AI system
- System
-
eLocust3m (PlantVillage) with AI data validation feeding FAO's Desert Locust Information Service
- Model
-
Not assessed
- Release
-
Exact release not established.
- Application developer
-
PlantVillage, Pennsylvania State University, with FAO - Role
-
The software checked submitted photographs and filtered unusable reports before FAO analysis.
- Configuration
-
The deployment used eLocust3M.
- Inputs and outputs
-
Not assessed
- Autonomy
-
Not assessed
- Workflow
-
Scouts and residents sent locust sightings through eLocust3m. PlantVillage’s software removed unusable data. FAO used the reports to direct control teams and aircraft.
- Human oversight
-
Not assessed
- Relation to AI
-
Two AI uses are documented: algorithms that double-check submitted photos (Times) and AI that filters unusable records out of FAO's daily intake (FAO). A Penn State deep-learning soil-moisture model is mentioned by the maker's university. The outcome figures belong to the entire control operation and no source isolates the AI's contribution. FAO is both co-developer and deployer, so its feature is maker-authored. The Times report is independent with named sources (Cressman, Ferrand, Hughes, Jeptoo, Owuor, Craig).
- AI contribution
-
Two AI uses are documented: algorithms that double-check submitted photos (Times) and AI that filters unusable records out of FAO's daily intake (FAO). A Penn State deep-learning soil-moisture model is mentioned by the maker's university. The outcome figures belong to the entire control operation and no source isolates the AI's contribution. FAO is both co-developer and deployer, so its feature is maker-authored. The Times report is independent with named sources (Cressman, Ferrand, Hughes, Jeptoo, Owuor, Craig).
Benefits
- Outcome identifiers
-
Not assessed
- Benefit
-
FAO estimates that the East African control campaign protected food supplies for 36.6 million people. AI helped process locust reports within that wider operation.
- Category
-
Reduced Risk
- Status
-
Not assessed
- Beneficiary groups
-
Society. Organizations. People.
- Beneficiaries
-
FAO’s survey and control teams, and people whose food supplies were threatened by locusts.
- Reach
-
FAO estimates that 36.6 million people benefited from the whole control campaign. The number attributable to AI is not established.
- Distribution and access
-
Not assessed
- Duration
-
Not assessed
- Expected?
-
Yes
- Costs and harms
-
Not assessed
Measurement
- Studies
-
Not assessed
- Study design
-
Not assessed
- Measurement
-
Not assessed
- Setting and sample
-
Not assessed
- Measures
-
Reports received and processed, crop and milk losses estimated to have been avoided, and the number of people whose food supplies were protected.
- Comparison
-
Assumed alternative: no locust control operations in East Africa (FAO's estimate of the losses that the control campaign averted)
- Results
-
Assumed comparison. Reference: loss of 4 million tonnes of cereal and 800 million litres of milk production, USD 1.56 billion in cereal and milk losses. Result: those losses prevented and the food security of 36.6 million people protected.
- Additional value from AI
-
Not assessed
- Limitations
-
FAO’s estimates cover the entire control campaign. They do not isolate the value of AI or document an individual farmer’s outcome.
- Denominators
-
Not assessed
- Materials for replication
-
Not assessed
Money
- Kind of value
-
cereal and milk losses avoided by the locust control operations in East Africa that the app and AI data cleaning fed
- Amount
-
Estimate: USD 1.56 billion
- Currency and prices
-
USD, stated in the source. Nominal source amount; price year not separately stated.
- Period and unit
-
East African response reported May 6, 2021; the amount-specific start date is unstated. Cereal and milk losses avoided across the regional response.
- Realization
-
Retrospective estimate.
- Recipients and payers
-
Recipient: Farmers, livestock keepers, and food consumers in affected East African countries. Payer: Not applicable to avoided production losses.
- Gross or net
-
Estimated gross production losses avoided by the response; response costs are not deducted.
- Included costs
-
Not assessed
- Comparison
-
Estimated losses without the control response; calculation details are not given in this account.
