SynerWood

Picture the power of computer vision flowing through your smartphone’s camera. Snap a photo of any piece of timber—a reclaimed joist, an exotic hardwood off-cut, a storm-felled log—and, in seconds, receive a predictive mechanical profile, ready for finite-element analysis. This is the spirit of SynerWood: turning overlooked or deconstructed wood into tomorrow's prime structural resource and closing the loop on a truly circular and renewable economy.

In practical terms, the technology relies on deep learning algorithms trained on a large database linking the visual features of wood to its mechanical performance, as measured in the laboratory. SynerWood is positioned as an intermediate solution: it offers far superior objectivity and accuracy than traditional visual inspection, without the cost and complexity of industrial scanners. It is a decision-support tool designed for sawmills, engineering firms, and construction sites.

My master's thesis has validated the proof-of-concept for this approach. I am now looking to scale this project, convinced of its economic potential. Optimizing timber grading can significantly reduce material waste (estimated at up to 40%) and improve the profitability of the sector. I am currently seeking funding to continue this development, either as part of a PhD or through the creation of a startup.