Search

In China, over 65% of human activities are concentrated in cities, resulting in a conflict between the supply and demand of ecosystem services (ESs). To alleviate this problem, many cities have adopted eco-friendly development modes, however, the effectiveness of these models in reducing ESs supply-demand conflicts has not been comprehensively reviewed, and the human and natural drivers behind these relationship shifts remain unclear. To bridge this gap, this study analyzed the shifts in the relationships between supply and demand of ESs across China from 2010 to 2020 at a city level, as well as identified the human and natural drivers behind them. Firstly, the InVEST models were integrated with socioeconomic data to evaluate the supply and demand distribution for three pivotal ESs: water yield (WY), habitat quality (HQ), and soil retention (SR). Then, a four-quadrant diagram approach was proposed to enhance the analysis of their spatiotemporal relationships. Furthermore, random forest models were employed to examine the drivers of the shifts in these relationships. The results showed that WY and SR services witnessed growth until 2015, and then receded, while HQ saw a modest decline from 2010 to 2020. Spatial synergies in the supply and demand of ESs were primarily observed in the southern cities, with a significant northward extension by 2020. From a temporal perspective, the percentage of cities achieving coordination in WY and SR services increased from 32.6% to 57.3%, respectively, in the 2010–2015 period to 42.4% and 63.3% between 2015 and 2020, meanwhile, HQ service conflicts diminished from 58.7% to 53.5%. The changes in socioeconomic and land use factors contributed to 64.3%, 36.1%, and 33.3% of the shifts in the supply-demand relationship for HQ, WY, and SR services, respectively. Our analysis highlights the potential of human-driven ecological management to enhance the balance of this relationship. It can support the design of city-specific policies that foster a balance between ecological processes and socio-economic development. • The supply and demand of three critical ecosystem services were evaluated. • The spatiotemporal supply-demand relationships of ecosystem services were identified. • The natural and human drivers of these relationship shifts were examined. [ABSTRACT FROM AUTHOR]

Soil salinization and sodification, the primary causes of land degradation and desertification in arid and semi-arid regions, demand effective monitoring for sustainable land management. This study explores the utility of partial least square (PLS) latent variables (LVs) derived from visible and near-infrared (Vis-NIR) spectroscopy, combined with remote sensing (RS) and auxiliary variables, to predict electrical conductivity (EC) and sodium absorption ratio (SAR) in northern Xinjiang, China. Using 90 soil samples from the Karamay district, machine learning models (Random Forest, Support Vector Regression, Cubist) were tested in four scenarios. Modeling results showed that RS and Land use alone were unreliable predictors, but the addition of topographic attributes significantly improved the prediction accuracy for both EC and SAR. The incorporation of PLS LVs derived from Vis-NIR spectroscopy led to the highest performance by the Random Forest model for EC (CCC = 0.83, R2 = 0.80, nRMSE = 0.48, RPD = 2.12) and SAR (CCC = 0.78, R2 = 0.74, nRMSE = 0.58, RPD = 2.25). The variable importance analysis identified PLS LVs, certain topographic attributes (e.g., valley depth, elevation, channel network base level, diffuse insolation), and specific RS data (i.e., polarization index of VV + VH) as the most influential predictors in the study area. This study affirms the efficiency of Vis-NIR data for digital soil mapping, offering a cost-effective solution. In conclusion, the integration of proximal soil sensing techniques and highly relevant topographic attributes with the RF model has the potential to yield a reliable spatial model for mapping soil EC and SAR. This integrated approach allows for the delineation of hazardous zones, which in turn enables the consideration of best management practices and contributes to the reduction of the risk of degradation in salt-affected and sodicity-affected soils. • The effectiveness of a variety of auxiliary variables was assessed in predicting EC and SAR. • PLS latent variables (LVs) derived from Vis-NIR led to the highest performance for predicting EC and SAR. • Among the various ML models, Random Forest (RF) demonstrated the highest efficiency. [ABSTRACT FROM AUTHOR]

Reliable nitrogen (N) fertilizer management indicators are essential for improving crop yields and minimizing environmental impacts for sustainable production. The objectives of this study were to assess the importance of major N management indicators (NMIs) for higher yield with low risks of environmental pollution in an intensive potato system under drip irrigation. Six drip-irrigated field experiments with no N application (Control), farmer practice (FP), and optimized N management (OM) based on N-balance, soil mineral N (N min), and target yield were conducted from 2018 to 2020 in Inner Mongolia, China. The response of NMIs to potato yield and yield-based environment impact indices (EI Y) was evaluated by the random forest algorithm. The N input, N losses from N leaching, ammonia (NH 3) volatilization, nitrous oxide (N 2 O) emission, N use efficiency (NUE), N surplus, and soil residual N after harvest were obtained to identify the best NMIs for high yield and minimal ecological impact. The N management practices in field experimental sites affected the importance of the order of NMIs on potato yield and EI Y. The NUE and N leaching were identified as the highest importance scores and the most essential controlling variables to potato yield and EI Y , respectively. The integrated NUE and N leaching indicator played a vital role in improving potato yield and reducing ecological impact. The OM treatment achieved 46.0%, 63.6%, and 64.6% lower in N application rate, N surplus, and reactive N loss, and 62.4% higher in NUE than the FP treatment while achieving equal potato yields, respectively. Those key NMIs can guide farmers in understanding their practice short comes to achieve both high productivity and environmental sustainability in intensive potato production systems under drip irrigation. • We assess the response of nitrogen (N) indicators to drip-irrigated potato system. • Yield and yield-base environment indices (EI Y) were affected by NUE and leaching. • The N surplus was an effective indicator for controlling N losses. [ABSTRACT FROM AUTHOR]

In the context of China's efforts to combat climate change and promote sustainable development, the solid waste treatment industry's environmental, social, and corporate governance (ESG) performance is receiving significant attention. To comprehensively assess the ESG performance of the solid waste treatment industry and identify company types, this study constructs a targeted ESG evaluation index system based on existing literature, SASB industry standards, and company reports and utilizes a random forest approach combined with K-means clustering to determine indicator weights. Based on this index system, the paper evaluates the ESG performance of 71 solid waste disposal companies (SWDCs) from 2013 to 2021 and identifies their ESG types from static and dynamic perspectives. In the static view, company types are determined based on annual ESG performance, while the dynamic view considers time-series changes to observe the evolution of company ESG types. The results show that the overall ESG performance of SWDCs falls within the 2-8-point range, indicating a noticeable high-low imbalance. Key initiatives to improve ESG performance in this industry include enhancing waste management measures, developing emergency plans, and reinforcing ESG disclosure. From a static perspective, this paper can identify companies into three categories: delayed development, single-wheel-driven, and coordinated development. Finally, from a dynamic perspective considering the time factor, companies are further subdivided into five types: continual leading, growth catch-up, slow progress, fluctuating change, and retrogressive inertia. This study not only provides targeted recommendations for different types of ESG companies but also helps various sectors of society better understand the ESG conditions of this high environmental risk industry, thereby enhancing the regulation and support for its sustainable development. [Display omitted] • ESG evaluation index system for solid waste disposal companies is proposed. • A random forest method based on k-means clustering is used to construct the index. • Comparing E, S, and G scores with industry averages to identify static ESG types. • Analyzing trends in annual static ESG types to identify dynamic ESG types. • Identify companies as three static ESG types and five dynamic ESG types. [ABSTRACT FROM AUTHOR]

