Data Lab Strategic Brief: Morocco Earthquake Impact Monitoring

A Strategic Brief is a high-level set of recommendations prepared by the Data Lab that address a given challenge. Recommendations may include internal and external data resources, specific colleagues and/or teams with relevant expertise, data management best practices, suggestions for exploration, and/or a list of relevant resources and similar projects.

Should you have any questions about the Brief, please contact: datalab@worldbank.org

Project Overview

In September 2023, a powerful 6.8 magnitude earthquake and a series of strong tremors and aftershocks wrought substantial damages in central Morocco. As of time of writing, the death toll has passed 2,800 and the earthquake’s aftermath is substantially impacting the people, infrastructure, and local economy of the two countries. [The World Bank issued a statement shortly after the quake, indicating its full support in the wake of the catastrophe](World Bank Statement on Morocco Earthquake). Effective World Bank and donor interventions will require a deep, data-driven understanding of these impacts.

The Morocco Country Economist and Poverty Team team has requested advisory on data and analytical resources that may support measurement and monitoring of socio-economic impacts, including population displacement and business impacts.

The Data Lab advisory is presented in three sections:

• Data Collection and Acquisition: Identified data resources that could support the earthquake socio-economic impact analysis.

• Data Management: Recommendations for managing derived project datasets.

• Data Analytics and Insight Dissemination: A menu of proposals for analytical work that could be coordinated through the Lab.

Data Collection and Acquisition

This section includes a range of data collection and acquisition recommendations, such as open data resources, leveraging private data partnerships, current World Bank subscriptions and licenses, survey solutions, and remote sensing.

Official UN Earthquake Reporting

ID	Dataset	Description	License	Access
1	United Nations Disaster Charter	The disaster charter releases multiple products such as - UNOSAT’s Live Web Map, Ground deformation maps, initial impact of earthquake on villages and initial impact on Night Time Lights.	Open for data products. Raw satellite imagery can be purchased.	Disaster Charter. (For details about purchasing satellite imagery please reach out to Ben Stewart)
2	UNOSAT Damage Assessment	This map illustrates potentially damaged structures/buildings by the earthquake.	Open	HdX Morocco dataset

Boundaries and shapefiles

Morocco’s borders have long been in contention making the boundary files difficult to publicly release or report on. We identified two data sources from which boundaries can be obtained. Although GADM is not a United Nayions’ source, it provides boudnaries at admin 3 and 4 levels which makes it easier to measure the impact of the earthquake.

ID	Dataset	Description	License	Access
3	UNOCHA Boundary Shapefiles	This dataset only has boundaries for admin level 0-2.	Open	HdX
4	GADM Boundary Shapefiles	This boundaries file is available from admin levels 0-4.	Open	GADM

Satellite Imagery for Detecting Land Surface Changes

ID	Dataset	Description	License	Access
5	United States Geological Survey (USGS) Landsat	Satellite imagery data that can be used to track changes in land area. USGS releases ShakeMaps in the aftermath of an earthquake which reports earthquake intensity using the Modified Mercelli Intensity Scale	Open	USGS; Project SharePoint
6	Copernicus Sentinel Data	Copernicus Open Access Hub hosts Sentinel radar data that can be used to track land area changes, regardless of cloud cover.	Open	Sentinel

Population,Demographics, and Human Settlement Data

ID	Dataset	Description	License	Access
7	WorldPop Population Density	The spatial distribution of population denstiy in 2020 based on country total adjusted to match corresponding UNDP estimate. Population desntiy per grid cell (~1km resolution)	Open	WorldPop; Project SharePoint
8	AtlasAI Human Settlement Layer	AtlasAI data show the extent of human settlements and population prior to the earthquake. This settlement map can be used to potentially bridge gaps of the 2013 household survey.	Proprietary	Submit a proposal though the Development Data Partnership
9	Facebook Population During Crisis	This shows the number of Facebook users observed in a location following a crisis compared to a precrisis baseline period. It can help responders identify areas that are heavily impacted by a disaster, analyze how populations are reacting and where they go when they evacuate, and make strategic decisions about how to position services or supplies.	Available for a limited time period through the Development Data Partnership.	Project SharePoint
10	UNOCHA Field Information Services Station (FISS) Subnational Population Statistics	Morocco Preliminary administrative level 2 (only) sex and age disaggregated 2014 population statistics	Open	HdX

