A CNN-LSTM based deep learning model with high accuracy and robustness for carbon price forecasting: A case of Shenzhen's carbon market in China.

Accurately predicting carbon trading prices using deep learning models can help enterprises understand the operational mechanisms and regulations of the carbon market. This is crucial for expanding the industries covered by the carbon market and ensuring its stable and healthy development. To ensure the accuracy and reliability of the predictions in practical applications, it is important to evaluate the model's robustness. In this paper, we built models with different parameters to predict carbon trading prices, and proposed models with high accuracy and robustness. The accuracy of the models was assessed using traditional survey indicators. The robustness of the CNN-LSTM model was compared to that of the LSTM model using Z-scores. The CNN-LSTM model with the best prediction performance was compared to a single LSTM model, resulting in a 9% reduction in MSE and a 0.0133 shortening of the Z-score range. Furthermore, the CNN-LSTM model achieved a level of accuracy comparable to other popular models such as CEEMDAN, Boosting, and GRU. It also demonstrated a training speed improvement of at least 40% compared to the aforementioned methods. These results suggest that the CNN-LSTM enhances model resilience. Moreover, the practicality of using Z-score to evaluate model robustness is confirmed.

Prediction of nitrous oxide emission of a municipal wastewater treatment plant using LSTM-based deep learning models.

Accurate assessment of greenhouse gas emissions from wastewater treatment plants is crucial for mitigating climate change. N2O is a potent greenhouse gas that is emitted from wastewater treatment plants during the biological denitrification process. In this study, we developed and evaluated deep learning models for predicting N2O emissions from a WWTP in Switzerland. Six key parameters were selected to obtain the optimal LSTM model by adjusting experimental parameter conditions. The optimal parameter condition was achieved with 150 neurons, the tanh activation function, the RMSprop optimization algorithm, a learning rate of 0.001, no dropout regularization, and a batch size of 128. Under the same conditions, we compared the performance of recurrent neural networks (RNNs) and Long Short-Term Memory (LSTM) networks. We found that LSTM models outperformed RNN models in predicting N2O emissions. The optimal LSTM model achieved a 36% improvement in mean absolute error (MAE), a 19% improvement in root mean squared error (RMSE), and a 6.92% improvement in R2 score compared to the RNN model. Additionally, LSTM models demonstrated better resilience to sudden changes in the target sequence, exhibiting a 9.54% higher percentage of explained variance compared to RNNs. These results highlight the potential of LSTM models for accurate and robust prediction of N2O emissions from wastewater treatment plants, contributing to effective greenhouse gas mitigation strategies.

[Characteristic of Nitrate Adsorption in Aqueous Solution by Iron and Manganese Oxide/Biochar Composites].

In this study, we synthesized Fe/Mn bimetallic oxide coated biochar sorbents by pyrolysis of wheat straw impregnated with ferric chloride and potassium permanganate and investigated their potential to adsorb nitrate in water. X-ray photoelectron spectroscopy and scanning electron microscopy analysis suggests that Fe(Ⅲ)/Mn(Ⅳ) bimetallic oxide particles emerge on the sorbents. The optimized sorbent could achieve a specific surface area of 153.116 m2·g-1 and a point of zero charge of 9.76. Batch nitrate adsorption experiments were carried out to investigate the influence of various factors, such as sorbent dosage, initial solution pH, and co-existing anions. Results show that the sorbent maintained a high adsorption capacity of 75.40%-78.70% over a wide range of pH from 1.00 to 9.05, and the sorption mechanism was interpreted as ligand exchange. The effects of co-existing anions on the nitrate sorption followed the decreasing order of Cl- > SO42- > PO43-. Furthermore, the adsorption isotherms were well described by the Langmuir model, and the sorbent could exhibit a quite competitively high capacity of 37.3613 mg·g-1 for nitrate removal. In addition, the accordance of sorption kinetics with the pseudo-second order model implied that the sorption could be a multi-stage controlled chemical process. In addition, the thermodynamic parameters suggested that the sorption reaction could be a spontaneous and endothermic process. The results demonstrated that the Fe/Mn bimetallic oxide coated biochar could serve as a promising agent for nitrate removal from water.

Quantification of nitrate sources and fates in rivers in an irrigated agricultural area using environmental isotopes and a Bayesian isotope mixing model.

Nitrate (NO3-) pollution in rivers caused by intensive human activities is becoming a serious problem in irrigated agricultural areas. To identify NO3- sources and reveal the impact of irrigation projects on NO3- pollution in rivers, the hydrochemistry and isotopes of irrigation water from the Yellow River (IW) and river water (RW), and potential source samples were analyzed. The mean NO3- concentrations in the IW and RW were 24.4 mg/L and 49.9 mg/L, respectively. Approximately 45.2% of RW samples (n = 31) exceeded the Chinese drinking water standard for NO3- (45 mg/L). The δ15N and δ18O values, combined with the Cl-/Na+, SO42-/Ca2+ ratio distributions, indicate that the NO3- in the RW mainly originated from chemical fertilizers, manure and sewage. A Bayesian model showed that manure and sewage contributed the most to the overall NO3- levels of the IW. In the RW, chemical fertilizers and IW contributed the most to the overall NO3- levels. The mean nitrate contribution to the RW from the combination of chemical fertilizers and IW is estimated to be 51.6%. Nitrogen from manure and sewage, soil N and precipitation also contributed. The NO3- pollution in rivers was largely influenced by the irrigation regime, with a large amount of nitrogen in chemical fertilizer lost because of low utilization efficiency and subsequent transfer, via irrigation runoff, into the rivers. This study suggests that with a detailed assessment of the sources and fate of NO3-, effective reduction strategies and better management practices can be implemented to control NO3- pollution in rivers.