Tag Archives: Somalia

Amplifying Somali Voices Using SMS and a Live Map: #SomaliaSpeaks

Somalia has been steadily slipping from global media attention over the past few months. The large scale crisis is no longer making headline news, which means that advocacy and lobbying groups are finding it increasingly difficult to place pressure on policymakers and humanitarian organizations to scale their intervention in the Horn of Africa. I recently discussed this issue with Al-jazeera’s Social Media Team whilst in Doha and pitched a project to them which has just gone live this hour.

The joint project combines the efforts of multiple partners including Al-Jazeera, Ushahidi, Souktel, Crowdflower, the African Diaspora Institute and the wider Somali Diaspora. The basis of my pitch to Al-jazeera was to let ordinary Somalis speak for themselves by using SMS to crowdsource their opinions on the unfolding crisis. My colleagues at Al-jazeera liked the idea and their editorial team proposed the following question:

Al Jazeera wants to know: how has the conflict of the last few months affected your life? Please include the name of your hometown in your response. Thank you!

So I reached out to my good friend Jacob Korenblum at Souktel. He and I had been discussing different ways we might combine our respective technologies to help in Somalia. Souktel has been working in Somalia and providing various SMS based solutions to several organizations. Jacob had previously mentioned that his team had a 50,000+ member SMS subscriber list. This proved to be key. Earlier this week, the Souktel team sent out the above question in Somali to about 5,000 of their subscribers. An effort was made to try and select geographically disbursed areas.

We’ve since received well over 2,000 text message replies and counting. In order to translate and geolocate these messages, I got in touch my colleagues Vaughn Hester and Lukas Biewald at Crowdflower in San Francisco. Crowdflower uses micro-tasking solutions to process and structure data flows. They were very keen to help and thanks to their support my Ushahidi colleagues Rob Baker and Linda Kamau were able to customize this Crowdflower plugin to translate, categorize and geo-locate incoming text messages:

 

They also wrote additional software so that text messages from Souktel could be automatically forwarded to the Crowdflower plugin which would then automatically push the processed SMS’s to a live Ushahidi map hosted by Al-jazeera. While the software development was moving forward, I connected  with colleagues from the Somali American Student Association who expressed an interest in supporting this project. Thanks to them and other members of the Somali Diaspora, hundreds of Somali voices were translated and shared on Al-jazeera’s public Ushahidi map of Somalia within days. But we still need lots of help. So if you speak Somali and English, then simply follow this link.

I wanted this project to serve as a two-way conversation, however, not just a one-way information flow from Somalia to the world. Every report  that gets mapped on an Ushahidi platform is linked to public discussion forum where readers can respond and share their views on said report. So I suggested that Al-jazeera invite their viewers/readers to comment on the text messages directly. The next step will be for Al-jazeera’s editorial team to select some of the most compelling and interesting comments and to text these back to the senders of the original text messages in Somalia. This two-way flow of information can be iterated and scaled given that the technologies and workflows are already in place.

In sum, the purpose of this project is to catalyze global media attention on Somalia by letting Somali voices take center stage—voices that are otherwise not heard in the international, mainstream media. If journalists are not going to speak about Somalia, then this project  invites Somalis speak to the world themselves. The project highlights  these voices on a live, public map for the world to bear witness and engage in a global conversation with people of Somalia, a conversation in which Somalis and the Diaspora are themselves at the centerfold. It is my sincere hope that advocacy and lobby group will be able to leverage the content generated by this project to redouble their efforts in response to the escalating crisis in Somalia.

I very much hope to see this type of approach used again in Somalia and elsewhere. It is fully inline with the motivations that inspired the launch of the first Ushahidi platform almost 4 years ago today: collective witnessing. Indeed, I am often reminded of what my friend Anand Giridharadas of the New York Times wrote last year vis-a-vis Ushahidi. To paraphrase:

They used to say that history is written by the victors. But today, before the victors win, if they win, there is a chance to scream out with a text message, a text message that will not vanish, a text message that will remain immortalized on a map for the world to bear witness. What would we know about what passed between Turks and Armenians, Germans and Jews, Hutus and Tutsis, if every one of them had had the chance, before the darkness, to declare for all time:

“I was here, and this is what happened to me”?

