In recent years, environmental pollution has become more and more serious, especially water pollution. In this study, the method of Gaussian process regression was used to build a prediction model for the sulphate content of lakes using several water quality variables as inputs. The sulphate content and other variable water quality data from 100 stations operated at lakes along the middle and lower reaches of the Yangtze River were used for developing the four models. The selected water quality data, consisting of water temperature, transparency, pH, dissolved oxygen conductivity, chlorophyll, total phosphorus, total nitrogen and ammonia nitrogen, were used as inputs for several different Gaussian process regression models. The experimental results showed that the Gaussian process regression model using an exponential kernel had the smallest prediction error. Its mean absolute error (MAE) of 5.0464 and root mean squared error (RMSE) of 7.269 were smaller than those of the other three Gaussian process regression models. By contrast, in the experiment, the model used in this study had a smaller error than linear regression, decision tree, support vector regression, Boosting trees, Bagging trees and other models, making it more suitable for prediction of the sulphate content in lakes. The method proposed in this paper can effectively predict the sulphate content in water, providing a new kind of auxiliary method for water detection.

Several algorithms for association rules are discussed which are AIS algorithm, SETM algorithm, Apriori algorithm etc. Their strengths and weaknesses are investigated. Their performance are compared and analyzed. Among all the algorithms, the most inefficient one is SETM algorithm but it is the most convenient one to combine DBMS.

Nanocomposite coating is a coating made of particles whose sizes are of nanoscale. The microhardness of the coating is an importance parameter. Currently, experimental method is mainly adopted in the coating's microhardness and performance research, with high research cost and long time period. In this paper, the content of the nano-particles in the plating liquid, current density, duty ratio, addition of additives and ultrasonic power are set as inputs; the micro hardness of the nanocomposite coating is set as output. Extremely randomised trees (ERT) are used to establish a strong prediction model. The prediction performance is the ERT model is superior to that of the single models such as linear regression, back-propagation neural network and radial basis function neural network, etc. and other ensemble learning methods. ERT model can be used for predicting the microhardness of nanocomposite coating, providing an efficient and highly reliable method for new material performance prediction.