Search

Using the data from the 4 seasonal survey cruises in Beibu Gulf carried out from 1998-1999, this study analyzed the taxonomic composition, the spatial distribution of the abundance and diversity of phytoplankton as well as the relationship between the abundance and the nutrients such as dissolved inorganic nitrate (DIN), dissolved phosphate (IP) and silicate (Si) by using the methods of GIS interpolation and grid regression analysis model. 382 species of phytoplankton were identified in the study with most of them being diatoms. The abundances in all seasons showed the same spatial distribution with the dense areas focusing on the northern coastal waters of the gulf, while in the southern part and from the gulf mouth to the open sea, the abundances were quite lower. The results of the grid regression analyses on the abundance of phytoplankton with the nutrients showed that in autumn there existed a weak positive relationship with DIN (R2=0.270), while in summer and winter it showed the weak negative relationship with IP (R2=0.304 in summer and 0.327 in winter), and also in summer a medium positive relationship with the variation of Si was found (R2=0.478). The N:P ratio in most of the gulf ranged from 0-15 with the average of about 13.8, and the analysis showed that the impact by the N:P ratio on phytoplankton caused the variation of diversity rather than the abundance.

There is a growing perception that the research of fishery water quality forecasting are popular and important topic today, due to the food quality security and health impact caused by exposing to water pollutants existing in aquaculture. This paper aims to prove the feasibility of predicting the organic pollutant levels of pond water via SVM. The experimental data in weekly time series are collected from the fishery ponds in Xiao Tangshan in Beijing. The functional characteristics, including the network structure, the kernel function selection and the parameter sensitivity of SVM are investigated. The performance of the SVM model and the conventional BP neural network in predicting is also compared.