Traditional mechanism models of greenhouses are difficult to reflect the real greenhouse environment due to nonlinear, multivariate, and strongly coupled characteristics. In this paper, extreme learning machine (ELM), back propagation (BP) neural network, and support vector machine (SVM) are used to predict and analyze the temperature, humidity, and light intensity of the greenhouse. The results show that the predicted values of ELM model are the most similar to the real?time parameters of greenhouse environment. In order to further improve the prediction accuracy of environmental parameters in the greenhouse, the improved sparrow search algorithm (ISSA) is used to optimize ELM model in this paper. The predicted environmental parameters are in good agreement with the measured data of a greenhouse in Tianjin, which confirms the feasibility of the proposed prediction model for the control of greenhouse environment.