Development of Analysis Technique of Lake and Marshes Due to Image Processing of Satellite Data Under the Knowlege Base and Fuzzy Statisitics

本文介绍了利用模糊回归模型对卫星数据进行水质分析的结果。进行了实例分析，并将模糊回归模型的结果与传统统计模型的相关系数进行了比较。为了绘制水质可能性分布图，提出了一种新的模糊水平切片方法，通过统计分析表明，遥感数据的CCT计数与水质无关。然而，模糊回归分析表明，CCT计数与水质的多个参数有关。考察模糊回归分析中目标函数间的极差对水质数据异常点的选取有一定的影响。从而明确了模糊回归模型在水质分析中的适用性。此外，在模糊统计过程中引入水质调查专家的知识，用模糊水平片法绘制了水质评价图。结果表明，估算图与实际水质数据的预测范围相吻合。此外，估算图上的污染等级分布与水质专家的知识也是一致的。此外，模糊水平条分法还可以将水质分为十级。因此，模糊水平条分法是绘制水质评价图的一种有效方法。本文用有限元方法建立了风引起的水流分析算法。结果表明，流量时间序列预测结果与水质估计图基本一致。

This report presents the results of using the fuzzy regression model to analyze the water quality from the satellite data. A case study has been conducted and the results of the fuzzy regression model have been compared with the correlation coefficient of the conventional statistical model. To draw the possibility distribution map of the water quality, a new method with the fuzzy level-slice is developed in this research.It is shown by statistical analysis that the CCT count number of the remote sensing data has no relation to the water quality. However, the fuzzy regressin analysis shows that the CCT count number is related to several parameters about the water quality. It has also been observed that an investigation of the extreme variation among the objective function of fuzzy regressin analysis has an effect on the selection of the irregular point of the water quality data. Therefore, it has been clarified that the fuzzy regression model is applicable to the analysis of the water quality. In additon, it is pssible to introduce the knowlegement of an expert in the investigation about water quality into the fuzzy statistical process.The estimation map of the water quality has been drown by using the fuzzy level-slice method. It is shown that the estimation map corresponds with the forecasted range from the actual data of water quality. It is also becomes clear that the distribution of the pollution level on the estimation map corresponds with the knowlege of the expert of the water quality. In additon, fuzzy level-slice method is possible to classify the water quality by ten level. Therefore, it can be concluded that the fuzzy level-slice method is useful technique for drawing the estimation map of the water quality. An analysis algorithm for the water flow due to a wind has been eeveloped by the finite element method. It has clarified that the time series forecasting results about the water flow corresponded with the estimation map of the water quality.