 Use #SomaliaSpeaks to witness the project on Twitter.

I want to specifically thank the following individuals who put an incredible amount of time and effort (most pro bono) to make this project happen: Robert Baker, Linda Kamau, Michael Moszczynski, Katie Highet, Jacob Korenblum, Vaughn Hester, Mohammed Dini, Hamza Haadoow, Andrew Jawitz and of course the excellent Al Jazeera team in Doha. Thank you all for going above and beyond to make this happen. 

Crowdsourcing Satellite Imagery Analysis for UNHCR-Somalia: Latest Results


253,711

That is the total number of tags created by 168 volunteers after processing 3,909 satellite images in just five days. A quarter of a million tags in 120 hours; that’s more than 2,000 tags per hour. Wow. As mentioned in this earlier blog post, volunteers specifically tagged three different types of informal shelters to provide UNHCR with an estimate of the IDP population in the Afgooye Corridor. So what happens now?

Our colleagues at Tomnod are going to use their CrowdRank algorithm to triangulate the data. About 85% of 3,000+ images were analyzed by at least 3 volunteers. So the CrowdRank algorithm will determine which tags had the most consensus across volunteers. This built-in quality control mechanism is a distinct advantage of using micro-tasking platforms like Tomnod. The tags with the most consensus will then be pushed to a dedicated UNHCR Ushahidi platform for further analysis. This project represents an applied research & development initiative. In short, we certainly don’t have all the answers. This next phase is where the assessment and analysis begins.

In the meantime, I’ve been in touch with the EC’s Joint Research Center about running their automated shelter detection algorithm on the same set of satellite imagery. The purpose is to compare those results with the crowdsourced tags in order to improve both methodologies. Clearly, none of this would be possible without the imagery and  invaluable support from our colleagues at DigitalGlobe, so huge thanks to them.

And of course, there would be no project at all were it not for our incredible volunteers, the best “Mapsters” on the planet. Indeed, none of those 200,000+ tags would exist were it not for the combined effort between the Standby Volunteer Task Force (SBTF) and students from the American Society for Photogrammetry and Remote Sensing (ASPRS); Columbia University’s New Media Task Force (NMTF) who were joined by students from the New School; the Geography Departments at the University of Wisconsin-Madison, the University of Georgia, and George Mason University, and many other volunteers including humanitarian professionals from the United Nations and beyond.

As many already know, my colleague Shadrock Roberts played a pivotal role in this project. Shadrock is my fellow co-lead on the SBTF Satellite Team and he took the important initiative to draft the feature-key and rule-sets for this mission. He also answered numerous questions from many volunteers throughout past five days. Thank you, Shadrock!

It appears that word about this innovative project has gotten back to UNHCR’s Deputy High Commissioner, Professor Alexander Aleinikoff. Shadrock and I have just been invited to meet with him in Geneva on Monday, just before the 2011 International Conference of Crisis Mappers (ICCM 2011) kicks off. We’ll be sure to share with him how incredible this volunteer network is and we’ll definitely let all volunteers know how the meeting goes. Thanks again for being the best Mapsters around!

 

Crowdsourcing Satellite Imagery Tagging to Support UNHCR in Somalia

The Standby Volunteer Task Force (SBTF) recently launched a new team called the Satellite Imagery Team. This team has been activated twice within the past few months. The first was to carry out this trial run in Somalia and the second was in partnership with AI-USA for this human rights project in Syria. We’re now back in Somalia thanks to a new and promising partnership with UNHCR, DigitalGlobe, Tomnod, SBTF and Ushahidi.

The purpose of this joint project is to crowdsource the geolocation of shelters in Somalia’s Afgooye corridor. This resembles our first trial run initiative only this time we have developed formal and more specialized rule-set and feature-key in direct collaboration with our colleagues at UNHCR. As noted in this document, “Because access to the ground is difficult in Somalia, it is hard to know how many people, exactly, are affected and in what areas. By using satellite imagery to identify different types of housing/shelters, etc., we can make a better and more rapid population estimate of the number of people that live in these shelters. These estimates are important for logistics and planning purposes but are also important for understanding how the displaced population is moving and changing over time.” Hence the purpose of this project.

