Understanding the mechanisms of pollutant removal in Wastewater Treatment Plants (WWTPs) is crucial for controlling effluent quality efficiently. However, the numerous treatment units, operational factors, and the underlying interactions between these units and factors usually obfuscate the comprehensive and precise understanding of the processes. We have previously proposed a machine learning (ML) framework to uncover complex cause-and-effect relationships in WWTPs. However, only one interpretable ML model, Random forest (RF), was studied and the interpretation method was not granular enough to reveal very detailed relationships between operational factors and effluent parameters. Thus, in this paper, we present an upgraded framework involving three interpretable tree-based models (RF, XGboost and LightGBM), three metrics (R², Root mean squared error (RMSE), and Mean absolute error (MAE)) and a more advanced interpretation system SHapley Additive exPlanations (SHAP). Details of the framework are provided along with a demonstration of its practical applicability based on a case study of the Umeå WWTP in Sweden. Results show that, for both labels TSS_e (Total suspended solids in effluent) and PO4_e (Phosphate in effluent), the XGBoost models are optimal whereas the RF models are the least optimal, due to overfitting and polarized fitting. This study has yielded multiple new and significant findings with respect to the control of TSS_e and PO4_e in the Umeå WWTP and other similarly configured WWTPs. Additionally, this study has produced two important generic findings relating to ML applications for WWTPs (or even other process industries) in terms of cause-and-effect investigations. First, the model comparison should be carried out from multiple perspectives to ensure that underlying details are fully revealed and examined. Second, using a precise, robust, and granular (feature attribution available for individual instances) explanation method can bring extra insight into both model comparison and model interpretation. SHAP is recommended as we found it to be of great value in this study.

Due to the intrinsic complexity of wastewater treatment plant (WWTP) processes, it is always challenging to respond promptly and appropriately to the dynamic process conditions in order to ensure the quality of the effluent, especially when operational cost is a major concern. Machine Learning (ML) methods have therefore been used to model WWTP processes in order to avoid various shortcomings of conventional mechanistic models. However, to the best of the authors' knowledge, no ML applications have focused on investigating how operational factors can affect effluent quality. Additionally, the time lags between process steps have always been neglected, making it difficult to explain the relationships between operational factors and effluent quality. Therefore, this paper presents a novel ML-based framework designed to improve effluent quality control in WWTPs by clarifying the relationships between operational variables and effluent parameters. The framework consists of Random Forest (RF) models, Deep Neural Network (DNN) models, Variable Importance Measure (VIM) analyses, and Partial Dependence Plot (PDP) analyses, and uses a novel approach to account for the impact of time lags between processes. Details of the framework are provided along with a demonstration of its practical applicability based on a case study of the Umeå WWTP in Sweden involving a large number of samples (105763) representing the full scale of the plant's operations. Two effluent parameters, Total Suspended Solids in effluent (TSSe) and Phosphate in effluent (PO4e), and thirty-two operational variables are studied. RF models are developed, validated using DNN models as references, and shown to be suitable for VIM and PDP analyses. VIM identifies the variables that most strongly influence TSSe and PO4e, while PDP elucidates their specific effects on TSSe and PO4e. The major findings are: (1) Influent temperature is the most influential variable for both TSSe and PO4e, but it affects them in different ways; (2) PO4e depends strongly on the TSS in aeration basins - higher TSS concentrations in aeration basins generally promote PO4 removal, but excess TSS can have negative effects; (3) In general, the impact of TSS in aeration basins on TSSe and PO4e increases with the distances of the basin from the merging outlet, so more attention should be paid to the TSS concentration in the third or fourth aeration basins than the first and second ones; (4) Returning excessive amounts of sludge through the second return sludge pipe should be avoided because of its adverse impact on TSSe removal. These results could support the development of more advanced control strategies to increase control precision and reduce running costs in the Umeå WWTP and other similarly configured WWTPs. The framework could also be applied to other parameters in WWTPs and industrial processes in general if sufficient high-resolution data are available.

Climate change is likely to have large effects on the Baltic Sea ecosystem. Simulations indicate 2–4 °C warming and 50–80 % decrease in ice cover by 2100. Precipitation may increase ~30 % in the north, causing increased land runoff of allochthonous organic matter (AOM) and organic pollutants and decreased salinity. Coupled physical–biogeochemical models indicate that, in the south, bottom-water anoxia may spread, reducing cod recruitment and increasing sediment phosphorus release, thus promoting cyanobacterial blooms. In the north, heterotrophic bacteria will be favored by AOM, while phytoplankton production may be reduced. Extra trophic levels in the food web may increase energy losses and consequently reduce fish production. Future management of the Baltic Sea must consider the effects of climate change on the ecosystem dynamics and functions, as well as the effects of anthropogenic nutrient and pollutant load. Monitoring should have a holistic approach, encompassing both autotrophic (phytoplankton) and heterotrophic (e.g., bacterial) processes.

Increasing demand for biofuel production and global competition for the use of natural resources are key factors in finding new and environmentally safe routes for methanol production. In the present study, life cycle assessment was used to analyse the potential environmental impact and environmental cost of a novel methanol production process from wood compared to a conventional processes. Both the novel and the conventional process were divided into three stages: pre-treatment, gasification, and syngas cleaning and methanol synthesis. The environmental impacts were assessed and compared using Simapro 9 (ecoinvent 3.5 database) and the ReCiPe 2016 (World-H) midpoint method. The results, expressed per tonne methanol, showed that the impact categories of global warming potential (GWP) and marine ecotoxicity potential were lower in the novel process in comparison to the conventional process (48.2 kg CO2 eq. vs. 63.1 kg CO2 eq., and 4.55 kg 1,4-DCB vs. 6.35 kg 1,4-DCB respectively). However, the novel process had a higher environmental impact in the pre-treatment stage. The results of the sensitivity analysis showed that the GWP of the novel process increased from 48.2 kg CO2 eq. to 216 kg CO2 eq. due to the replacement of Na2CO3 by K2CO3. The human toxicity impact categories showed significant impact on environmental cost. These findings will help relevant industries to reduce their environmental impact and improve the production efficiency of methanol from wood.

Long-range atmospheric transport is a major pathway for delivering persistent organic pollutants to the oceans. Atmospheric deposition and volatilization of chlorinated pesticides and algae-produced bromoanisoles (BAs) were estimated for Bothnian Bay, northern Baltic Sea, based on air and water concentrations measured in 2011–2012. Pesticide fluxes were estimated using monthly air and water temperatures and assuming 4 months ice cover when no exchange occurs. Fluxes were predicted to increase by about 50 % under a 2069–2099 prediction scenario of higher temperatures and no ice. Total atmospheric loadings to Bothnian Bay and its catchment were derived from air–sea gas exchange and “bulk” (precipitation + dry particle) deposition, resulting in net gains of 53 and 46 kg year⁻¹ for endosulfans and hexachlorocyclohexanes, respectively, and net loss of 10 kg year⁻¹ for chlordanes. Volatilization of BAs releases bromine to the atmosphere and may limit their residence time in Bothnian Bay. This initial study provides baseline information for future investigations of climate change on biogeochemical cycles in the northern Baltic Sea and its catchment.