Kuzi's SMS alerts may warn of locusts up to three months ahead

AI system

System: Kuzi (machine-learning locust prediction and SMS alert tool)
Model: Not assessed
Release: Not assessed
Application developer: Selina Wamucii, Nairobi
Role: Not assessed
Configuration: Not assessed
Inputs and outputs: Not assessed
Autonomy: Not assessed
Workflow: Satellite, soil-sensor and ground meteorological data feeds. SMS delivery in Kiswahili, Amharic and Somali.
Human oversight: Not assessed
Relation to AI: Only the maker's CEO is quoted; no evaluation of the machine-learning model, no official use, and no documented alert that changed an outcome were found.
AI contribution: Not assessed

Outcome identifiers: Not assessed
Benefit: Selina Wamucii's Kuzi combines satellite, soil-sensor and weather data with machine learning to map locust risk for Kenya, Uganda, Ethiopia and Somalia; maker statements only, no outcome evidence.
Category: Improved Knowledge Discovery
Status: Not assessed
Beneficiary groups: People. Society.
Beneficiaries: Not assessed
Reach: Not assessed
Distribution and access: Not assessed
Duration: Not assessed
Expected?: Yes
Costs and harms: Not assessed

Participants: Developer: Selina Wamucii, Nairobi. Operator: Selina Wamucii (free SMS service for users in Kenya, Uganda, Ethiopia and Somalia).
Jurisdictions: Benefit: Nairobi, Kenya. Developer: Kenya. Operator: Kenya.
Ownership and control: Not assessed
Dependencies: Not assessed
Cross-border connections: Not assessed
Geopolitical implications: Not assessed

Conditions for replication: Funding for further features, which the CEO said was being sought.
Replication attempts: Not assessed
Later findings: No evaluation, official adoption or later report on Kuzi after January 2021 was found.
Availability: Not assessed
Institutional decision: Not assessed
Grounds: Not assessed
Action and result: Not assessed
Success criterion: Not assessed

Assessed benefits: People. Society.
Depth: Not assessed
Reasons: People: No user, ministry or FAO confirmation of an alert received or acted on. Society: No evaluation of forecast skill or of crop losses avoided.
Observed or intended: Not assessed
Rubric: Not assessed
Assessor and date: Not assessed
Alternative assessments: Not assessed
Fill: Independently reported

Kind: Not assessed
Related entries: Not assessed
Field: Agriculture / pest early warning. Desert locust forecasting.
Purpose: Predict where desert locusts will breed and migrate and warn farmers and pastoralists by SMS months in advance.
Dates: Date basis unassessed: 2021 (precision unassessed). Updated: 21 October 2026.
Stage: Not assessed
Version: SHA-256: 80b7cab69185…

News report Independent author

Diwakar A. Kuzi, an AI-powered tool helping African farmers fight locusts. TRT World, 13 January 2021.
News report Independent author

Synced. Kenyan-Developed APP Utilizes ML to Predicate the Migration and Breeding of Locusts. Synced Review, 18 January 2021.