AI system
- System
-
MaxEnt ecological-niche model of desert locust breeding (Kimathi et al.)
- Model
-
The Maxent algorithm.
- Release
-
Maxent 3.4.1.
- Application developer
-
International Center of Insect Physiology and Ecology (icipe) with DLCO-EA, Kenya Plant Protection Services and FAO co-authors
- Role
-
The model estimated areas suitable for desert locust breeding.
- Configuration
-
Researchers used Maxent software version 3.4.1.
- Inputs and outputs
-
The model used occurrence and environmental data to estimate suitable habitat.
- Autonomy
-
Not assessed
- Workflow
-
FAO and Moroccan breeding-site time series 1985–2020. Bioclimatic covariates and NOAA CPC soil moisture data. A 70/30 cross-validation split.
- Human oversight
-
Not assessed
- Relation to AI
-
The paper itself labels MaxEnt a machine learning algorithm and reports cross-validated AUCs. Nothing in the cited source shows that a forecast changed a survey or control decision.
- AI contribution
-
The paper itself labels MaxEnt a machine learning algorithm and reports cross-validated AUCs. Nothing in the cited source shows that a forecast changed a survey or control decision.
Benefits
- Outcome identifiers
-
Not assessed
- Benefit
-
the Mauritania model had the highest mean AUC (0.887)
- Category
-
Improved Knowledge Discovery
- Status
-
Not assessed
- Beneficiary groups
-
Organizations. Society.
- Beneficiaries
-
Not assessed
- Reach
-
Not assessed
- 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
-
the Mauritania model had the highest mean AUC (0.887)
- Comparison
-
Not assessed
- Results
-
the Mauritania model had the highest mean AUC (0.887)
- Additional value from AI
-
Not assessed
- Limitations
-
Not assessed
- Denominators
-
Not assessed
- Materials for replication
-
Not assessed
Money
- Kind of value
-
Not assessed
- Amount
-
Not assessed
- Currency and prices
-
Not assessed
- Period and unit
-
Not assessed
- Realization
-
Not assessed
- Recipients and payers
-
Not assessed
- Gross or net
-
Not assessed
- Included costs
-
Not assessed
- Comparison
-
Not assessed
- Method
-
Not assessed
- Return and payback
-
Not assessed
People and places
- Participants
-
Developer: International Center of Insect Physiology and Ecology (icipe) with DLCO-EA, Kenya Plant Protection Services and FAO co-authors. Operator: None documented (research model).
- Jurisdictions
-
Developer:
Kenya. - Ownership and control
-
Not assessed
- Dependencies
-
Not assessed
- Cross-border connections
-
Not assessed
- Geopolitical implications
-
Not assessed
Follow-up
- Conditions for replication
-
Environmental drivers in the East African projection area comparable to the training countries.
- Replication attempts
-
Not assessed
- Later findings
-
No report of the breeding predictions being used in control operations or evaluated later was found.
- Availability
-
Not assessed
- Institutional decision
-
Not assessed
- Grounds
-
Not assessed
- Action and result
-
Not assessed
- Success criterion
-
Not assessed
Evidence
- Source numbers
-
AIBD-0194-source-0001
- Citations
-
Numbered references below.
- Language
-
Not assessed
- Source relationships
-
Developer
- 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
-
Organizations. Society.
- Depth
-
Not assessed
- Reasons
-
Organizations: No use of the predictions by FAO, DLCO-EA or national control centers is documented in the paper. Society: No field outcome is reported.
- Observed or intended
-
Not assessed
- Rubric
-
Not assessed
- Assessor and date
-
Not assessed
- Alternative assessments
-
Not assessed
- Fill
-
The makers' claim
Entry details
- Kind
-
Not assessed
- Related entries
-
Not assessed
- Field
-
Agriculture / pest forecasting. Desert locust early warning.
- Purpose
-
Predict regions suitable for desert locust breeding so that preventive control can be targeted before hoppers cause damage.
- Dates
-
Date basis unassessed: 2020 (precision unassessed). Updated: 21 October 2026.
- Stage
-
Not assessed
- Version
-
SHA-256: 33798993354e…
References
- Other identifiers
-
Not assessed
- Category mappings
-
Not assessed
- Brief
-
Not assessed
- Revisions
-
4 revisions. Latest: 21 October 2026.
Sources
-
Peer-reviewed study Developer
Kimathi E, Tonnang HEZ, Subramanian S, Cressman K, Abdel-Rahman EM, Tesfayohannes M, Niassy S, Torto B, Dubois T, Tanga CM, Kassie M, Ekesi S, Mwangi D, Kelemu S. Prediction of breeding regions for the desert locust Schistocerca gregaria in East Africa. Scientific Reports 10:11937 (2020). doi:10.1038/s41598-020-68895-2
The model generated from Mauritania had the highest mean AUC value (0.887), followed by the models from Saudi Arabia (0.884), and Morocco (0.820).