SlideShare une entreprise Scribd logo
1  sur  59
Télécharger pour lire hors ligne
Modeled Population Estimates
from Satellite Imagery and
Microcensus Data
Vince Seaman
Sr. Program Officer, Polio
Global Development Division
Bill & Melinda Gates Foundation
1
© 2013 Bill & Melinda Gates Foundation |
*** Confidential – for internal use only *** 2
WHY ALL THE RESOURCES FOR GIS WORK IN NIGERIA?
AFTER RECORDING ONLY 21 POLIO CASES IN 2010, NIGERIA EXPERIENCED LARGE
INCREASES IN 2011 & 2012…
2
798
388
21
62
122
53
6 0
0
100
200
300
400
500
600
700
800
900
2008 2009 2010 2011 2012 2013 2014 2015
Polio Cases in Nigeria, 2009-15
• Many cases from settlements
not visited by vaccination teams
• Microplans were incomplete
• Target populations were
inaccurate and grossly inflated
in many areas, leading to data
falsification and vaccine waste
• Quality of monitoring and
coverage data was poor
What was behind this?
© 2013 Bill & Melinda Gates Foundation |
*** Confidential – for internal use only ***
3
Ward Maps
from Nigeria
- Incomplete
- Inaccurate
- Out of Date
© 2013 Bill & Melinda Gates Foundation |
*** Confidential – for internal use only *** 4
Existing Public Geodata are Limited to Urban Centers
Automated Feature Extraction (FE) Settlements (ORNL)Adamawa State, Nigeria (OpenStreet Maps)
© 2013 Bill & Melinda Gates Foundation |
*** Confidential – for internal use only *** 5
Manual & Automated Feature Extraction of Satellite Imagery Field Data Collection Settlement Attributes used to
create Ward Boundaries
Points of Interest
2013-16: GIS Base Layers Collected for 11 Northern States
© 2013 Bill & Melinda Gates Foundation |
*** Confidential – for internal use only ***
BASEMAP SUPPORTED GIS TRACKING OF VACCINATION TEAMS
6
Given to Ward Focal Person (WFP)
at LGA HQ each morning
WFP Returns to Ward take-off point
and gives phones to vaccinators
WFP returns to LGA-HQ where
GPS tracks are downloaded
Vaccinators return phone to
WFP at the end of their day
Feedback for daily coverage provided to
WFPs and LGA team at daily meeting
5a-6:30a 7a-8a
11a-5p
2p–8p
Tracks uploaded to
EOCs/Dashboard via MiFi
Missed Settlement Report
generated at end of days 4 & 5
GPS – enabled
Android phone
Collects time-stamped
GIS coordinates every 2
minutes
Team Movements Visualized = Improved Accountability
http://vts.eocng.org
© 2013 Bill & Melinda Gates Foundation |
*** Confidential – for internal use only *** 8
Post Campaign
Reports at all
Levels:
LGA/Ward Overview
• GeoCoverage
• Settlements Visited & % of total
• Target Population visited &
% of total
• Heat Map showing
visited/missed settlements
http://vts.eocng.org/
Settlement Total U5 Houses Total U5
UNG MAIGADI 5055 1011 45 369 75
State Master List GIS Est
Kaduna – Birnin Gwari LGA
Other Use Cases for
Remote Sensing
Resources
Can we validate local
administrative
population data?
• Census data unavailable below
Admin 1 level
• Inflated population counts
result in vaccine, bed net, and
other critical supply shortages
• Validation tool needed
500 people or
5000 people?
WorldPop:
Redistributing census count data
All Public Population Density Resources based on
National Census Data
November 14, 2018
Demographics &
Mobility mapping
Andy Tatem, University of Southampton
Total Population: 170,123,740
(July 2012 estimate)
Administrative units - 774
The Solution: High Resolution
Population Distribution
In Northern Nigeria
BudhendraBhaduri
EddieBright,AnilCheriyadat, AmyRose,JakeMcKee,Jeanette
Weaver,MaryUrban,RajuVatsavai
Neighborhood Housing Characteristics Give Different LINE PATTERNS
Local line patterns a good descriptor of the spatial arrangements. Line statistics can representative of structural dimensions
All Urban Areas Have 4-6
Neighborhood Types
- Based on size, shape, and
orientation of structures
- Neighborhood type is related to
building use: residential,
commercial, mixed-use, etc.
Local geospatial
neighborhoods are
represented using rich
feature descriptors
composed of edge,
texture, lines and
spectral attributes
Managed by UT-Battelle
for the Department of Energy
Neighborhood Classification Scheme – N. Nigeria
 Neighborhood Type Layer for Nigeria (based on Kano metro area)
– established 7 residential settlement types (6 Urban, 1 rural) + non-residential
 Population density of each neighborhood type determined
from microcensus data (>100 clusters for each type)
M: rural
Z: non-residential
Slums
Slums
November 14, 2018 © 2013 Bill & Melinda Gates Foundation | 15
NHtypeState Nigeria
A 8.1
B 19.3
C 0.3
D 2.7
E 0.3
F 0.9
M 67.3
Z 1.1
23% of Nigerians live
in Urban areas.
Of those, 36% live in slum
(Type A) neighborhoods.
Cross River = 64% of the urban population lives in Type A Sokoto =46% of the urban population lives in Type A
GIS Population Model Microcensus Methods – Middle and Southern States
Middle/South Total = 1600 clusters in 8 statesMicrocensus Methods:
• All buildings assigned to one of 8 neighborhood
types (Z= non-residential)
• 200 polygons selected randomly for each state
representing all neighborhood types in that state
equally (approx. 10,000 HH/state)
• Each polygon contains approx. 50 residential
structures
• Microcensus team obtains total population and the
U5 count for each HH in polygon
• Decision for which microcensus data is used for
which state based on proximity and demographics
OUTPUT: 90-meter population grid with total counts, or selected demographic
197,696,904 196,477,453
NPC 2017
Census
GIS Estimates
Adjusted, 2017
GIS Estimates Nearly Identical to Census Projections at the National level
What explains the differences at
the sub-national levels?
Census projections assume:
- states grow at a similar rate
(2.7 – 3.4%/yr)
- all LGAs in a state grow at the
same rate.
GIS estimates indicate that yearly
state growth rates range from -
2.8% (Bayelsa) to 16.3% (FCT).
Differences between GIS estimates and Census projections
increase in magnitude from National  Local levels
Potential Impact for Polio:
National GIS U5 Estimate = 31,715,584
Mar 2017 NID: Total OPV = 59,445,512
19
Pending
• Haiti – Population estimates and settlement features for entire country;
settlement names and POIs limited to existing data sources.
• DRC – Population estimates, settlements/POIs, and Health Zone catchment
areas for Kinshasa & Bandundu. Bas Congo in process.
• Cameroon – Settlement features for entire country; 80% of settlement