Forest fires threaten global ecosystems, socio-economic structures, and public safety. Accurately assessing forest fire susceptibility is critical for effective environmental management. Supervised learning methods dominate this assessment, relying on a substantial dataset of forest fire occurrences for model training. However, obtaining precise forest fire location data remains challenging. To address this issue, semi-supervised learning emerges as a viable solution, leveraging both a limited set of collected samples and unlabeled data containing environmental factors for training. Our study employed the transductive support vector machine (TSVM), a key semi-supervised learning method, to assess forest fire susceptibility in scenarios with limited samples. We conducted a comparative analysis, evaluating its performance against widely used supervised learning methods. The assessment area for forest fire susceptibility lies in Dayu County, Jiangxi Province, China, renowned for its vast forest cover and frequent fire incidents. We analyzed and generated maps depicting forest fire susceptibility, evaluating prediction accuracies for both supervised and semi-supervised learning methods across various small sample scenarios (e.g., 4, 8, 12, 16, 20, 24, 28, and 32 samples). Our findings indicate that TSVM exhibits superior prediction accuracy compared to supervised learning with limited samples, yielding more plausible forest fire susceptibility maps. For instance, at sample sizes of 4, 16, and 28, TSVM achieves prediction accuracies of approximately 0.8037, 0.9257, and 0.9583, respectively. In contrast, random forests, the top performers in supervised learning, demonstrate accuracies of approximately 0.7424, 0.8916, and 0.9431, respectively, for the same small sample sizes. Additionally, we discussed three key aspects: TSVM parameter configuration, the impact of unlabeled sample size, and performance within typical sample sizes. Our findings support semi-supervised learning as a promising approach compared to supervised learning for forest fire susceptibility assessment and mapping, particularly in scenarios with small sample sizes. • We used the transductive support vector machine (TSVM) for forest fire susceptibility assessment with limited samples. • The prediction accuracy of TSVM outperforms common supervised learning methods in small sample scenarios. • TSVM as a semi-supervised learning exploits unlabeled data to improve prediction accuracy. [ABSTRACT FROM AUTHOR]

Soil loss is an environmental concern of global importance. Accurate simulation of soil loss in small watersheds is crucial for protecting the environment and implementing soil and water conservation measures. However, predicting soil loss while meeting the criteria of high precision, efficiency, and generalizability remains a challenge. Therefore, this study first used three machine learning (ML) algorithms, namely, random forest (RF), support vector machine (SVM), and artificial neural network (ANN) to develop soil loss models and predict soil loss rates (SLRs). These soil loss models were constructed using field observation data with an average SLR of 1756.48 t/km2 from rainfall events and small watersheds in the hilly-gully region of the Loess Plateau, China. During training, testing and generalizability stages, the average coefficients of determination from the RF, SVM, and ANN models were 0.903, 0.860, and 0.836, respectively. Similarly, the average Nash-Sutcliffe coefficients of efficiency from the RF, SVM and ANN models were 0.893, 0.791 and 0.814, respectively. These results indicated that MLs have superior predictive performance and generalizability, and broad prospects for predicting SLRs. This study also demonstrated that the RF model outperformed better than the SVM and ANN models. Therefore, the RF model was used to simulate the SLR of each small watershed in the Chabagou watershed. Our results showed the four-year (2017–2020) average annual SLR of the small watersheds ranged from 0.73 to 1.63 × 104 t/(km2∙a) in the Chabagou watershed. Additionally, the results also indicated the SLR of small watersheds under the rainstorm event with a 100-year recurrence interval was 4.4–51.3 times that of other rainfall events.Furthermore, this study confirmed that bare land was the predominant source of soil loss in the Chabagou watershed, followed by cropland land and grassland. This study helps to provide the theoretical basis for deploying soil and water conservation measures to realize the sustainable utilization of soil resources in the future. [Display omitted] • Three machine learning algorithms were first used to build soil loss models. • Random forest demonstrated the most favorable performance for soil loss modeling. • Soil loss caused by rainstorms was 4.4–51.3 times that of other rainfall events. • Bare land was the predominant source of soil loss. [ABSTRACT FROM AUTHOR]

Biodiversity datasets with high spatial resolution are critical prerequisites for river protection and management decision-making. However, traditional morphological biomonitoring is inefficient and only provides several site estimates, and there is an urgent need for new approaches to predict biodiversity on fine spatial scales throughout the entire river systems. Here, we combined the environmental DNA (eDNA) and remote sensing (RS) technologies to develop a novel approach for predicting the spatial distribution of aquatic insects with high spatial resolution in a disturbed subtropical Dongjiang River system of southeast China. First, we screened thirteen RS-based vegetation indices that significantly correlated with the eDNA-inferred richness of aquatic insects. In particular, the green normalized difference vegetation index (GNDVI) and normalized difference red-edge2 (NDRE2) were closely related to eDNA-inferred richness. Second, using the gradient boosting decision tree, our data showed that the spatial pattern of eDNA-inferred richness could achieve a high spatial resolution to 500 m reach and accurate prediction of more than 80%, and the prediction efficiency of the headwater streams (Strahler stream order = 1) was slightly higher than the downstream (Strahler stream order >1). Third, using the random forest algorithm, the spatial distribution of aquatic insects could reach a prediction rate of over 70% for the presence or absence of specific genera. Overall, this study provides a new approach to achieving high spatial resolution prediction of the distribution of aquatic insects, which supports decision-making on river diversity protection under climate changes and human impacts. [Display omitted] • EDNA and remote sensing datasets are combined to predict species distribution. • Thirteen RS-based vegetation indices are closely related to eDNA-inferred richness. • Aquatic insects can achieve spatial distribution prediction within 500 m reach. [ABSTRACT FROM AUTHOR]

