Source identification and prediction of nitrogen and phosphorus pollution of Lake Taihu by an ensemble machine learning technique

● A machine learning model was used to identify lake nutrient pollution sources. ● XGBoost model showed the best performance for lake water quality prediction. ● Model feature size was reduced by screening the key features with the MIC method. ● TN and TP concentrations of Lake Taihu are mainly affected by endogenous sources. ● Next-month lake TN and TP concentrations were predicted accurately. Effective control of lake eutrophication necessitates a full understanding of the complicated nitrogen and phosphorus pollution sources, for which mathematical modeling is commonly adopted. In contrast to the conventional knowledge-based models that usually perform poorly due to insufficient knowledge of pollutant geochemical cycling, we employed an ensemble machine learning (ML) model to identify the key nitrogen and phosphorus sources of lakes. Six ML models were developed based on 13 years of historical data of Lake Taihu’s water quality, environmental input, and meteorological conditions, among which the XGBoost model stood out as the best model for total nitrogen (TN) and total phosphorus (TP) prediction. The results suggest that the lake TN is mainly affected by the endogenous load and inflow river water quality, while the lake TP is predominantly from endogenous sources. The prediction of the lake TN and TP concentration changes in response to these key feature variations suggests that endogenous source control is a highly desirable option for lake eutrophication control. Finally, one-month-ahead prediction of lake TN and TP concentrations (R² of 0.85 and 0.95, respectively) was achieved based on this model with sliding time window lengths of 9 and 6 months, respectively. Our work demonstrates the great potential of using ensemble ML models for lake pollution source tracking and prediction, which may provide valuable references for early warning and rational control of lake eutrophication.     

Prediction and cause investigation of ozone based on a double-stage attention mechanism recurrent neural network

● Used a double-stage attention mechanism model to predict ozone. ● The model can autonomously select the appropriate time series for forecasting. ● The model outperforms other machine learning models and WRF-CMAQ. ● We used the model to analyze the driving factors of VOCs that cause ozone pollution. Ozone is becoming a significant air pollutant in some regions, and VOCs are essential for ozone prediction as necessary ozone precursors. In this study, we proposed a recurrent neural network based on a double-stage attention mechanism model to predict ozone, selected an appropriate time series for prediction through the input attention and temporal attention mechanisms, and analyzed the cause of ozone generation according to the contribution of feature parameters. The experimental data show that our model had an RMSE of 7.71 μg/m³ and a mean absolute error of 5.97 μg/m³ for 1-h predictions. The DA-RNN model predicted ozone closer to observations than the other models. Based on the importance of the characteristics, we found that the ozone pollution in the Jinshan Industrial Zone mainly comes from the emissions of petrochemical enterprises, and the good generalization performance of the model is proved through testing multiple stations. Our experimental results demonstrate the validity and promising application of the DA-RNN model in predicting atmospheric pollutants and investigating their causes.     

Factors affecting the distribution of microplastics in soils of China

● Microplastic (MP) abundance in soil of China was highly heterogeneous. ● MP abundance was higher near large rivers and central land affected by monsoons. ● MP abundance was correlated with longitude, mulching film, and average temperature. ● Factors suitable for predicting MP pollution using models were discussed. Microplastics (MPs) are found worldwide in high abundance, posing a potential threat to ecosystems. Despite the ubiquity of MPs in the environment, very little is known about the regional distribution of MPs and underlying factors affecting this distribution in the field, which likely include human activity, but also features of the environment itself. Here, out of a total of 1157 datapoints investigated in 53 Chinese studies, 9.68% datapoints were removed as outliers in the heterogeneity analysis. This review revealed that the abundance of MPs was highly heterogeneous. In addition, microplastic (MP) distribution maps based on China demonstrated that the highest abundance of MPs tended to occur near large rivers and central land affected by the intersection of two monsoons. The model-fitting and previous studies showed that MP abundance in China was correlated with longitude, agricultural mulching film usage per capita, temperature, and precipitation. However, due to the heterogeneity of MPs and the low matching degree between the current environmental data and the sampling points, this pattern was not as evident as reported in any single study. Factors affecting the distribution of MPs can not be captured by linear relationships alone, and systematic selection of suitable environmental factors and further model optimization are needed to explore the cause of MP pollution in soil. Overall, this review revealed an uneven distribution of MPs and serves as a reference for model prediction to assess and control plastic pollution in natural soil environments.     

