The proposed methodology presents a comprehensive analysis of soft sensor modeling techniques for air ozone prediction. We compare the performance of three different modeling techniques: LR (linear regression), NN (neural networks), and RFR (random forest regression). Additionally, we evaluate the impact of different variable sets on prediction performance. Our findings indicate that neural network models, particularly the RNN (recurrent neural networks), outperform the other modeling techniques in terms of prediction accuracy. The proposed methodology evaluates the impact of different variable sets on prediction performance, finding that variable set E demonstrates exceptional performance and achieves the highest average prediction accuracy among various software sensor models. In comparing variable set E and A, B, C, D, it is observed that the inclusion of an additional input feature, PM10, in the latter sets does not improve overall performance, potentially due to multicollinearity between PM10 and PM2.5 variables. The proposed methodology provides valuable insights into soft sensor modeling for air ozone prediction.Among the 72 sensors, sensor NNR[Y]C outperforms all other evaluated sensors, demonstrating exceptional predictive performance with an impressive R2 of 0.8902, low RMSE of 24.91, and remarkable MAE of 19.16. With a prediction accuracy of 81.44%, sensor NNR[Y]C is reliable and suitable for various technological applications.
The study addresses the critical issue of accurately predicting ammonia nitrogen (NH3-N) concentration in a sequencing batch reactor (SBR) system, achieving reduced consumption through automatic control technology. NH3-N concentration serves as a key indicator of treatment efficiency and environmental impact; however, its complex dynamics and the scarcity of measurements pose significant challenges for accurate prediction. To tackle this problem, an innovative Transformer-long short-term memory (Transformer-LSTM) network model was proposed, which effectively integrates the strengths of both Transformer and LSTM architectures. The Transformer component excels at capturing long-range dependencies, while the LSTM component is adept at modeling sequential patterns. The innovation of the proposed methodology resides in the incorporation of dissolved oxygen (DO), electrical conductivity (EC), and oxidation-reduction potential (ORP) as input variables, along with their respective rate of change and cumulative value. This strategic selection of input features enhances the traditional utilization of water quality indicators and offers a more comprehensive dataset for prediction, ultimately improving model accuracy and reliability. Experimental validation on NH3-N datasets from the SBR system reveals that the proposed model significantly outperforms existing advanced methods in terms of root mean squared error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). Furthermore, by integrating real-time sensor data with the Transformer-LSTM network and automatic control, substantial improvements in water treatment processes were achieved, resulting in a 26.9% reduction in energy or time consumption compared with traditional fixed processing cycles. This methodology provides an accurate and reliable tool for predicting NH3-N concentrations, contributing significantly to the sustainability of water treatment and ensuring compliance with emission standards.
2 May 2025 in Environmental Science: Water Research & Technology
Water quality monitoring in wastewater treatment is crucial due to its significant impact on environmental sustainability and public health. Small wastewater treatment facilities often encounter challenges such as limited resources, lack of advanced monitoring technologies, and difficulties in maintaining effluent quality standards. This study aims to address these challenges by proposing an integrated methodology that employs a particle swarm optimization-based long short-term memory (PSO-LSTM) model in conjunction with a random forest regression (RFR) model for the prediction of ammonia nitrogen (NH3-N) concentrations. The methodology integrates the strengths of both models to enhance predictive accuracy and stability. The PSO algorithm optimizes hyperparameters of the LSTM, effectively searching the solution space to balance exploration and exploitation. This optimization facilitates the handling of complex non-linear data patterns while improving computational efficiency. The integrated PSO-LSTM-RFR approach demonstrated superior performance on the test set, achieving a coefficient of determination (R2) of 0.9105, a root mean square error (RMSE) of 2.9706, and a mean absolute error (MAE) of 2.5430. The results confirm that the proposed methodology significantly enhances predictive performance due to the complementary advantages of the models. The synergy between RFR and LSTM allows for effective handling of non-linear relationships and sequential data trends, leading to more accurate predictions. The findings underscore the potential of the integrated PSO-LSTM-RFR model to enhance predictive efficacy in wastewater treatment processes, ultimately contributing to more effective water quality management strategies.
19 January 2026 in Journal of Environmental Management