names and POIs collected, population estimates in-process.
• Other GRID3 countries to be completed in 2018: Ethiopia, Tanzania, Zambia
http://geopode.world/
November 14, 2018
© 2013 Bill & Melinda Gates
Foundation |
20
Select the Layers tab to
see the drop-down
Map layers and Total
Population or < 5
population can be
selected here
Type in coordinates to go
to a specific place
Custom Demographics
slider: 0-12 mos, 5 year
intervals
Polygon and point
buffer options
Print Screen
Change
Basemap
Scale Bar
POPULATION MODEL – USER INTERFACE OPTIONS
SELECT USER-DEFINED BUFFER AROUND A POINT
21
Retrieving settlement names and estimated
population/target population using a 2km buffer
around a Health Facility
Other Potential Output Columns:
• H2R/Outreach Settlement? Y/N
• Target Pop: <12mos, <15 years
• Vaccine/Supply requirements
Custom polygons can be drawn for catchment areas
Delineating team day areas to estimate resource requirements22
Architecture
http://geopode.world/
© 2013 Bill & Melinda Gates Foundation |
*** Confidential – for internal use only *** 23
Challenges Identified using Population Estimates
• Flat national demographic fractions are not accurate
• Administrative Boundary shapefiles are imprecise
• Census Projections are Not Reliable Below the State Level
• Cluster Surveys may not sample representative neighborhoods
GIS estimates use U5 population modeled from DHS, MICS and other survey data
Alegana, et al. 2015 http://rsif.royalsocietypublishing.org/
Nigeria uses 20% of total population to estimate the U5 target, but the modeled range is 11 – 23%
MOST COUNTRIES USE A FIXED % FOR KEY DEMOGRAPHIC GROUPS, BUT
THE ACTUAL VALUES VARY WIDELY State %U1 %U5 %U15
Abia 2.5% 13.2% 37.9%
Adamawa 2.9% 18.5% 52.2%
Akwa Ibom 3.2% 13.1% 36.1%
Anambra 2.3% 14.0% 39.7%
Bauchi 3.6% 20.7% 54.2%
Bayelsa 3.5% 14.7% 38.9%
Benue 2.5% 15.3% 44.8%
Borno 3.2% 21.6% 56.5%
Cross River 2.9% 13.3% 37.2%
Delta 2.8% 14.2% 38.8%
Ebonyi 2.4% 14.4% 42.4%
Edo 2.1% 13.0% 36.6%
Ekiti 2.0% 12.2% 35.4%
Enugu 2.2% 14.3% 41.2%
Fct, Abuja 2.2% 15.0% 41.2%
Gombe 3.1% 19.8% 53.1%
Imo 2.5% 13.9% 39.5%
Jigawa 3.6% 22.5% 58.2%
Kaduna 2.9% 18.3% 48.9%
Kano 3.1% 21.1% 54.3%
Katsina 3.3% 21.1% 54.8%
Kebbi 3.4% 19.6% 52.2%
Kogi 2.0% 14.3% 41.9%
Kwara 2.2% 13.3% 37.9%
Lagos 2.0% 13.0% 35.2%
Nasarawa 2.5% 15.7% 44.4%
Niger 3.1% 17.2% 47.1%
Ogun 1.9% 13.3% 38.4%
Ondo 2.1% 13.1% 38.2%
Osun 1.7% 12.6% 37.2%
Oyo 1.8% 12.5% 36.3%
Plateau 2.4% 16.5% 46.0%
Rivers 3.0% 13.4% 36.0%
Sokoto 3.6% 20.7% 52.8%
Taraba 2.7% 16.2% 47.0%
Yobe 3.7% 22.2% 57.2%
Zamfara 3.2% 20.7% 55.4%
National Average 2.7% 16.9% 46.0%
Nigeria Official % 4.0% 20.0% 47.6%
GIS Modeled % U1, U5 and U15
Administrative Boundaries
Nearly all existing data is inaccurate !
VTS
Boundary
Published
Census
Boundary
Metro LGAs
Reported sub-national
boundaries do not align
with GIS data collected
in Nigeria
New Polio “Operational”
Boundaries (VTS), GADM*
and UN-WHO (Census) all
Differ
Gwale LGA, Kano State
Jan 2015
VTS
Boundary
GADM
Boundary
UN/Census
Boundary
*GADM = internationally-recognized global boundary
resource developed by Robert Hijmans & colleagues at
the University of California, Berkeley and the University
of California, Davis (Alex Mandel)
http://www.gadm.org/
“Official”
Boundaries
Inaccurate?
GIS Population Estimates: VTS, GADM1, UN-WHO Boundaries
1GADM Version 2.8, March 2016. http://www.gadm.org/
VTS Boundaries
Pop. Est. = 678,198
GADM Boundaries
Pop. Est. = 372,703
UN-WHO (Census) Boundaries
Pop. Est. = 484,934
Gwale LGA, Kano State, Nigeria
Use of incorrect
boundaries impacts
population estimates
November 14, 2018 © 2013 Bill & Melinda Gates Foundation | 28
NIE - Yearly growth projections are not reliable at sub-national levels
Census projections result from a flat growth rate of (2.7-3.4%/year) applied at the state level,
but urban population growth has rapidly outpaced rural growth.
SOLUTION: GIS estimates, based on 2015-16 imagery building footprint, reflect actual urban and
rural population distribution down to the settlement level
2006 and 2014 Kano
Settlement Extents
Percent Change in Settled
Area by LGA, 2006-2014
Managed by UT-Battelle
for the Department of Energy
Calculated Rates of Annual Population Change for Both Methods (2006-2014)
0
1
2
3
4
5
6
7
8
9
Prorating
Modeling
(Census Projections)
(GIS Estimates)
Z = Non-ResidentialNeighborhood Types - Kano Metro Area
Cluster Survey Samples –
Are they representative?
2016 National HH Survey Cluster
locations Kano Metro LGAs
Survey Cluster –
HH Points
> 90% of Household cluster points from
Type B & E, none from Types A & F.
70% of population lives in Type B & E,
17% in Types A & F.
Micro-Census of
One Ward in Sokoto State
Sokoto SERICC / EOC
2 May 2018
Center for Global Health
Global Immunization Division/Polio Eradication Branch/Nigeria Team
GIS Estimates – Validation Data
Goals:
• Validate the enumeration results of the Demand Generation project
for children younger than 1 in one ward
• Obtain a more accurate count of the total population living in the
selected ward
• Validate the GIS estimates for different age groups in the selected
ward
*
* Ward boundary from Vaccination Tracking
System (VTS)
Magarya Ward
Boundary
• from polio Vaccination
Tracking System (VTS)
• “operational” status –
not authorized by GoN
• no other shapefiles
exist for Ward
boundaries (Admin3)
Populated Portion of Magarya Ward (VTS Operational Boundary)
Boundary does
not follow street
or natural feature
Magarya Ward (Wurno LGA) selected for small size, ease of access
CDC aligned
boundaries to
closest road
Enumeration
Output
• Residential status of all
HHs collected
• Age/gender for all
residents
• All buildings geocoded
• Some points fell
outside VTS boundary
Ward Boundary
Adjusted
• New boundary
captures all
enumerated HHs
• Represents “true”
Ward boundary
Ward Population
Queried from GIS
Raster
• Landscan V1.1 gridded
layer (90 meter resolution)
• Dots represent centroid of
each 90 meter grid square
• Value is estimate of total
population w/in each
square
• Values are counted if
centroid is within Ward
boundary
8673
282
1548
2931
8708
337
1887
4833
26,205
396
2546
5241
16,994
680
3399
8089
3584
TOTAL U1 U5 U15
MAGARYA ENUMERATION
GIS estimate <1%
variance from
enumerated value
*
Technical and Programmatic Guidance
Adjustment of target population in the context of the
Global Polio Eradication Initiative (GPEI)
Version 1.1 13 Feb, 2018
