Crowdsourcing for food security

By Myroslava Lesiv, IIASA Ecosystems Services and Management Program.

The public can contribute considerably to science by filling the gaps of missing information in many research areas, for example, monitoring land use, biodiversity, or forest degradation. Crowdsourcing campaigns organized by research institutions bring together citizens interested in science and help solving research questions to the benefit of the whole world.

This June, the IIASA Geo-Wiki team ran the Global Field Size campaign, encouraging citizen scientists to classify field sizes on satellite images. Its aim was to develop a global field sizes dataset, which will be used as input to create an improved global cropland field size map for agricultural monitoring and food security assessments. The field sizes dataset can also help us determine what types of satellite data are needed for agricultural monitoring in different parts of the world.

Geo-Wiki interface for collecting field size data. Background layer: Google Maps.

Why are field sizes so important? They provide us with valuable information to tackle challenges of food security. A recent study showed that more than a half the food calories produced globally comes from smallholder farmers, who often make up the most vulnerable parts of population, living in poverty. Within this scope, the field size dataset fills the gaps of missing information, especially for countries that have a limited food supply and lack a well-developed agricultural monitoring system.

The Global Field Size campaign has been one of the most successful crowdsourcing campaigns run through the Geo-Wiki engagement platform. Within one month, 130 participants completed 390,000 tasks – that is, they classified the field sizes in 130,000 locations around the globe!

So we can see that crowdsourcing is powerful, but can we trust the data? Is it accurate enough to be used in different applications? I think it is! The Geo-Wiki team has significant experience in running crowdsourcing campaigns; one of the key lessons we have learned from previous Geo-Wiki campaigns is the importance of training the public to increase the quality of the crowdsourced data.

This campaign was designed so that the participants learned over time how to delineate fields in different regions of the world, and, at the same time, pay special attention to the quality of their submissions. At the end of the campaign, the majority of participants gave us a feedback that, to them, this campaign was indeed a learning exercise. From our end, I have to add, this was also a challenging campaign, as fields are so diverse in shape, continuity of coverage, crop type, irrigation, etc.

Global distribution of dominant field sizes. Cartography by Myroslava Lesiv. Country boundaries: GAUL. Software: ArcMap 10.1.

During the campaign, the crowd was asked to identify whether there were fields in a certain location, and determine the relevant field sizes by the visual interpretation of very high-resolution Google and Bing imagery. A “field” was defined as an agricultural area that included annual or perennial croplands, fallow, shifting cultivation, pastures or hayfields. The collected data can also be used to identify areas falsely mapped as cropland.

Now the team is focused on summarizing the results of the campaign, processing the collected field size data, and preparing them for scientific publication. We will ensure that the published dataset is of high quality and can be used by others with confidence!

This article gives the views of the author, and not the position of the Nexus blog, nor of the International Institute for Applied Systems Analysis.

New portal links local and global flood data

By Ian McCallum, IIASA Ecosystems Services and Management Program

Communities need information to prepare for and respond to floods – to inform risk reduction strategies and strengthen resilience, improve land use planning, and generally prepare for when disaster strikes. But across much of the developing world, data are sparse at best for understanding the dynamics of flood risk. When and if disaster strikes, massive efforts are required in the response phase to develop or update information about basic infrastructure, for example, roads, bridges and buildings. In terms of strengthening community resilience it is important to know about the existence and location of such features as community shelters, medical clinics, drinking water, and more.

The risk Geo-Wiki platform
The Risk Geo-Wiki is online platform established in 2014, which acts not only as a repository of available flood related spatial information, but also provides for two-way information exchange. You can use the platform to view available information about flood risk at any location on the globe, along with geo-tagged photos uploaded by yourself or other users via a mobile application Geo-Wiki Pictures. The portal is intended to be of practical use to community leaders and NGOs, governments, academia, industry and citizens who are interested in better understanding the information available to strengthen flood resilience.

The Risk Geo-Wiki showing geo-tagged photographs overlaid upon satellite imagery across the Karnali basin, Nepal. © IIASA

With only a web browser, and a simple registration, anyone can access flood-related spatial information worldwide. Available data range from flood hazard, exposure and risk information, to biophysical and socioeconomic data. All of this information can be overlaid upon satellite imagery or OpenStreetMap, along with on-ground pictures taken with the related mobile application Geo-Wiki Pictures.  You can use these data to understand the quality of available global products or to visualize the numerous local datasets provided for specific flood affected communities. People interested in flood resilience will benefit from visiting the platform and are welcome to provide additional information to fill many of the existing gaps in information.

