干旱区生态环境知识资源中心

Soil secondary salinization is one of the typical ecological side effects caused by land and water resources development in northwestern arid China. Factors that affect the occurrences and developments of salinization come from both natural conditions and human activities. Research on the mechanisms of salinization, build dynamic prediction model of salt accumulation and analyze sensitivities to different factors would supply effective references to the prediction and prevention of soil salinization. It is well known that related factors are always intertexture together, affecting each other, which result in multivariable, nonlinear and overall influences that work on the process of soil salinization. Artificial intelligence technologies may play important role in this domain. In this paper, genetic artificial neural network based model is built to simulate and evaluate soil salt accumulation and sensitivity of soil salinization. Example is taken from the Shule River watershed, typical arid area in northwestern China. Basic data of June 2000 are prepared depending on GIS and Remote Sensing. Precipitations, evaporations, groundwater levels, groundwater chemical analysis data and soil accumulation data are achieved and interpolated in the research area. Slope of the land are derived from DEM, MODIS images are used in the process of dealing with land use information. At the same time, landform and soil type are considered in model building. Soil salt accumulation is analyzed with its 8 influenced factors with verified models. Results showing that groundwater TDS is the most sensitive factor followed by groundwater level, evaporation and the depth of upper bed of clay. In most cases clay layers play key roles in soil salt accumulation, precipitation and slop have similar sensitivities. Results would have better research and application value in and areas of northwestern China.