We’ll be tagging three different types of shelters: (1) Large permanent structures; (2) Temporary structures with a metal roof; and (3) Temporary shelters without a metal roof. Each of these shelter types is described in more details in the rule-set along with real satellite imagery examples—the feature key. The rule-set describes the shape, color, tone and clustering of the different shelter types. As per previous SBTF Satellite Team deployments, we will be using Tomnod’s excellent microtasking platform for satellite imagery analysis.

Over 100 members of the SBTF have joined the Satellite Team to support this project. One member of this team, Jamon, is an associate lecturer in the Geography Department at the University of Wisconsin-Madison. He teaches on a broad array of technologies and applications of Geographic Information Science, including GPS and  satellite imagery analysis. He got in touch today to propose offering this project for class credit to his 36 undergraduate students who he will supervise during the exercise.

In addition, my colleague and fellow Satellite Team coordinator at the SBTF, has recruited many graduate students who are members of the American Society for Photogrammetry and Remote Sensing (ASPRS) to join the SBTF team on this project. The experience that these students bring to the team will be invaluable. Shadrock has also played a pivotal role in making this project happen: thanks to his extensive expertise in remote sensing and satellite imagery, he took the lead in developing the rule-set and feature-key in collaboration with UNHCR.

The project officially launches this Friday. The triangulated results will be pushed to a dedicated UNHCR Ushahidi map for review. This will allow UNCHR to add additional contextual data to the maps for further analysis. We also hope that our colleagues at the European Commission’s Joint Research Center (JRC) will run their automated shelter tagging algorithm on the satellite imagery for comparative analysis purposes. This will help us better understand the strengths and shortcomings of both approaches and more importantly provide us with insights on how to best improve each individually and in combination.

Amplifying Somali Voices Using SMS and a Live Map

Update: http://irevolution.net/2011/12/08/somaliaspeaks

I recently had the pleasure to meet with Al-Jazeera’s Social Media Team in Doha, Qatar. It was immediately clear that they were also interested in partnering on a joint project in Somalia when I suggested a few ideas. Several weeks later, this project is almost ready to launch. The purpose of this initiative is to let Somalis speak for themselves and to amplify those voices in the international media.

As Al-Jazeera has noted, Somalia is quickly slipping from global media attention. With Somalia out of the headline news, however, advocacy and lobbying groups will find it increasingly difficult to place pressure on policymakers and humanitarian organiza-tions to scale their intervention in this major crisis. This project therefore offers a direct and innovative way to keep Somalia in the international news. The project described below is the product of a novel collaborative effort between Al-Jazeera, Ushahidi, Souktel and Crowdflower in direct partnership with the Somali Diaspora.

The project will “interview” ordinary Somalis in Somalia and let them speak for themselves in the international media space. Interview questions drafted by Al-Jazeera will be broadcast via SMS by Souktel to 10% of their existing 50,000+ subscribers in the country. The interview questions will also invite Somalis to share in which town they are based. (Note that we are reviewing the security protocols for this). The Somali Diaspora will then translate and geolocate incoming text messages from Somali to English using a customized Crowdflower plugin. The processed messages will then be pushed (in both Somali and English) to a live Ushahidi map. Al-Jazeera will promote the live map across their main-stream and social media channels. Mapped SMS’s will each have a comments section for viewers and readers to share their thoughts. Al-Jazeera will then select the most compelling responses and text these back to the original senders in Somalia. This approach is replicable and scalable given that the partners and technologies are largely in place already.

In sum, the purpose of this project is to increase global media attention on Somalia by letting Somali voices take center stage—voices that are otherwise not heard in the international, mainstream media. If journalists are not going to speak about Somalia, then lets invite Somalis speak to the world themselves. The project will highlight these voices on a live, public map for the world to engage in a global conversation with the people of Somalia, a conversation in which Somalis and the Diaspora are themselves at the centerfold.