Economic Activity and Financial Transaction Data (Direct and Proxy)

ID	Dataset	Description	License	Access
10	Meta Relative Wealth Index	The Relative Wealth Index from Meta identifies areas that are richer/poorer in comparison to other areas within the country. This dataset has been made publicly available for Morocco and can be used to identify areas where there are likely to be more vulnerable populations.	Open	HdX; Project SharePoint
11	Nighttime Lights	Nighttime lights have proven to be useful predictors of numerous dimensions of human activity: electrification, population, GDP, etc. Recent developments have made the entire nightly archive of nighttime lights available in the public domain, and novel tools have made generating a consistent timeline of nighttime lights across the DMSP and VIIRS sensors possible. These data are accessible through a WB collaboration with the US National Oceanic and Atmospheric Administration (NOAA).	Open	NightTime Lights Data. For support in utilizing Nighttime Lights, contact the Geospatial Operations Support Team (GOST): gost@worldbank.org or Rob Marty (DIME)
12	Global Findex Survey 2021	The Global Findex Database provides almost 300 indicators on topics such as account ownership, payments, saving, credit, and financial resilience. Findex data is reported for all indicators by country, region, and income group. Data is also included summarized by gender, income (adults living in the richest 60% and poorest 40% of households), labor force participation (adults in and out of the workforce), age (young and older adults), and rural and urban residence.	Open	Global Findex database; Project SharePoint
13	Bank Al-Maghrib Financial Inclusion and Market Infrastructure Report	National and subnational financial statistics broken down by areas, age and gender.	Proprietary	Project SharePoint
14	UNOCHA Financial Tracking Services	FTS publishes data on humanitarian funding flows as reported by donors and recipient organizations. It presents all humanitarian funding to a country and funding that is specifically reported or that can be specifically mapped against funding requirements stated in humanitarian response plans.	Open	HdX
15	Google Search Trends to monitor changes in travel plans	Search trends data from the Google Trends API can be used to identify trends in search terms of specific words over time. For instance, it can be used to look for ‘flights to Morocco’	Proprietary	Submit a proposal to the Development Data Partnership.
16	Facebook Business Activity Trends	Business Activity Trends measures relative Facebook business page activity (posts, comments, etc.). Index values are compared to a rolling three month-prior baseline. The data is released daily and at a subnational level, aggregated by sector (e.g., retail, grocery). During crises, the expectation is that activity levels will decline.	Proprietary	Submit a proposal to the Development Data Partnership

Geospatial Infrastructure Data (Roads, Buildings, Power Grids, Internet Connectivity)

ID	Dataset	Description	License	Access
16	Open Street Maps	Open Street Map hosts crowd-sourced points of interest, amenities, roads, and other physical features for Morocco. There is an active community of volunteers updating these maps, including labeling collapsed buildings.	Open	OpenStreetMaps; HdX
17	Microsoft Building Footprints	Microsoft has used AI to generate recent baseline building footprints for Morocco that are accessible through an open-source license.	Open	Building footprint respository;
18	Google Building Footprints	A dataset of building footprints in Morocco, in the area of the 8 September earthquake.	Open	Google footprints on HdX
19	Meta Electricity Grid Distribution Maps	Using gridfinder, an open-source tool for predicting the location of electricity network lines using night-time lights satellite imagery and OpenStreetMap data, Meta has released a map that shows the predicted electricity distribution grid and transmission lines.	Open	Electricity Distribution Maps
20	Ookla Speedtest Intelligence Data	Ookla provides internet connectivity data which allows to see pre-earthquake and post-earthquake internet speeds across the country. This can be used as a proxy to identify areas that would be harder to reach and a proxy to identify areas where infrastructure may be damaged because of the earthquake. Quarterly data at a subnational level is available publicly and the more temporally and spatially granular datasets can be accessed through The Partnership.	Open and Proprietary	Quarterly data: Ookla Open Data portal Daily data: accessible by submitting a proposal to the Development Data Partnership.
21	Facebook Network Coverage Maps	This dataset shows showing where people on Facebook have cellular connectivity. This can be used to measure the impact of the earthquake on cellular network infrastructure.	Proprietary	Project SharePoint

