Diatom identification including life cycle stages through morphological and texture descriptors

A lightweight convolutional neural network (CNN) model for diatom classification: DiatomNet

Diatoms are a type of algae with many species. Accurate and quick classification of diatom species is important in many fields, such as water quality analysis and weather change forecasting. Traditional methods for diatom classification, specifically morphological taxonomy and molecular detection, are time-consuming and may not provide satisfactory performance. However, in recent years, deep learning has demonstrated impressive performance in this task, just like other image classification problems. On the other hand, networks with more layers do not guarantee increased accuracy. While increasing depth can be useful in capturing complex features and patterns, it also introduces challenges such as vanishing gradients, overfitting, and optimization challenges. Therefore, in our work, we propose DiatomNet, a lightweight convolutional neural network (CNN) model that can classify diatom species accurately while requiring low computing resources. A recently introduced dataset consisting of 3,027 diatom images and 68 diatom species is used to train and evaluate the model. The model is compared with well-known and successful CNN models (i.e., AlexNet, GoogleNet, Inceptionv3, ResNet18, VGG16, and Xception) and their customized versions obtained with transfer learning. The comparison is based on several success metrics: accuracy, precision, recall, F-measure, number of learnable parameters, training, and prediction time. Eventually, the experimental results reveal that DiatomNet outperforms the other models regarding all metrics with just a few exceptions. Therefore, it is a lightweight but strong candidate for diatom classification tasks.

Microscopic image recognition of diatoms based on deep learning

Diatoms are a crucial component in the study of aquatic ecosystems and ancient environmental records. However, traditional methods for identifying diatoms, such as morphological taxonomy and molecular detection, are costly, are time consuming, and have limitations. To address these issues, we developed an extensive collection of diatom images, consisting of 7983 images from 160 genera and 1042 species, which we expanded to 49,843 through preprocessing, segmentation, and data augmentation. Our study compared the performance of different algorithms, including backbones, batch sizes, dynamic data augmentation, and static data augmentation on experimental results. We determined that the ResNet152 network outperformed other networks, producing the most accurate results with top-1 and top-5 accuracies of 85.97% and 95.26%, respectively, in identifying 1042 diatom species. Additionally, we propose a method that combines model prediction and cosine similarity to enhance the model's performance in low-probability predictions, achieving an 86.07% accuracy rate in diatom identification. Our research contributes significantly to the recognition and classification of diatom images and has potential applications in water quality assessment, ecological monitoring, and detecting changes in aquatic biodiversity.

Machine Learning and Deep Learning Based Computational Approaches in Automatic Microorganisms Image Recognition: Methodologies, Challenges, and Developments

Microorganisms or microbes comprise majority of the diversity on earth and are extremely important to human life. They are also integral to processes in the ecosystem. The process of their recognition is highly tedious, but very much essential in microbiology to carry out different experimentation. To overcome certain challenges, machine learning techniques assist microbiologists in automating the entire process. This paper presents a systematic review of research done using machine learning (ML) and deep leaning techniques in image recognition of different microorganisms. This review investigates certain research questions to analyze the studies concerning image pre-processing, feature extraction, classification techniques, evaluation measures, methodological limitations and technical development over a period of time. In addition to this, this paper also addresses the certain challenges faced by researchers in this field. Total of 100 research publications in the chronological order of their appearance have been considered for the time period 1995-2021. This review will be extremely beneficial to the researchers due to the detailed analysis of different methodologies and comprehensive overview of effectiveness of different ML techniques being applied in microorganism image recognition field.

Geometric morphometric analysis of spore shapes improves identification of fungi

Morphology of organisms is an essential source of evidence for taxonomic decisions and understanding of ecology and evolutionary history. The geometric structure (i.e., numeric description of shape) provides richer and mathematically different information about an organism's morphology than linear measurements. A little is known on how these two sources of morphological information (shape vs. size) contribute to the identification of organisms when implied simultaneously. This study hypothesized that combining geometric information on the outline with linear measurements results in better species identification than either evidence alone can provide. As a test system for our research, we used the microscopic spores of fungi from the genus Subulicystidium (Agaricomycetes, Basidiomycota). We analyzed 2D spore shape data via elliptic Fourier and principal component analyses. Using flexible discriminant analysis, we achieved the highest species identification success rate for a combination of shape and size descriptors (64.7%). The shape descriptors alone predicted species slightly better than size descriptors (61.5% vs. 59.1%). We conclude that adding geometric information on the outline to linear measurements improves the identification of the organisms. Despite the high relevance of spore traits for the taxonomy of fungi, they were previously rarely analyzed with the tools of geometric morphometrics. Therefore, we supplement our study with an open access protocol for digitizing and summarizing fungal spores' shape and size information. We propagate a broader use of geometric morphometric analysis for microscopic propagules of fungi and other organisms.

