Search

Chlorophyll-a (Chl-a) accurate inversion in inland water is important for water environmental protection. In this study, we tested the Genetic Algorithm optimized Back Propagation (GA-BP) neural network model to precisely simulated the Chl-a in an inland lake using Landsat 8 OLI images. The result show that the R2 of GA-BP neural network model has increased 28.17% compared to traditional BP neural network model. Then this GA-BP model was applied to another two scenes of Landsat 8 OLI image with the R2 of 0.961, 0.954 respectively for March 26 2018, October 26 2018. And the spatial distribution have shown a reasonable result of Chl-a variation in Lake Donghu. This study can provide a new method for Chla concentration inversion in urban lakes and support water environment protection on a large scale.

Chlorophyll-a (Chl-a) estimation in inland waters is an essential environmental issue. This study aimed to identify a band ratio model for Chl-a simulation using Landsat 8 OLI data and in situ Chl-a measuring in Lake Donghu. The band B1and B2, respectively at the wavelength of 443 nm and 483 nm, in the band ratio model [B1/B2] performed best in Chl-a estimation with the R2 of 0.6215. K-means cluster analysis based on water quality indexes (Chl-a, pH, DO, TN, TP, COD, Turbidity) was conducted to further improve the accuracy of inversion model. The MAPE of the optimal [B1/B2] algorithm has decreased by 4.81% and 39.87% respectively for 17 December 2017 (R2=0.7669, N=42) and 26 March 2018 (R2=0.9156, N=45).

Abstract: This study focus on the design and development of a Geo-Web portal by embracing the capabilities within the context of Service Oriented Architecture (SOA) and Rich Internet Application (RIAs) to support data mashup and visualization. By leveraging the latest protocols of several open web service standards and two popular RIAs frameworks including the Microsoft Silverlight and the ESRI ArcGIS API for Silverlight, the web portal enables users to retrieve desired data from diverse online data repositories, and seamlessly integrate and visualize geospatial data and time series data in a unified environment. Moreover, the web portal provides an easy-to-use and geoanalytically web environment to deliver interactive, responsive and effective web application experiences for users to facilitate their scientific research activities. With the aim of mashing a variety of data together to support the study of water environmental assessment on the Lake Tahoe Basin located in USA, several investigations were implemented to demonstrate the feasibility and effectiveness of the web portal. [Copyright &y& Elsevier]

Abstract: This study presents the design and implement of a visual intelligent modeling system by combinational application of genetic algorithm, wavelet analysis, artificial neural network model components and visual modeling technology to support interactive and fast modeling of the complex, non-linear, and dynamic process. To overcome local optima problems of ANN, a hybrid intelligent genetic neural network algorithms (HIGANN) has been established by recombining the strength of back propagation (BP) in weight learning, wavelet analysis in data preprocess and GA''s capability of global searching the architecture space. Meanwhile, to tackle the problems of low modeling efficiencies and complex programming design using conventional modeling technologies, based on an open modeling interface standard, an visual modeling tool with the good expansibility is established to facilitate the linkage and combination of different optimization models in a single environment with visual feedback and real-time interaction. In order to verify the feasibility and validity of the prototype system, a case study of runoff forecasting for some watershed located on the Qinjiang river basin, central China was carried out by using BP, HIGANN model separately. The results show that the visual intelligent modeling system can greatly enhance the easy-to-use capabilities and flexibility of interactive modeling and appeal in offering a positive prospect of improving the efficiency and robustness of current practice in hydrological modeling. [Copyright &y& Elsevier]