Data for Understanding Critical Needs and Access to Services

ID	Dataset	Description	License	Access
22	GDLET Project (News data)	The GDELT Project “monitors the world’s broadcast, print, and web news from nearly every corner of every country in over 100 languages and identifies the people, locations, organizations, themes, sources, emotions, counts, quotes, images and events.”  While there are some limitations to the use of the GDELT APIs, if the team were interested in tracking news mentions of specific key words or sentiments by time and place, this is a useful starting point, since the data are free and open source.	Open	GDELT Project; For support running queries: datalab@worldbank.org
23	Premise Humanitarian Needs Surveys	Premise is collecting the following humanitarian data in Morocco since the earthquake. Needs assessment (sentiment) - pressing needs in the Contributor’s community Earthquake aid (sentiment) - asking how they feel about government and external response efforts to the earthquake  Hospitals (observational) - asking Contributors to record the locations of and take photos of hospitals in their areas Road conditions (observational) - asking Contributors to document the main roads and motorways in their areas that have been affected by the earthquake Earthquake damage (observational) - asking Contributors to identify and take photos and videos of earthquake damage in their areas Fuel prices and availability (observational) - asking Contributors to find where fuel is sold and report on the price They can also conduct custom surveys based on the needs of World Bank teams.	Proprietary	To access, contact datapartnership@worldbank.org or Submit a proposal to the Development Data Partnership.

Data for Monitoring the Movement of People

All the datasetswithin this category can be accessed by submitting a proposal to the Development Data Partnership.

ID	Dataset	Description	License	Access
24	Outlogic Observation Panel (Mobile Device GPS Data)	Outlogic collects a mobile location data panel that includes mobility metrics (speed, bearing, altitude, vertical accuracy) and other detection capabilities (IoT, Wi-Fi, and Beacon). The Data Lab team has used these data to track movement across borders between Syria and Lebanon.	Proprietary	Submit a proposal to the Development Data Partnership
25	Veraset Movement Data	Veraset provides a similar service to Outlogic – mobility data comprises population location and movement data derived primarily from mobile device GPS, Wi-Fi, and IoT signals. A similar analysis to Outlogic can be performed using Veraset da	Proprietary	Submit a proposal to the Development Data Partnership
26	Mapbox Movement	Mapbox Movement is a global data set derived from 20B+ location updates daily, which may be used to understand aggregate activity, density, and movement over time at the city, regional, or country scale.	Proprietary	Submit a proposal to the Development Data Partnership
27	Mapbox Traffic Matrix API	The Mapbox Matrix API is built on anonymized mobile device telemetry data and supports large scale traffic and road network analyses. The API may be used to identify areas poorly served by critical services. This dataset has been used in the past by WB colleagues to analyze spatial accessibility of health facilities. The usefulness of this dataset depends on the availability of Mapbox data for Morocco.	Proprietary	Submit a proposal to the Development Data Partnership
28	Facebook Movement Between Places during Crisis	This dataset shows how many Facebook users who have enabled Location Services have moved from one area to another and if this movement is more or less than a normal day before a crisis or event	Proprietary	Project SharePoint

---

Data Management

This section includes data privacy policy, data storage and access policy and infrastructure, compute infrastructure, data license compliance, data security classifications, data sovereignty policy, etc.

Privacy and Security Considerations

At this stage, the Lab does not have specific recommendations to the team regarding data management. That said, the Lab would like to ensure the team is aware that some analyses conducted over the course of the earthquake relief project may involve use of sensitive data and/or generate sensitive results. The Bank has two sets of guiding policies for secure data management and for protecting the privacy of individuals. The Task Team Leader and team members working closely with sensitive data and/or results are advised to review these policies before beginning project implementation.

• World Bank Policy on Data Privacy

• World Bank Policy on Access to Information

Data Storage

As data are sourced and analyzed, the Lab recommends they is added to the World Bank Development Data Hub. This will ensure data are available to all Bank staff (as appropriate) for reuse, minimizing additional effort and duplication of acquisition by other teams. For assistance making data available, contact Rochelle O’Hagan (rohagan@worldbank.org).

---

Data Analytics and Insight Dissemination

With acquired data and sufficient data management procedures and infrastructure in place, how do we responsibly generate and share insights from these data? This section includes economics and statistical analysis, data science (AI/ML), app development, geospatial analytics, code collaboration best practices, reproducible code best practices, data product licensing, etc.