According to frontier settlement theory, physical topography is a critical factor that shapes a region's psychological landscape. To determine whether physical topography also impacts generalized trust, we conducted an exploratory study to investigate the relationship between mountainousness and individual's generalized trust (N = 26,910) in China. The multilevel modeling analysis revealed positive associations between the standard deviation of elevation and generalized trust. Random Forest analyses confirmed mountainousness indicators as significant predictors of generalized trust and also uncovered a complex nonlinear relationship between these indicators and generalized trust. Our results revealed that individuals residing in China's mountainous areas are more prone to trust others. • The present research investigates the association between mountainousness and generalized trust in China. • The standard deviation of elevation is positively correlated with generalized trust. • Random forest analyzes reveal nonlinear relationships between mountainousness indicators and generalized trust. • Individuals residing in China's mountainous areas are more prone to trust others. [ABSTRACT FROM AUTHOR]

Over the past centuries, freshwater fish introductions and extinctions have been the major environmental and ecological crises in various water bodies in China. However, consequences of such crises on freshwater fish biodiversity in China remain only partially or locally studied. Furthermore, identifications of relatively sensitive areas along with stressors (i.e., environmental and anthropogenic drivers) influencing freshwater fish biodiversity patterns are still pending. Taxonomic, functional, and phylogenetic facets of biodiversity can well describe and evaluate the underlying processes affecting freshwater fish biodiversity patterns under different dimensionalities. Here we thus evaluated temporal changes in these facets of freshwater fish biodiversity as well as a new developed biodiversity index, multifaceted changes in fish biodiversity, for over a century at the basin level throughout China using both alpha and beta diversity approaches. We also identified the drivers influencing the changes in fish biodiversity patterns using random forest models. The results showed that fish assemblages in Northwest and Southwest China (e.g., Ili River basin, Tarim basin, and Erhai Lake basin) experienced extreme temporal and multifaceted changes in the facets of biodiversity compared with other regions, and environmental factors (e.g., net primary productivity, average annual precipitation, and unit area) largely drove these changes. Since fish faunas in over 80% of China's water bodies covering more than 80% of China's surface were currently undergoing taxonomic, functional, and phylogenetic homogenization, targeted conservation and management strategies should be proposed and implemented, especially for the areas with relatively high changes in biodiversity. [Display omitted] • A new multifaceted biodiversity index was developed to assess biodiversity impacts. • We comprehensively evaluated changes in freshwater fish biodiversity throughout China. • Extreme changes in fish biodiversity mostly occurred in Northwest and Southwest China. • Environmental factors largely drove the changes in fish biodiversity in China. • Adapted conservation and management strategies were proposed for vulnerable areas. [ABSTRACT FROM AUTHOR]

Fourfinger threadfin (Eleutheronema tetradactylum) are the commercially important fish along the southern coast of China. The economic value of wild E. tetradactylum was much higher than their farmed counterparts, therefore mislabeling of production methods may lead to premium prices. In the present study, multi-element signatures of fin ray were used to determine the wild caught and pond-cultured E. tetradactylum from southern coast of China. The elemental composition of fish calcified structures was related to the ambient water environment, and could record the water chemistry difference between the aquaculture pond and the natural seawater. Our results demonstrated that multi-element compositions of fish fin rays were significantly different between the wild and cultured fish. Linear discriminant analysis (LDA) and random forest (RF) model correctly discriminated the wild and cultured E. tetradactylum. The classification accuracies of wild and cultured E. tetradactylum were 100% by LDA. The classification accuracies of identifying the source of cultured E. tetradactylum were 95%. However, the fin ray elemental signatures could not differentiate the different wild groups. This strategy provides a promising alternative method to protect against mislabeling of E. tetradactylum. • Fin ray can be used to determine elemental characteristics for fourfinger threadfin. • Fin ray elemental signatures distinguishedcultured and wild fourfinger threadfin. • Fin ray elemental signatures identified the source of cultured fourfinger threadfin. [ABSTRACT FROM AUTHOR]

Municipal solid waste management and disposal in China have significantly evolved since 2000. Due to China's vast land area and significant socioeconomic and geographic disparities, nationwide waste management strategies need to be further evaluated. This study quantified the effect of social, economic, and geographic drivers on municipal waste disposal activities in 31 provincial-level administrative regions from 2003 to 2020, by establishing a methodology integrated by two-way fixed effects regression model, panel random forest, and spatial Durbin model. The results showed, in the past two decades, socio-economic-geo indicators significantly co-decided the landfill and incineration activities. In particular, the explanatory ability of GDP per capita was above 45%, while land resources and city size also showed great significance. Spatial autocorrelation analysis showed that the relationship between landfill/incineration rates and socio-economic-geo drivers changed notably from unobvious to significant with economic growth. Furthermore, the local economy and land resources displayed more impact than those of the neighboring regions, while sci-tech and education showed clear spatial spillover effects. Chinese government would carefully assess the full-scale promotion policy of incineration plants, landfill is still hold as a reasonable option for regions with specific socio-economic-geo conditions. [Display omitted] • Quantifying the effect socio-economic-geo drivers on municipal waste disposal. • An integrated methodology was established. • The explanatory ability of per capital GDP surpassed 45% for waste disposal. • Economic and land drivers affect the local more than its neighboring regions. • A significant spatial spill-over effect was displayed by sci-tech and education. [ABSTRACT FROM AUTHOR]

