This work aims to investigate the methane emissions from integrated vertical-flow constructed wetlands (IVCWs) when ethanol is added as an external carbon source. In this study, a gradient of ethanol (0, 2, 4, 8, 16 and 32 mmol/L) was added as the carbon source in an IVCW planted with Cyperus alternifolius L. The results showed that the methane emission flux at an ethanol concentration of 32 mmol/L was 32.34 g CH4 m−2 day−1 less than that of the control experiment (0 mmol/L) and that the methane emission flux at an ethanol concentration of 16 mmol/L was 5.53 g CH4 m−2 day−1 less than that at 0 mmol/L. In addition, variations in the water quality driven by the different ethanol concentrations were found, with a redox potential range of −64 mV to +30 mV, a pH range of 6.6–6.9, a chemical oxygen demand (COD) removal rate range of 41% to 78%, and an ammonia nitrogen removal rate range of 59% to 82% after the ethanol addition. With the average CH4-C/TOC (%) value of 35% driven by ethanol, it will be beneficial to understand that CH4-C/TOC can be considered an ecological indicator of anthropogenic methanogenesis from treatment wetlands when driven by carbon sources or carbon loading. It can be concluded that adding ethanol as an external carbon source can not only meet the water quality demand of the IVCW treatment system but also stimulate and increase the average CH4 emissions from IVCWs by 23% compared with the control experiment. This finding indicates that an external carbon source can stimulate more CH4 emissions from IVCWs and shows the importance of carbon sources during sewage treatment processes when considering greenhouse emissions from treated wetlands.
Accurate traffic flow prediction not only relies on historical traffic flow information, but also needs to take into account the influence of a variety of external factors such as weather conditions and the distribution of neighbouring POIs. However, most of the existing studies have used historical data to predict future traffic flows for short periods of time. Spatio-Temporal Graph Neural Networks (STGNN) solves the problem of combining temporal properties and spatial dependence, but does not extract long-term trends and cyclical features of historical data. Therefore, this paper proposes a MIFPN (Multi information fusion prediction network) traffic flow prediction method based on the long and short-term features in the historical traffic flow data and combining with external information. First, a subsequence converter is utilised to allow the model to learn the temporal relationships of contextual subsequences from long historical sequences that incorporate external information. Then, a superimposed one-dimensional inflated convolutional layer is used to extract long-term trends, a dynamic graph convolutional layer to extract periodic features, and a short-term trend extractor to learn short-term temporal features. Finally, long-term trends, cyclical features and short-term features are fused to obtain forecasts. Experiments on real datasets show that the MIFPN model improves by an average of 11.2% over the baseline model in long term predictions up to 60 min ago.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)