If you want to help out with this initiative, we’re looking for Somali-English speakers to translate and map the incoming text messages. It’s important that volunteers are familiar with the location of many cities, towns, etc., in Somalia in order to map the SMS’s. If you have the skills and time, then please add your name, email address and short bio here—would be great to have you on the team!

 

Microtasking Advocacy and Humanitarian Response in Somalia

I’ve been working on bridging the gap between the technology innovation sector and the humanitarian & human rights communities for years now. One area that holds great promise is the use of microtasking for advocacy and humanitarian response. So I’d like to share two projects I’m spearheading with the support of several key colleagues. I hope these pilot projects will further demonstrate the value of mainstreaming microtasking. Both initiatives are focused on Somalia.

The first pilot project plans to leverage Souktel‘s large SMS subscriber base in Somalia to render local Somali voices and opinions more visibile in the mainstream media. This initiative combines the efforts of a Somali celebrity, members of the Somali Diaspora, a major international news organization, Ushahidi and CrowdFlower. In order to translate, categorize and geolocate incoming text messages, I reached out to my colleagues at CrowdFlower, a San Francisco-based company specializing in microtasking.

I had catalyzed a partnership with Crowdflower during the PakReport deploy-ment last year and wanted to repeat this successful collaboration for Somalia. To my delight, the team at Crowdflower was equally interested in contri-buting to this initiative. So we’ve started to customize a Crowdflower plugin for Somalia. This interface will allow members of the Somali Diaspora to use a web-based platform to translate, categorize and geolocate incoming SMS’s from the Horn of Africa. The text messages processed by the Diaspora will then be published on a public Ushahidi map.

Our international media partner will help promote this initiative and invite comments in response to the content shared via SMS. The media group will then select the most compelling replies and share these (via SMS) with the authors of the original text messages in Somalia.  The purpose of this project is to catalyze more media and world attention on Somalia, which is slowly slipping from the news. We hope that the content and resulting interaction will generate the kind of near real-time information that advocacy groups and the Diaspora can leverage in their lobbying efforts.

The second pilot project is a partnership between the Standby Volunteer Task Force (SBTF), UNHCR, DigitalGlobe and Tomnod. The purpose of this project, is to build on this earlier trial run and microtask the tagging of informal shelters in a certain region of the country to identify where IDPs are located and also esti-mate the total IDP population size. The microtasking part of this project is possible thanks to the Tomnod platform, which I’ve already blogged about in the context of this recent Syria project. The project will use a more specialized rule-set and feature-key developed with UNHCR to maximize data quality.

We are also partnering with the European Commission’s Joint Research Center (JRC) on this UNCHR project. The JRC team will run their automated shelter-detection algorithms on the same set of satellite images. The goal is to compare and triangulate crowdsource methods with automated approaches to satellite imagery analysis.

There are several advantages to using microtasking solutions for advocacy and humanitarian purposes. The first is that the tasks can easily be streamlined and distributed far and wide. Secondly, this approach to microtasking is highly scalable, rapid and easily modifiable. Finally, microtasking allows for quality control via triangulation, accountability and statistical analysis. For example, only when two volunteers translate an incoming text message from Somalia in a similar way does that text message get pushed to an Ushahidi map of local Somali voices. The same kind of triangulation can be applied to the categorization and geolocation of text messages, and indeed shelters in satellite imagery.

Microtasking is no silver bullet for advocacy and humanitarian response. But it is an important new tool in the tool box that can provide substantial support in times of crisis, especially when leveraged with other traditional approaches. I really hope the two projects described above take off. In the meantime, feel free to browse through my earlier blog posts below for further information on related applications of microtasking:

·  Combining Crowdsourced Satellite Imagery Analysis with Crisis Reporting
·  OpenStreetMap’s Microtasking Platform for Satellite Imagery Tracing
·  Crowdsourcing Satellite Imagery Analysis for Somalia
· Crowdsourcing the Analysis of Satellite Imagery for Disaster Response
· Wanted for Pakistan: A Turksourcing Plugin for Crisis Mapping
· Using Massive Multiplayer Games to Turksource Crisis Information
· From Netsourcing to Crowdsourcing to Turksourcing Crisis Information
· Using Mechanical Turk to Crowdsource Humanitarian Response


The Horn of Africa and the Crisis Mapping Community

“… the Horn of Africa famine and the associated crises gravely affecting millions of people has not animated the crisis-mapping community and its online platforms to the extent of post-Haiti or, more recently, following the 2011 earthquake in Japan.”

