AI system
- System
-
BirdCast migration forecast model and Lights Out Action Alerts
- Model
-
Not assessed
- Release
-
Not assessed
- Application developer
-
Cornell Lab of Ornithology, Colorado State University (forecasts now produced with Purdue University and University of Illinois)
- Role
-
Not assessed
- Configuration
-
Not assessed
- Inputs and outputs
-
Not assessed
- Autonomy
-
Not assessed
- Workflow
-
Continental weather-radar archive to train the forecast. A local partner that translates forecasts into alerts. Municipal endorsement of lights-out practice.
- Human oversight
-
Not assessed
- Relation to AI
-
The learned forecast model identifies the nights on which alerts are issued. The proclamation and alert program are documented by the operating partner, not the model's makers. The collision-reduction evidence comes from a separate Chicago study co-authored by BirdCast scientists and is not specific to Houston. The counterfactual for Houston is unproven.
- AI contribution
-
The learned forecast model identifies the nights on which alerts are issued. The proclamation and alert program are documented by the operating partner, not the model's makers. The collision-reduction evidence comes from a separate Chicago study co-authored by BirdCast scientists and is not specific to Houston. The counterfactual for Houston is unproven.
Benefits
- Outcome identifiers
-
Not assessed
- Benefit
-
Houston Audubon issues Lights Out alerts from BirdCast forecasts; City of Houston proclaimed Lights Out Nights on 9 April 2021.
- Category
-
Improved Environmental Sustainability
- Status
-
Not assessed
- Beneficiary groups
-
People. 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
-
Not assessed
- Comparison
-
Not assessed
- Results
-
Not assessed
- 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: Cornell Lab of Ornithology, Colorado State University (forecasts now produced with Purdue University and University of Illinois). Operator: Houston Audubon (Birds Houston) and City of Houston.
- Jurisdictions
-
Benefit: Houston,
United States. Developer: United States. Operator: United States. - Ownership and control
-
Not assessed
- Dependencies
-
Not assessed
- Cross-border connections
-
Not assessed
- Geopolitical implications
-
Not assessed
Follow-up
- Conditions for replication
-
Forecast skill on peak nights. Building managers actually act on alerts. Monitoring to measure collisions before and after.
- Replication attempts
-
1 follow-up entries. Outcome unresolved: 1.
- Later findings
-
17 April 2022. Birds Houston's program timeline records Houston-area cities jointly asking businesses and residents to go Lights Out for birds in April 2022 and a statewide Lights Out gathering at Texas A&M University in August 2023.
- Availability
-
Not assessed
- Institutional decision
-
Not assessed
- Grounds
-
Not assessed
- Action and result
-
Not assessed
- Success criterion
-
Not assessed
Evidence
- Source numbers
-
AIBD-0103-source-0001–0004
- Citations
-
Numbered references below.
- Language
-
Not assessed
- Source relationships
-
Operator, 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
-
People. Organizations. Society.
- Depth
-
People: Not assessed. Organizations: 1. Society: Not assessed.
- Reasons
-
People: Residents and building managers receive timed alerts, but no individual outcome is documented. Organizations: A municipal proclamation and partner alert program were adopted; the partner page reports no measured change in collisions at Houston buildings. Society: The collision evidence is a Chicago study co-authored by BirdCast scientists; Houston's own collision change is unmeasured.
- Observed or intended
-
Not assessed
- Rubric
-
Not assessed
- Assessor and date
-
Not assessed
- Alternative assessments
-
Not assessed
- Fill
-
The deployer's account
Entry details
- Kind
-
Not assessed
- Related entries
-
Not assessed
- Field
-
Conservation and biodiversity. Migratory bird collision prevention / urban lighting policy.
- Purpose
-
Forecast nightly bird migration intensity from weather radar and weather models so that cities, building owners and residents can reduce lighting on high-migration nights.
- Dates
-
Date basis unassessed: 2021 (precision unassessed). Updated: 21 October 2026.
- Stage
-
Not assessed
- Version
-
SHA-256: 64721b437e1e…
References
- Other identifiers
-
Not assessed
- Category mappings
-
Not assessed
- Brief
-
Not assessed
- Revisions
-
5 revisions. Latest: 21 October 2026.
Sources
-
Peer-reviewed study Developer
Van Doren, B. M., Willard, D. E., Hennen, M., Horton, K. G., et al. (2021). Drivers of fatal bird collisions in an urban center. PNAS 118(24).
We estimate that halving lighted window area decreases collision counts by 11× in spring and 6× in fall.
-
Press release Deployer
Houston Audubon / Birds Houston (n.d.). Lights Out for Birds. birdshouston.org.
April 9, 2021: City of Houston proclaims 'Lights Out Nights' in Houston to help migrating birds traveling through the region
our staff were able to track migration predictions for the region and issue alerts to the community when a chance of high migration coincided with weather events
-
Press release Developer
BirdCast (n.d.). Migration forecast maps. birdcast.org.
By learning associations between weather variables and migration, we can use the model to predict a bird migration intensity given a particular weather forecast.