The rationale and applications of Meta-Sorter. (IMAGE)
Caption
The rationale and applications of Meta-Sorter. a, The process of model construction and transfer learning of Meta-Sorter. Two input files, biome ontology and samples' taxonomic structures with detailed biome information, are required in model construction and transfer learning. The yellow box shows that the neural network model was constructed based on 118,592 existing samples with detailed information on 134 biomes and their biome ontology. The blue box shows that the transfer neural network model was constructed using 34,209 newly introduced samples from 35 biomes (including 3083 samples from eight newly introduced biomes) and transfer learning to the existing neural network model. b–d, The applications of Meta-Sorter. Meta-Sorter decoded the samples' biome labels annotated as “Mixed biome” into detailed biome labels (b). Meta-sorter refined the biome labels in more detail to obtain more valuable information for reference (c). Meta-Sorter corrected the mis-annotated samples' labels to avoid cascading accumulation (d).
Credit
Environmental Science and Ecotechnology
Usage Restrictions
Credit must be given to the creator. Only noncommercial uses of the work are permitted. No derivatives or adaptations of the work are permitted.
License
CC BY-NC-ND