The illegal timber trade is the most profitable natural resource crime, valued at 50-152 billion USD per year. Up to 90% of tropical timber may be illegally sourced, with significant negative consequences for producer countries, including unsustainable deforestation, biodiversity loss, loss of long-term income for forest-based communities and major loss of revenue for governments. To tackle this global challenge, accurate, cost-effective, and high-throughput tools are needed to identify the species and origin of processed timber to ensure compliance with timber export and import laws. In this proposal we will combine two of the most powerful timber species identification techniques, namely XyloTron and Direct Analysis in Real Time – Time Of Flight Mass Spectrometry (DART-TOFMS, metabolomic profiling) to improve timber identification accuracy. The XyloTron is a hand-held device that captures images from the transverse anatomical wood surface, stores them in a database, and the adjoining software performs a classification algorithm to allow species identification. With DART-TOFMS, wood slivers are placed in a heated helium gas stream, resulting in thermal desorption and ionization of the molecules. The result is a fingerprint based on low molecular weight molecules (< 1000 Daltons (atomic mass units), predominantly metabolites), which is then the basis for the species identification. Both techniques are available at the Royal Botanic Gardens, Kew under the current World Forest ID Programme (https://worldforestid.org/). The applicant will (1) assist the World Forest ID staff at Kew in analysing these samples and (2) be responsible for developing a deep learning model at Brunel University, combining the data of XyloTron and DART-TOFMS for improved timber identification accuracy.