Total projected savings
in 2018:
~$143m
• Microplanning requirements for fixed-post vaccination campaigns
(e.g. Polio-IPV, Measles, Yellow Fever, etc.)
– The activity should take place over “X” days maximum
– Children should not have to walk more than 1km to get vaccinated
– Fixed-Post capacity (# of children vaccinated per day)
• 60 children a day in rural areas
• 100 children a day in urban areas
• Question: how many fixed posts are required and where should they
be located?
Fixed-Post Vaccination Microplanning:
Determining Optimum post location and resource requirements
4
2
Fixed Post Microplanning
Settlements
within 1km
clustered
# of Health
Camp days
calculated
Problem:
Vaccination Posts or
Health Camps (HCs)
had to be located no
further than 1km from
any resident.
Solution:
An automated tool was
created that clustered
settlements within 1km
of one another.
Target populations were
then used to determine
the number of days the
HC would work in a
cluster.
Result:
>95% coverage overall,
no missed settlements
2017-18 National
Measles Campaign
Nigeria
• GIS maps and
population estimates
used to support
microplanning and
locating vaccination
posts in the North.
• Traditional
microplanning used in
the south (GIS
mapping in-process).
Unweighted Measles Vaccination Post-Campaign Coverage Survey, by EA
– Nigeria, 2017-18
Source: Nigeria MVC Post Campaign Coverage Survey, 2017-18
90% to <95%
≥95%
>0% to <90%
0%
Proportion of Surveyed
Children Vaccinated
GIS
Microplanning
States
© 2013 Bill & Melinda Gates Foundation |
*** Confidential – for internal use only ***
Digital Elevation
Map (DEM) layers
can detect
changes in
elevation based
on the resolution.
For 30 meter
resolution, the
contour lines are
spaced 30 meters
apart.
Environmental Surveillance Site Assessment
- catchment area size, location and population estimates
Junction Point
Drainage Line
Watershed-Catchment
Est. Population
Collected at Junction
http://maps.novel-t.ch/
Mobile ODK Tools Available for ES Data Collection
BLUE LINE Field data
Collection
Sample Data Collection Options to Improve Specimen Tracking
Each Kit has bar code
to identify specimen
1. Select Site Name from drop-down list
2. Scan Bar Code
3. Collect GPS Coordinates (date, time stamp)
4. Enter site specific info
5. Select Name of S.O. from drop-down list
6. Upload Form (to Lab, CO, RO, POLIS?)
Surveillance Officer
Collects Specimen
ODK App on Android
Phone Documents
Sample Collection
1. Bar Code scanned upon arrival in Lab
2. Updates ODK Data Form
3. Transit time auto-calculated
4. Results of Lab Analysis added
5. Upload Form (to CO, RO, POLIS?)
Scan Bar Code with
Android phone
Public Health & Other Applications
Ebola Outbreak Response SupportPolio Environmental Surveillance
IPV & RI Microplanning
LQAS Cluster Selection and Validation
Imagery Change Analysis in Conflict Settings
Bed net Distribution - CRS
Electric Power Grid Planning - WB
Health Zone Catchment Areas, DRC
(NTD-HAT)
eSURV – AFP Surveillance Tracking
AVADAR – Community-Based
AFP Surveillance
Others
Nigeria Geo-Referenced Infrastructure and
Demographic Data for Development (GRID3) Project
29/06/2018
2018-19: DRC, Tanzania, Zambia, Mozambique
Ecopia Building Footprint Layer (© DigitalGlobe)
Tanzania, Zambia, Mozambique, Sierra Leone, Somalia*)
New Developments in Automated Feature Extraction
Country Acq.Date Format Acq. Date Vendor As Of Source
Nigeria 2016 TPK Tiles 2016 ORNL 2016-18 ORNL-Flowminder
Nigeria 2014-16 ESRI Cache
Cameroon 2015 ESRI Cache 2016 ORNL
Afghanistan 2015 TPK Tiles 2016 ORNL 2017 Flowminder-UNFPA
Pakistan 2015 TPK Tiles 2016 ORNL
Lake Chad Region 2017 ORNL 2017 ORNL-Flowminder
Ethiopia1
2017 ORNL
Zambia1
2017 ORNL
DRC2
2016-17 2016-17 ORNL 2018 ORNL-Flowminder
Haiti 2016 TPK Tiles 2016 ORNL
Ghana 2018 TIF 2018
Tanzania 2018 Ecopia
Mozambique 2018 Ecopia
Sierra Leone 2018 Ecopia
Somalia-South 2018 Ecopia
Somalia-North 2016 DG
1
Awaiting licensing 2
partial
*All imagery is 4-6 band, color, 0.5m, <10% cloud cover
Imagery* Settlement Layer GIS Population Estimates
BMGF Polio - Imagery & Derivative Products Resources
Share the
VISION!
Contact Info:
Vince Seaman, Ph.D.
Sr. Program Officer, Polio - Global Development
Bill & Melinda Gates Foundation
V +1.206.770.2351
C +1.206.669-7259
E Vincent.Seaman@gatesfoundation.org
54 | Copyright © 2015 Intellectual Ventures Management, LLC (IV). All rights reserved.
Remote Sensing to Locate HIV High-Risk Populations
Primary goal
• Automatic
identification of
fishing boats
• Small boats such
as dugout
canoes, not large
commercial
vessels
Secondary factors
• Season and date
• Water hyacinth
• Proximity to
roads and
settlements
Boat in water
(Asembo Bay, Kenya) Boats on shore
A large fish market
(Kisumu, Kenya)
DiSARM is a tool
being used at national
scale in Namibia and
Botswana to help
malaria programs plan,
implement and monitor
indoor residual spray
campaigns.
Observed Predicted
• Ensemble machine learning used to predict which buildings are residential and non-residential
• ~85-90% of residential and non-residential correctly classified
• Sturrock et al (2018)
Predicting residential structures for Malaria IRS
57
Working with 38 wards, containing in total 141,812 rooms
(structures)
Operational units can be selected for inclusion in the campaign and an
estimate of the number of structures in those areas is presented
Nigeria GRID3 priority focal areas for now include: Health, Education, Water Resource, Agriculture, Population/Demography and
Survey. Some of the potential Use cases considered include:
Potential Use-cases for GRID3 Data in Nigeria
S/N Thematic Area Use-Case
1 Survey Testing Traditional vs Gridded population survey methodology with NBS.
2 Health 1. Developement of National geo-mapped Health facility Registry.
2. Emergency refferel care services (Linking ambulances to Facilities).
3 Education 1. School maps visualization.
2. School catchment area maps.
3. Gender ratio, Student-Teacher ratio maps etc
4 Water Resurces 1. Access to water per settlement
2. Flood disaster prediction
5 Agriculture 1. Land Use management
2. Farm-Market distance
3. Sustainability Oriented Agrological Production Mapping (SOAPM)
6 Census 1. Support to hybrid census (including micro-census)
2. Verifying EADs using high resolution imagery;
3. Real time monitoring of enumeration
7 Governance 1. community focused monitoring and tracking implementation of projects

