This paper aims at investigating the change over time in the environmental awareness in rural Chinese communities and its correlation with environmental management measures implemented at the local level. We identify three main components of awareness, namely: perception, behavior, and attitude toward environmental management measures. Data were collected from two surveys in three villages in northern China in 2006 and 2015 that interviewed 125 and 129 respondents, respectively, and were analyzed employing an Analytic Hierarchy Process (AHP) approach. The results discussed in the paper show that environmental awareness increased between 2006–2015, and was mainly manifested in better environmental behavior and understanding of environmental status due an improvement in rural infrastructure and a greater amount of information provided to rural residents about the environment. Place of residence had a considerable influence on respondents’ environmental awareness: residents in eco-villages had a higher environmental awareness than those living in common agricultural villages. This appears to indicate a positive nexus between the comprehensiveness of environmental management measures implemented locally, and environmental awareness. Also, the universality of environment issues reduced the importance of socioeconomic and demographic factors in determining the degree of environmental awareness. However, more attention should be paid to villagers’ external behavior and inner feelings, such as their attitude to governmental management policies. These findings yield important policy implications that are relevant to the promotion of environmental awareness in China’s rural communities, and the adoption of more effective environmental management measures.

Accurate rainfall prediction remains a challenging problem because of the high volatility and complicated essence of atmospheric data. This study proposed a hybrid model (DSP) that combines the advantages of discrete wavelet transform (DWT), support vector regression (SVR), and Prophet to forecast rainfall data. First, the rainfall time series is decomposed into high-frequency and low-frequency subseries using discrete wavelet transform (DWT). The SVR and Prophet models are then used to predict high-frequency and low-frequency subsequences, respectively. Finally, the predicted rainfall is determined by summing the predicted values of each subsequence. A case study in China is conducted from 1 January 2014 to 30 June 2016. The results show that the DSP model provides excellent prediction, with RMSE, MAE, and R² values of 6.17, 3.3, and 0.75, respectively. The DSP model yields higher prediction accuracy than the three baseline models considered, with the prediction accuracy ranking as follows: DSP > SSP > Prophet > SVR. In addition, the DSP model is quite stable and can achieve good results when applied to rainfall data from various climate types, with RMSEs ranging from 1.24 to 7.31, MAEs ranging from 0.52 to 6.14, and R² values ranging from 0.62 to 0.75. The proposed model may provide a novel approach for rainfall forecasting and is readily adaptable to other time series predictions.