Wildlife Hazard ManagementPredictive AnalyticsOperational SafetyResearch & Methodology

From Data to Foresight

Turning BASH Records into Predictive Safety

CDR Edilson “Eddie” DaSilva

CDR Edilson “Eddie” DaSilva

Avigilance Advisor

September 27, 20263 min read
Share
Military training jet on approach at dusk with birds crossing the flight path

I have been involved in many bird strike investigations, and in every one, I have seen a pattern:

an experienced crew, a routine mission, and an impact that should not have happened. Many of

these investigations resulted in valuable lessons being overlooked. The aircraft is retrieved, and a

report is filed. However, the data collected is often forgotten, buried in rarely visited databases.

This is the paradox of BASH data (Bird/Wildlife Aircraft Strike Hazard). We have been keeping

strike data for years, but seldom do we fully capitalize on it. The data exists, but we’re not using it to

its maximum capacity. That underuse is usually the result of several constraints, including limited

access to data, lack of training on how to assess and use the information, and lack of standardized

reporting formats. The result is that key insights are locked up and not easily shared across

enterprises. This year’s U.S. Aviation Wildlife Management Conference in Cleveland, Ohio,

highlighted this shortfall. Wildlife strikes remain a significant concern to flight safety.

In military flight training, strikes have even more serious consequences. Low altitude flights,

high mission frequency, and predictable flight paths create training base exposure to wildlife. When

a strike means a change of route or delays in training and operational readiness, the cost is more

than just financial. Thus, AI-powered forecasting increases the value of data for addressing these

risks. One Air Force training base last year, for example, used an AI-powered system that ingested

past strike data, seasonal bird migratory patterns, and live radar feeds to predict an elevated risk of

bird activity near a main flight corridor. In response, the base temporarily modified takeoff times and

flight paths, leading to a dramatic drop in bird strike incidents during the high-risk period. Artificial

intelligence is not meant to replace the wildlife professional but rather to augment that individual’s

experience with predictive intelligence.

That’s the idea behind Avigilance FeatherWatch. The system translates wildlife strike data into

easy-to-understand risk insights, helping BASH teams spot problems early and take preventative

action. All these solutions come together today. Avian radars track near-misses, drones monitor

species and their movements, and local experts supplement the program with insights raw data alone

cannot deliver. We must use these tools and act quickly on what we learn.

That is a common challenge. Absence of standard data fields for global BASH reporting limits

risk prediction. But small steps toward standardization can be meaningful. One early step

organizations could take is to standardize a small set of key data fields, such as date, location, species,

altitude and phase of flight, across all reports. Sharing best practices for reporting formats among

bases and agencies would also make the data more consistent and useful. But the first step is not to

build a new system but to appreciate the value of the data we already have. The future of wildlife

collision prevention will be evidence-based, predictive, and collaborative. Now it's time to think of

our databases as valuable sources of information.De

References

Altringer, L., Begier, M. J., Washburn, J. E. & Shwiff, S. A. (2024). Estimating the impact of airport

wildlife hazards management on realized wildlife strike risk. Scientific Reports 14.

https://doi.org/10.1038/s41598-024-79946-3

Yiu, C. Y., Li, W.-C., Ng, K. K. H., Chi, C.-F. & Schiefele, J. (2026). Enhancing aviation safety with artificial intelligence: A systematic literature review on recent advances, challenges and future perspectives. Advanced Engineering Informatics 71(B), 104378. https://doi.org/10.1016/j.aei.2026.104378

Washburn, B. E., Maher, D., Beckerman, S. F., Majumdar, S., Pullins, C. K. & Guerrant, T. L. (2022).

Monitoring Raptor Movements with Satellite Telemetry and Avian Radar Systems: An Evaluation for

Synchronicity. Remote Sensing 14(11). https://doi.org/10.3390/rs14112658

(n.d.). Aviation Safety Reporting System (ASRS) - About ASRS Data. ASRS - About ASRS Data.

https://asrs.arc.nasa.gov/search/dbol/aboutdata.html

CDR Edilson “Eddie” DaSilva

About the Author

CDR Edilson “Eddie” DaSilva

Avigilance Advisor

Commander Edilson "Eddie" DaSilva, MSc, is a Brazilian Navy helicopter pilot and air safety investigator with over 20 years of operational aviation experience. He brings 12+ years in accident investigation, now supporting CENIPA, and 8+ years in SMS, safety auditing and operational risk analysis. As an Avigilance advisor, Eddie ensures predictive risk intelligence supports sound operational judgement, effective risk controls and disciplined safety decision-making.

Connect on LinkedIn →

Enjoyed this article?

Share