Abstract:Selenium (Se) is one of the essential trace elements for humans and animals. In order to scientifically predict the Se content of crops and achieve rational exploitation of Se-rich land resources. Methods: This study systematically collected and analyzed 13042 top soil samples, 313 sets of maize, 164 sets of potatoes and their corresponding root soil samples, studied the distribution characteristics and influencing factors of soil Se content in the area. The BP neural network prediction model for Se content of potato and maize was established, and the rational planning of Se rich cropping areas was carried out. Results: The mean value of soil Se content was 0. 164 μg/g with uneven spatial distribution. The Se-rich areas were found in the Qingshui River Plain in the study area and distributed in successive patches. The Se content of soils in the study area was mainly controlled by soil parent material, weathering and denudation of rocks, migration with river water, and agricutural irrigation, accopanied by an increase in organic matter content, resulting in an enrichment of Se in Quaternay alluvial and diluvial plain. The Se enrichment rates of potato and maize grain samples in the study area are 82. 32% and 38. 02%, respectively, and the content of heavy metal in potato and maize grains do not exceed the national food safety standard, which indicated that Se-rich crops planting could be developed in the study area. Conclusions: Se content of potato and maize grains are mainly related to the content Se, S, pH and organic matter in the corresponding root soil. According to the prediction models, the planting area of Se-rich potato in the study area is 1050. 11 km 2 and the planting area of Se-rich maize for crop grains 19. 19 km 2. This study provides a scientific basis for the planning of local planting areas and crop adjustment.