Although studies have estimated the associations of PM 2.5 with total mortality or cardiopulmonary mortality, few have comprehensively examined cause-specific mortality risk and burden caused by ambient PM 2.5. Thus, this study investigated the association of short-term exposure to PM 2.5 with cause-specific mortality using a death-spectrum wide association study (DWAS). Individual information of 5,450,764 deaths during 2013–2018 were collected from six provinces in China. Daily PM 2.5 concentration in the case and control days were estimated by a random forest model. A time-stratified case-crossover study design was applied to estimate the associations (access risk, ER) of PM 2.5 with cause-specific mortality, which was then used to calculate the population-attributable fraction (PAF) of mortality and the corresponding mortality burden caused by PM 2.5. Each 10 μg/m3 increase in PM 2.5 concentration (lag03) was associated with a 0.80 % [95 % confidence interval (CI): 0.73 %, 0.86 %] rise in total mortality. We found greater mortality effect at PM 2.5 concentrations < 50 μg/m3. Stratified analyses showed greater ERs in females (1.01 %, 95 %CI: 0.91 %, 1.11 %), children ≤ 5 years (2.17 %, 95 %CI: 0.85 %, 3.51 %), and old people ≥ 70 years. We identified 33 specific causes (level 2) of death which had significant associations with PM 2.5 , including 16 circulatory diseases, 9 respiratory diseases, and 8 other causes. The PAF estimated based on the overall association between PM 2.5 and total mortality was 3.16 % (95 %CI: 2.89 %, 3.40 %). However, the PAF was reduced to 2.88 % (95 %CI: 1.88 %, 3.81 %) using the associations of PM 2.5 with 33 level 2 causes of death, based on which 250.15 (95 %CI: 163.29, 330.93) thousand deaths were attributable to short-term PM 2.5 exposure across China in 2019. Overall, this study provided a comprehensive picture on the death-spectrum wide association between PM 2.5 and morality in China. We observed robust positive cause-specific associations of PM 2.5 with mortality risk, which may provide more precise basis in assessing the mortality burden of air pollution. [Display omitted] • We estimate association of short-term exposure to PM 2.5 with cause-specific mortality. • A time-stratified case-crossover study design was used in 5.4 million deaths in China. • Short-term exposure to PM 2.5 is associated with mortality from 33 specific causes. • Mortality burden of PM 2.5 using associations with total mortality was overestimated. • The results provide more precise basis in assessing mortality burden of air pollution. [ABSTRACT FROM AUTHOR]

Cyanobacteria blooms in aquaculture ponds harm the harvesting of aquatic animals and threaten human health. Therefore, it is crucial to identify key drivers and develop methods to predict cyanobacteria blooms in aquaculture water management. In this study, we analyzed monitoring data from 331 aquaculture ponds in central China and developed two machine learning models - the least absolute shrinkage and selection operator (LASSO) regression model and the random forest (RF) model - to predict cyanobacterial abundance by identifying the key drivers. Simulation results demonstrated that both machine learning models are feasible for predicting cyanobacterial abundance in aquaculture ponds. The LASSO model (R 2 = 0.918, MSE = 0.354) outperformed the RF model (R 2 = 0.798, MSE = 0.875) in predicting cyanobacteria abundance. Farmers with well-equipped aquaculture ponds that have abundant water monitoring data can use the nine environmental variables identified by the LASSO model as an operational solution to accurately predict cyanobacteria abundance. For crude ponds with limited monitoring data, the three environmental variables identified by the RF model provide a convenient solution for useful cyanobacteria prediction. Our findings revealed that chemical oxygen demand (COD) and total organic carbon (TOC) were the two most important predictors in both models, indicating that organic carbon concentration had a close relationship with cyanobacteria growth and should be considered a key metric in water monitoring and pond management of these aquaculture ponds. We suggest that monitoring of organic carbon coupled with phosphorus reduction in feed usage can be an effective management approach for cyanobacteria prevention and to maintain a healthy ecological state in aquaculture ponds. • Two machine learning models were developed for cyanobacteria abundance predicting. • Organic carbon concentration was identified as a key metric for cyanobacteria bloom. • The LASSO model was provided which can precisely predict cyanobacteria abundance. • Organic carbon monitoring coupled with phosphorus reduction in feed were suggested. [ABSTRACT FROM AUTHOR]

Mushroom poisoning is a highly publicized food safety concern, and commercial fraud by adulterating cheap species in the wild mushroom supply chain often occurs. To safeguard the lives and property of consumers, it is necessary to develop accurate methods to discriminate the edibility and species of wild mushrooms. Near-infrared (NIR) spectroscopy has become a popular analytical tool due to its key advantages. This work aimed to investigate the feasibility of discriminating the edibility and species of wild bolete mushrooms using NIR spectroscopy-based two-dimensional correlation spectroscopy (2DCOS) combined with Red-Green-Blue (RGB) image analysis and multivariate analysis methods. The results showed that the data driven version of soft independent modeling of class analogy (DD-SIMCA) model had excellent sensitivity (0.98) but the specificity was only 0.59. This model was not suitable to accurately discriminate the edibility of boletes, but can be used for screening a potentially poisonous species of boletes (Caloboletus calopus). As for species discrimination, random forests (RF) model had great classification and generalization ability and the accuracy of the training set and test set was 97.22% and 100%, respectively. Therefore, FT-NIR spectroscopy combined with DD-SIMCA and RF models had the potential to discriminate the edibility and species of wild bolete mushrooms. • Seven major boletes species were collected from 14 regions in southwestern China. • 2DCOS combined with RGB and multivariate analysis methods to discriminate boletes. • First discrimination of wild boletes edibility by using FT-NIR and DD-SIMCA model. • Combined unsupervised (PCA and HCA) and supervised methods (PLS-DA, RF and SVM). [ABSTRACT FROM AUTHOR]

The development of coal resources is necessary, but it has a huge negative impact on land, ecology, and the environment. With the increasing awareness of environmental protection and the requirements of related regulations, the design and practice of reclamation projects run through the mining life cycle and continue for a long time after the coal production. High-precision monitoring of mining disturbance and reclamation, quantifying the degree and time of vegetation disturbance and restoration, is of great significance to minimize the environmental effect of mining. Remote sensing, widely used as efficient monitoring tool, but there is not enough research on disturbance and reclamation monitoring taking into account large-scale areas and high temporal and spatial accuracy. Especially when mining sites remain unknown, how to distinguish the disturbance of coal mining and other human activities affecting the surface land cover has become a challenge. Therefore, this paper proposed a method to reconstruct the time series of mining disturbance and reclamation in a large area by using the POI (point of interest) and Landsat time series images using multiple buffer analysis methods. The process includes: (1) Retrieval of POI in the study area based on the public mining list using Python crawler, and buffering 100 km for preliminary extraction of potential mining areas; (2) Using spectral index mask and random forest algorithm to accurately extract the exposed coal on the Google Earth Engine (GEE) platform; (3) Buffering 10 km to identify the occurrence of disturbance and reclamation, using pixel-based temporal trajectory identification of LandTrendr algorithm under GEE. The method successful detect the change points of surface coal mining disturbance and reclamation in eastern Inner Mongolia of China. The results show that: (1) The method can effectively identify the extent of surface coal mining disturbance and reclamation, and the overall extraction accuracy is 81%. (2) Surface coal mining disturbance in eastern Inner Mongolia was concentrated in 2006–2011. By 2020, the total disturbed area is 627.8 km2, with an average annual disturbance of 18.5 km2, and the annual maximum disturbance to the ground reached 64.6 km2 in 2008. With the total reclaimed area being 236.3 km2, the reclamation rate is about 37.6%. This study provides a systematic solution and process for monitoring the disturbance and reclamation of surface coal mining in a large range with little known about the mines' location. It can effectively identify the mining disturbance and reclamation process which can also be extended to other areas, providing a quantitative assessment of mining disturbance and reclamation, which can support further ecological restoration decision-making. [Display omitted] • A remote sensing procedure of surface coal mine classification, disturbance and reclamation monitoring is developed. • Landsat, random forest, web scraping, and Google Earth Engine has been used to detect 73 surface coal mining sites. • 0.94% of the total study area has been disturbed by surface mining. • The developed procedure is able to reveal the surface coal mine reclamation pattern. [ABSTRACT FROM AUTHOR]