State-of-the-art applications of machine learning in the life cycle of solid waste management

● State-of-the-art applications of machine learning (ML) in solid waste (SW) is presented. ● Changes of research field over time, space, and hot topics were analyzed. ● Detailed application seniors of ML on the life cycle of SW were summarized. ● Perspectives towards future development of ML in the field of SW were discussed. Due to the superiority of machine learning (ML) data processing, it is widely used in research of solid waste (SW). This study analyzed the research and developmental progress of the applications of ML in the life cycle of SW. Statistical analyses were undertaken on the literature published between 1985 and 2021 in the Science Citation Index Expanded and Social Sciences Citation Index to provide an overview of the progress. Based on the articles considered, a rapid upward trend from 1985 to 2021 was found and international cooperatives were found to have strengthened. The three topics of ML, namely, SW categories, ML algorithms, and specific applications, as applied to the life cycle of SW were discussed. ML has been applied during the entire SW process, thereby affecting its life cycle. ML was used to predict the generation and characteristics of SW, optimize its collection and transportation, and model the processing of its energy utilization. Finally, the current challenges of applying ML to SW and future perspectives were discussed. The goal is to achieve high economic and environmental benefits and carbon reduction during the life cycle of SW. ML plays an important role in the modernization and intellectualization of SW management. It is hoped that this work would be helpful to provide a constructive overview towards the state-of-the-art development of SW disposal.     

Development of machine learning multi-city model for municipal solid waste generation prediction

● A database of municipal solid waste (MSW) generation in China was established. ● An accurate MSW generation prediction model (WGMod) was constructed. ● Key factors affecting MSW generation were identified. ● MSW trends generation in Beijing and Shenzhen in the near future are projected. Integrated management of municipal solid waste (MSW) is a major environmental challenge encountered by many countries. To support waste treatment/management and national macroeconomic policy development, it is essential to develop a prediction model. With this motivation, a database of MSW generation and feature variables covering 130 cities across China is constructed. Based on the database, advanced machine learning (gradient boost regression tree) algorithm is adopted to build the waste generation prediction model, i.e., WGMod. In the model development process, the main influencing factors on MSW generation are identified by weight analysis. The selected key influencing factors are annual precipitation, population density and annual mean temperature with the weights of 13%, 11% and 10%, respectively. The WGMod shows good performance with R² = 0.939. Model prediction on MSW generation in Beijing and Shenzhen indicates that waste generation in Beijing would increase gradually in the next 3–5 years, while that in Shenzhen would grow rapidly in the next 3 years. The difference between the two is predominately driven by the different trends of population growth.     

A hybrid Wavelet-CNN-LSTM deep learning model for short-term urban water demand forecasting

● A novel deep learning framework for short-term water demand forecasting. ● Model prediction accuracy outperforms other traditional deep learning models. ● Wavelet multi-resolution analysis automatically extracts key water demand features. ● An analysis is performed to explain the improved mechanism of the proposed method. Short-term water demand forecasting provides guidance on real-time water allocation in the water supply network, which help water utilities reduce energy cost and avoid potential accidents. Although a variety of methods have been proposed to improve forecast accuracy, it is still difficult for statistical models to learn the periodic patterns due to the chaotic nature of the water demand data with high temporal resolution. To overcome this issue from the perspective of improving data predictability, we proposed a hybrid Wavelet-CNN-LSTM model, that combines time-frequency decomposition characteristics of Wavelet Multi-Resolution Analysis (MRA) and implement it into an advanced deep learning model, CNN-LSTM. Four models - ANN, Conv1D, LSTM, GRUN - are used to compare with Wavelet-CNN-LSTM, and the results show that Wavelet-CNN-LSTM outperforms the other models both in single-step and multi-steps prediction. Besides, further mechanistic analysis revealed that MRA produce significant effect on improving model accuracy.     