I’m somewhat concerned by the phrasing of this statement, which comes from this recent article published by ICT4Peace. Perhaps the author is simply unaware of the repeated offers made by the crisis mapping community to provide crisis mapping solutions, mobile information collection platforms, short codes, call center services, etc., to several humanitarian organizations including UN OCHA, UNDP and WFP over the past three months.

In the case of OCHA, the team in Somalia replied that they had everything under control. In terms of UNDP, the colleagues we spoke with simply did/do not have the capacity, time or skill-set to leverage new crisis mapping solutions to improve their situational awareness or better communicate with disaster affected comm-unities. And WFP explained that lack of access rather than information was the most pressing challenge they were facing (at least two months ago), an issue echoed by two other humanitarian organizations.

This excellent report by Internews details the complete humanitarian tech-nology failure in Dadaab refugee camp and underscores how limited and behind some humanitarian organizations still are vis-a-vis the prioritization of “new” in-formation and communication technologies (ICTs) to improve humanitarian response and the lives of refugees in crisis situations. These organizations require support and core funding to “upgrade”. Throwing crisis mapping technologies at the problem is not going to solve many problems if the under-lying humanitarian mechanisms are not in place to leverage these solutions.

This is not a criticism of humanitarian organizations but rather hard reality. I’ve had numerous conversations with both technology and humanitarian colleagues over the past three months about how to reach for low hanging fruits and catalyze quick-wins with even the most minimal ICT interventions. But as is often the case, the humanitarian community is understandably overwhelmed and genu-inely trying to do the best they can given the very difficult circumstances. Indeed, Somalia presents a host of obvious challenges and risks that were not present in either Haiti or Japan. (Incidentally, only a fraction of the crisis mapping commu-nity was involved in Japan compared to overall efforts in Somalia).

Perhaps ICT4Peace is also unaware that some colleagues and I spent many long days and nights in August and September preparing the launch of a live crisis map for Somalia, which ESRI, Google, Nethope and several other groups provided critical input on. See my blog post on this initiative here. But the project was torpedoed by a humanitarian organization that was worried about the conse-quences of empowering the Somali Diaspora, i.e., that they would become more critical of the US government’s perceived inaction as a result of the information they collected—a consequence I personally would have championed as an indica-tor of success.

Maybe ICT4Peace is also unaware that no humanitarian organization formally requested the activation of the Standby Volunteer Task Force (SBTF) in August. That said, the SBTF did engage in this pilot project to crowdsource the geo-tagging of shelters in Somalia in September as a simple trial run. Since then, the SBTF has officially partnered with UNHCR and the Joint Research Center (JRC) to geo-tag IDP camps in specific regions in Somalia next month. Digital Globe is a formal partner in this project, as is Tomnod. Incidentally, JRC is co-hosting this year’s International Conference of Crisis Mappers (ICCM 2011).

ICT4Peace is perhaps also not aware of a joint project between Ushahidi and UN OCHA Kenya to provide crisis mapping support, or of recent conversations with Al Jazeera, Souktel, the Virgin Group, K’naan, PopTech, CeaseFire, PeaceTXT, GSMA, DevSeed and others on implementing crisis mapping and SMS solutions for Somalia. In addition, the Humanitarian Open Street Map Team (HOT) has been busy improving the data for Somalia and the only reason they haven’t been able to go full throttles forward is because of data licensing issues beyond their control. Colleagues from the Harvard Humanitarian Initiative (HHI) have also been offering their help where and when they can.

