Abstract: Vegetables are important cash crops, and it is of great significance to people’s life to guarantee long-term high yields of vegetables in total. In order to investigate the remote sensing monitoring model of the growth condition of Chinese cabbage during the whole reproductive period, this study takes Chinese cabbage under different water and nitrogen treatments as the research object, uses UAV multispectral remote sensing technology, optimizes the spectral data（band reflectance, vegetation index） by cluster-factor analysis as input variables, and it takes the soil water content and relative chlorophyll content（SPAD） observed quasi-simultaneously on the ground as output variables. The SPAD and soil moisture content monitoring model of Chinese cabbage leaves were constructed by using three methods: Extreme Learning Machine（ELM）, Multiple linear regression（MLR）, and Particle Swarm Optimization-Extreme Learning Machine（PSO-ELM）.The spatial and temporal distribution characteristics of soil moisture and SPAD in the experimental area were analyzed by use of inverse images. The main findings were as follows:（1） Different water and nitrogen treatments had highly significant effects on SPAD of Chinese cabbage, while water treatments were not significant.（2） Cluster-factor analysis obviously eliminated the multicollinearity problem between input variables, and the VIF among the treated variables were all 1.（3） The validation set determination coefficients R2 of the soil water content prediction models constructed by ELM, MLR, and PSO-ELM models were 0.54, 0.53, 0.66, respectively, and the root mean square errors RMSE were 0.01, 0.03, 0.03 respectively, and the performance deviation rates RPD were 1.42, 1.46, 1.72, respectively; the constructed leaf SPAD prediction models R2 were 0.65, 0.75, 0.74, RMSE were 2.39, 2.43, 2.46, and the RPD were 1.66, 2, 1.96, respectively. By comprehensive comparison, PSO-ELM has the highest simulation accuracy for the two indexes. The results of the study provide effective reference value for the research of prescription decision during the growth process of Chinese cabbage.