Approaching the upper boundary of driver-response relationships: identifying factors using a novel framework integrating quantile regression with interpretable machine learning

● A novel framework integrating quantile regression with machine learning is proposed. ● It aims to identify factors driving observations to upper boundary of relationship. ● Increasing N:P and TN concentration help fulfill the effect of TP on CHL. ● Wetter and warmer decrease potential and increase eutrophication control difficulty. ● The framework advances applications of quantile regression and machine learning. The identification of factors that may be forcing ecological observations to approach the upper boundary provides insight into potential mechanisms affecting driver-response relationships, and can help inform ecosystem management, but has rarely been explored. In this study, we propose a novel framework integrating quantile regression with interpretable machine learning. In the first stage of the framework, we estimate the upper boundary of a driver-response relationship using quantile regression. Next, we calculate “potentials” of the response variable depending on the driver, which are defined as vertical distances from the estimated upper boundary of the relationship to observations in the driver-response variable scatter plot. Finally, we identify key factors impacting the potential using a machine learning model. We illustrate the necessary steps to implement the framework using the total phosphorus (TP)-Chlorophyll a (CHL) relationship in lakes across the continental US. We found that the nitrogen to phosphorus ratio (N׃P), annual average precipitation, total nitrogen (TN), and summer average air temperature were key factors impacting the potential of CHL depending on TP. We further revealed important implications of our findings for lake eutrophication management. The important role of N׃P and TN on the potential highlights the co-limitation of phosphorus and nitrogen and indicates the need for dual nutrient criteria. Future wetter and/or warmer climate scenarios can decrease the potential which may reduce the efficacy of lake eutrophication management. The novel framework advances the application of quantile regression to identify factors driving observations to approach the upper boundary of driver-response relationships.     

A critical review of the emerging research on the detection and assessment of microplastics pollution in the coastal,marine, and urban Bangladesh

● Coastal and marine regions are the most studied for microplastic pollution. ● Tourism is a major cause of microplastic pollution in coastal regions. ● Sediments contain larger microplastics while fish ingest smaller microplastics. ● Inland lakes, rivers, and freshwater fish are impacted by microplastic pollution. ● Microplastics are found in edible salts, however, presence is less in refined salt. The research on the extent and effects of microplastics pollution in the Global South is only getting started. Bangladesh is a South Asian country with one of the fastest growing economies in the world, however, such exponential economic growth has also increased the pollution threats to its natural and urban environment. In this paper, we reviewed the recent primary research on the assessment of the extent of microplastics pollution in Bangladesh. From the online databases, we developed a compilation of emerging research articles that detected and quantified microplastics in different coastal, marine, and urban environments in Bangladesh. Most of the studies focused on the coastal environment (e.g., beach sediment) and marine fish, while limited data were available for the urban environment. We also discussed the relationship of the type of anthropogenic activities with the observed microplastic pollution. The Cox’s Bazar sea beach in south-east Bangladesh experienced microplastics pollution due to tourism activities, while fishing and other anthropogenic activities led to microplastics pollution in the Bay of Bengal. While microplastics larger than 1 mm were prevalent in the beach sediments, smaller microplastics with size below 0.5 mm were prevalent in marine fish samples. Moreover, the differences in microplastic abundance, size, shape, color, and polymer type found were depended on the sampling sites and relevant anthropogenic activities. It is imperative to identify major sources of microplastics pollution in both natural and urban environment, determine potential environmental and human health effects, and develop mitigating and prevention strategies for reducing microplastics pollution.     

