BlackBox: 39N was founded to close the gap between how often coal ash embankments are inspected and how quickly they can fail. We believe the earliest warning signs of structural failure are already visible in the drone photogrammetry utilities capture — if every survey actually gets analyzed.
Full bio coming soon.
Our approach builds on a concept for image segmentation and tension-crack detection documented in peer-reviewed, publicly available research. BlackBox: 39N's models, training pipeline, and implementation are our own — purpose-built for this surface type, this crack morphology, and this failure mode.
Our product, Ortholens, takes its name from its two halves: ortho, for the orthomosaic processing that turns each drone survey into a measurable, georeferenced map; andlens, for the machine-learning analysis that finds a specific signature on it.
We are not building a general-purpose computer vision platform that tries to see everything at once. Each lens is trained for a single, well-defined signature on a client's own data. Our first is tension cracking in coal ash embankments; the same pipeline can be trained for others — erosion gullies, waste leakage, sinkholes — scoped with you in a consultation.
That focus is deliberate. It lets each lens go deep on a well-understood risk instead of shallow across many, and it keeps every output squarely in the hands of the engineers responsible for the facility.
A tool for engineers. Never a replacement for them.
We work directly with utility engineering teams, asset integrity groups, and the engineering firms supporting them — not procurement generalists. If there's a signature beyond tension cracking you need to track, ask about a consultation. Available under NDA before any imagery changes hands.