To better understand the seasonal variation characteristics and trend of water quality in Lake Yilong, we monitored water quality parameters and measured nutrients, including the water temperature (WT), Chlorophyll-a (Chl-a), dissolved oxygen (DO) and pH from September 2016 to May 2020, total nitrogen (TN) and total phosphorus (TP) from October 2016 to August 2018. The results showed that the lake water was well mixed, resulting in no significant thermal stratification. The DO content was decreased in the northwest part of the lake during September and October, resulting in a hypoxic condition. It also varied at different locations of the lake and showed a high heterogeneity and seasonal variability. The Chl-a concentration in Lake Yilong demonstrated seasonal and spatial changes. It was maximum at the center and southwest area of the lake in January. However, in the northwest part of the lake, the maximum value appeared in September and October. The content of TN in the rainy season increased by 75% compared with that in dry season and TP content show a downward trend (from 0.11 mg/L to 0.05 mg/L). The comprehensive nutrition index evaluation shows that the water quality of Lake Yilong in 2016 was middle eutrophic (TLI = 60.56), and that in 2017 (TLI = 56.05) and 2018 (TLI = 56.38) was weak eutrophic, showing that the nutritional status has improved. TN remained at a high level (2.15 ± 0.48 mg/L), water quality needs further improvement. Based on our monitoring and analysis, it is recommended that human activities in the watershed of the lake should be constrained and managed carefully to maintain the water quality of the lake and adopt effective water quality protection and ecological restoration strategies and measures to promote continuous improvement of water quality, for a sustainable social development.

Abstract. Existing key-word based image search engines return images whose title or immediate surrounding text contains the search term as a keyword. When the search term is ambiguous and means different things, the results often come in a mixed bag of different entities. This paper proposes a novel framework that understands the context and thus infers the most likely entity in the given image by disambiguating the terms in the context into the corresponding concepts from external knowledge in a process called conceptualization. The images can subsequently be clustered by the most likely associated entities. This approach outperforms the best competing image clustering techniques by 29.2% in NMI score. In addition, the framework automatically annotates each cluster of images by its key entities which allows users to quickly identify the images they want.

Clustering of images from search results can improve the user experience of image search. Most of the existing systems use both visual features and surrounding texts as signals for clustering while this paper demonstrates the use of an external knowledge base to make better sense out of the text signals in a prototype system called CISC. Once we understand the semantics of the text better, the result of the clustering is significantly improved. In addition to clustering the images by their semantic entities, our system can also conceptualize each image cluster into a set of concepts to represent the meaning of the cluster.