Water quality soft-sensor prediction in anaerobic process using deep neural network optimized by Tree-structured Parzen Estimator

● Hybrid deep-learning model is proposed for water quality prediction. ● Tree-structured Parzen Estimator is employed to optimize the neural network. ● Developed model performs well in accuracy and uncertainty. ● Usage of the proposed model can reduce carbon emission and energy consumption. Anaerobic process is regarded as a green and sustainable process due to low carbon emission and minimal energy consumption in wastewater treatment plants (WWTPs). However, some water quality metrics are not measurable in real time, thus influencing the judgment of the operators and may increase energy consumption and carbon emission. One of the solutions is using a soft-sensor prediction technique. This article introduces a water quality soft-sensor prediction method based on Bidirectional Gated Recurrent Unit (BiGRU) combined with Gaussian Progress Regression (GPR) optimized by Tree-structured Parzen Estimator (TPE). TPE automatically optimizes the hyperparameters of BiGRU, and BiGRU is trained to obtain the point prediction with GPR for the interval prediction. Then, a case study applying this prediction method for an actual anaerobic process (2500 m³/d) is carried out. Results show that TPE effectively optimizes the hyperparameters of BiGRU. For point prediction of COD_eff and biogas yield, R² values of BiGRU, which are 0.973 and 0.939, respectively, are increased by 1.03%–7.61% and 1.28%–10.33%, compared with those of other models, and the valid prediction interval can be obtained. Besides, the proposed model is assessed as a reliable model for anaerobic process through the probability prediction and reliable evaluation. It is expected to provide high accuracy and reliable water quality prediction to offer basis for operators in WWTPs to control the reactor and minimize carbon emission and energy consumption.     

China’s carbon neutrality: an extensive and profound systemic reform

● China has pledged ambitious carbon peak and neutrality goals for mitigating global climate change. ● Major challenges to achieve carbon neutrality in China are summarized. ● The new opportunities along the pathway of China’s carbon neutrality are discussed from four aspects. ● Five policy suggestions for China are provided. China is the largest developing economy and carbon dioxide emitter in the world, the carbon neutrality goal of which will have a profound influence on the mitigation pathway of global climate change. The transition towards a carbon-neutral society is integrated into the construction of ecological civilization in China, and brings profound implications for China’s socioeconomic development. Here, we not only summarize the major challenges in achieving carbon neutrality in China, but also identify the four potential new opportunities: namely, the acceleration of technology innovations, narrowing regional disparity by reshaping the value of resources, transforming the industrial structure, and co-benefits of pollution and carbon mitigation. Finally, we provide five policy suggestions and highlight the importance of balancing economic growth and carbon mitigation, and the joint efforts among the government, the enterprises, and the residents.     

A new prediction method of industrial atmospheric pollutant emission intensity based on pollutant emission standard quantification

● Established a quantification method of pollutant emission standard. ● Predicted the SO₂ emission intensity of single coking enterprises in China. ● Evaluated the influence of pollutant discharge standard on prediction accuracy. ● Analyzed the SO₂ emissions of Chinese provincial and municipal coking enterprises. Industrial emissions are the main source of atmospheric pollutants in China. Accurate and reasonable prediction of the emission of atmospheric pollutants from single enterprise can determine the exact source of atmospheric pollutants and control atmospheric pollution precisely. Based on China’s coking enterprises in 2020, we proposed a quantitative method for pollutant emission standards and introduced the quantification results of pollutant emission standards (QRPES) into the construction of support vector regression (SVR) and random forest regression (RFR) prediction methods for SO₂ emission of coking enterprises in China. The results show that, affected by the types of coke ovens and regions, China’s current coking enterprises have implemented a total of 21 emission standards, with marked differences. After adding QRPES, it was found that the root mean squared error (RMSE) of SVR and RFR decreased from 0.055 kt/a and 0.059 kt/a to 0.045 kt/a and 0.039 kt/a, and theR² increased from 0.890 and 0.881 to 0.926 and 0.945, respectively. This shows that the QRPES can greatly improve the prediction accuracy, and the SO₂ emissions of each enterprise are highly correlated with the strictness of standards. The predicted result shows that 45% of SO₂ emissions from Chinese coking enterprises are concentrated in Shanxi, Shaanxi and Hebei provinces in central China. The method created in this paper fills in the blank of forecasting method of air pollutant emission intensity of single enterprise and is of great help to the accurate control of air pollutants.     