Traditional Chinese fermented shrimp paste is a national geographical indication product with a distinctly regional flavor. The great commercial value and highly appreciated aroma urgently require establishing reliable methods to define the origin of shrimp paste and dissect the aroma essence. Therefore, in this study, flavoromics, chemometrics, and data augmented machine learning were performed to analyze shrimp paste from different regions of Bohai Bay, China. The results showed that shrimp paste contained several volatile compounds, including sulfur-containing compounds, nitrogen-containing compounds, aldehydes, and alcohols. In addition, chemometric and flavor association networks indicated that higher salt content produces some volatile compounds, such as 2-heptanone and phenylethanol. Furthermore, the prominent fruitiness and fermented aromas were associated with some key aroma substances, such as (E)-2-octenal and phenylethanol. Finally, a classification model for the origin identification of shrimp paste was developed. The results showed that seven trained machine learning models, including random forest (RF), support vector machine (SVM), and artificial neural network (ANN), were able to accurately (100%) identify the origin of shrimp paste. In summary, this study provides a theoretical support and application basis for identifying the origin and protection of the characteristic geographical flavor of shrimp paste. • First analysis of shrimp paste from different regions of China using machine learning. • OPLS-DA reveals the relationship of fermentation information and volatile components. • The visual flavor network was constructed based on key aroma substances. • RF and ANN are reliable ways to identify the origin of shrimp paste. [ABSTRACT FROM AUTHOR]

In northern China, central heating, as an important source of urban particulate matter (UPM), causes more than half of the air pollution during the heating season and has significant spatial-temporal heterogeneity. Owing to the limitations of stationary air monitoring networks, few studies distinguish between heating/non-heating seasons and few have been conducted in urban areas. However, fixed monitoring cannot accurately capture the dynamic exposure of residents to UPM, and there is a lack of comprehensive evaluation of the factors affecting UPM. Therefore, this study used wearable Sniffer 4D equipment to monitor the concentrations of UPM (PM 1 , PM 2.5 , and PM 10) in selected typical areas of Shenyang City from March 2019 to February 2020. A random forest model was combined with land use and point-of-interest data to analyze the contributions and marginal effects of multiple influences on UPM, in both heating and non-heating seasons. The results showed that in the eastern part of the study area, UPM showed completely opposite spatial distribution characteristics during the two seasons. The concentrations of UPM were higher during the heating season than during the non-heating season. The results indicated that temperature and humidity were important factors in diffusing UPM. The production and operation of boilers were important for the production of UPM. In two-dimensional landscape pattern indices, the percentage of forest and Shannon diversity index were the first and second most important factors, respectively. The three-dimensional pattern of buildings had important effects on the transport and diffusion of UPM (landscape height range >100, floor area ratio >1.3, and landscape volume density >5). Wearable devices could monitor the real situation of residents' exposure to UPM and quantify the factors influencing the spatial-temporal distribution of UPM in an ecological sense. These results provide a scientific basis for urban planning and for health risk reduction for residents. [Display omitted] • Wearable devices used for long-term urban areas particulate pollution exposure. • Quantified the influencing factors of urban particulate matter in ecological sense. • Human impact on urban particulate matter raised 2–3 times in the heating season. • Boilers were major impact on urban particulate matter apart from natural factors. [ABSTRACT FROM AUTHOR]

Sludge management accounts for a large share of economic costs and energy consumption in wastewater treatment and has become an important challenge for urban sustainability. Accurately predicting regional sludge generation by incorporating spatial characteristics to find carbon reduction potential can help improve the sustainability of wastewater treatment and formulate tailored mitigation strategies. This is especially true in China, which along with the world's largest wastewater treatment capacity, also faces rapid growth in sludge generation, insufficient disposal capacity, and low recycling rates. In this study, data from 3,495 wastewater treatment plants were used to screen sludge driving factors in 338 Chinese cities, and a random forest regression model was used to predict future sludge generation and associated carbon emissions at the provincial level under Shared Socioeconomic Pathways. The results showed that GDP, built-up area, and carbon content of foods had relatively high q-values (above 0.5). Indicating that economic development, urban form, and food consumption were the major factors influencing sludge generation. By 2060, total sludge generation in China is expected to be between 195% and 241% of the 2017 total in the five SSP scenarios. Improved disposal methods should be implemented to reduce carbon emissions in regions that have stable sludge growth, while fast-developing areas should focus on sludge reduction. In Central and Western China, it may be possible to control sludge generation at the source given expected changes in dietary structure and urban compact development change, while in Eastern China greater use of anaerobic digestion and sludge-to-resource treatment may be more effective. Combining anaerobic digestion and low carbon disposal methods could reduce about 50 Mts GHG emissions in China by 2060. [Display omitted] • Urban form, economy, and food are key factors affecting sludge generation. • A random forest regression was built to fit the nonlinear trends of sludge growth. • A declining growth in provincial sludge generation was forecast until 2060. • Carbon reduction strategies should be based on regional sludge patterns. • A Low Carbon Disposal method can reduce carbon emissions by 50% by 2060. [ABSTRACT FROM AUTHOR]

