In his catalogue of British Museum Crustacea, Adam White listed two swimming crabs from Borneo as a new species, Amphitrite argentata, but he did not provide a description and therefore the name was a nomen nudum. Later, Alphonse Milne-Edwards described the larger of these male specimens as Neptunus argentatus and credited the species to White. Now assigned to Monomia Gistel, 1848, M. argentata was recently considered to represent a species-complex; however, its nomenclature and taxonomy have been confused over a long period of time. Furthermore, the larger syntype examined by Alphonse Milne-Edwards is no longer extant. The present study compared the smaller extant M. argentata male of White, here designated as the lectotype, with the description by A. Milne-Edwards. This dried specimen was re-examined using X-ray and computed tomography scanning techniques in order to reveal the general morphology of the first male gonopod (G1). Fresh material was collected and identified with confidence as M. argentata. This species was redescribed to modern standards including illustrations, details of coloration and new scanning electron micrographs of the G1 were provided. The validity of this species was further endorsed by comparing DNA sequences with congeners from the South China Sea. To conclude, the type status, authority and associated species-complex of M. argentata are discussed.

Here we describe a new species of Xiphonectes A. Milne-Edwards, 1873 (Brachyura: Portunidae) from southern Madagascar. Xiphonectes aculeatus sp. nov. is morphologically most similar to X. latibrachium (Rathbun, 1906) from Hawaii, and X. paralatibrachium Crosnier, 2002, from the Marquesas Islands, French Polynesia. All three species have a carapace with six anterolateral teeth, a long spine on the inner dorsal margin of the cheliped carpus, and a produced, flattened, anterior region on the third maxilliped merus. Among these species, Xiphonectes aculeatus sp. nov. is easily distinguished by the acutely produced posterodistal angle on the meri of its swimming legs, dorsal and marginal structures on its carapace, and most notably, the shape of its frontal teeth.

Collections of benthic organisms were obtained during previous Soviet research cruises in the Mediterranean Sea, 1974Sea, -1980. Material was collected by bottom grabs or trawls from the depths of 20-500m. Collecting stations were allocated in the Aegean, Adriatic, Tyrrhenian, Balearic, Alboran, and Ionian Seas, and between Sicily and Tunisia. Among decapod crustaceans collected, 8 species of portunid crabs were present, i.e., Liocarcinus. corrugatus

A new species of West African freshwater crab of the genus Potamonautes is described from specimens collected in Senegal. The crabs were collected from burrows in the banks of small streams as well as from the nearby Gambia River in Niokolo Koba National Park. This new species is distinguished from Senegalese congeners by a combination of characters of the carapace, chelipeds, thoracic sternum, and gonopods. The new species is compared to other freshwater crabs from the family Potamonautidae found in West Africa. RÉSUMÉ Une nouvelle espèce de crabe d'eau douce ouest africain du genre Potamonautes est décrite à partir de spécimens récoltés au Sénégal. Ces crabes furent récoltés dans des terriers dans des bancs de petits ruisseaux aussi bien que dans la proche Gambia River dans le Parc National du Niokolo Koba. La nouvelle espèce se distingue de ses congénères sénégalais par un ensemble de caractères de la carapace, les pinces, le sternum thoracique et les gonopodes. La nouvelle espèce est comparée à d'autres crabes d'eau douce de la famille des Potamonautidae trouvés en Afrique de l'Ouest.

Earthquake prediction, which is a key issue that has long existed among seismologists, is of high scientific importance. An earthquake prediction model can output the time of earthquake occurrence in advance using machine learning methods, which is receiving increasing attention. Earthquake prediction involves a large variety of data mining steps, which requires a large amount of time for processing data and model development. Thus, an efficient and accurate prediction method is needed. Aiming to solve this problem, we propose Auto-REP, an automated machine learning-based regression model. Our contribution of Auto-REP is using laboratory seismic data to develop a regression pipeline in an automated manner, and eventually obtain the prediction results of laboratory earthquake occurrence. The automated pipeline consists of feature extraction, feature selection, modelling algorithm and optimization. With this approach we extract features from each of the earthquake channels which results in a massive feature space. The hyperparameters of the model are optimized by a Bayesian technique as part of the automated approach. The experimental results shows that the MAE and MSE of our model in the training and testing datasets are 1.48, 1.51 and 1.52, 1.59. The results demonstrate that our Auto-REP method can predict laboratory earthquakes efficiently and accurately.