Contenu connexe

Similaire à IMED 2018: Modeled Population Estimates from Satellite Imagery and Microcensus Data

M-governance project - NRBuzz presentation by A.Salim, A.Orwa &amp; H. Moraa
M-governance project - NRBuzz presentation by A.Salim, A.Orwa &amp; H. MoraaM-governance project - NRBuzz presentation by A.Salim, A.Orwa &amp; H. Moraa
M-governance project - NRBuzz presentation by A.Salim, A.Orwa &amp; H. Moraa
iHub Research
 
Tim meeting with investors - agosto 2014
Tim   meeting with investors - agosto 2014Tim   meeting with investors - agosto 2014
Tim meeting with investors - agosto 2014
TIM RI
 
Meeting with Investors - November 2014
Meeting with Investors - November 2014Meeting with Investors - November 2014
Meeting with Investors - November 2014
TIM RI
 
Meeting with TIM in Brasilia
Meeting with TIM in BrasiliaMeeting with TIM in Brasilia
Meeting with TIM in Brasilia
TIM RI
 
Interoperable and Distributed Processing in GIS to Sustain the Development of...
Interoperable and Distributed Processing in GIS to Sustain the Development of...Interoperable and Distributed Processing in GIS to Sustain the Development of...
Interoperable and Distributed Processing in GIS to Sustain the Development of...
Forokoro Kone
 

Similaire à IMED 2018: Modeled Population Estimates from Satellite Imagery and Microcensus Data (20)

2015 ReSAKSS Conference – Day 2 - Maximo Torero
2015 ReSAKSS Conference – Day 2 - Maximo Torero2015 ReSAKSS Conference – Day 2 - Maximo Torero
2015 ReSAKSS Conference – Day 2 - Maximo Torero
 
SDG Prioritization to Leave No One Behind
SDG Prioritization to Leave No One BehindSDG Prioritization to Leave No One Behind
SDG Prioritization to Leave No One Behind
 
M-governance project - NRBuzz presentation by A.Salim, A.Orwa &amp; H. Moraa
M-governance project - NRBuzz presentation by A.Salim, A.Orwa &amp; H. MoraaM-governance project - NRBuzz presentation by A.Salim, A.Orwa &amp; H. Moraa
M-governance project - NRBuzz presentation by A.Salim, A.Orwa &amp; H. Moraa
 
Determinants of Mobile Broadband Use in Developing Economies: Evidence from N...
Determinants of Mobile Broadband Use in Developing Economies: Evidence from N...Determinants of Mobile Broadband Use in Developing Economies: Evidence from N...
Determinants of Mobile Broadband Use in Developing Economies: Evidence from N...
 
AKADEMIYA2063-CORAF Regional Learning Event, July 6 2021: Predicting Crop Pr...
 AKADEMIYA2063-CORAF Regional Learning Event, July 6 2021: Predicting Crop Pr... AKADEMIYA2063-CORAF Regional Learning Event, July 6 2021: Predicting Crop Pr...
AKADEMIYA2063-CORAF Regional Learning Event, July 6 2021: Predicting Crop Pr...
 
Tim meeting with investors - agosto 2014
Tim   meeting with investors - agosto 2014Tim   meeting with investors - agosto 2014
Tim meeting with investors - agosto 2014
 
Pro-Poor Urban Development: China and Africa Workshop Introductory Session on...
Pro-Poor Urban Development: China and Africa Workshop Introductory Session on...Pro-Poor Urban Development: China and Africa Workshop Introductory Session on...
Pro-Poor Urban Development: China and Africa Workshop Introductory Session on...
 
Pro-Poor Urban Development: China and Africa Workshop - "Participatory mappin...
Pro-Poor Urban Development: China and Africa Workshop - "Participatory mappin...Pro-Poor Urban Development: China and Africa Workshop - "Participatory mappin...
Pro-Poor Urban Development: China and Africa Workshop - "Participatory mappin...
 
Meeting with Investors - November 2014
Meeting with Investors - November 2014Meeting with Investors - November 2014
Meeting with Investors - November 2014
 
Community-level data
Community-level dataCommunity-level data
Community-level data
 
Regional Snapshot: 2019 Federal Opportunity Zones
Regional Snapshot: 2019 Federal Opportunity ZonesRegional Snapshot: 2019 Federal Opportunity Zones
Regional Snapshot: 2019 Federal Opportunity Zones
 
wcms_718539 (1).pdf
wcms_718539 (1).pdfwcms_718539 (1).pdf
wcms_718539 (1).pdf
 
The role of ict in poverty alleviation among rural farmers in abia state
The role of ict in poverty alleviation among rural farmers in abia stateThe role of ict in poverty alleviation among rural farmers in abia state
The role of ict in poverty alleviation among rural farmers in abia state
 
Meeting with TIM in Brasilia
Meeting with TIM in BrasiliaMeeting with TIM in Brasilia
Meeting with TIM in Brasilia
 
Session4.2_India.ppt
Session4.2_India.pptSession4.2_India.ppt
Session4.2_India.ppt
 
Express Technology Sabha Award 2015 E-Governance Champion presentation
Express Technology Sabha Award 2015 E-Governance Champion presentationExpress Technology Sabha Award 2015 E-Governance Champion presentation
Express Technology Sabha Award 2015 E-Governance Champion presentation
 
Land expropriation, peri-urbanization and income diversification: Evidence fr...
Land expropriation, peri-urbanization and income diversification: Evidence fr...Land expropriation, peri-urbanization and income diversification: Evidence fr...
Land expropriation, peri-urbanization and income diversification: Evidence fr...
 
Interoperable and Distributed Processing in GIS to Sustain the Development of...
Interoperable and Distributed Processing in GIS to Sustain the Development of...Interoperable and Distributed Processing in GIS to Sustain the Development of...
Interoperable and Distributed Processing in GIS to Sustain the Development of...
 
Community-level data
Community-level dataCommunity-level data
Community-level data
 
Blum investment assessment_final_subm
Blum investment assessment_final_submBlum investment assessment_final_subm
Blum investment assessment_final_subm
 

Plus de Louisa Diggs

Plus de Louisa Diggs (20)

Workshop: Quantifying Error in Training Data for Mapping and Monitoring the E...
Workshop: Quantifying Error in Training Data for Mapping and Monitoring the E...Workshop: Quantifying Error in Training Data for Mapping and Monitoring the E...
Workshop: Quantifying Error in Training Data for Mapping and Monitoring the E...
 
