Estimation of mango yields with SoYield®

Software and digital applications Sustainable agriculture
SoYield® is a decision support tool (DST) which makes it possible to estimate the yield of mango trees, at the scale of the orchard and at the scale of a territory. It meets the needs of producers and stakeholders in the sector as well as those of public policy support services
Soyield © Soyield, Cirad

Soyield © Soyield, Cirad

Mango sector and yield estimate

SoYield® is a decision support tool that takes the form of a mobile application and a web application. The mobile application allows mango growers or trackers to go out in the field, sample their plots with pictures of their orchard and estimate the yield. A web application or API services are being studied to consolidate all yield data generated by users to create a multi-source and multi-scale geographic information system.

The operation is very simple and is aimed at a wide spectrum of users. Through the mobile application, the farmer takes a limited number of photos of mango trees based on the margin of error that he has predetermined in order to obtain a live harvest yield estimate. The system takes into account the species of fruit to perform its calculations. At the early stage of development, the tool is intended for three countries: Senegal, Ivory Coast and Ghana.

Stage of development

TRL8 - Qualification of the complete system in an operational environment

TRL8 - Qualification of the complete system in an operational environment

What are the strengths of SoYield®?

The SoYield decision support tool®:

  • is user-friendly and is based on a photo-taking system;
  • adjusts the number of shots according to the margin of error defined by the producer;
  • integrates the algorithms used to obtain the level of yield by variety;
  • sends the expected result in real time;
  • connects suppliers and buyers via a dedicated module;
  • aggregates data on a larger geographic scale.

SoYield® at the service of the Mango sector in Africa

Two tools brought together in a single solution that meets different but complementary players and needs.

A smartphone application for producers

SoYield is easy to use in the field. The application provides a level of information that allows the producer to negotiate better the sale of his production with potential buyers.

The research team
SoYield® mobilized the expertise of two research units at CIRAD. The first, the Hortsys research unit, which specializes in horticultural cropping systems, particularly fruit trees. Its researchers provided their expertise on sampling strategies in order to identify the agronomic model and the algorithm used to estimate yields. The second, the Amap research unit (Botany and modeling of the architecture of plants and vegetation), which contributes to fruit remote sensing processes by training neural networks.
Sowit company provided its expertise to industrialize these models and develop a user interface suitable to the greater number.

References and intellectual property

Patents

SoYield® is a registered trademark owned by Sowit. The neural training models and algorithms come from PixFruit® expertise

Publications

Carlier Maxime. 2021. Development of methods for the estimation of dimensions and individual mass of mangoes by image analysis. Lyon: INSA Lyon, 49 p. Master's thesis 2: Bioinformatics and modelling: National Institute of Applied Sciences of Lyon

https://agritrop.cirad.fr/599148/ 

Faye E., Sarron J., Diatta J., Borianne P. 2019. In: Bonnet Pascal (ed.), Roche Mathieu (ed.), Kirchner Hélène (ed.). AgriNumA'2019. Summaries of communications. PixFruit: a data acquisition, management and sharing tool for standardization of the mango sector in West Africa at the service of its stakeholders. Dakar: Cirad, p. 10-11. AgriNumA 2019: Symposium "Digital Agriculture in Africa", 2019-04-28/2019-04-30, Dakar (Senegal).

http://publications.cirad.fr/une_notice.php?dk=592757 

Sarron J., Malézieux E., Sane CAB, Faye E.. 2019. In: Bonnet Pascal (ed.), Roche Mathieu (ed.), Kirchner Hélène (ed.). AgriNumA'2019. Summaries of communications. Mapping of mango orchard production based on tree structure parameters and land cover assessed by drone. Dakar: Cirad, 1 p. AgriNumA 2019: Symposium "Digital Agriculture in Africa", 2019-04-28/2019-04-30, Dakar (Senegal).

http://publications.cirad.fr/une_notice.php?dk=592663 

See also