Discovery of emerging organic pollutants in the atmosphere through an omics approach

● We review the framework of discovering emerging pollutants through an omics approach. ● High-resolution MS can digitalize atmospheric samples to full-component data. ● Chemical features and databases can help to translate untargeted data to compounds. ● Biological effect-directed untargeted analyses consider both existence and toxicity. Ambient air pollution, containing numerous known and hitherto unknown compounds, is a major risk factor for public health. The discovery of harmful components is the prerequisite for pollution control; however, this raises a great challenge on recognizing previously unknown species. Here we systematically review the analytical techniques on air pollution in the framework of an omics approach, with a brief introduction on sample preparation and analysis, and in more detail, compounds prioritization and identification. Through high-resolution mass spectrometry (HRMS, typically coupled with chromatography), the complicated environmental matrix can be digitalized into “full-component” data. A key step to discover emerging compounds is the prioritization of compounds from massive data. Chemical fingerprints, suspect lists and biological effects are the most vital untargeted strategies for comprehensively screening critical and hazardous substances. Afterward, compressed data of compounds can be identified at various confidence levels according to exact mass and the derived molecular formula, MS libraries, and authentic standards. Such an omics approach on full-component data provides a paradigm for discovering emerging air pollutants; nonetheless, new technological advancements of instruments and databases are warranted for further tracking the environmental behaviors, hence to evaluate the health risk of key pollutants.     

Relationship between groundwater cadmium and vicinity resident urine cadmium levels in the non-ferrous metal smelting area,China

● This study systematically examined the relationship between groundwater Cd and UCL. ● The study covered 211 UCL and sociological characteristic from nine groundwater samples. ● We found a significant positive correlation between groundwater Cd and UCL. ● Smoking status and education level also significantly affected UCL. Cadmium (Cd) has received widespread attention owing to its persistent toxicity and non-degradability. Cd in the human body is mainly absorbed from the external environment and is usually assessed using urinary Cd. Hunan Province is the heartland of the Chinese non-ferrous mining area, where several serious Cd pollution events have occurred, including high levels of Cd in the urine of residents. However, the environmental factors influencing high urinary Cd levels (UCLs) in nearby residents remain unclear. Therefore, 211 nearby residents’ UCLs and the corresponding sociological characteristics from nine groundwater samples in this area were analyzed using statistical analysis models. Groundwater Cd concentration ranged from 0.02 to 1.15 μg/L, aligning with class III of the national standard; the range of UCL of nearby residents was 0.37–36.60 μg/L, exceeding the national guideline of 0–2.5 μg/L. Groundwater Cd levels were positively correlated with the UCL (P < 0.001, correlation coefficient 95 % CI = 9.68, R² = 0.06). In addition, sociological characteristics, such as smoking status and education level, also affect UCL. All results indicate that local governments should strengthen the prevention and abatement of groundwater Cd pollution. This study is the first to systematically evaluate the relationship between groundwater Cd and UCL using internal and external environmental exposure data. These findings provide essential bases for relevant departments to reduce Cd exposure in regions where the heavy metal industry is globally prevalent.     

