Search for: All records

The comprehensive properties of high-entropy alloys (HEAs) are highly-dependent on their phases. Although a large number of machine learning (ML) algorithms has been successfully applied to the phase prediction of HEAs, the accuracies among different ML algorithms based on the same dataset vary significantly. Therefore, selection of an efficient ML algorithm would significantly reduce the number and cost of the experiments. In this work, phase prediction of HEAs (PPH) is proposed by integrating criterion and machine learning recommendation method (MLRM). First, a meta-knowledge table based on characteristics of HEAs and performance of candidate algorithms is established, and meta-learning based on the meta-knowledge table is adopted to recommend an algorithm with desirable accuracy. Secondly, an MLRM based on improved meta-learning is engineered to recommend a more desirable algorithm for phase prediction. Finally, considering poor interpretability and generalization of single ML algorithms, a PPH combining the advantages of MLRM and criterion is proposed to improve the accuracy of phase prediction. The PPH is validated by 902 samples from 12 datasets, including 405 quinary HEAs, 359 senary HEAs, and 138 septenary HEAs. The experimental results shows that the PPH achieves performance than the traditional meta-learning method. The average prediction accuracy of PPH in all, quinary, senary, and septenary HEAs is 91.6%, 94.3%, 93.1%, and 95.8%, respectively. 

Ciliates are abundant microplankton that are widely distributed in the ocean. In this paper, the distribution patterns of ciliate diversity in the South China Sea (SCS) were analyzed by compiling community data from previous publications. Based on morphological identification, a total of 592 ciliate species have been recorded in the SCS. The ciliate communities in intertidal, neritic and oceanic water areas were compared in terms of taxonomy, motility and feeding habit composition, respectively. Significant community variation was revealed among the three areas, but the difference between the intertidal area and the other two areas was more significant than that between neritic and oceanic areas. The distributions of ciliates within each of the three areas were also analyzed. In the intertidal water, the community was not significantly different among sites but did differ among habitat types. In neritic and oceanic areas, the spatial variation of communities among different sites was clearly observed. Comparison of communities by taxonomic and ecological traits (motility and feeding habit) indicated that these traits similarly revealed the geographical pattern of ciliates on a large scale in the SCS, but to distinguish the community variation on a local scale, taxonomic traits has higher resolution than ecological traits. In addition, we assessed the relative influences of environmental and spatial factors on assembly of ciliate communities in the SCS and found that environmental selection is the major process structuring the taxonomic composition in intertidal water, while spatial processes played significant roles in influencing the taxonomic composition in neritic and oceanic water. Among ecological traits, environmental selection had the most important impact on distributions.