No abstract

The mid-lower reaches of the Hanjiang River Basin, located in the core of economic development in Hubei Province, is an integral part of the Yangtze River Economic Belt. In recent years, the watershed ecosystem has become more sensitive to climate changes and human activities, thus affecting the regional vegetation cover. To maintain a stable watershed ecosystem, it is critical to analyze and evaluate the vegetation change and its response to temperature, precipitation, and human activities in this region. This study, based on the trend analysis, partial correlation analysis, and residual analysis, evaluated the change characteristics of vegetation cover as well as the corresponding driving factors in the basin from 2001 to 2015. The results showed that (1) the overall spatial pattern of vegetation cover in the study area was “high in the west and north, lower on both sides of Hanjiang River, and lowest in the center and southeast,” and the pattern changed parabolically with the increasing elevation. (2) Over the 15 years, vegetation cover in the basin showed an increasing trend, and the increased and decreased areas were 90.72 and 9.23%, respectively. (3) The response of vegetation cover to climatic factors varies greatly depending on the increasing elevation. That is, the lag effect under the impact of temperature disappeared gradually, while it became more evident under the impact of precipitation. (4) On the whole, human activities had a positive effect on the regional vegetation cover. The negative effect in the areas around the Nanyang Basin and the positive effect in most parts of the Jianghan Plain were gradually decreased.

Abstract:Data mining is a process by which the data can be analyzed so as to generate useful knowledge. It aims to use existing data to invent new facts and to uncover new relationships previously unknown even to experts. Bayesian network is a powerful tool for dealing with uncertainties, and has a widespread use in the area of data mining. In this paper, we focus on development of a data mining application for agriculture based on Bayesian networks. Let features (or objects) as variables or the nodes in Bayesian network, let directed edges present the relationships between features, and the relevancy intensity can be regarded as confidence between the variables. Accordingly, it can find the relationships in the agricultural data by learning a Bayesian network. After defining the domain variables and data preparation, we construct a model for agricultural application based on Bayesian network learning method. The experimental results indicate that the proposed method is feasible and efficient, and it is a promising approach for data mining in agricultural data.

No abstract

No abstract