Legacies and health risks of heavy metals,polybrominated diphenyl ethers,and polychlorinated dibenzo-dioxins/furans at e-waste recycling sites in South China

● Heavy metals and organic toxins may persist in legacy sites for a long time. ● Contaminants pose potential harms to the nearby community (HI > 1). ● PCDD/Fs had the risk of endocrine disruption and reproductive risk. ● Further intervention is needed to reduce pollution and related risks. Informal electronic-waste (e-waste) recycling sites pose substantial health risks to surrounding environments and populations, yet they are not properly regulated. In this study, the soil levels of copper, lead, cadmium, eight polybrominated diphenyl ethers (PBDEs), and 18 polychlorinated dibenzo-dioxins/furans (PCDD/Fs) were measured at two e-waste recycling sites in South China between 2014 and 2019. Both sites have been abandoned for natural restoration. Our results indicate that the mean Cd and PCDD/F levels at Site A in 2019 were higher than those recommended by current safety guidelines. Meanwhile, the highest exposure among children was 1.36 × 10⁻² mg/(kg·d) for Cu, followed by 5.05 × 10⁻³ mg/(kg·d) for Pb, 9.71 ng/(kg·d) for PBDEs, and 6.82 ng TEQ/(kg·d) for PCDD/Fs. Children were at elevated risk for health problem posed by Pb and Cu exposure at both sites (hazard quotient > 1) and by PCDD/Fs at Site A. Further risk assessment was conducted on the target organs and endpoints of heavy metals and PCDD/Fs. The hazard index (HI) for the target organ mixed-risk of heavy metals was high (HI = 1.27), as was that of PCDD/Fs (HI = 1.66), which can disrupt endocrine function and pose a risk of reproductive toxicity in children. Owing to incomplete cleaning, contaminants persist in soils over long periods and may harm nearby environments and communities. Our study demonstrates that heavy metal, PBDE, and PCDD/F contamination have not yet been remediated, and intervention is needed to reduce pollution and associated risks in areas affected by e-waste.     

Plastic materials and water sources actively select and shape wastewater plastispheres over time

● Wastewater MPs exhibited resistomes and therefore health threats. ● High density of alkB gene indicates both HDPE and PET can be utilized by microbes. ● Plastics and waters actively selected and shaped the plastispheres over time. ● A broader phylogenetic spectrum of MHET-degrading microorganisms was annotated. The daily use of plastics presents a serious pollution issue due to their extremely slow degradation. Microplastics and the biofilm that grows on plastics (i.e., the plastisphere) are important subsets of plastic wastes. Many studies have been conducted to reveal the structures of the plastispheres, the driving factors for the formation of the plastisphere, and the ability of the plastispheres to degrade plastics in a variety of water bodies. However, the plastispheres related to wastewater are understudied. In this study, we used a microcosmic strategy to study the evolution of the plastispheres associated with microplastics (MPs) over time in wastewater. We found that plastic materials and water sources did not actively select and shape the plastispheres at an early stage, but the active selection for a unique niche of the plastisphere occurred after 14 d of growth. In addition, we confirmed that the alkB gene was densely present, and metagenomics showed some additional chemical reactions, which suggests that MPs are consumed by the microbes in the plastispheres. Additionally, metagenomics identified some metagenome-assembled genomes (MAGs) associated with high-density polyethylene (HDPE) and polyethylene terephthalate (PET). The identification of HDPE-associated MAGs and PET-associated MAGs further supports the notion that the selection for a unique niche of the plastisphere is driven by plastic materials and water sources (in this study, after 14 d of growth). Our discoveries bring new views on the behavior of the wastewater-associated plastisphere, especially how long it takes a wastewater plastisphere to form.     