In sum, to say that the crisis mapping community has not been as “animated” in response to the crisis in the Horn is misleading and rather unfortunate given that ICT4Peace is co-hosting this year’s International Conference of Crisis Mappers (ICCM 2011). All ICT4Peace had to do was to send one simple email to the CrisisMappers.net membership to get all the above information (and likely more). Just because these efforts are not captured on CNN or on the front pages of the UN Chronicle does not mean that there haven’t been numerous ongoing efforts behind the scenes by dozens of different partners and members of the crisis mapping community.

I would therefore not be so quick to dismiss the perceived inaction of this comm-unity. I would also not make an automatic assumption that crisis mapping platforms and mobile technology solutions will always be “easy” or feasible to deploy in every context, especially if this is attempted reactively in the middle of a complex humanitarian crisis. Both Haiti and Japan provided permissive envi-ronments, unlike recent crisis mapping projects in Libya, Egypt and the Sudan which present serious security challenges. Finally, if direct offers of support by the crisis mapping community are not leveraged by field-based humanitarian organizations, then how exactly is said crisis mapping community supposed to be more animated?

Crowdsourcing Satellite Imagery Analysis for Somalia: Results of Trial Run

We’ve just completed our very first trial run of the Standby Task Volunteer Force (SBTF) Satellite Team. As mentioned in this blog post last week, the UN approached us a couple weeks ago to explore whether basic satellite imagery analysis for Somalia could be crowdsourced using a distributed mechanical turk approach. I had actually floated the idea in this blog post during the floods in Pakistan a year earlier. In any case, a colleague at Digital Globe (DG) read my post on Somalia and said: “Lets do it.”

So I reached out to Luke Barrington at Tomnod to set up distributed micro-tasking platform for Somalia. To learn more about Tomond’s neat technology, see this previous blog post. Within just a few days we had high resolution satellite imagery from DG and a dedicated crowdsourcing platform for imagery analysis, courtesy of Tomnod . All that was missing were some willing and able “mapsters” from the SBTF to tag the location of shelters in this imagery. So I sent out an email to the group and some 50 mapsters signed up within 48 hours. We ran our pilot from August 26th to August 30th. The idea here was to see what would go wrong (and right!) and thus learn as much as we could before doing this for real in the coming weeks.

It is worth emphasizing that the purpose of this trial run (and entire exercise) is not to replicate the kind of advanced and highly-skilled satellite imagery analysis that professionals already carry out.  This is not just about Somalia over the next few weeks and months. This is about Libya, Syria, Yemen, Afghanistan, Iraq, Pakistan, North Korea, Zimbabwe, Burma, etc. Professional satellite imagery experts who have plenty of time to volunteer their skills are far and few between. Meanwhile, a staggering amount of new satellite imagery is produced  every day; millions of square kilometers’ worth according to one knowledgeable colleague.

This is a big data problem that needs mass human intervention until the software can catch up. Moreover, crowdsourcing has proven to be a workable solution in many other projects and sectors. The “crowd” can indeed scan vast volumes of satellite imagery data and tag features of interest. A number of these crowds-ourcing platforms also have built-in quality assurance mechanisms that take into account the reliability of the taggers and tags. Tomnod’s CrowdRank algorithm, for example, only validates imagery analysis if a certain number of users have tagged the same image in exactly the same way. In our case, only shelters that get tagged identically by three SBTF mapsters get their locations sent to experts for review. The point here is not to replace the experts but to take some of the easier (but time-consuming) tasks off their shoulders so they can focus on applying their skill set to the harder stuff vis-a-vis imagery interpretation and analysis.

The purpose of this initial trial run was simply to give SBTF mapsters the chance to test drive the Tomnod platform and to provide feeback both on the technology and the work flows we put together. They were asked to tag a specific type of shelter in the imagery they received via the web-based Tomnod platform:

There’s much that we would do differently in the future but that was exactly the point of the trial run. We had hoped to receive a “crash course” in satellite imagery analysis from the Satellite Sentinel Project (SSP) team but our colleagues had hardly slept in days because of some very important analysis they were doing on the Sudan. So we did the best we could on our own. We do have several satellite imagery experts on the SBTF team though, so their input throughout the process was very helpful.