The Morocco Country Economist and Poverty team have specifically requested recommendations for measuring and monitoring the following:

• Demographics update for affected areas (last household surveys were conducted in 2013);

• Impact on tourism, short and mid-term;

• General impact on well-being of more vulnerable populations; and

• Other potential macro-economic / regional economic impacts.

For each activity, the Data Lab can generate reusable methods and initial insights, and then train Bank teams to continue adjusting the methodology and generating the insights themselves, as needed. To the extent possible, insights will be geospatially aggregated to a granular level, enabling the CMU to quickly visualize correlations between indicators by location – e.g., a relative damage index, population demographics, population movement, nighttime lights, internet availability. To the extent possible, the Lab would welcome collaboration with other teams preparing such indicators, to ensure comparability.

The Lab coordinates the production of analytical work with team members from across the Bank, including (but not limited to) colleagues from DEC Analytics and Tools, Global Operations Support Team, GFDRR, Development Data Hub, Development Data Partnership, ITS Technology and Innovation Lab, and ITS.

I.      Understanding Displacement Patterns

The Data Lab can undertake the following activities to better understand population movements (who, where, and when) resulting from the earthquake:

Topic	Description
Data Sources	Mobile location data from partners through the Development Data Partnership (tbc)
General Approach	With the popularization of smartphone usage and connectivity across the world, the last decade has witnessed the emergence of massive mobility datasets, such call detail records, geo-tagged posts from social media platforms and generated from GPS devices. These datasets have propelled a rich scientific production on various applications of mobility analysis, ranging from epidemiology to disaster resilience, urban planning and transportation engineering. Through the Development Data Partnership,staff now have access to high-frequency location-based mobility data, constituted of high temporal and spatial resolution timestamped geographical points generated by GPS-enabled devices. By overlaying population and socioeconomic data with mobility data, the project team will be able to produce an analysis based on the estimation of home locations and population displacement to be delivered on a weekly basis. The results could shed light on the earthquake’s effects on different areas and/or populations aggregated by seismic intensity, wealth group or additional features that become available. In addition, a point of  interest rate visit analysis may show to what degree the decrease in movement and activity in business and commercial centers may correlate to the economic outlook, comparing with historical data.The project team may leverage both Meta (pending availaility) and mobile device generated data, as well as official UN statsitics and other data sources as they become available to support cross-validation. All analytics will be supported by at least two data sources, where possible – for example, combining Meta movement statistics with mobile-device location data and comparing with official UNHCR data. See also: Mobility for resilience: displacement analysis — mobilkit documentation and Observed Cross-Border Mobility Traces in Lebanon and Syria
Outputs	Data Pipeline and Pre-Processing. The Development Data Partnership handles data delivery, data management and data engineering on behalf of all  staff and, in doing so, creates economies of scale. Datasets. All datasets used in the analysis will be documented and hosted on the World Bank Development Data Hub (for ease of sharing) and a project SharePoint (for the CMU’s ease of use). Code and Documentation. All methods will be fully documented and reproducible, so that the analysis can be quickly updated by the CMU as new data are available. Indicators. Displacement by seismic intensity, home locality, wealth group. Maps.  Displacement by seismic intensity, home locality, wealth group. Training and Support. The Lab will provide the CMU with training so they may tweak the methodology and continue updating the insights on their own. The Lab would be available for technical assistance, as needed.
Limitations	The methodology relies on private intent data in the form of mobile location data. In other words, the input data was not produced or collected to analyze the population of interest or address the research question as its primary goal but repurposed for the public good. The< benefits and caveats when using private intent data have been extensively discussed in the World Development Report 2021.  On the one hand, the mobility data panel is spatially and temporally granular and readily available, on the other hand it is created as a convenience sampling which constitutes an important source of bias. The panel composition is not entirely known and susceptible to change, the data collection and the composition of the mobility data panel cannot be controlled. Due to the nature of the problem and the cardinality, the results can be complex and better analyzed and interpreted when looking at the interactive maps, instead of annual indicators.
Estimated Resources	Compute and Storage. AWS S3 and AWS EC2 r6i.16xlarge (under Data Lab’s custody). ITS charges for mobility data compute and storage services – equivelant to 5-6 days GF-level staff time. Staff Hours. ~12 days GF-level staff time.

