoring
Geographical information
ex) home address and elevation
Temporal information
ex) hot moments and weather change
Detecting
anomalies
Complexity of STN datasets
Inflow
Ex) earthquake event
Pipes can be damaged which reduces the flow
rates
Inspections of individual network components
such as buried pipes are often impractical due to
exceedingly large costs and time.
Monitoring data
Network flow
Pressure
Transmission time
OD matrix
Cost Matrix
Flow Matrix
Structure Matrix
1
2
1
3
2 3
4
4
5
5
6
7
8
6
7
9
10 8
11
9
13
12
10
outflow
Detect the water leakage
Recover the damaged pipe line
outflow
14
11
15
12
16
seismogenic outflow
rupture
Event data
Spatial Location
Temporal property
The challenge here is that the anomaly detection algorithm
would be intractable due to the size of the spatio-temporal
network datasets.
Lagrangian reference frame
Time
Water quality
index
1
2
3
4
5
6
7
8
9
10
20
20
20
20
20
20
20
20
20
20
Measurement methods
 Eulerian
: stationary point
 Lagrangian : moving point
Water Quality Index :
40 (bad) – 0 (good)
Moving sensor
Time
Water quality
index
1
2
3
4
20
30
40
40
Environmental Forensics
: Where did contaminant come from ?
: What are hotspots and hot moments ?
Introduction to Environmental Forensics
Brian L. Murphy, Robert D. Morrison
Time
Water quality
index
1
2
3
4
5
6
7
8
9
10
20
40
20
40
20
20
40
20
40
40
Lagrangian reference frame
Access of STN datasets requires a Lagrangian frame of reference which coordinates
STN datasets with STN connectivity.
Time
Time
Time
Time
1
2
3
4
5
6
7
8
9
10
0
0
0
0
0
0
0
0
0
0
1
2
3
4
5
6
7
8
9
10
0
90
0
90
0
0
0
0
0
0
1
2
3
4
5
6
7
8
9
10
0
0
90
0
90
0
0
0
0
0
1
2
3
4
5
6
7
8
9
10
0
0
0
0
0
0
0
0
0
0
(Source: http://www.sfgate.com/cgi-bin/news/oilspill/busan)
Lagrangian reference frame
Need new STN database systems
Example) A moving fluid (ABD)
STN database systems
Snapshot model
Data types
Storage models
Access Methods
Indexes
Queries
Time expanded
graph
General frameworks to analyze STN datasets
- STN models for complex real-world networks
- Novel network analysis models
Mathematical approach
- Real-world network model is unknown or too complex to be mathematically described.
Heterogeneous multi-modal networks
Example) Nokia water supply contamination
Water supply network
Ground water network
River Network
Source: www.crisiscommunication.fi/files/download/ForOnline_NokiaCase.pdf
Sewerage network
STN data integration problem
- Heterogeneous multi-modal networks
- Time-varying properties
- Correlation properties
Population map
Conclusion
Water resource management is one of most important
part for our survival.
We need a Spatio-temporal network databases and
analysis tools to monitoring, analyzing, controlling, and
optimizing of all aspects of water flows.
We poses 3 main challenges to handle spatio-temporal
network datasets for water flows.
Acknowledgement
This work was supported by NSF and USDOD.
References
1. Water: How can everyone have sufficient clean water without conflict?(2010),
United Nations, http://goo.gl/pdsr0, Retrieved Mar 17, 2011.
2. Smarter planet, Wikipedia, http://goo.gl/ay5W8, Retrieved Mar 17, 2011.
3. Water Management, Wikipedia, http://goo.gl/aNllg, Retrieved Mar 17, 2011.
4. Let’s Build a Smarter Planet: Smarter Water Management,
Dr. Cameron Brooks, Sep 22, 2010, IBM, http://goo.gl/XvCIB
5. IBM Smarter Water Keynote(2010), IBM, http://goo.gl/4zRMw
6. Water supply network, Wikipedia, http://goo.gl/cF4IG, Retrieved Mar 17, 2011.
7. Nokia water supply contamination, Wikipedia, http://goo.gl/fDfVx, Retrieved May 30, 2011.
8. Batchelor, G.: An introduction to fluid dynamics. Cambridge Univ Pr (2000)
9. Chartres, C., Varma, S.: Out of Water: From Abundance to Scarcity and
How to Solve the World’s Water Problems. Ft Pr (2010)
10. Chen, F., et al.: Activity analysis based on low sample rate smart meters.
In: Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data
mining(to appear). ACM (2011)
11. Dai, J., Chen, F., Sahu, S., Naphade, M.: Regional behavior change detection via local spatial scan.
In: Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic
Information Systems. pp. 490–493. ACM (2010)
12. Marien, M.: Jc glenn, tj gordon and e. florescu, 2010 state of the future,
the millennium project, washington, http://www.stateofthefuture.org. Futures (2010)
13. Molden, D.: Water for food, water for life: a comprehensive assessment of
water management in agriculture. Earthscan/James & James (2007)
14. Perry, W.: Grand challenges for engineering. Engineering (2008)
15. Vardi, Y.: Network Tomography: Estimating Source-Destination Traffic Intensities from Link Data.
Journal of the American Statistical Association 91(433) (1996)
Water Pipelines
open
closed
Flow direction
Flow rate
closed
Pressure
open

similar documents