- Method
-
Not assessed
- Return and payback
-
Not assessed
People and places
- Participants
-
Developer:
PlantVillage, Pennsylvania State University, with FAO. Operator: FAO Desert Locust Information Service and national locust control operations in Kenya, Ethiopia and Somalia. - Jurisdictions
-
Developer:
United States. Operator: 
Italy. - Ownership and control
-
Not assessed
- Dependencies
-
Not assessed
- Cross-border connections
-
Not assessed
- Geopolitical implications
-
Not assessed
Follow-up
- Conditions for replication
-
Scouts need smartphones or satellite devices where networks are unavailable. FAO staff must review reports daily, and control teams and aircraft must be available to act on them.
- Replication attempts
-
2 follow-up entries. Outcome unresolved: 2.
- Later findings
-
15 June 2022. In June 2022 FAO declared the East Africa upsurge over and said it had trained 3,800 people across the region to use applications such as eLocust3 to report locusts.
- Availability
-
Not assessed
- Institutional decision
-
Not assessed
- Grounds
-
Not assessed
- Action and result
-
Not assessed
- Success criterion
-
Not assessed
Evidence
- Source numbers
-
AIBD-0193-source-0001–0004
- Citations
-
Numbered references below.
- Language
-
Not assessed
- Source relationships
-
Developer, Independent
- Original evidence
-
Not assessed
- Access and versions
-
Not assessed
- Supported findings
-
Not assessed
- Evidence links
-
Not assessed
- Evidence strength
-
Not assessed
- Missing evidence
-
Not assessed
Grades
- Assessed benefits
-
Society. Organizations. People.
- Depth
-
Society: 3. Organizations: 2. People: Not assessed.
- Reasons
-
FAO states that the campaign prevented the loss of 4 million metric tons of cereal and 800 million liters of milk. PlantVillage helped FAO process up to 2,500 reports a day, about a quarter of which were initially unusable. The campaign estimates cover many interventions, so they cannot be assigned to AI alone.
- Observed or intended
-
Not assessed
- Rubric
-
Not assessed
- Assessor and date
-
Not assessed
- Alternative assessments
-
Not assessed
- Fill
-
Independently reported
Entry details
- Kind
-
Not assessed
- Related entries
-
Not assessed
- Field
-
Agriculture / pest early warning. Desert locust control.
- Purpose
-
Collect georeferenced locust sightings from anyone with a smartphone. Automatically check photos and remove unusable records so that FAO can direct survey and control teams.
- Dates
-
Date basis unassessed: 2021 (precision unassessed). Updated: 25 October 2026.
- Stage
-
Not assessed
- Version
-
SHA-256: 7a5092b62a33…
References
- Other identifiers
-
Not assessed
- Category mappings
-
Not assessed
- Brief
-
Not assessed
- Revisions
-
8 revisions. Latest: 25 October 2026.
Sources
-
News report Independent author
Nuwer R. As Locusts Swarmed East Africa, This Tech Helped Squash Them. The New York Times, 8 April 2021.
Since February 2020, the F.A.O. estimates that this effort in East Africa has averted the loss of agricultural products with a commercial value of $1.5 billion
-
Press release Developer
FAO. A high-tech response is helping countries win the battle against Desert Locusts. FAO feature story, 6 May 2021.
nearly 25 percent of the data is unusable or incorrect and FAO again turned to PlantVIllage to harness artificial intelligence to rapidly identify and remove the unwanted data.
-
Press release Developer
LaJeunesse S. Penn State responds: App aids UN efforts to control Africa's locust infestation. Penn State News, 21 February 2020.
a very basic version, eLocust3M, was rapidly developed by Penn State and released for use on mobile phones through Google Play Store on Feb. 20.
-
Press release Developer
FAO. FAO Desert Locust campaign: East Africa upsurge suppressed, Kenya free from Desert Locust. Interview with Cyril Ferrand and Carla Mucavi, FAO newsroom, 15 June 2022.