Flood resilience and data gaps
One of the aims of the Risk Geo-Wiki is to identify and address data gaps on flood resilience and community-based disaster risk reduction. For example, there is a big disconnect between information suitable for global flood risk modelling and that necessary for community planning. Global modelers need local information with which to validate their forecasts while community planners want both detailed local information and an understanding of their communities in the wider region. The Flood Resilience Alliance is working with many interested groups to help fill this gap and at the same time help strengthen community resilience against floods and to develop and disseminate knowledge and expertise on flood resilience.

The Risk Geo-Wiki showing modelled global flood risk data overlaid at community level. While this data is suitable at the national and regional level, it is too coarse for informing community level decisions. © IIASA


Practical applications for local communities
Already, communities in Nepal, Peru, and Mexico have uploaded data to the site and are working with us on developing it further.  For local communities who have uploaded spatial information to the site, it allows them to visualize their information overlaid upon satellite imagery or OpenStreetMap. Furthermore, if they have used Geo-Wiki Pictures to document efforts in their communities, these geo-tagged photos will also be available.

Community and NGO members mapping into OSM with mobile devices in the Karnali basin, Nepal. © Wei Liu, IIASA

In addition to local communities who have uploaded information, the Risk Geo-Wiki will provide important data to others interested in flood risk, including researchers, the insurance industry, NGOs, and donors. The portal provides a source of information that is both easily visualized and overlaid on satellite imagery with local images taken on the ground if available. Such a platform allows anyone interested to better understand flood events over their regions and communities of interest. It is, however, highly dependent upon the information that is made available to the platform, so we invite you to contribute. In particular if you have geographic information related to flood exposure, hazard, risk and vulnerability in the form of images or spatial data we would appreciate you getting in contact with us.

About the portal:
The Risk Geo-Wiki portal was established by the International Institute for Applied Systems Analysis (IIASA) in the context of the Flood Resilience Alliance. It was developed by the Earth Observation Systems Group within the Ecosystems Services and Management Program at IIASA.

Further information

This article gives the views of the author, and not the position of the Nexus blog, nor of the International Institute for Applied Systems Analysis.

Interview: Taking Geo-Wiki to the ground

Steffen Fritz has just been awarded an ERC Consolidator Grant to fund a research project on crowdsourcing and ground data collection on land-use and land cover. In this interview he talks about his plans for the new project, CrowdLand. 

Pic by Neil Palmer (CIAT).

Farmers in Kenya are one group which the Crowdland Project aims to involve in their data gathering. Photo credit: Neil Palmer, CIAT

What’s the problem with current land cover data?
There are discrepancies between current land cover products, especially in cropland data. It’s all based on satellite data, and in these data, it is extremely difficult to distinguish between cropland and natural vegetation in certain parts of the world if you do not use so-called very high resolution imagery, similar to a picture you take from space. With this high-resolution data you can see structures like fields and so on, which you can then use to distinguish between natural vegetation and cropland. But this is a task where currently people are still better at than computers–and there is a huge amount of data to look at.

In our Geo-Wiki project and related efforts such as the Cropland Capture game, we have asked volunteers to look at these high-resolution images and classify the ground cover as cropland or not cropland. The efforts have been quite successful, but our new project will take this even further.

How will the new project expand on what you’ve already done in Geo-Wiki?
The big addition is to go on the ground. Most of the exercises we currently do are based on the desktop or the phones, or tablets, asking volunteers to classify imagery that they see on a screen.

What this project aims to do is to improve data you collect on the ground, known as in-situ data.  You can use photography, GPS sensors, but also your knowledge you have about what you see. We will use volunteers to collect basic land cover data such as tree cover, cropland, and wetlands, but also much more detailed land-use information. With this type of data we can document what crops are grown where, whether they are irrigated, if the fields are fertilized, what exact type of crops are growing, and other crop management information which you cannot see in satellite imagery. And there are some things you can’t even see when you’re on the ground, thus you need to ask the farmer or recruit the farmer as a data provider. That’s an additional element this project will bring, that we will work closely with farmers and people on the ground.

For the study, you have chosen Austria and Kenya. Why these two countries?
In Austria we have much better in situ data. For example, the Land Use Change Analysis System (LUCAS) in Europe collects in situ data according to a consistent protocol. But this program is very expensive, and the agency that runs it, Eurostat, is discussing how to reduce costs. Additionally the survey is only repeated every three years so fast changes are not immediately recorded. Some countries are not in favor of LUCAS and they prefer to undertake their own surveys. Then however you lose the overall consistency and there is no Europe-wide harmonized database which allows for comparison between countries.   Our plan is to use gaming, social incentives, and also small financial incentives to conduct a crowdsourced LUCAS survey. Then we will examine what results you get when you pay volunteers or trained volunteers compared to the data collected by experts.