Our entire work flow along with comments and feedback on the trial run is available in this open and editable Google Doc. You’ll note the pages (and pages) of comments, questions and answers. This is gold and the entire point of the trial run. We definitely welcome additional feedback on our approach from anyone with experience in satellite imagery interpretation and analysis.

The result? SBTF mapsters analyzed a whopping 3,700+ individual images and tagged more than 9,400 shelters in the green-shaded area below. Known as the “Afgooye corridor,” this area marks the road between Mogadishu and Afgooye which, due to displacement from war and famine in the past year, has become one of the largest urban areas in Somalia. [Note, all screen shots come from Tomnod].

Last year, UNHCR used “satellite imaging both to estimate how many people are living there, and to give the corridor a concrete reality. The images of the camps have led the UN’s refugee agency to estimate that the number of people living in the Afgooye Corridor is a staggering 410,000. Previous estimates, in September 2009, had put the number at 366,000″ (1).

The yellow rectangles depict the 3,700+ individual images that SBTF volunteers individually analyzed for shelters: And here’s the output of 3 days’ worth of shelter tagging, 9,400+ tags:

Thanks to Tomnod’s CrowdRank algorithm, we were able to analyze consensus between mapsters and pull out the triangulated shelter locations. In total, we get 1,423 confirmed locations for the types of shelters described in our work flows. A first cursory glance at a handful (“random sample”) of these confirmed locations indicate they are spot on. As a next step, we could crowdsource (or SBTF-source, rather) the analysis of just these 1,423 images to triple check consensus. Incidentally, these 1,423 locations could easily be added to Google Earth or a password-protected Ushahidi map.

We’ve learned a lot during this trial run and Luke got really good feedback on how to improve their platform moving forward. The data collected should also help us provide targeted feedback to SBTF mapsters in the coming days so they can further refine their skills. On my end, I should have been a lot more specific and detailed on exactly what types of shelters qualified for tagging. As the Q&A section on the Google Doc shows, many mapsters weren’t exactly sure at first because my original guidelines were simply too vague. So moving forward, it’s clear that we’ll need a far more detailed “code book” with many more examples of the features to look for along with features that do not qualify. A colleague of mine suggested that we set up an interactive, online quiz that takes volunteers through a series of examples of what to tag and not to tag. Only when a volunteer answers all questions correctly do they move on to live tagging. I have no doubt whatsoever that this would significantly increase consensus in subsequent imagery analysis.

Please note: the analysis carried out in this trial run is not for humanitarian organizations or to improve situational awareness, it is simply for testing purposes only. The point was to try something new and in the process work out the kinks so when the UN is ready to provide us with official dedicated tasks we don’t have to scramble and climb the steep learning curve there and then.

In related news, the Humanitarian Open Street Map Team (HOT) provided SBTF mapsters with an introductory course on the OSM platform this past weekend. The HOT team has been working hard since the response to Haiti to develop an OSM Tasking Server that would allow them to micro-task the tracing of satellite imagery. They demo’d the platform to me last week and I’m very excited about this new tool in the OSM ecosystem. As soon as the system is ready for prime time, I’ll get access to the backend again and will write up a blog post specifically on the Tasking Server.

Analyzing Satellite Imagery of the Somali Crisis Using Crowdsourcing

 Update: results of satellite imagery analysis available here.

You gotta love Twitter. Just two hours after I tweeted the above—in reference to this project—a colleague of mine from the UN who just got back from the Horn of Africa called me up: “Saw your tweet, what’s going on?” The last thing I wanted to was talk about the über frustrating day I’d just had. So he said, “Hey, listen, I’ve got an idea.” He reminded me of this blog post I had written a year ago on “Crowdsourcing the Analysis of Satellite for Disaster Response” and said, “Why not try this for Somalia? We could definitely use that kind of information.” I quickly forgot about my frustrating day.

Here’s the plan. He talks to UNOSAT and Google about acquiring high-resolution satellite imagery for those geographic areas for which they need more information on. A colleague of mine in San Diego just launched his own company to develop mechanical turk & micro tasking solutions for disaster response. He takes this satellite imagery and cuts it into say 50×50 kilometers square images for micro-tasking purposes.