II. Understanding Economic Impacts

The Lab proposes focusing on the following key business activity and business supporting infrastructure indicators:

II.A. Observed Electricity Usage at Night

By comparing pre- and post-earthquake nighttime light data, we can identify changes in availability of electricity, mass movements of people, and changes in oil refining (through flaring). Some of our sample work using this methodology can be seen as part of the Syria Economic Monitor. Monitoring nighttime light data over a longer historical time period – e.g., since 2013, when the last household surveys were conducted in the affected region – can also shed light on current demographics of the impacted population.

Topic	Description
Data Sources	Nightly VIIRS nighttime lights and Global Gas Flaring Reduction Partnership (for locations of gas flaring facilities)
General Approach	1.     Download, clean, pre-process data for area of interest. 2.     Generate separate map layers for lights observed in gas flaring locations and lights in other locations. 3.     Generate maps and statistics showing changes in nighttime light intensity over time by area of interest.  Here is an example.
Outputs	Datasets. All datasets used in the analysis will be documented and hosted on the World Bank Development Data Hub (for ease of sharing) and a project SharePoint (for the CMU’s ease of use). Code and Documentation. All methods will be fully documented and reproducible, so that the analysis can be quickly updated by the CMU as new data are available. Indicators. Annual since 2013 and bi-weekly since 2023 percent change in nighttime light intensity by area of interest. Maps. Static maps showing percent change in observable nighttime lights (with and without flaring) over time, aggregated by a common geospatial index for cross-indicator comparison, and/or aggregated by area of interest. Training and Support. The Lab will provide the CMU team with training so they may tweak the methodology and continue updating the insights on their own. The Lab would be available for technical assistance, as needed
Limitations	Nighttime lights are a common data source for measuring local economic activity. However, it is a proxy that is strongly—although imperfectly—correlated with measures of interest, such as population, local GDP, and wealth. Consequently, care must be taken in interpreting reasons for changes in lights.
Estimated Resources	Compute. Nighttime light analysis compute costs scale with the area of interest. For the earthquake zone, these costs would be negligible and not charged to the project team. Staff Time.  7 days GF-level staff time

II.B. Internet Connectivity Availability and Quality

In Morocco, the internet underpins modern business and the government’s ability to communicate resources to those in need, especially in Marrakech. Understanding changes in availability post-earthquake are an immediate proxy for damages to this critical infrastructure.

Topic	Description
Data Sources	Ookla Speedtest Intelligence Data Meta Network Coverage Maps (pending availability) Geospatial layer of earthquake-impacted locations
General Approach	1.     Obtain Ookla  baseline and most recent subnational data for internet quality through the  Development Data Partnership. 2.     Compare data from Ookla and Meta’s network connectivity maps (pending Meta availability) 3.     Identify areas where there was an earthquake and verify if there is a change in internet connectivity pre-event and post-event.
Outputs	Datasets. All datasets used in the analysis will be documented and hosted on the World Bank Development Data Hub (for ease of sharing) and a project SharePoint (for the CMU’s ease of use). Code and Documentation. All methods will be fully documented and reproducible, so that the analysis can be quickly updated by the CMU as new data are available. Indicators. Change in internet speed/network connectivity at a province/district level | Identified districts where there might be people that are difficult to reach via the internet  Maps. Combined network connectivity map using both Ookla and Meta datasets.  Training and Support. The Lab will provide the CMU team with training so they may tweak the methodology and continue updating the insights on their own. The Lab would be available for technical assistance, as needed.
Limitations	Meta Network Coverage Maps are only pertaining to Facebook users. In Morocco, as of March 2022, there were more than  26 million active Facebook users. The population of the country as of 2021 was more than 37 million. Although this could make Facebook data fairly reliable in Morocco, it does not cover everyone. Ookla speedtest data is a collection of speed tests conducted on the Ookla platform. This dataset also does not cover the entire population. Additionally, their dataset is crowdsourced, and their sampling methodology is untested.
Estimated Resources	Staff Time. 5 days GF-level staff time

II.C. Damaged or Inaccessible Local Businesses

By layering road and building footprint damages with points of interest, we can generate statistics on impacted businesses, banks, and other ancillary services critical to local functioning economies.

