To understand the interactions among eutrophication, algal bloom, and POPs (persistent organic pollutants) in freshwater ecosystems, the cumulative selectivity of PAHs (polycyclic aromatic hydrocarbons) in phytoplankton, water, and sediment with different eutrophication level waters were identified in a typical plain river network region located in Nanjing City. Results showed that a total of 33 algal species belonging to 27 genera and 4 phyla were identified in 15 sites of urban water bodies, and most of them belonged to the type Cyanobacteria–Bacillariophyta. The eutrophication level of these rivers and lakes led to the sample site specificity of algal composition and abundance. The planktonic algae mainly accumulated the 2-ring and 3-ring PAHs, and the sediment mainly enriched the high-ring PAHs. However, the enrichment capacity of planktonic algae on PAHs was much higher than that of sediment. Cyanophyta and some species of Bacillariophyta and Chlorophyta in mesotrophic (βm) and meso-eutrophic water bodies (ßαm) preferentially accumulated lower-ring PAHs (naphthalene, acenaphthylene, and phenanthrene). Some other specific algae species, such as Euglenophyta, some species of Bacillariophyta, and most Chlorophyta in mesotrophic and moderate eutrophic water bodies, had strong capacities to enrich high-ring PAHs subsuming benzo[a]anthracene, chrysene, and anthracene. The eutrophication level of water bodies affected the cumulative selectivity of PAHs by shaping the site specificity of phytoplankton composition, which may be related to water quality, sediment characteristics, phytoplankton composition, and the algal cell walls.
Many studies have been concentrated on the distribution of algae in lakes, rivers, and seas, however, few studies have been concerned about their distribution and relation with polluted urban rivers. In this study, the spatio-temporal variation characteristics of water quality and algae community in Nanjing city were investigated with microscopic examination for one year. Results showed that the water pollution in this area was mainly related to high concentration of nitrogen (NH3-N and TN (Total nitrogen). There was a total of 77 species of algae in the studied rivers from June 2016 to May 2017, among which 73 species of planktic algae and 34 species of epipelic algae, in which the abundance and biomass of the latter were 1925 and 904 times that of the former, respectively. The two kinds of algae had different change tendencies which were related to seasons. For planktic algae, the abundance and biomass decreased in this season sequence: summer, spring, autumn, and winter. For epipelic algae, the abundance and biomass were relatively higher in winter. The dominant community of planktic algae was Chlorophyta-Bacillariophyceae-Cyanobacteria type, while that of epipelic algae was Bacillariophyceae—Cyanobacteria type. Most of the present algae were bi-trophic species, and were tightly related to the pollution characteristics of the rivers. The key environmental factors for planktic algae are T, TN, and TP, and those for Epipelic algae are N:P and TN. The relation between the community composition of planktic and epipelic algae and environmental parameters are highly complex, and it is worth carrying out further study to clarify their interaction mechanism.
Big data-driven technologies, especially machine learning and deep learning technologies, have been extensively employed in mineral prospectivity prediction. Several approaches have been proposed to learn the deep characteristics of geoscience data, enhance the accuracy of prediction and reduce uncertainty. Nevertheless, the approaches always contain the following two limitations. Firstly, the formation of mineral resources often involves the coupling of multiple factors on a certain spatio-temporal scale, resulting in rare labelled deposits and insufficient number of training samples. Secondly, training Deep Neural Network (DNN) is very challenging. Many approaches are subject to weak interpretability and lack of organic combination with geoscience knowledge. To address these two problems, we propose Geo-Rnet and GCAE (Geological Convolutional Autoencoder). Geo-Rnet is a multi-class mineral prospectivity prediction approach based on improved DNN. GCAE is able to effectively augment multi-disciplinary geoscience data by constructing upon an optimized Convolutional Autoencoder. The experimental results show that most of prospective areas predicted by Geo-Rnet overlap with the labelled mineralization locations, with an average accuracy of 91.1%. In addition, 89.98% of the ore deposits are located in the predicted areas. The results indicate the effectiveness of Geo-Rnet and GCAE for multi-class prediction of mineral resources. Finally, we classify the target area into several mineral prospectiviy areas according to their different mineral types. The research provides an innovative approach for mineral prospectivity prediction in the target area.INDEX TERMS Deep neural network, Geo-Rnet, multi-class, mineral prediction.
Precipitation images play an important role in meteorological forecasting and flood forecasting, but how to characterize precipitation images and conduct rainfall similarity analysis is challenging and meaningful work. This paper proposes a rainfall similarity research method based on deep learning by using precipitation images. The algorithm first extracts regional precipitation, precipitation distribution, and precipitation center of the precipitation images and defines the similarity measures, respectively. Additionally, an ensemble weighting method of Normalized Discounted Cumulative Gain-Improved Particle Swarm Optimization (NDCG-IPSO) is proposed to weigh and fuse the three extracted features as the similarity measure of the precipitation image. During the experiment on similarity search for daily precipitation images in the Jialing River basin, the NDCG@10 of the search results reached 0.964, surpassing other methods. This indicates that the method proposed in this paper can better characterize the spatiotemporal characteristics of the precipitation image, thereby discovering similar rainfall processes and providing new ideas for hydrological forecasting.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.