文献类型： 会议论文

第一作者： Shanshan Li

作者： Shanshan Li ¹ ; Yisheng Miao ¹ ; Xiao Han ¹ ; Wei Guo ¹ ;

作者机构： 1.National Engineering Research Center for Information Technology in Agriculture, Beijing 100097, China,Research Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China,Key Laboratory of Digital Village Technology, Ministry of Agriculture and Rural Affairs, People's Republic of China, Beijing 100097, China

关键词： Water and fertilizer;Intelligence;Multi-source data;Irrigation decision

会议名称： CAAI International Conference on Artificial Intelligence

主办单位：

页码： 206-217

摘要： At present, the integrated irrigation management and control system of water and fertilizer has met the requirements of automatic control of farmland water and fertilizer, gradually transforming the traditional manual operation into facility industrialization. However, this method has a weak use of data, and there is still a large gap between the calculation method and intelligent management and control. Taking greenhouse cabbage as the main research object, based on the cultivation environmental parameters, growth morphological parameters, water and fertilizer irrigation requirements during the growth period of cabbage, and using the efficient allocation ability of attention mechanism to data feature weights, this paper proposes the establishment of water and fertilizer intelligent decision-making management and control model integrating multi-source data input. The results showed that the prediction error of the intelligent decision-making irrigation model for water and fertilizer for greenhouse cabbage was relatively small, RMSE was 0.002447 m~3/Day, MAE is 0.001779 m~3/Day, and the coupling relationship between multi-source data is comprehensively analyzed, and the overall performance of model decision-making is improved through multi-feature extraction.

分类号： tp3