Back to Observatory
Larvia: A shrimp larvae analysis app using Deep Learning
Description of the service
Larvia (Larva + AI, in Spanish), is a counting, individual weight estimation, weight grading, uniformity estimation, health status estimation, and geolocation of aquaculture samples service, including larvae and juvenile in raceways. In addition, in our web dashboard, our users can follow up on their seeding/reviews, and through business intelligence tools, make better business and production decisions.
Problem that it solves
Technicians usually count larvae or juveniles individually only to obtain the number of animals per gram. This process takes 3 to 5 minutes and is subject to human error. In less than 15 seconds, Larvia allows users to retrieve larvae size data, plus a histogram of weights, lengths, average weight, average length, coefficient of variation, uniformity, number of animals per size, pigmentation histogram, and georeferenced location, as well as images to validate detection accuracy. This service also gives access to a web dashboard with business intelligence tools for decision-making.Type of AI app used
Events detection (anomaly detection and early warning), Recognition
Main results to June 30, 2021
The quality of detection has been improved, from having only larvae to having larvae and juveniles.
Three main bottlenecks faced during implementation
Data labeling
Lessons learned in the design or use of AI for social impact
These tools streamline production by enabling better decision-making.
Country of origin
Geographic scope of operations
Ecuador, Peru, Mexico, Brazil, US Nicaragua, Honduras, Saudi Arabia, Thailand
Website
https://larvia.ai/Type of executing entity
StartupSector/industry
Sustainable Development Goal(s) to which your AI solution contributes
2 (zero hunger)
8 (decent work and economic growth)
9 (industry, innovation, and infrastructure)
IA app developed internally or by a third party
Internally
Name of implementing entity
Larvia SA
Stakeholders involved
Private entrepreneurs: Ivan Ramirez, Chris Olsen, Jaime Rodriguez
Percentage of the development team that are women
20%
Year they started using AI-based models
2018It may interest you
Responsible and Widespread Adoption of Artificial Intelligence in Latin America and the Caribbean
This self-assessment tool is designed to allow the mitigation of ethical risks associated with the use/application of new technologies. It is available so that the ethical performance of each system can be evaluated from the beginning.
El presente documento presenta un estudio de caso de un proyecto piloto en el estado de Jalisco que utilizó inteligencia artificial (IA) para el tamizaje de la Retinopatía Diabética.