Take part in citizen science for food security

According to the team involved, there is currently no global dataset based on the spatial distribution of the world's staple crops. This lack of accurate maps showing the distribution of crops currently hampers policy and investment, potentially impeding efforts to improve food security – particularly against the backdrop of climate change.

Globally, detailed information on crops can help to identify where investment might be most effective in boosting agricultural productivity, while at regional levels this information can be used to help understand the effects of drought and other disasters on food production.

Moreover, such crop type maps are an important prerequisite to enable many follow up investigations for example on agricultural productivity, environmental impact of fertilisers and pesticides or the decline of pollinators. Several initiatives in the ESA Earth Observation Programmes are supporting the generation of such crop type maps. However, commonly the critical ingredient that is missing is the ground reference data.

Citizen science provides an opportunity to improve this situation.

The Earth Challenge 2020 aims to use citizen science to address major environmental issues such as air pollution and food supply. ESA joined the Earth Challenge 2020 consortium of strategic partners to work together in addressing some of the issues. The involvement of citizens is fostered, among others, through the Earth Challenge 2020 App that features several thematic widgets.

The new Food Supply widget asks volunteers around the globe to interpret and label different street-level photographs of six major crop types.

In addition to advancing work on food security and preparing for the increasing global population amid climate change, this campaign will help clarify the contributions that citizen science can make to satellite observations, and vice versa.

Ian McCallum from IIASA, explains, “Currently much of the best information we have on crop species distribution globally is derived from models.

“This includes data from the Food and Agriculture Organization of the United Nations and the Spatial Production Allocation Model (SPAM). The SPAM data, for example, are provided at 10 km resolution for 42 crops. While this data provides a comprehensive set of information for the modelling community, the research community and policymakers require a much finer level of detail, both spatially and temporally.”

This innovative citizen science approach to labelling street-level photographs of crop types will be linked to the global Earth observation archives through the Euro Data Cube platform. This ESA-funded activity provides the environment for linking citizen-interpreted information with automatically-derived agricultural parcel boundaries.

Together these provide the essential inputs to machine learning approaches that allow deriving high-resolution crop-type maps over large areas.

ESA’s Patrick Griffiths said, “While the availability and quality of Earth observation data has greatly increased over the last years, for example, through Europe’s Copernicus programme and the Sentinel satellites, the general lack of reference and training data is hindering many innovative applications.

“Once in place, this workflow will allow training data to be generated in a highly automated manner and link up with Earth observation data and machine learning technologies. Today’s release of the widget is a first crucial step towards that goal.”

Steffen Fritz from IIASA added, “Apart from providing valuable data, the app widget will provide a fun way for people to test and increase their knowledge about crops and learn more about the global food supply chain.”

The Earth Challenge App directs first-time users to install the Earth Challenge version of Picture Pile via GooglePlay or the AppStore, after which they can start labelling images. As the number of street-level images grows, users can choose to label images close to their home and anywhere else in the world.