Carbon (C) and nitrogen (N) cycles of terrestrial ecosystems play key roles in global climate change and ecosystem sustainability. In recent decades, climate change has threatened the nutrient balance of dryland ecosystems. However, its impact on soil organic carbon (SOC) and soil total nitrogen (STN) in drylands of China are still unclear. In this study, the structural equation model (SEM) was used to explain the relationship between environmental variables used by the best model and SOC or STN. Then Adaptive Boosting Regressor (AdaBoost), Gradient Boosting Regression (GBRT), Extreme gradient boosting Regression (XGBoost) and Random Forest Regression (RF) were used to establish the prediction model of SOC and STN based on soil samples along with environmental variables. The performance of these models was assessed based on a 10-fold cross-validation method using three statistical indicators. Finally, we predicted the SOC and STN of soil samples from 2000 to 2019 based on the best model. Overall, the RF model performed better at predicting SOC and STN in drylands than the other three prediction models (AdaBoost, GBRT, XGBoost). Climate factors were the main factors affecting SOC and STN in the study area. In the Alashan, a dryland in northern China, the precipitation in the growing season increased from 2000 to 2019, at a rate of 12.9 mm/decade. During the same period, the annual sunshine duration significantly decreased by 66 h/decade. Along with interannual hydrothermal variability, SOC showed a fluctuating upward trend at a rate of 0.04 g/kg/decade, while STN exhibited a fluctuating downward trend at 0.003 g/kg/decade from 2000 to 2019. Due to the effects of climate change, dryland were considered as potential sites for carbon sequestration. However, due to the annual hydrothermal variance causing dynamic annual changes, it was deemed unstable. Moreover, it would cause STN loss, which might reduce soil fertility. More attention should be paid to STN monitoring in dryland in the future. • The Random Forest Regression model performed better to predict SOC and STN in dryland. • The precipitation in the growing season increased and the annual sunshine duration significantly decreased in Alashan area. • Climate change increased SOC and decreased STN in study areas. [ABSTRACT FROM AUTHOR]

Heavy metals are a group of anthropogenic contaminants in estuary ecosystems. Bacteria in estuaries counteract the highly concentrated metal toxicity through metal resistance genes (MRGs). Presently, metagenomic technology is popularly used to study MRGs. However, an easier and less expensive method of acquiring MRG information is needed to deepen our understanding of the fate of MRGs. Thus, this study explores the feasibility of using a machine learning approach—namely, random forests (RF)—to predict MRG abundance based on the 16S rRNA amplicon sequenced datasets from subtropical estuaries in China. Our results showed that the total MRG abundance could be predicted by RF models using bacterial composition at different taxonomic levels. Among them, the relative abundance of bacterial phyla had the highest predicted accuracy (71.7 %). In addition, the RF models constructed by bacterial phyla predicted the abundance of six MRG types and nine MRG subtypes with substantial accuracy (R2 > 0.600). Five bacterial phyla (Firmicutes, Bacteroidetes, Patescibacteria, Armatimonadetes, and Nitrospirae) substantially determined the variations in MRG abundance. Our findings prove that RF models can predict MRG abundance in South China estuaries during the wet season by using the bacterial composition obtained by 16S rRNA amplicon sequencing. • An easier and cheaper way of acquiring metal resistance genes (MRGs) was established. • Random forest models by bacterial compositions can accurately predict MRG levels. • Random forest models based on bacterial phyla had the highest predicted accuracy. • Several bacterial phyla determined the MRG variations have been identified. [ABSTRACT FROM AUTHOR]

Reliable forecast of municipal solid waste (MSW) generation is crucial for sustainable and efficient waste management. Big data analysis is a novel method to forecast MSW more accurately. Thus, this study employs five kinds of supervised machine learning approaches including linear regression, polynomial regression, support vector machine, random forest, and extreme gradient boosting (XGBoost) to examine their forecast performances. China's MSW generation from 2020 to 2060 under five shared socioeconomic pathways (SSPs) is further predicted and the mechanisms between MSW generation and socioeconomic features are explored. Results show that population and GDP are two dominant indicators in MSW prediction, and XGBoost model is proved to be effective in MSW forecast. MSW generation of China in 2060 is estimated to be 464–688 megatons under different SSPs scenarios, about four to six times of that in 2000. SSP3 that has the most population, least GDP and the highest climate change challenges is the only scenario showing a potential of MSW peak during the study period. The key for MSW increase is mainly the increase of per capita MSW caused by GDP. Finally, several policy recommendations are raised to reduce the overall MSW generation. • China's MSW generation under SSPs is predicted using machine learning methods. • Population and GDP are identified to be two dominant factors in MSW prediction. • XGBoost is proved to be superior to other prediction models. • The highest MSW generation appears under the fossil-fueled development pathway. • Per capita MSW but not GDP should be restricted for fast developing countries. [ABSTRACT FROM AUTHOR]

Litterfall production is a major process within forest ecosystems that plays a crucial role in the global carbon cycle. Accordingly, studies have explored the abiotic and biotic features that influence litterfall production. In addition to traditional statistical models, the rapid development of nonparametric and nonlinear machine learning models, such as random forest (RF), light gradient boosting machine (LightGBM), and categorical boosting (CatBoost), have provided new methods of predicting the production of forest litterfall. Here, we evaluated the ability of the abovementioned models and mixed effect random forest (MERF) models to predict total annual litterfall production—based on several abiotic and biotic features—using 968 records from 314 forest sites covering the full geographical range of Chinese forests. In general, machine learning models were found to outperform linear mixed models. In particular, the MERF models ranked the highest in terms of performance (R 2 = 0.7), which may be attributed to their ability to characterize nonlinear relationships between features and litterfall production. The key drivers were climate-related features and forest age, with the mean annual temperature and age positively correlated with litterfall production. Furthermore, the correlation between forest type and litterfall production was more significant for needleleaf forests than for other forest types. For needleleaf and broadleaf forests in several regions in China, the future litterfall production was predicted to be the highest under IPCC representative concentration pathway (RCP) 8.5, followed by RCP 4.5, RCP 2.6, and the original scenarios (sample data). Improved models to better understand and estimate litterfall production in forests at present and in the future are required for forest management planning to minimize the negative impacts of climate change on forest ecosystems. • Machine learning models demonstrated improved performance in predicting litterfall. • Regional prediction was improved by characterizing the non-linear relationships. • The MERF models ranked the highest in terms of performance (R 2 [0.7], RMSE [0.31]). • Climate-related features and forest age were the key drivers affecting litterfall. • Future litterfall generation was predicted to be the highest under RCP 8.5. [ABSTRACT FROM AUTHOR]