• The dynamic of Lake TSI can be evaluated by Landsat 8 OLI derived FUI. • Sunshine is the main influencing factor for Lake Dianchi. • Temperature and wind are most relevant factor for Lake Donghu and Chaohu. • Pollution account for 10.5%–60.7% for eutrophication dynamics. Lakes eutrophication have been a complex and serious problem for China's Yangtze River Basin. A series of algorithms based on different remote sensing dataset have been proposed to simulate the lakes trophic state. However, these algorithms are often targeted at a particular lake and cannot be applied to a watershed management. In this study, a Forel-Ule index (FUI) method based on Landsat 8 OLI image is proposed to simulate trophic state index (TSI) in three typical urban lakes (Dianchi, Donghu, and Chaohu) from 2013 to 2018. The results show that the Landsat 8 derived FUI can well represent the lake TSI with an accuracy of R 2 = 0.6464 for the in situ experimental TSI dataset (N = 115) and R 2 = 0.8065 for the lake average TSI dataset (N = 315). In the study period 2013–2018, the order of the simulated TSI is Dianchi > Chaohu > Donghu. Seasonal dynamics show differences where the percentage of eutrophic area in summer is significantly lower than the other seasons for Lake Dianchi and Chaohu. However, the percentage of eutrophic area for Lake Donghu is highest in summer and lowest in winter. To further detect the driving factors of eutrophication in study lakes, the Pearson correlation and multiple linear regression analyses were conducted. The results show that sunshine and temperature are, respectively, the most and the second most significant factors for Lake Dianchi with explanations of 14.8% and 22.0%; temperature and pollution are the main influencing factors for Lake Donghu (39.2% and 10.9% explanation, respectively) and Chaohu (57.2% and 60.7% explanations, respectively). In addition, the wind is another negatively significant factor for Lake Chaohu with an explanation of 31.3%. Our results serve as an example for other lakes in the Yangtze River Basin and support the formulation of effective strategies to reduce seasonal eutrophication. [ABSTRACT FROM AUTHOR]

Harmful algal blooms (HABs) cause environmental problems worldwide. Continuous monitoring and forecasting of harmful algal blooms are necessary for marine resources managers to detect the intensity and spatial extent of HABs and provide early warnings to the public. In this study, we introduce an integrated web-based system for the monitoring and forecasting of coastal HABs. The system is named the Harmful Algal Blooms Monitoring and Forecasting System (HMFS). HMFS integrates in situ observations, a remote-sensing-based model, hydrodynamic and water quality model and Web-Based Geographic Information System (GIS) techniques into one environment. The in situ sensors and remote sensing model provide automatic and continuous monitoring of the coastal water conditions. The numerical models provide short-term prediction and early warning of HAB of up to 5 days. The overall forecast accuracy is more than or equal to 50% for the major coastal areas of Shenzhen in 2018. By leveraging a web-based GIS technique and Service-Oriented Architecture (SOA), the web portal of HMFS provides a graphic interface for users and mangers to view real-time in situ measurements and remote sensing maps, explore numerical model forecasts and get early warning information. HMFS was applied to Shenzhen, which is a rising megacity in Southern China. The application study demonstrated the applicability and effectiveness of HMFS for monitoring and predicting HABs. [ABSTRACT FROM AUTHOR]

Lakes are highly valuable natural resources for water supply, fishing, transportation and recreation. Specially, urban lakes are highly valued by local residents. However, due to near-lake development, lake ecosystems are being threatened by human intervention including nutrient pollution, increases in populations and intensification of land use. The ability to continuously monitoring and understanding water quality changes in lakes is important for sustaining lake ecosystems. This study developed a framework to monitor and analyze water quality variables based on long-term Landsant observations, including Landsat 5 TM, Landsat 7 ETM+ and Landsat 8 OLI. Lake Donghu, the largest urban lake in China, was selected as the study area. This lake is fully located within urban area of the Wuhan city and covers an area of 30.7 km2. It is a typical shallow lake with limited contamination purification capabilities. The framework employs a set of machine learning algorithms to establish relationships between the in-situ measurements obtained from the Lake Donghu and remote sensing bands reflectance. Then the relationships were used to model spatial distributions of water quality variables where in-situ measurements were unavailable. The machine learning algorithms employed include support vector machine, random forest, artificial neuron network and others. The modeled water quality variables include chlorophyll-a, turbidity and dissolved oxygen. The framework was used to estimate these water quality variables during the period from 1990-2016. It was found that the framework provides a reliable way to monitor and estimate water quality states and to detect possible water quality changes. [ABSTRACT FROM AUTHOR]