Topic	Description
Data Sources	Building footprint geospatial layers (Microsoft AI-generated footprints, Google AI-generated footprints, and/or Open Street Map volunteer-generated footprints) | Earthquake damaged buildings geospatial layer (pending availability - team can also coordination of generating damage layers using open radar data from the European Space Agency, upon request) | Road network and point-of-Interest data (from government, or, if not available, from Open Street Map)
General Approach	1.     Collect point-of-interest data. 2.     Set up baseline map layer: Add roads and admin boundaries and intersect building footprints with business points-of-interest. 3.     Overlay baseline map with damaged road and building footprint layer. 4.     Generate a list, by sector and local admin boundary, of directly damaged businesses. 5.     Run a network analysis to identify those businesses that are not accessible because of roadway damage.
Outputs	Datasets. All datasets used in the analysis will be documented and hosted on the World Bank Development Data Hub (for ease of sharing) and a project SharePoint (for the CMU’s ease of use). Code and Documentation. All methods will be fully documented and reproducible, so that the analysis can be quickly updated by the CMU as new data are available. Indicators. Number of damaged/inaccessible businesses by sector and by local admin boundary. Map. Single map showing locations of damaged or inaccessible businesses. Training and Support. The Lab will provide the CMU team with training so they may tweak the methodology and continue updating the insights on their own. The Lab would be  available for technical assistance, as needed.
Limitations	Analysis is contingent on availability of good building footprint, infrasturcture, and point-of-interest data and damage layers.
Estimated Resources	Staff Time. ~ 15 days GF-level staff hours (more if team also tasked with creating preliminary damage data based on radar data).

II.D. Observed Business Facebook Page Activity

Many local businesses use Facebook as their primary business website. Facebook records levels of activity on these pages, aggregates activity by location and sector, and presents as generalized trend indicators for levels of business activity.

Topic	Description
Data Sources	Business Activity Trends from Meta (#20) \
General Approach	1.     Identify areas where there is a change in Business activity compared to a baseline in November 2022. 2.     Identify if the change can be attributed to the earthquake or just change in network connectivity by overlaying with geospatial earthquake affected area map and network connectivity map. 3. An example of this can be seen in our work for Turkiye Earthquake Impact
Outputs	Datasets. All datasets used in the analysis will be documented and hosted on the World Bank Development Data Hub (for ease of sharing) and a project SharePoint (for the CMU’s ease of use). Code and Documentation. All methods will be fully documented and reproducible, so that the analysis can be quickly updated by the CMU as new data are available. Indicators. Sectors that have been potentially impacted due to the earthquake \
Limitations	Business Activity Trends captures the rate of posting (posts and visits) on Facebook business pages. Thus, offline and off-Facebook activities are not captured and along with social media usage, connectivity and cultural customs, may contribute as serious limitation and source of bias. In other words. the index is not representative of the other business happening in the area. There is also a bias towards the service sector as they are more likely to be active on Facebook.
Estimated Resources	Staff Hours. 16 hours GF-level staff time

III. Understanding Social Impacts

Since the last household survey in the region was conducted in 2013, the team will attempt to use alternative data to provide insights into trends since that period.

To get a sense of “need intensity,” the team can explore use of the Google Health Trends API (available through the Development Data Partnership) to determine temporally and by region changes in queries related to key terms provided by the Task Team (e.g., ““water,” “money transfer,” “pediatrician,” “hospital”). The method can be adjusted to incorporate other datasets, such as social media data (e.g., Twitter which has roughly 1 million users in Morocco).