More and more hyper-spectral satellites will be used to estimate total suspended matter (TSM) in waters instead of multi-spectral satellites, such as China's Gaofen-5 and Zhuhai-1. Although they have not been widely used because of the consistency of sampling and image time. Hence, the study based on measured hyper-spectroscopy is important for applying to hyper-spectral satellites. Fractional-order derivatives (FODs) considers more detailed spectral information, and it is a better spectral preprocessing method than conventional integer-order derivatives. The application and analysis of FODs for spectra in waters is rare. If FOD is successfully applied to estimate TSM, the TSM mapping with FOD using hyper-spectral satellites will be meaningful. Based on these points, this study aimed to apply FOD to predict TSM and to prove the prediction feasibility of FOD in waters. Different prediction models and eight FOD transformation processes with increment of 0.25 per step for 392 spectral reflectance data from China were used and compared. The prediction models include the optimum models of the single wavelength, ratio index, difference index and TSM index at each FOD order, and the random forest (RF) model with all wavelengths was also used. Discrete wavelet transform (DWT) was used to reduce noise and improve the model accuracy after using FOD. Our results achieved the followings First, FOD enhanced spectral characteristics at 500–600 nm and 800 nm that were affected by TSM. Second, the correlation between TSM and FOD spectra was enhanced (e.g., the correlation coefficients of 19 wavelengths (789–807 nm) of 0.75-order were higher than 0.8 but the original spectra were not). Third, FOD improved the performance of different prediction models, and the RF model from 0.5-order to 1.25-order derivative spectra all led good results (). Fourth, DWT can reduce the noise and improve the performance, and FOD-DWT model of 1.25-order led the R2 of 0.84, RMSE of 16.30 and MAPE of 78.62 in validation. Overall, our results suggest that FOD can improve the prediction performance for most models, and the optimum order of some models is not integer. Our results also provide a reference for predicting other water quality parameters and mapping these parameters using hyper-spectral satellites. The accurate estimation of TSM is helpful for protecting ecological and social environments. • Fractional-order derivative enhances the correlation with total suspended matter. • The performance of fractional-order derivative is better than that of integer order derivative. • Discrete wavelet transform effectively reduces the noise and improve the performance. • Fractional-order derivative provides a possibility to map total suspended matter using hyper-spectral images. [ABSTRACT FROM AUTHOR]

Habitat models can be used to analyze the relationships between species distribution and environmental variables. Different models and response variables are usually selected to evaluate the habitat of species according to their ecological traits. In this study, six habitat models were compared to quantify the spatio-temporal distribution of small yellow croaker (Larimichthys polyactis) in Haizhou Bay, including Generalized Additive Model (GAM), K-Nearest Neighbor (KNN), Multivariate Adaptive Regression Splines (MARS), Generalized Boosted regression Model (GBM), Random forest (RF) and Artificial neural network (NN). We also compared the performance of habitat models with four types of response variables, i.e., (1) presence–absence, (2) habitat ranks, (3) probability and (4) abundance. Model performances were evaluated and assessed through cross validations. Principal component analysis (PCA) and coefficient of variation (CV) were applied to compare the performance of these habitat models. Results showed that machine learning algorithms were better than statistical methods. Random forest (RF) performed the best in identifying the spatio-temporal distribution of small yellow croakers based on PCA and CV analysis. The importance of explanatory variables varied with the type of response variables in habitat modeling. In addition, facing different response variables, species showed different response relationships to explanatory variables. This species was found mainly distributed in the central coastal areas of Haizhou Bay at depths between 10 and 30 m according to predicated distribution maps by optimal models. Bottom temperature, bottom salinity and prey had great impacts on spatial distributions of small yellow croaker. This study proposed a framework to evaluate the performance of different habitat models and response variables, which could be extended to other marine organisms and facilitate the application of habitat models. This study enhances our understanding of the underlying ecological mechanisms that drive spatial distribution of marine species. 1. Six habitat models with four types of response variables, i.e., (1) presence–absence, (2) habitat ranks, (3) probability and (4) abundance, were used to quantify the spatio-temporal distribution of small yellow croaker. 2. Principal component analysis (PCA) and coefficient of variation (CV) were applied to compare the performance of these habitat models based on results of cross validations. 3. The environmental data extracted from the Finite-Volume Community Ocean Model (FVCOM) was used to predict the spatial distribution of small yellow croaker. 4. We proposed a frame work to evaluate the performance of different habitat models and response variables, which could be extended to other marine organisms and improve the application of habitat models. [ABSTRACT FROM AUTHOR]

Accurate prediction of dissolved oxygen time series is important for improving the water environment and aiding water resource management. In this study, four stand-alone models including multiple linear regression (MLR), support vector machine (SVM), artificial neural network (ANN) and random forest (RF), and four hybrid models based on wavelet transform (WT) including WT-MLR, WT-SVM, WT-ANN and WT-RF were used to predict the daily dissolved oxygen (DO) at 1–5-day lead times in the Dongjiang River Basin, China. To make the prediction robust, the maximal information coefficient (MIC) was used to capture comprehensive information between DO and explanatory variables. The 5-fold cross validation grid search approach was used to optimize parameters of machine learning tools. Two types of frameworks of WT: direct framework (i.e., only the explanatory variables were decomposed) and multicomponent framework (i.e., both explanatory variables and target variables were decomposed) were used to construct hybrid models. The results show that MIC extracts four optimal explanatory variables: previous DO, water temperature, air temperature and air pressure. Four evaluation parameters including correlation coefficient (R), Nash-Sutcliffe efficiency (NSE), mean absolute error (MAE) and root mean square error (RMSE) indicate that the prediction accuracy decreases as the lead time changes from 1 to 5 days. In terms of the stand-alone models, MLR model outperforms the other three models with higher NSE values of 0.616–0.921, and lower RMSE values of 0.503–1.111. With regard to the hybrid models, WT-ANN and WT-MLR models exhibit higher performance, and multicomponent framework performs better than direct framework in all hybrid models. In general, the multicomponent framework of WT can improve the prediction accuracy of stand-alone models at a certain degree, while the direct framework shows no obvious advantage. • Using stand-alone models and hybrid wavelet-based models to estimate river dissolved oxygen levels at 1–5-day lead times. • Extracting four explanatory variables using maximal information coefficient. • Hybrid wavelet-based models outperform stand-alone models at a certain degree. • The multicomponent framework of wavelet transform outperforms the direct framework. [ABSTRACT FROM AUTHOR]

