A step towards intelligent EBSD microscopy: machine-learning prediction of twin activity in MgAZ31.

Although microscopy is often treated as a quasi-static exercise for obtaining a snapshot of events and structure, it is clear that a more dynamic approach, involving real-time decision making for guiding the investigation process, may provide deeper insights, more efficiently. On the other hand, many applications of machine learning involve the interpretation of local circumstances from experience gained over many observations; that is, machine learning potentially provides an ideal solution for more efficient microscopy. This paper explores the potential for informing the microscope's observation strategy while characterising critical events. In particular, the identification of regions likely to experience twin activity (twin interaction with grain boundary) in AZ31 magnesium is attempted, from only local information. EBSD-based observations in the neighbourhoods of twin activity are fed into a machine-learning environment to inform the future search for such events, and the accuracy of the resultant decisions is quantified relative to the number of prior observations. The potential for utilising different types of local information, and their resultant value in the prediction process, is also assessed. After applying an attribute selection filter, and various other machine-learning tools, a decision-tree model is able to classify likely neighbourhoods of twin activity with 85% accuracy. The resultant framework provides the first step towards an intelligent microscopy for efficient observation of stochastic events during in situ microscopy campaigns. LAY DESCRIPTION: One role of artificial intelligence is to predict future events after learning from many previous observations. In materials science, various phenomena (such as crack nucleation) are difficult to predict because they have been insufficiently observed. Furthermore, observation is difficult, precisely because their location cannot be predicted, leading to a chicken and egg conundrum. This paper applies machine learning to the search for twin nucleation sites in a magnesium alloy, in an attempt to guide the observation of twin nucleation events in a microscope based on previous observations. As more data is obtained, the accuracy of the location prediction will increase. In the current case, the machine-learning tool achieved 85% accuracy for predicting the location of twin interactions with grain boundaries after several thousand observations. The resultant framework provides the first step towards an intelligent microscopy for efficient observation of stochastic events during in situ microscopy campaigns.

Integrative taxonomy resolves the cryptic and pseudo-cryptic Radula buccinifera complex (Porellales, Jungermanniopsida), including two reinstated and five new species.

Molecular data from three chloroplast markers resolve individuals attributable to Radula buccinifera in six lineages belonging to two subgenera, indicating the species is polyphyletic as currently circumscribed. All lineages are morphologically diagnosable, but one pair exhibits such morphological overlap that they can be considered cryptic. Molecular and morphological data justify the re-instatement of a broadly circumscribed ecologically variable R. strangulata, of R. mittenii, and the description of five new species. Two species Radula mittenii Steph. and R. notabilis sp. nov. are endemic to the Wet Tropics Bioregion of north-east Queensland, suggesting high diversity and high endemism might characterise the bryoflora of this relatively isolated wet-tropical region. Radula demissa sp. nov. is endemic to southern temperate Australasia, and like R. strangulata occurs on both sides of the Tasman Sea. Radula imposita sp. nov. is a twig and leaf epiphyte found in association with waterways in New South Wales and Queensland. Another species, R. pugioniformis sp. nov., has been confused with Radula buccinifera but was not included in the molecular phylogeny. Morphological data suggest it may belong to subg. Odontoradula. Radula buccinifera is endemic to Australia including Western Australia and Tasmania, and to date is known from south of the Clarence River on the north coast of New South Wales. Nested within R. buccinifera is a morphologically distinct plant from Norfolk Island described as R. anisotoma sp. nov. Radula australiana is resolved as monophyletic, sister to a species occurring in east coast Australian rainforests, and nesting among the R. buccinifera lineages with strong support. The molecular phylogeny suggests several long-distance dispersal events may have occurred. These include two east-west dispersal events from New Zealand to Tasmania and south-east Australia in R. strangulata, one east-west dispersal event from Tasmania to Western Australia in R. buccinifera, and at least one west-east dispersal from Australia to New Zealand in R. australiana. Another west-east dispersal event from Australia to Norfolk Island may have led to the budding speciation of R. anisotoma. In contrast, Radula demissa is phylogeographically subdivided into strongly supported clades either side of the Tasman Sea, suggesting long distance dispersal is infrequent in this species.