Using Active Learning to Quantify how Training Data Errors Impact Classificat...
Using Active Learning to Quantify how Training Data Errors Impact Classificat...Using Active Learning to Quantify how Training Data Errors Impact Classificat...
Using Active Learning to Quantify how Training Data Errors Impact Classificat...
 
Machine Learning for Better Maps
Machine Learning for Better MapsMachine Learning for Better Maps
Machine Learning for Better Maps
 
Generating Training Data from Noisy Measrements
Generating Training Data from Noisy MeasrementsGenerating Training Data from Noisy Measrements
Generating Training Data from Noisy Measrements
 
Cropped Field Boundaries, Food Systems, & Fire
Cropped Field Boundaries, Food Systems, & FireCropped Field Boundaries, Food Systems, & Fire
Cropped Field Boundaries, Food Systems, & Fire
 
Challenges to Large Scale Mapping: Can Data Geometry Help?
Challenges to Large Scale Mapping: Can Data Geometry Help?Challenges to Large Scale Mapping: Can Data Geometry Help?
Challenges to Large Scale Mapping: Can Data Geometry Help?
 
A Random Walk of Issues Related to Training Data and Land Cover Mapping
A Random Walk of Issues Related to Training Data and Land Cover MappingA Random Walk of Issues Related to Training Data and Land Cover Mapping
A Random Walk of Issues Related to Training Data and Land Cover Mapping
 
Assessing Land Cover Change using Uncertain Data
Assessing Land Cover Change using Uncertain DataAssessing Land Cover Change using Uncertain Data
Assessing Land Cover Change using Uncertain Data
 
Informal Settlements and Cadastral Mapping
Informal Settlements and Cadastral MappingInformal Settlements and Cadastral Mapping
Informal Settlements and Cadastral Mapping
 
Sources of Map Error in Public Health Activities and Operations Research
Sources of Map Error in Public Health Activities and Operations ResearchSources of Map Error in Public Health Activities and Operations Research
Sources of Map Error in Public Health Activities and Operations Research
 
Measuring the impact of label noise on semantic segmentation using rastervision
Measuring the impact of label noise on semantic segmentation using rastervisionMeasuring the impact of label noise on semantic segmentation using rastervision
Measuring the impact of label noise on semantic segmentation using rastervision
 
Mapping Smallholder Yields Using Micro-Satellite Data
Mapping Smallholder Yields Using Micro-Satellite DataMapping Smallholder Yields Using Micro-Satellite Data
Mapping Smallholder Yields Using Micro-Satellite Data
 
Crowdsourcing Land Cover and Land Use Data: Experiences from IIASA
Crowdsourcing Land Cover and Land Use Data: Experiences from IIASACrowdsourcing Land Cover and Land Use Data: Experiences from IIASA
Crowdsourcing Land Cover and Land Use Data: Experiences from IIASA
 
IMED 2018: The use of remote sensing, geostatistical and machine learning met...
IMED 2018: The use of remote sensing, geostatistical and machine learning met...IMED 2018: The use of remote sensing, geostatistical and machine learning met...
IMED 2018: The use of remote sensing, geostatistical and machine learning met...
 
IMED 2018: Predicting the environmental suitability of podoconiosis in Ethiopia
IMED 2018: Predicting the environmental suitability of podoconiosis in EthiopiaIMED 2018: Predicting the environmental suitability of podoconiosis in Ethiopia
IMED 2018: Predicting the environmental suitability of podoconiosis in Ethiopia
 
IMED 2018: Landcover/habitat
IMED 2018: Landcover/habitatIMED 2018: Landcover/habitat
IMED 2018: Landcover/habitat
 
IMED 2018: An intro to Remote Sensing and Machine Learning
IMED 2018: An intro to Remote Sensing and Machine LearningIMED 2018: An intro to Remote Sensing and Machine Learning
IMED 2018: An intro to Remote Sensing and Machine Learning
 
IMED 2018: Mapping Monkeypox risk in the Congo Basin using Remote Sensing and...
IMED 2018: Mapping Monkeypox risk in the Congo Basin using Remote Sensing and...IMED 2018: Mapping Monkeypox risk in the Congo Basin using Remote Sensing and...
IMED 2018: Mapping Monkeypox risk in the Congo Basin using Remote Sensing and...
 
IMED 2018: Predicting spatiotemporal risk of yellow fever using a machine lea...
IMED 2018: Predicting spatiotemporal risk of yellow fever using a machine lea...IMED 2018: Predicting spatiotemporal risk of yellow fever using a machine lea...
IMED 2018: Predicting spatiotemporal risk of yellow fever using a machine lea...
 
IMED 2018: Innovations and Challenges in the Use of Open-source Remote Sensin...
IMED 2018: Innovations and Challenges in the Use of Open-source Remote Sensin...IMED 2018: Innovations and Challenges in the Use of Open-source Remote Sensin...
IMED 2018: Innovations and Challenges in the Use of Open-source Remote Sensin...
 

Dernier

Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night StandCall Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdf
MarinCaroMartnezBerg
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
amitlee9823
 
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangalore
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service BangaloreCall Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangalore
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangalore
amitlee9823
 
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
amitlee9823
 
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get CytotecAbortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Riyadh +966572737505 get cytotec
 
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
only4webmaster01
 
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al BarshaAl Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
AroojKhan71
 
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 

Dernier (20)

Sampling (random) method and Non random.ppt
Sampling (random) method and Non random.pptSampling (random) method and Non random.ppt
Sampling (random) method and Non random.ppt
 
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night StandCall Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
 
Accredited-Transport-Cooperatives-Jan-2021-Web.pdf
Accredited-Transport-Cooperatives-Jan-2021-Web.pdfAccredited-Transport-Cooperatives-Jan-2021-Web.pdf
Accredited-Transport-Cooperatives-Jan-2021-Web.pdf
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdf
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
 
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% SecureCall me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
 
Generative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusGenerative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and Milvus
 
CebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptxCebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptx
 
Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signals
 
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangalore
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service BangaloreCall Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangalore
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangalore
 
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
 
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get CytotecAbortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
 
Anomaly detection and data imputation within time series
Anomaly detection and data imputation within time seriesAnomaly detection and data imputation within time series
Anomaly detection and data imputation within time series
 
Mature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxMature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptx
 
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightCheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
 
Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -
Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -
Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -
 
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
 
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
 
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al BarshaAl Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
 
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
 

IMED 2018: Modeled Population Estimates from Satellite Imagery and Microcensus Data