III.A. Demographics

Topic	Description
Data Sources	Meta Relative Wealth Index; Meta Population Density; Atlas.AI demographics (pre-approved by data partner through the Development Data Partnership and available upon request); Nighttime light imagery; Urban foorprint evolution from DLR (2012 - 2019).
General Approach	1. Baseline. The team will review the last HH survey from 2013 and set up geospatial baselayers for analysis.  2. Data Review. The team will then review alternative data sources – nighttime lights from 2012 - 2023, built-up human settlement data from 2012-2019, most recent Meta demographic data, and Atlas.AI indicators derived from LSMS, satellite imagery machine learning techniques,and other sources. The review will include generation of descriptive statistics and qualitative evaluation of potential sampling biases.    3.Trend Analysis.The team will analyze changes in the size and location of the population in the earthquake affected area from 2013 through 2023 and, to the extent possible with the data sources, analyze changes in age cohorts and relative wealth.
Outputs	Datasets. All datasets used in the analysis will be documented and hosted on the World Bank Development Data Hub (for ease of sharing) and a project SharePoint (for the CMU’s ease of use). Code and Documentation. All methods will be fully documented and reproducible, so that the analysis can be quickly updated by the CMU as new data are available. Indicators. The trend analysis will include production of population size and density by location and - pendng data quality - statistics on changes in age cohort sizes and relative wealth.  Maps. The team will prepare a map represeting, at a minimum, population density and location changes from 2013 through the present.f Training and Support. The Lab will provide the CMU team with training so they may tweak the methodology and continue updating the insights on their own. The Lab would be available for technical assistance, as needed.
Limitations	Meta, Atlas.AI, and DLR datasets are all derived, in part, using machine learning, which means we may not be able to describe all of the explanatory variables. Further, given the high poverty level of some of the affected population, there may be some sampling bias in the results.
Estimated Resources	Staff Time. 4-5 days GF-level staff time.

III.B. Observed Needs

Topic	Description
Data Sources	Google Search Trends API | Premise crowd-sourced survey data (to be confirmed) | Network Connectivity map obtained through a combination of Ookla + Meta internet quality (pending Meta data availability)
General Approach	1.     Identify search terms that can be queried on Google Trends API 2.     Map the changes in search terms over the weeks prior to the earthquake and weeks post the earthquake 3.     Verify if this change can be attributed to a change in network coverage 4.     Identify areas where there is an unnatural spike in number of times a search term appears 5.     Verify findings with official statistics and Premise field survey results (pending availability)  6.     Identify areas where there is a need based on the Premise survey and verify if such a need is absent from Google Trends because of a lack of network connectivity.
Outputs	Datasets. All datasets used in the analysis will be documented and hosted on the World Bank Development Data Hub (for ease of sharing) and a project SharePoint (for the CMU’s ease of use). Code and Documentation. All methods will be fully documented and reproducible, so that the analysis can be quickly updated by the CMU as new data are available. Indicators. Changes in surveyed prices of key goods (fuel, foods, etc.) by district; Summary of observed needs through surveys and social media by district. Maps. Dynamic map of price changes in surveyed goods by location in Morocco over time | Dynamic map of observed needs over time by location. Training and Support. The Lab will provide the CMU team with training so they may tweak the methodology and continue updating the insights on their own. The Lab would be available for technical assistance, as needed.
Limitations	Premise data are crowdsourced and may not be representative of the affected population.  Google Trends relies on people with an active internet connection to search, which excludes people without internet access or who do not use Google search.
Estimated Resources	Staff Time. ~ 4 days GF-level staff hours (more if field verification is used)

IV. Dissemination and Capacity Building

Since analytical results from this work could support additional teams and counterparts, the team has created a centralized repository of all datasets used in analytical work using SharePoint to ensure all data are accessible (where licensing permits), and that all methodologies are similarly made available through GitHub, so that others can reproduce the results. See the starter code respository for this project, here: GitHub - datapartnership/morocco-earthquake-impact: Alternative data analytics for understanding impacts of the 2023 Morocco earthquake

Additionally, the Lab can produce a web-based map for layering indicators for ready comparative analysis, as well as an Excel workbook for ease of indicator dissemination across the widest possible audience, upon request.

Additional Resources

Potential Partners and Collaborators

• The World Bank participates in a collaboration with the UN High Commissioner for Refugees (UNHCR) Joint Data Center (JDC) (https://www.jointdatacenter.org/), which supports data collection on internally displaced peoples. The team may consider reaching out to the World Bank focal point for this collaboration, Harriet Kasidi Mugera (hmugera@worldbank.org), to determine what data may be available on displaced peoples that would be relevant.

• The UN Pulse Lab Jakarta has previously developed methodologies for monitoring economic shock impacts using banking data, internal population movement using mobile phone data, and disaster response management using social media data. These methodologies may also be applicable to earthquake response. If the team were interested in collaboration, enquiries could be made to Pulse Lab Jakarta (plj@un.or.id; please cc: datalab@worldbank.org)

Development Data Partnership’s Community and Documentation

The Development Data Partnership fosters a community of data practitioners and maintains a robust data documentation and code collaboration platform based on GitHub, which is recognized as a good practice in the World Bank and in partner international organizations. See more at https://docs.datapartnership.org.