Diatoms, a kind of algae microorganisms with several species, are quite useful for water quality determination, one of the hottest topics in applied biology nowadays. At the same time, deep learning and convolutional neural networks (CNN) are becoming an extensively used technique for image classification in a variety of problems. This paper approaches diatom classification with this technique, in order to demonstrate whether it is suitable for solving the classification problem. An extensive dataset was specifically collected (80 types, 100 samples/type) for this study. The dataset covers different illumination conditions and it was computationally augmented to more than 160,000 samples. After that, CNNs were applied over datasets pre-processed with different image processing techniques. An overall accuracy of 99% is obtained for the 80-class problem and different kinds of images (brightfield, normalized). Results were compared to previous presented classification techniques with different number of samples. As far as the authors know, this is the first time that CNNs are applied to diatom classification.

This paper deals with automatic taxa identification based on machine learning methods. The aim is therefore to automatically classify diatoms, in terms of pattern recognition terminology. Diatoms are a kind of algae microorganism with high biodiversity at the species level, which are useful for water quality assessment. The most relevant features for diatom description and classification have been selected using an extensive dataset of 80 taxa with a minimum of 100 samples/taxon augmented to 300 samples/taxon. In addition to published morphological, statistical and textural descriptors, a new textural descriptor, Local Binary Patterns (LBP), to characterize the diatom’s valves, and a log Gabor implementation not tested before for this purpose are introduced in this paper. Results show an overall accuracy of 98.11% using bagging decision trees and combinations of descriptors. Finally, some phycological features of diatoms that are still difficult to integrate in computer systems are discussed for future work.

Benthic diatoms have traditionally been used as bioindicators of aquatic ecosystems. Because diatom-based monitoring of water quality is required by European legislation, molecular-based methods had emerged as useful alternatives to classical methods based on morphological identification using light microscopy. The aim of this study was to test the reliability of DNA metabarcoding combined with High-Throughput Sequencing (HTS) techniques in the bioassessment of the trophic status of 22 Mediterranean shallow ponds in NW Spain. For each pond, the Trophic Diatom Index (TDI) was calculated from inventories obtained by identification using light microscopy (LM) followed by high-throughput sequencing (HTS) at the molecular level. Ponds were subsequently classified into five water quality classes. The results showed a good correspondence between both methods, especially after applying a correction factor that depended on the biovolume of the cells. This correspondence led to the assignment to the same quality class in 59% of the ponds. The determination and quantification of valves or DNA sequences was one of the main pitfalls, which mainly included those related to the variability in the relative abundances of some species. Accordingly, ponds with similar relative abundances for the dominant species were assigned to the same quality class. Moreover, other difficulties leading the discrepancies were the misidentification of some species due to the presence of semi-cryptic taxa, the incompleteness of the reference database and the bioinformatic protocol. Thus, the validation of DNA-based methods for the identification of freshwater diatoms represents an important goal, as an alternative to using traditional methods in Mediterranean shallow ponds.