MSWNet: A visual deep machine learning method adopting transfer learning based upon ResNet 50 for municipal solid waste sorting

● MSWNet was proposed to classify municipal solid waste. ● Transfer learning could promote the performance of MSWNet. ● Cyclical learning rate was adopted to quickly tune hyperparameters. An intelligent and efficient methodology is needed owning to the continuous increase of global municipal solid waste (MSW). This is because the common methods of manual and semi-mechanical screenings not only consume large amount of manpower and material resources but also accelerate virus community transmission. As the categories of MSW are diverse considering their compositions, chemical reactions, and processing procedures, etc., resulting in low efficiencies in MSW sorting using the traditional methods. Deep machine learning can help MSW sorting becoming into a smarter and more efficient mode. This study for the first time applied MSWNet in MSW sorting, a ResNet-50 with transfer learning. The method of cyclical learning rate was taken to avoid blind finding, and tests were repeated until accidentally encountering a good value. Measures of visualization were also considered to make the MSWNet model more transparent and accountable. Results showed transfer learning enhanced the efficiency of training time (from 741 s to 598.5 s), and improved the accuracy of recognition performance (from 88.50% to 93.50%); MSWNet showed a better performance in MSW classsification in terms of sensitivity (93.50%), precision (93.40%), F1-score (93.40%), accuracy (93.50%) and AUC (92.00%). The findings of this study can be taken as a reference for building the model MSW classification by deep learning, quantifying a suitable learning rate, and changing the data from high dimensions to two dimensions.     

Evaluating the impact of sulfamethoxazole on hydrogen production during dark anaerobic sludge fermentation

● SMX promotes hydrogen production from dark anaerobic sludge fermentation. ● SMX significantly enhances the hydrolysis and acidification processes. ● SMX suppresses the methanogenesis process in order to reduce hydrogen consumption. ● SMX enhances the relative abundance of hydrogen-VFAs producers. ● SMX brings possible environmental risks due to the enrichment of ARGs. The impact of antibiotics on the environmental protection and sludge treatment fields has been widely studied. The recovery of hydrogen from waste activated sludge (WAS) has become an issue of great interest. Nevertheless, few studies have focused on the impact of antibiotics present in WAS on hydrogen production during dark anaerobic fermentation. To explore the mechanisms, sulfamethoxazole (SMX) was chosen as a representative antibiotic to evaluate how SMX influenced hydrogen production during dark anaerobic fermentation of WAS. The results demonstrated SMX promoted hydrogen production. With increasing additions of SMX from 0 to 500 mg/kg TSS, the cumulative hydrogen production elevated from 8.07 ± 0.37 to 11.89 ± 0.19 mL/g VSS. A modified Gompertz model further verified that both the maximum potential of hydrogen production (P_m) and the maximum rate of hydrogen production (R_m) were promoted. SMX did not affected sludge solubilization, but promoted hydrolysis and acidification processes to produce more hydrogen. Moreover, the methanogenesis process was inhibited so that hydrogen consumption was reduced. Microbial community analysis further demonstrated that the introduction of SMX improved the abundance of hydrolysis bacteria and hydrogen-volatile fatty acids (VFAs) producers. SMX synergistically influenced hydrolysis, acidification and acetogenesis to facilitate the hydrogen production.     

The distribution and availability of phosphorus fractions in restored cut slopes soil aggregates: a case study of subalpine road,Southwest China

