Drones detect crop stresses more effectively

Flying a specially equipped unmanned aerial vehicle (UAV) – also known as a drone – a team of International Potato Center (CIP) researchers from South America and Africa used remote-sensing technology to obtain data on orange-fleshed sweet potato fields in Tanzania. The joint study ran for two weeks in the spring of 2015. Roberto Quiroz, project leader at CIP-Lima in Peru, where the image-processing and data analyses were completed, explained the added value of UAV technology. ‘The quality of the data taken by the drones was great, and discrimination of land uses and the estimation of the area for each use were achieved with high accuracy.’

The East Africa study was part of a larger project that focused on the use of UAVs for collecting detailed crop information via high-quality aerial imagery, and built on prior work by CIP researchers in Peru. With funding from the Bill and Melinda Gates Foundation, the researchers plan to develop a remote sensing system for agriculture that is designed to fit the needs of smallholder farmers. By using aerial data these farmers can make more informed decisions about when to plant crops and which varieties they should grow, reducing their risk of crop failure and hunger.

Local scientists’ involvement

The setting for the field study was the rural landscape of the Mwanza region of northern Tanzania, some 200 kilometres west of Serengeti National Park, along the southern end of Lake Victoria. This is where farmers produce more sweet potatoes than anywhere else in Tanzania.

Lima-based CIP team-members, working with experts from Nairobi, used an Oktokoper XL eight-armed UAV to collect data on several farms during the project period, with advance approval from individual farmers. The team gathered aerial data from many sweet potato fields, as well as fields of sweet pepper, cassava, sorghum, cotton, rice and maize. They also met with government officials, scientists and local farmers to explain the project and its goals.

On their first day in the field, the team met with scientists at the Lake Zone Agricultural Research and Development Institute (LZARDI), in Ukiriguru. Part of Tanzania’s Ministry of Agriculture and Food Security, LZARDI is an agricultural research and promotion agency that focuses on different crops.

Adolfo Posadas, the Nairobi-based leader of the CIP mission, explained to the LZARDI scientists that CIP was developing a wide range of open-source products as part of the project, from software for programming flights and processing post-flight images, to instructions for assembling commercially available drones and sensors. ’The principal outcome of this project will be to transfer all of this technology so it is freely available to the next user,’ Posadas said. This will reduce costs significantly, although a commercial UAV would still be needed.

Drone demonstration

In a serendipitous surprise, a LZARDI field just a few meters from the conference room proved an excellent starting place — containing fourteen varieties of orange-fleshed sweet potato growing side-by-side in different sections, allowing CIP researchers to gather a large amount of data about the varieties they hoped to study in one place.

At the field, the CIP researchers began the multi-step process of collecting drone imagery. First, they used measuring tape to mark rectangular sections of the field. At each corner, they drove markers into the ground, taking specific GPS coordinates for each – creating ground control points that are used during image processing to make aerial images geographically accurate.

At the same time, Luis Silva, a UAV pilot based at CIP-Lima, readied the UAV for flight, adding propellers, sensors and other finishing touches. Pre-flight checks completed, Silva launched the Oktokopter and flew it smoothly over the field, shooting photographs as he went. The first UAV flight used a standard camera, while the second flight used a multispectral camera, which captures and measures light at visible and near-infrared wavelengths.

Making use of different cameras is important because each plant variety has a small but measurable difference in the wavelength of light it reflects when exposed to sunlight — like a distinctive signature. By measuring this spectral signature, users can identify from the air whether a crop is sweet potato, cassava or something else, and may also be able to determine which variety the crop is.

The signatures of sweet potato varieties

The spectral signature can reveal whether individual plants are thriving or whether they are stressed by drought, nutritionally deficient, or under attack by insects or a virus. Such changes can be detected in aerial, multispectral images before they can be seen by the naked eye. Collecting these signatures is a key part of CIP’s project, with the eventual goal of building a spectral library that contains signatures for each sweet potato variety.

During each flight, the drone also took images of the field at different altitudes, ranging from five to hundred metres. This was part of an effort to find the best altitude for shooting photographs for agricultural analysis. Eventually, the researchers hope these aerial images will be superimposed over larger-scale images from satellites to provide better detail on nationwide crop production than is currently possible or affordable.

Everina Lukonge, a plant breeder at LZARDI and one of the many scientists who helped the CIP team through its work in Tanzania, explained how UAV-based remote-sensing provides an improvement over the current rough estimates made by crop statisticians. ‘When the statistics are not known, you cannot estimate production,’ she said. ‘If you have UAV-gathered data, it means you can estimate the food. Maybe next season there is hunger. Maybe there is a bumper crop, so you can look for a market. It can help in planning and budget allocation.’

Improving the quality of statistics

Now that the CIP researchers have demonstrated the drone-based system’s capability to acquire accurate, high-quality information in the real world, they hope to obtain permission from Kenya and Uganda to fly above other farms. ‘We just need a permanent permit to move back in and help the local bureau of statistics and other authorities generate the data they need for improving the quality of agricultural statistics,’ project-leader Quiroz said.

CIP's researchers also hope that their remote sensing project will encourage other African nations to begin their own experiments with remote sensing. They captured their work in the field in Tanzania on video with assistance from a graduate student from the University of Missouri-Columbia in the US, and plan to release a film on remote sensing and agriculture in the near future.

‘It was important to document the process, because these are new technologies that we want to share with other potential developers and users in Africa,’ said Corinne Valdivia, Associate Professor of Agricultural and Applied Economics at the University of Missouri-Columbia, a UAV project participant who studies how new technologies become part of the toolbox for key decision-makers. ‘They will be instrumental in finding the pathways for reproducing and adapting the technologies for use in their own countries.’

Related links

Website of the International Potato Center.
http://cipotato.org

Three articles from CIP website: ‘Creating a Community of Practice’ (http://goo.gl/PK8Gh0); ‘Beyond flying UAVs’ (http://goo.gl/vc5muF); ‘Invasion of the Potato Drones’ (http://goo.gl/KdC7V6).