Nonsubsampled contourlet transform based tone-mapping operator to optimize the dynamic range of diatom shells

The diatoms have intricate silica-based cell walls with multi-scale patterns. High dynamic range (HDR) imaging is widely used to examine the three-dimensional structure of diatoms for recovering the wide range of contrast and brightness. In order to construct a HDR image of a diatom, multiple images of the specimen are taken at different exposure settings with bright or dark field microscopy. In the proposed method, multi-scale decomposition based on nonsubsampled contourlet transform is adopted to separate the structured and detailed information of the HDR image. And then, by processing all layers independently, the tone-mapped image is reconstructed to retain details present in the dark and light regions. Quantitative and qualitative analysis is performed in order to assess the performance of the proposed and seven existing tone-mapping operators. In analysis, the study indicates that the proposed method enhances the diatom frustules to extract more details.

Diatoms recovery from wastewater: Overview from an ecological and economic perspective

Alarming water pollution is toxic to the aquatic ecosystem leading to a sharp decline in species diversity. Diatoms have great potency to survive in contaminated water bodies, hence they can be compelling bioindicators to monitor the change in the environmental matrices effectively. Around the globe, researchers are intended to evaluate the impact of pollution on the diatoms recovery and techniques used for the assessment. The diatoms are precious for futuristic need viz. value-added products, energy generation, pharmaceuticals, and aquaculture feedstocks. All these applications led to a significant rise in diatoms research among the scientific community. This review presents different isolation practices, cultivation, and other challenges associated with the diatoms. A precise focus is given to diatoms isolation techniques from highly polluted water bodies with the main thrust towards obtaining an axenic culture to elucidate the significance of pure diatom cultures. Recovery of "jewels of the sea" from polluted water signifies the prospective ecological and economic aspects.

Biosynthesis of silver nanoparticles from marine diatoms Chaetoceros sp., Skeletonema sp., Thalassiosira sp., and their antibacterial study

•

Marine Diatoms have been envisaged for AgNP synthesis.

•

The average size of AgNP ranges from 150 to 350 nm.

•

Diatom based AgNP exhibits excellent biocidal activity.

•

These AgNP showed inhibition against both Gram-positive and Gram negative bacteria.

Diatoms are a reservoir of metabolites with diverse applications and silver nanoparticle (AgNP) from diatoms holds immense therapeutic potentials against pathogenic microbes owing to their silica frustules. In the present study, Chaetoceros sp., Skeletonema sp., and Thalassiosira sp were used for synthesis of AgNP. The average particle size of AgNP synthesized was 149.03 ± 3.0 nm, 186.73 ± 4.9 nm, and 239.46 ± 44.3 nm as reported in DLS whereas 148.3 ± 46.8 nm, 238.0 ± 60.9 nm, and 359.8 ± 92.33 nm in SEM respectively. EDX analysis strongly indicates the confirmation of AgNP displaying a sharp peak of Ag⁺ ions within the spectra. High negative zeta potential values indicate a substantial degree of stabilization even after three months. The antibacterial efficacy of biosynthesized AgNP tested against Aeromonas sp., Escherichia coli, Bacillus subtilis, Staphylococcus aureus, and Streptococcus pneumonia exhibits broad-spectrum antibacterial activity. This study encourages the synthesis of diatom based AgNP for a variety of applications owing least toxicity and biodegradable nature.

An Integrated Approach of Multi-Community Monitoring and Assessment of Aquatic Ecosystems to Support Sustainable Development

Aquatic ecosystems are one of the most threatened ecosystems in the world resulting in the decline of aquatic biodiversity. Monitoring and the assessment of aquatic ecosystems are necessary to protect and conserve these ecosystems as monitoring provides insights into the changes in the aquatic ecosystem over a long period of time and assessment indicates the status of these ecosystems. This paper presents an overview of different methods for the hydromorphological, physical–chemical and the biological monitoring and assessment of surface waters. Furthermore, recently developed monitoring and assessment methods are discussed to support sustainable water management and contribute to the implementation of the Sustainable Development Goals 6 (SDG6 related to clean water and sanitation) and 15 (SDG15 related to terrestrial and freshwater systems) of the United Nations. However, many other SDGs are dependent on freshwater, such as food (e.g., SDG2) and climate-related SDGs. We presented an innovative concept for integrated monitoring and assessment. The main new elements are the monitoring of all communities and the use of integrated socio-environmental models to link these communities to ecosystem interactions and functions as a basis for determining their relation to the SDGs. Models can also allow to determine the effects of changes in SDGs on the different elements of the concept, and serve in this manner as tools for the selection of an optimal balance between the SDGs in the context of sustainable development.