● There was no significant difference in soil aggregates TP along altitude gradient. ● Overall, PAC dropped steadily as aggregate size increased. ● In soil aggregate sizes, TPi > TPo > R-P at 3009,3347 and 3654 m except 3980 m. ● Active NaHCO₃-Pi was the main AP source. ● Proportion of small aggregate sizes was emphasized to increase AP storage. The distribution and availability of phosphorus (P) fractions in restored cut slope soil aggregates, along altitude gradients, were analyzed. Samples were collected at 3009, 3347, 3654 and 3980 m of altitude. We examined soil aggregates total phosphorus (TP), available phosphorus (AP) and phosphorus activation coefficient (PAC), and discovered that there was no significant difference in TP levels between all four altitudes samples (p > 0.05). However, there was a significant difference in AP at 3009, 3347 and 3980 m of altitude (p < 0.05). At the altitudes of 3009, 3347 and 3654 m, the AP accumulation in small size aggregates was more advantageous. Overall, PAC dropped steadily as soil aggregates sizes increased, as shown: PAC (3654 m) > PAC (3347 m) > PAC (3009 m) > PAC (3980 m). In all particle size soil aggregates, the distribution of the P fractions was as follows: total inorganic phosphorus (TPi) > total organic phosphorus (TPo) > residual phosphorus (R-P), at 3009, 3347 and 3654 m, but a different registry was observed at 3980 m of altitude: TPo > TPi > R-P. Through correlation and multiple stepwise regression analysis, it was concluded that active NaHCO₃-Pi was the main AP source. It was also suggested that more attention should be given to the ratio of small particle size aggregates to increase soil AP storage. In order to improve the activation capacity and supply of soil P, along with promotion of the healthy development of soil ecosystem on slope land, it was suggest that inorganic P fertilizer and P activator could be added to soil at both low (3009 m) and high altitudes (3980 m).     

PM2.5 concentration declining saves health expenditure in China

● Monthly hospitalization expenses are sensitive to increases in PM_2.5 exposure. ● The increased PM_2.5 causes patients with CHD and LRI to stay longer in the hospital. ● The impact of PM_2.5 on total expenses for stroke is greater in southern China. ● Males may be more sensitive to air pollution than females. Air pollution has been a severe issue in China. Exposure to PM_2.5 has adverse health effects and causes economic losses. This study investigated the economic impact of exposure to PM_2.5 pollution using monthly city-level data covering 88.5 million urban employees in 2016 and 2017. This study mainly focused on three expenditure indicators to measure the economic impact considering lower respiratory infections (LRIs), coronary heart disease (CHD), and stroke. The results show that a 10 µg/m³ increase in PM_2.5 would cause total monthly expenses of LRIs, CHD, and stroke to increase by 0.226%, 0.237%, and 0.374%, respectively. We also found that LRI, CHD, and stroke hospital admissions increased significantly by 10%, 8.42%, and 5.64%, respectively. Furthermore, the total hospital stays of LRIs, CHDs, and strokes increased by 2.49%, 2. 51%, and 1.64%, respectively. Our findings also suggest heterogeneous impacts of PM_2.5 exposures by sex and across regions, but no statistical evidence shows significant differences between the older and younger adult subgroups. Our results provide several policy implications for reducing unequal public health expenditures in overpolluted countries.     

Predicting the elemental compositions of solid waste using ATR-FTIR and machine learning

● A method based on ATR-FTIR and ML was developed to predict CHNS contents in waste. ● Feature selection methods were used to improve models’ prediction accuracy. ● The best model predicted C, H, and N contents with accuracy R ² ≥ 0.93, 0.87, 0.97. ● Some suitable models showed insensitivity to spectral noise. ● Under moisture interference, the models still had good prediction performance. Elemental composition is a key parameter in solid waste treatment and disposal. This study has proposed a method based on infrared spectroscopy and machine learning algorithms that can rapidly predict the elemental composition (C, H, N, S) of solid waste. Both noise and moisture spectral interference that may occur in practical application are investigated. By comparing two feature selection methods and five machine learning algorithms, the most suitable models are selected. Moreover, the impacts of noise and moisture on the models are discussed, with paper, plastic, textiles, wood, and leather as examples of recyclable waste components. The results show that the combination of the feature selection and K-nearest neighbor (KNN) approaches exhibits the best prediction performance and generalization ability. Particularly, the coefficient of determination (R²) of the validation set, cross validation and test set are higher than 0.93, 0.89, and 0.97 for predicting the C, H, and N contents, respectively. Further, KNN is less sensitive to noise. Under moisture interference, the combination of feature selection and support vector regression or partial least-squares regression shows satisfactory results. Therefore, the elemental compositions of solid waste are quickly and accurately predicted under noise and moisture disturbances using infrared spectroscopy and machine learning algorithms.