  • 1. Modeled Population Estimates from Satellite Imagery and Microcensus Data Vince Seaman Sr. Program Officer, Polio Global Development Division Bill & Melinda Gates Foundation 1
  • 2. © 2013 Bill & Melinda Gates Foundation | *** Confidential – for internal use only *** 2 WHY ALL THE RESOURCES FOR GIS WORK IN NIGERIA? AFTER RECORDING ONLY 21 POLIO CASES IN 2010, NIGERIA EXPERIENCED LARGE INCREASES IN 2011 & 2012… 2 798 388 21 62 122 53 6 0 0 100 200 300 400 500 600 700 800 900 2008 2009 2010 2011 2012 2013 2014 2015 Polio Cases in Nigeria, 2009-15 • Many cases from settlements not visited by vaccination teams • Microplans were incomplete • Target populations were inaccurate and grossly inflated in many areas, leading to data falsification and vaccine waste • Quality of monitoring and coverage data was poor What was behind this?
  • 3. © 2013 Bill & Melinda Gates Foundation | *** Confidential – for internal use only *** 3 Ward Maps from Nigeria - Incomplete - Inaccurate - Out of Date
  • 4. © 2013 Bill & Melinda Gates Foundation | *** Confidential – for internal use only *** 4 Existing Public Geodata are Limited to Urban Centers Automated Feature Extraction (FE) Settlements (ORNL)Adamawa State, Nigeria (OpenStreet Maps)
  • 5. © 2013 Bill & Melinda Gates Foundation | *** Confidential – for internal use only *** 5 Manual & Automated Feature Extraction of Satellite Imagery Field Data Collection Settlement Attributes used to create Ward Boundaries Points of Interest 2013-16: GIS Base Layers Collected for 11 Northern States
  • 6. © 2013 Bill & Melinda Gates Foundation | *** Confidential – for internal use only *** BASEMAP SUPPORTED GIS TRACKING OF VACCINATION TEAMS 6 Given to Ward Focal Person (WFP) at LGA HQ each morning WFP Returns to Ward take-off point and gives phones to vaccinators WFP returns to LGA-HQ where GPS tracks are downloaded Vaccinators return phone to WFP at the end of their day Feedback for daily coverage provided to WFPs and LGA team at daily meeting 5a-6:30a 7a-8a 11a-5p 2p–8p Tracks uploaded to EOCs/Dashboard via MiFi Missed Settlement Report generated at end of days 4 & 5 GPS – enabled Android phone Collects time-stamped GIS coordinates every 2 minutes
  • 7. Team Movements Visualized = Improved Accountability http://vts.eocng.org
  • 8. © 2013 Bill & Melinda Gates Foundation | *** Confidential – for internal use only *** 8 Post Campaign Reports at all Levels: LGA/Ward Overview • GeoCoverage • Settlements Visited & % of total • Target Population visited & % of total • Heat Map showing visited/missed settlements http://vts.eocng.org/
  • 9. Settlement Total U5 Houses Total U5 UNG MAIGADI 5055 1011 45 369 75 State Master List GIS Est Kaduna – Birnin Gwari LGA Other Use Cases for Remote Sensing Resources Can we validate local administrative population data? • Census data unavailable below Admin 1 level • Inflated population counts result in vaccine, bed net, and other critical supply shortages • Validation tool needed 500 people or 5000 people?
  • 10. WorldPop: Redistributing census count data All Public Population Density Resources based on National Census Data
  • 11. November 14, 2018 Demographics & Mobility mapping Andy Tatem, University of Southampton Total Population: 170,123,740 (July 2012 estimate) Administrative units - 774 The Solution: High Resolution Population Distribution In Northern Nigeria BudhendraBhaduri EddieBright,AnilCheriyadat, AmyRose,JakeMcKee,Jeanette Weaver,MaryUrban,RajuVatsavai
  • 12. Neighborhood Housing Characteristics Give Different LINE PATTERNS Local line patterns a good descriptor of the spatial arrangements. Line statistics can representative of structural dimensions
  • 13. All Urban Areas Have 4-6 Neighborhood Types - Based on size, shape, and orientation of structures - Neighborhood type is related to building use: residential, commercial, mixed-use, etc. Local geospatial neighborhoods are represented using rich feature descriptors composed of edge, texture, lines and spectral attributes
  • 14. Managed by UT-Battelle for the Department of Energy Neighborhood Classification Scheme – N. Nigeria  Neighborhood Type Layer for Nigeria (based on Kano metro area) – established 7 residential settlement types (6 Urban, 1 rural) + non-residential  Population density of each neighborhood type determined from microcensus data (>100 clusters for each type) M: rural Z: non-residential Slums Slums
  • 15. November 14, 2018 © 2013 Bill & Melinda Gates Foundation | 15 NHtypeState Nigeria A 8.1 B 19.3 C 0.3 D 2.7 E 0.3 F 0.9 M 67.3 Z 1.1 23% of Nigerians live in Urban areas. Of those, 36% live in slum (Type A) neighborhoods. Cross River = 64% of the urban population lives in Type A Sokoto =46% of the urban population lives in Type A
  • 16. GIS Population Model Microcensus Methods – Middle and Southern States Middle/South Total = 1600 clusters in 8 statesMicrocensus Methods: • All buildings assigned to one of 8 neighborhood types (Z= non-residential) • 200 polygons selected randomly for each state representing all neighborhood types in that state equally (approx. 10,000 HH/state) • Each polygon contains approx. 50 residential structures • Microcensus team obtains total population and the U5 count for each HH in polygon • Decision for which microcensus data is used for which state based on proximity and demographics
  • 17. OUTPUT: 90-meter population grid with total counts, or selected demographic
  • 18. 197,696,904 196,477,453 NPC 2017 Census GIS Estimates Adjusted, 2017 GIS Estimates Nearly Identical to Census Projections at the National level What explains the differences at the sub-national levels? Census projections assume: - states grow at a similar rate (2.7 – 3.4%/yr) - all LGAs in a state grow at the same rate. GIS estimates indicate that yearly state growth rates range from - 2.8% (Bayelsa) to 16.3% (FCT). Differences between GIS estimates and Census projections increase in magnitude from National  Local levels Potential Impact for Polio: National GIS U5 Estimate = 31,715,584 Mar 2017 NID: Total OPV = 59,445,512
  • 19. 19 Pending • Haiti – Population estimates and settlement features for entire country; settlement names and POIs limited to existing data sources. • DRC – Population estimates, settlements/POIs, and Health Zone catchment areas for Kinshasa & Bandundu. Bas Congo in process. • Cameroon – Settlement features for entire country; 80% of settlement names and POIs collected, population estimates in-process. • Other GRID3 countries to be completed in 2018: Ethiopia, Tanzania, Zambia http://geopode.world/
