What's that weed in my rice field?

25 January 2017

Rice field in northwest Cambodia
Rice field in northwest Cambodia

A new smartphone application has been developed by University of Sydney researchers that will help the plight of Cambodian farmers to manage weeds in their rice fields.

Associate Professor Daniel Tan from Agriculture and Environment at the University of Sydney has commissioned the app as part of an Australian Centre for International Agricultural Research (ACIAR) project that is examining sustainable intensification and diversification in the lowland rice system in northwest Cambodia. The app was developed by a Master of Agriculture and Environment student, Yehezkiel Henson from Dr Bob Martin's Cambodian weed database with start-up funding from the International Environmental Weeds Foundation (IEWF) and the Crawford Fund and converted into a mobile app by Nic Barker under the supervision of Associate Professor Rosanne Quinnell from the Faculty of Science. Both Nic and Rosanne are members of the CampusFlora App development team.

"WeedID contains a photo dictionary of ten of the most common weeds in northwest Cambodian rice fields during different stages of growth. We have images of seeds, seedlings, mature plants and flowers that will all help to identify the weeds which are devastating Cambodian farmers' rice crops. The database will be expanded to 30 weeds to cover over 95% of the most common weeds in Cambodian rice fields. Weed seed contamination in the rice grain harvest can result in price downgrades and product rejection at the rice mills.

Weeds can have a huge impact on the quality and quantity of rice that is produced and in turn this can have devastating financial implications for smallholder farmer livelihoods and food security.

Different weeds require different management techniques to remove or reduce them. Depending on the life cycle, nutrient requirements or mode of reproduction, we will employ a different method of management. Some weeds, such as awnless barnyard grass (Echinochloa colona) can be managed simply by flooding the fields to drown them. Sometimes we may need to apply specific selective herbicides to manage them, as in the case of the smallflower umbrella plant (Cyperus difformis), also known as 'dirty Dora' in Australia. The WeedID app contains specific management information and details the most appropriate way to manage the weed," said Associate Professor Daniel Tan.

The motivation for the mobile phone app has stemmed from the statistics surrounding mobile phone use in Cambodia.

"The Cambodian Business Review recently reported on smartphone use in the country, citing figures from the World Bank that suggest there are 133 phones for every 100 people, which is more than the United States of America, which has 110 phones per 100 people. The article also indicated that smartphone ownership is growing more than 40 percent each year. The use of mobile phones is obvious to us when in the field and conducting research in Cambodia. Everyone seems to have a couple of phones and they frequently access the internet and social media.

The Cambodian smallholder farmers we work with are also hungry for information and will use the technology and resources available to them to solve problems. Farmers have been showing us photos of pest animals, weeds and diseased plants taken on their phones, which our team have been able to identify. This prompted the idea to develop a free, user-friendly mobile tool to identify the weeds they have in their rice fields so that they can manage their weeds better.

There are very useful identification guides online and in paper form, but this app goes one step further to improve the accessibility of identification and management tools.

The idea is that farmers will be able to observe a weed in their field, identify it using the photo dictionary and then apply the appropriate management technique.

We have some more work to do but we have a prototype ready for iPhones and Androids and we are currently taking these to farmers in Cambodia so they can provide us with an appraisal of the usability and effectiveness of the app. So far, we have surveyed the farmers involved with our ACIAR project and the feedback is incredibly encouraging. We have constructive information on ways to improve the app. We have also translated the app into Khmer which will improve access to the information and management solutions," Daniel said.

Interviewing farmers about the produce they grow, profitability, concerns, and the effectiveness of the WeedID App as part of the ACIAR project in the region
Interviewing farmers about the produce they grow, profitability, concerns, and the effectiveness of the WeedID App as part of the ACIAR project in the region

The desired outcome is that the farming communities will have improved yields, financial gains and will build their knowledge surrounding crop management.

"Our project is working to understand what might help to lift communities out of poverty and this is just one small step to improving the crops that support the livelihood for farming families.

We have started with weeds as they are the most common issue identified by the rice farmers we have been working with in this ACIAR funded project. If the effectiveness and uptake of this app is apt, perhaps we can consider other issues that are identifiable through this medium, including a picture dictionary of animal pests or common diseases," said project lead, Associate Professor Daniel Tan.

WeedID Android app
WeedID iOS app