Plasmonic nanomaterials have outstanding optoelectronic properties potentially enabling the next generation of catalysts, sensors, lasers and photothermal devices. Owing to optical and electron techniques, modern nanoplasmonics research generates large datasets characterizing features across length scales. Furthermore, optimizing syntheses leading to specific nanostructures requires time-consuming multiparametric approaches. These complex datasets and trial-and-error practices make nanoplasmonics research ripe for the application of machine learning (ML) and advanced data processing methods. ML algorithms capture relationships between synthesis, structure and performance in a way that far exceeds conventional simulation and theory approaches, enabling effective performance optimization. For example, neural networks can tailor the nanostructure morphology to target desired properties, identify synthetic conditions and extract quantitative information from complex data. Here we discuss the nascent field of ML for nanoplasmonics, describe the opportunities and limitations of ML in nanoplasmonic research, and conclude that ML is potentially transformative, especially if the community curates and shares its big data.

Figure caption: Orange arrows indicate an experimental process, yellow arrows refer to the fitting of experimental data and blue arrows are for simulation or modelling processes. ML can be trained to map from any form of computerized input data to any form of computerized output data, and hence can be used to replace any of the blue or yellow arrows, or even to connect any pair data-bearing boxes, as seen in the ML link between manufacturing conditions and plasmon data. DDA, discrete dipole approximation; DLS, dynamic light scattering; EDS, energy dispersive X-ray spectroscopy; FEM, finite-element model; NNFM, non-negative matrix factorization; RI, refractive index.