We then develop a web-based interface where volunteers from the Standby Volunteer Task Force (SBTF) sign in and get one high resolution 50×50 km image displayed to them at a time. For each image, they answer the question: “Are there any human shelters discernible in this picture? [Yes/No].” If yes, what would you approximate the population of that shelter to be? [1-20; 21-50; 50-100; 100+].” Additional questions could be added. Note that we’d provide them with guidelines on how to identify human shelters and estimate population figures.

No shelters discernible in this image

Each 50×50 image would get rated by at least 3 volunteers for data triangulation and quality assurance purposes. That is, if 3 volunteers each tag an image as depicting a shelter (or more than one shelter) and each of the 3 volunteers approximate the same population range, then that image would get automatically pushed to an Ushahidi map, automatically turned into a geo-tagged incident report and automatically categorized by the population estimate. One could then filter by population range on the Ushahidi map and click on those reports to see the actual image.

If satellite imagery licensing is an issue, then said images need not be pushed to the Ushahidi map. Only the report including the location of where a shelter has been spotted would be mapped along with the associated population estimate. The satellite imagery would never be released in full, only small bits and pieces of that imagery would be shared with a trusted network of SBTF volunteers. In other words, the 50×50 images could not be reconstituted and patched together because volunteers would not get contiguous 50×50 images. Moreover, volunteers would sign a code of conduct whereby they pledge not to share any of the imagery with anyone else. Because we track which volunteers see which 50×50 images, we could easily trace any leaked 50×50 image back to the volunteer responsible.

Note that for security reasons, we could make the Ushahidi map password protected and have a public version of the map with very limited spatial resolution so that the location of individual shelters would not be discernible.

I’d love to get feedback on this idea from iRevolution readers, so if you have thoughts (including constructive criticisms), please do share in the comments section below.

Crisis Mapping Somalia with the Diaspora

The state of Minnesota is home to the largest population of Somalis in North America. Like any Diaspora, the estimated 25,000 Somalis who live there ar closely linked to family members back home. They make thousands of phone calls every week to numerous different locations across Somalia. So why not make the Somali Diaspora a key partner in the humanitarian response taking place half-way across the world?

In Haiti, Mission 4636 was launched to crowdsource micro needs assessments from the disaster affected population via SMS. The project could not have happened without hundreds of volunteers from the Haitian Diaspora who translated and geo-referenced the incoming text messages. There’s no doubt that Diasporas can play a pivotal role in humanitarian response but they are typically ignored by large humanitarian organizations. This is why I’m excited to be part of an initiative that plans to partner with key members of the Diaspora to create a live crisis map of Somalia.

This is a mock-up for illustration only

The project is still in very early stages so there’s not much to show right now but I’m hopeful that the stars will align next week so we can formally launch the initiative. The basic game plan is as follows:

  • A short survey of some 10 questions is being drafted by public health professionals with experience in humanitarian response. These questions will try to capture the most essential indicators. More questions are be added at a later stage.
  • Humanitarian colleagues who have been working with the Somali Diaspora in Minnesota for years are now in the process of recruiting trusted members of the community.
  • These trusted members of the Diaspora will participate in a training this weekend on basic survey and interview methods. The training will also provide them with a hands-on introduction to the Ushahidi platform where they’ll  enter the survey results.
  • If everything goes well, these community members will each make several phone calls to friends and relatives back home next week. They’ll ask the questions from the survey and add the answers to the Ushahidi map. Elders in the community will fill out a paper-based form for other colleagues to enter online.
  • Trusted members of the Diaspora will continue to survey contacts back home on a weekly basis. New survey questions are likely to be added based on feedback from other humanitarian organizations. Surveys may also be carried out every other day or even on a daily basis for some of the questions.

If the pilot is successful, then colleagues in Minnesota may recruit additional trusted members of the community to participate in this live crisis mapping effort. There’s a lot more to the project including several subsequent phases but we’re still at the early stages so who knows where this will go. But yes, we’re thinking through the security implications, verification issues, data visualization features, necessary analytics, etc. If all goes well, there’ll be a lot more information to share next week in which case I’ll add more info here and also post an update on the Ushahidi blog.