  • 20. November 14, 2018 © 2013 Bill & Melinda Gates Foundation | 20 Select the Layers tab to see the drop-down Map layers and Total Population or < 5 population can be selected here Type in coordinates to go to a specific place Custom Demographics slider: 0-12 mos, 5 year intervals Polygon and point buffer options Print Screen Change Basemap Scale Bar POPULATION MODEL – USER INTERFACE OPTIONS
  • 21. SELECT USER-DEFINED BUFFER AROUND A POINT 21 Retrieving settlement names and estimated population/target population using a 2km buffer around a Health Facility Other Potential Output Columns: • H2R/Outreach Settlement? Y/N • Target Pop: <12mos, <15 years • Vaccine/Supply requirements
  • 22. Custom polygons can be drawn for catchment areas Delineating team day areas to estimate resource requirements22 Architecture http://geopode.world/
  • 23. © 2013 Bill & Melinda Gates Foundation | *** Confidential – for internal use only *** 23 Challenges Identified using Population Estimates • Flat national demographic fractions are not accurate • Administrative Boundary shapefiles are imprecise • Census Projections are Not Reliable Below the State Level • Cluster Surveys may not sample representative neighborhoods
  • 24. GIS estimates use U5 population modeled from DHS, MICS and other survey data Alegana, et al. 2015 http://rsif.royalsocietypublishing.org/ Nigeria uses 20% of total population to estimate the U5 target, but the modeled range is 11 – 23% MOST COUNTRIES USE A FIXED % FOR KEY DEMOGRAPHIC GROUPS, BUT THE ACTUAL VALUES VARY WIDELY State %U1 %U5 %U15 Abia 2.5% 13.2% 37.9% Adamawa 2.9% 18.5% 52.2% Akwa Ibom 3.2% 13.1% 36.1% Anambra 2.3% 14.0% 39.7% Bauchi 3.6% 20.7% 54.2% Bayelsa 3.5% 14.7% 38.9% Benue 2.5% 15.3% 44.8% Borno 3.2% 21.6% 56.5% Cross River 2.9% 13.3% 37.2% Delta 2.8% 14.2% 38.8% Ebonyi 2.4% 14.4% 42.4% Edo 2.1% 13.0% 36.6% Ekiti 2.0% 12.2% 35.4% Enugu 2.2% 14.3% 41.2% Fct, Abuja 2.2% 15.0% 41.2% Gombe 3.1% 19.8% 53.1% Imo 2.5% 13.9% 39.5% Jigawa 3.6% 22.5% 58.2% Kaduna 2.9% 18.3% 48.9% Kano 3.1% 21.1% 54.3% Katsina 3.3% 21.1% 54.8% Kebbi 3.4% 19.6% 52.2% Kogi 2.0% 14.3% 41.9% Kwara 2.2% 13.3% 37.9% Lagos 2.0% 13.0% 35.2% Nasarawa 2.5% 15.7% 44.4% Niger 3.1% 17.2% 47.1% Ogun 1.9% 13.3% 38.4% Ondo 2.1% 13.1% 38.2% Osun 1.7% 12.6% 37.2% Oyo 1.8% 12.5% 36.3% Plateau 2.4% 16.5% 46.0% Rivers 3.0% 13.4% 36.0% Sokoto 3.6% 20.7% 52.8% Taraba 2.7% 16.2% 47.0% Yobe 3.7% 22.2% 57.2% Zamfara 3.2% 20.7% 55.4% National Average 2.7% 16.9% 46.0% Nigeria Official % 4.0% 20.0% 47.6% GIS Modeled % U1, U5 and U15
  • 25. Administrative Boundaries Nearly all existing data is inaccurate ! VTS Boundary Published Census Boundary Metro LGAs Reported sub-national boundaries do not align with GIS data collected in Nigeria
  • 26. New Polio “Operational” Boundaries (VTS), GADM* and UN-WHO (Census) all Differ Gwale LGA, Kano State Jan 2015 VTS Boundary GADM Boundary UN/Census Boundary *GADM = internationally-recognized global boundary resource developed by Robert Hijmans & colleagues at the University of California, Berkeley and the University of California, Davis (Alex Mandel) http://www.gadm.org/ “Official” Boundaries Inaccurate?
  • 27. GIS Population Estimates: VTS, GADM1, UN-WHO Boundaries 1GADM Version 2.8, March 2016. http://www.gadm.org/ VTS Boundaries Pop. Est. = 678,198 GADM Boundaries Pop. Est. = 372,703 UN-WHO (Census) Boundaries Pop. Est. = 484,934 Gwale LGA, Kano State, Nigeria Use of incorrect boundaries impacts population estimates
  • 28. November 14, 2018 © 2013 Bill & Melinda Gates Foundation | 28 NIE - Yearly growth projections are not reliable at sub-national levels Census projections result from a flat growth rate of (2.7-3.4%/year) applied at the state level, but urban population growth has rapidly outpaced rural growth. SOLUTION: GIS estimates, based on 2015-16 imagery building footprint, reflect actual urban and rural population distribution down to the settlement level 2006 and 2014 Kano Settlement Extents Percent Change in Settled Area by LGA, 2006-2014
  • 29. Managed by UT-Battelle for the Department of Energy Calculated Rates of Annual Population Change for Both Methods (2006-2014) 0 1 2 3 4 5 6 7 8 9 Prorating Modeling (Census Projections) (GIS Estimates)
  • 30. Z = Non-ResidentialNeighborhood Types - Kano Metro Area Cluster Survey Samples – Are they representative? 2016 National HH Survey Cluster locations Kano Metro LGAs Survey Cluster – HH Points > 90% of Household cluster points from Type B & E, none from Types A & F. 70% of population lives in Type B & E, 17% in Types A & F.
  • 31. Micro-Census of One Ward in Sokoto State Sokoto SERICC / EOC 2 May 2018 Center for Global Health Global Immunization Division/Polio Eradication Branch/Nigeria Team GIS Estimates – Validation Data Goals: • Validate the enumeration results of the Demand Generation project for children younger than 1 in one ward • Obtain a more accurate count of the total population living in the selected ward • Validate the GIS estimates for different age groups in the selected ward
  • 32. * * Ward boundary from Vaccination Tracking System (VTS)
  • 33. Magarya Ward Boundary • from polio Vaccination Tracking System (VTS) • “operational” status – not authorized by GoN • no other shapefiles exist for Ward boundaries (Admin3)
  • 34. Populated Portion of Magarya Ward (VTS Operational Boundary) Boundary does not follow street or natural feature
  • 35. Magarya Ward (Wurno LGA) selected for small size, ease of access CDC aligned boundaries to closest road
  • 36. Enumeration Output • Residential status of all HHs collected • Age/gender for all residents • All buildings geocoded • Some points fell outside VTS boundary
  • 37. Ward Boundary Adjusted • New boundary captures all enumerated HHs • Represents “true” Ward boundary
  • 38. Ward Population Queried from GIS Raster • Landscan V1.1 gridded layer (90 meter resolution) • Dots represent centroid of each 90 meter grid square • Value is estimate of total population w/in each square • Values are counted if centroid is within Ward boundary
  • 39. 8673 282 1548 2931 8708 337 1887 4833 26,205 396 2546 5241 16,994 680 3399 8089 3584 TOTAL U1 U5 U15 MAGARYA ENUMERATION GIS estimate <1% variance from enumerated value *
  • 40. Technical and Programmatic Guidance Adjustment of target population in the context of the Global Polio Eradication Initiative (GPEI) Version 1.1 13 Feb, 2018 Total projected savings in 2018: ~$143m