In Kenya, the idea is similar, but in general in the developing world we have very limited information, and the resources are not there for major surveys like in Europe. In order to remedy that the idea is again to use crowdsourcing and use a “bounded crowd” which means people who have a certain level of expertise, and know about land cover and land use, for example people with a surveyor background, university students, or interested citizens who can be trained. But in developing countries in particular it’s important to use financial incentives. Financial incentives, even small ones, could probably help to collect much larger amounts of data. Kenya is a good choice also because it has quite a good internet connection, a 3G network, and a lot of new technologies evolving around mobile phones and smartphone technology.

What will happen with the data you collect during this project?
First, we will analyze the data in terms of quality.  One of our research questions is how good are the data collected by volunteers compared to data collected by experts. Another research question is how can imperfect but large data collected by volunteers be filtered and combined so that it becomes useful and fulfills the scientific accuracy requirements.

Then we will use these data and integrate them into currently existing land use and land cover data, and find ways to make better use of it. For example, in order to make projections about future land-use and to better quantify current yield gaps it is crucial to get accurate current information on land-use, including spatially explicit information on crop types, crop management information and other data.

Once we have done some quality checks we will also make these data available for other researchers or interested groups of people.

Crowdsourcing for land cover is in its infancy. There have been lots of crowdsourcing projects in astronomy, archaeology, and biology, for example, but there hasn’t been much on land use, and there is huge potential there. ”We need to not only better understand the quality of the data we collect, but also expand the network of institutions who are working on this topic.”

Note: This article gives the views of the interviewee, and not the position of the Nexus blog, nor of the International Institute for Applied Systems Analysis.

How games can help science: Introducing Cropland Capture

By Linda See, Research Scholar, IIASA Ecosystems Services and Management Program

Researchers estimate we spend 3 billion hours a week on game playing. CC Image courtesy TheErin on Flickr

Researchers estimate we spend 3 billion hours a week on game playing. CC Image courtesy TheErin on Flickr

On a recent rush hour train ride in London I looked around to see just about everybody absorbed in their mobile phone or tablet. This in itself is not that unusual. But when I snooped over a few shoulders, what really surprised me was that most of those people were playing games. I hope this bodes well for our new game, Cropland Capture, introduced last week.

Cropland Capture is a game version of our citizen science project Geo-Wiki, which has a growing network of interested experts and volunteers who regularly help us in validating land cover through our competitions. By turning the idea into a game, we hope to reach a much wider audience.

Playing Cropland Capture is simple: look at a satellite image and tell us if you see any evidence of cropland. This will help us build a better map of where cropland is globally, something that is surprisingly uncertain at the moment. This sort of data is crucial for global food security, identifying where the big gaps in crop yields are, and monitoring crops affected by droughts, amongst many other applications.

Gamification and citizen science
The idea of Cropland Capture is not entirely unique. There are an astonishingly large number of games available for high tech gaming consoles, PCs and increasingly, mobile devices. While the majority of these games are pure entertainment, some are part of an emerging genre known as ”serious games” or ”games with a purpose.” These are games that either have an educational element or through the process of playing them, you can help scientists in doing their research. One of the most successful examples is the game FoldIt, where teams of players work together to decode protein structures. This is not an easy task for a computer to do, but some people are exceptionally talented at seeing these patterns. The result has even led to new scientific discoveries that have been published in high level journals such as Nature.

Jane McGonigal, in her book Reality is Broken (Why Games Make us Better and How They Can Change the World), estimates that we spend 3 billion hours a week alone on game playing, and that the average young person spends more time gaming by the end of their school career than they have actually spent in school. Although these figures may seem alarming, McGonigal argues that there are many positive benefits associated with gaming, including the development of problem-solving skills, the ability to cope better with problems such as depression or chronic pain, and even the possibility that we might live ten years longer if we played games. If people spent just a fraction of this time on “serious games” like FoldIt and Cropland Capture, imagine how much could be achieved.

Since the game started last Friday, 185 players have validated 119,777 square kilometers of land (more than twice the land area of Denmark).

photo

Cropland Capture is easy to play – simply swipe the picture left or right to say whether there is cropland or not.

Get in the game
You can play Cropland Capture on a tablet (iPad or Android) or mobile phone (iPhone or Android). Download the game from the Apple’s App Store or the Google Play Store. For those who prefer an online version, you can also play the game at: http://www.geo-wiki.org/games/croplandcapture/. For more information about the game, check out our videos at:  http://www.geo-wiki.org/games/instructions-videos/. During the next six months, we will be providing regular updates on Twitter (@CropCapture) and Facebook.

The game is being played for  six months, where the top scorer each week will be crowned the weekly winner. The 25 weekly winners will then be entered into a draw at the end of the competition to win three big prizes: an Amazon Kindle, a smartphone, and a tablet. The game was launched only last week so there is plenty of time to get involved and help scientific research.