  • 41. • Microplanning requirements for fixed-post vaccination campaigns (e.g. Polio-IPV, Measles, Yellow Fever, etc.) – The activity should take place over “X” days maximum – Children should not have to walk more than 1km to get vaccinated – Fixed-Post capacity (# of children vaccinated per day) • 60 children a day in rural areas • 100 children a day in urban areas • Question: how many fixed posts are required and where should they be located? Fixed-Post Vaccination Microplanning: Determining Optimum post location and resource requirements
  • 42. 4 2 Fixed Post Microplanning Settlements within 1km clustered # of Health Camp days calculated Problem: Vaccination Posts or Health Camps (HCs) had to be located no further than 1km from any resident. Solution: An automated tool was created that clustered settlements within 1km of one another. Target populations were then used to determine the number of days the HC would work in a cluster. Result: >95% coverage overall, no missed settlements
  • 43. 2017-18 National Measles Campaign Nigeria • GIS maps and population estimates used to support microplanning and locating vaccination posts in the North. • Traditional microplanning used in the south (GIS mapping in-process).
  • 44. Unweighted Measles Vaccination Post-Campaign Coverage Survey, by EA – Nigeria, 2017-18 Source: Nigeria MVC Post Campaign Coverage Survey, 2017-18 90% to <95% ≥95% >0% to <90% 0% Proportion of Surveyed Children Vaccinated GIS Microplanning States
  • 45. © 2013 Bill & Melinda Gates Foundation | *** Confidential – for internal use only *** Digital Elevation Map (DEM) layers can detect changes in elevation based on the resolution. For 30 meter resolution, the contour lines are spaced 30 meters apart. Environmental Surveillance Site Assessment - catchment area size, location and population estimates
  • 46. Junction Point Drainage Line Watershed-Catchment Est. Population Collected at Junction http://maps.novel-t.ch/
  • 47. Mobile ODK Tools Available for ES Data Collection BLUE LINE Field data Collection
  • 48. Sample Data Collection Options to Improve Specimen Tracking Each Kit has bar code to identify specimen 1. Select Site Name from drop-down list 2. Scan Bar Code 3. Collect GPS Coordinates (date, time stamp) 4. Enter site specific info 5. Select Name of S.O. from drop-down list 6. Upload Form (to Lab, CO, RO, POLIS?) Surveillance Officer Collects Specimen ODK App on Android Phone Documents Sample Collection 1. Bar Code scanned upon arrival in Lab 2. Updates ODK Data Form 3. Transit time auto-calculated 4. Results of Lab Analysis added 5. Upload Form (to CO, RO, POLIS?) Scan Bar Code with Android phone
  • 49. Public Health & Other Applications Ebola Outbreak Response SupportPolio Environmental Surveillance IPV & RI Microplanning LQAS Cluster Selection and Validation Imagery Change Analysis in Conflict Settings Bed net Distribution - CRS Electric Power Grid Planning - WB Health Zone Catchment Areas, DRC (NTD-HAT) eSURV – AFP Surveillance Tracking AVADAR – Community-Based AFP Surveillance Others
  • 50. Nigeria Geo-Referenced Infrastructure and Demographic Data for Development (GRID3) Project 29/06/2018 2018-19: DRC, Tanzania, Zambia, Mozambique
  • 51. Ecopia Building Footprint Layer (© DigitalGlobe) Tanzania, Zambia, Mozambique, Sierra Leone, Somalia*) New Developments in Automated Feature Extraction
  • 52. Country Acq.Date Format Acq. Date Vendor As Of Source Nigeria 2016 TPK Tiles 2016 ORNL 2016-18 ORNL-Flowminder Nigeria 2014-16 ESRI Cache Cameroon 2015 ESRI Cache 2016 ORNL Afghanistan 2015 TPK Tiles 2016 ORNL 2017 Flowminder-UNFPA Pakistan 2015 TPK Tiles 2016 ORNL Lake Chad Region 2017 ORNL 2017 ORNL-Flowminder Ethiopia1 2017 ORNL Zambia1 2017 ORNL DRC2 2016-17 2016-17 ORNL 2018 ORNL-Flowminder Haiti 2016 TPK Tiles 2016 ORNL Ghana 2018 TIF 2018 Tanzania 2018 Ecopia Mozambique 2018 Ecopia Sierra Leone 2018 Ecopia Somalia-South 2018 Ecopia Somalia-North 2016 DG 1 Awaiting licensing 2 partial *All imagery is 4-6 band, color, 0.5m, <10% cloud cover Imagery* Settlement Layer GIS Population Estimates BMGF Polio - Imagery & Derivative Products Resources
  • 53. Share the VISION! Contact Info: Vince Seaman, Ph.D. Sr. Program Officer, Polio - Global Development Bill & Melinda Gates Foundation V +1.206.770.2351 C +1.206.669-7259 E Vincent.Seaman@gatesfoundation.org
  • 54. 54 | Copyright © 2015 Intellectual Ventures Management, LLC (IV). All rights reserved. Remote Sensing to Locate HIV High-Risk Populations Primary goal • Automatic identification of fishing boats • Small boats such as dugout canoes, not large commercial vessels Secondary factors • Season and date • Water hyacinth • Proximity to roads and settlements Boat in water (Asembo Bay, Kenya) Boats on shore A large fish market (Kisumu, Kenya)
  • 55. DiSARM is a tool being used at national scale in Namibia and Botswana to help malaria programs plan, implement and monitor indoor residual spray campaigns.
  • 56. Observed Predicted • Ensemble machine learning used to predict which buildings are residential and non-residential • ~85-90% of residential and non-residential correctly classified • Sturrock et al (2018) Predicting residential structures for Malaria IRS
  • 57. 57
  • 58. Working with 38 wards, containing in total 141,812 rooms (structures) Operational units can be selected for inclusion in the campaign and an estimate of the number of structures in those areas is presented
  • 59. Nigeria GRID3 priority focal areas for now include: Health, Education, Water Resource, Agriculture, Population/Demography and Survey. Some of the potential Use cases considered include: Potential Use-cases for GRID3 Data in Nigeria S/N Thematic Area Use-Case 1 Survey Testing Traditional vs Gridded population survey methodology with NBS. 2 Health 1. Developement of National geo-mapped Health facility Registry. 2. Emergency refferel care services (Linking ambulances to Facilities). 3 Education 1. School maps visualization. 2. School catchment area maps. 3. Gender ratio, Student-Teacher ratio maps etc 4 Water Resurces 1. Access to water per settlement 2. Flood disaster prediction 5 Agriculture 1. Land Use management 2. Farm-Market distance 3. Sustainability Oriented Agrological Production Mapping (SOAPM) 6 Census 1. Support to hybrid census (including micro-census) 2. Verifying EADs using high resolution imagery; 3. Real time monitoring of enumeration 7 Governance 1. community focused monitoring and tracking implementation of projects