Due to the COVID-19 outbreak, the Chinese government implemented nationwide traffic restrictions and self-quarantine measures from January 23 to April 8 (in Wuhan), 2020. We estimated how these measures impacted ambient air pollution and the subsequent consequences on health and the health-related economy in 367 Chinese cities. A random forests modeling was used to predict the business-as-usual air pollution concentrations in 2020, after adjusting for the impact of long-term trend and weather conditions. We calculated changes in mortality attributable to reductions in air pollution in early 2020 and health-related economic benefits based on the value of statistical life (VSL). Compared with the business-as-usual scenario, we estimated 1239 (95% CI: 844–1578) PM 2.5 -related deaths were avoided, as were 2777 (95% CI: 1565–3995) PM 10 -related deaths, 1587 (95% CI: 98–3104) CO-related deaths, 4711 (95% CI: 3649–5781) NO 2 -related deaths, 215 (95% CI: 116–314) O 3 -related deaths, and 1088 (95% CI: 774–1421) SO 2 -related deaths. Based on the reduction in deaths, economic benefits for in PM 2.5 , PM 10 , CO, NO 2 , O 3 , and SO 2 were 1.22, 2.60, 1.36, 4.05, 0.20, and 0.95 billion USD, respectively. Our findings demonstrate the substantial benefits in human health and health-related costs due to improved urban air quality during the COVID lockdown period in China in early 2020. • The business-as-usual (BAU) air pollution were predicted, after adjusting for long-term trends and weather conditions. • The observed national average concentrations over February and March, 2020 were significantly lower than BAU scenario. • Considerable health and health-related economic benefits were estimated due to air quality improvements. • Higher health and economic benefits applied mostly in east, north, and central provinces. [ABSTRACT FROM AUTHOR]

Turbidity is an indication of water quality and enables the growth of pathogenic microorganisms. For drinking water treatment plants (DWTPs), violent fluctuations in turbidity are highly disruptive to operational performance due to the lag in process parameter adjustments. Such risks must be carefully managed to guarantee safe drinking water. Machine learning techniques have been proven to be effective for modeling complex nonlinear environmental systems, and this study adopted such a technique to develop a model for predicting source water turbidity for DWTPs to allow DWTPs to make proactive interventions in advance. A random forest (RF) model used preprocessed (empirical mode decomposition and quartile rejecting) meteorological factors (wind speed, wind direction, air temperature, and rainfall) as the input variables, to establish the turbidity prediction of a lake with significant turbidity in China's South Tai Lake. The modeling process included four main stages: (1) source data analysis, (2) raw data preprocessing, (3) modeling and tuning, and (4) model evaluation. The results of the RF model indicated that the correlation coefficient between the predicted and actual sequences is over 0.7, and more than 55% of the predicted values could control the errors within 20% compared to the actual measured values, suggesting that machine learning techniques are suitable for predicting the turbidity of raw source water. It was found that the RF model can provide a modest performance boost because of its stronger capacity to capture nonlinear interactions in the data. The findings of this study can inform the development of turbidity prediction models using readily available meteorological forecast data. The model can be applied to other DWTPs using similar shallow lakes as water sources. [Display omitted] • RF model driven by meteorological variables was developed for turbidity prediction. • The comprehensive effect of wind field on turbidity was described quantitatively. • Empirical mode decomposition and quartile rejecting were used to preprocess the data. • The prediction model performed comparably or better than its counterparts reported. [ABSTRACT FROM AUTHOR]

The frequency and intensity of compound hot extremes will be likely to increase in the context of global warming. Epidemiological studies have demonstrated the adverse effect of simple hot extreme events on mortality, but little is known about the effects of compound hot extremes on mortality. Daily meteorological, demographic, and mortality data during 2011–2017 were collected from 160 streets in Guangzhou City, China. We used distributed lag non-linear model (DLNM) to analyze the associations of different hot extremes with mortality risk in each street. Street-specific associations were then combined using a meta-analysis approach. To assess the spatial distribution of vulnerability to compound hot extremes, vulnerable characteristics at street level were selected using random forest model, and then we calculated and mapped spatial vulnerability index (SVI) at each street in Guangzhou. At street level, compared with normal day, compound hot extreme significantly increased mortality risk (relative risk(RR)=1.43, 95%CI:1.28–1.59) with higher risk for female (RR=1.54 [1.35–1.76]) and the elderly(RR for aged 65–74=1.41 [1.14–1.74]; RR for ≥75years=1.63 [1.45–1.84]) than male (RR=1.32 [1.15–1.52]) and population <65 years (RR=1.01 [0.83–1.22]). Areas with high vulnerability were in the urban center and the edge of suburban. High proportion of population over 64 years old in urban center, and high proportions of outdoor workers and population with illiteracy in suburban areas were the determinants of spatial vulnerability. We found that compound hot extreme significantly increased mortality risk at street level, which is modified by socio-economic and demographic factors. Our findings help allocate resources targeting vulnerable areas at fine-spatial scale.° • Compound hot extreme increased 43% mortality compared to normal day with high vulnerability for the elderly and female. • Areas with high vulnerability were in the urban center and the edge of suburban. • High proportion of the elderly or outdoor workers or population with illiteracy contribute to spatial vulnerability. [ABSTRACT FROM AUTHOR]

Cadmium (Cd) is a highly toxic heavy metal that occurs widely in the environment and poses extensive threats to human health, animals, and plants. This study aims to identify and apportion multi-source and multi-phase Cd pollution from natural and anthropogenic inputs using ensemble models that include random forest (RF) in agricultural soils on Karst areas. The contributions of natural and anthropogenic factors to Cd accumulation were quantitatively assessed using the RF machine learning method. The results revealed that the main influencing factors were pH, organic carbon (C org), and elevation. Moreover, the interaction effects of pH and C org on distance and elevation were also quantified and visualised. It is observed that pH and C org had stronger effects on soil Cd concentration than that of distance when pH > 7.02 and C org > 1.53. In other words, higher Cd content in the soil along roadways may be caused by the interaction of distance, pH and C org , with pH and C org playing the dominant role in our case. Moreover, the maximum contribution of a single factor, elevation, to Cd concentration was about 0.13 mg/kg, and its interactions reached 1.082 mg/kg and 0.83 mg/kg, respectively, when combined with pH and C org at 194.0 m. However, with increasing elevation, pH and C org gradually took over the leading roles. This result not only gives us a quantitative understanding of the relationship between the factors that affect soil cadmium accumulation, but also provides an accurate method for source apportionment of heavy metals in soil. • Natural factors play a dominant role in Soil Cd accumulation in karst area of southern China. • Quantified the contributions of anthropogenic and natural factors to soil Cd accumulation using the random forest method. • The RF and partial dependence graphs were useful for quantifying and visualising the interactions among factors. [ABSTRACT FROM AUTHOR]

Identification of risk factors for antibiotic treatment failure is urgently needed in acute exacerbations of chronic obstructive pulmonary disease (AECOPD). Here we investigated the relationship between sputum microbiome and clinical outcome of choice of initial antibiotics during hospitalization of AECOPD patients. Sputum samples of 41 AECOPD patients and 26 healthy controls were collected from Guangzhou Medical University, China. Samples were processed for 16S rRNA gene-based microbiome profiling. Thirty patients recovered with initial antibiotic treatment (antibiotic success or AS), while 11 patients showed poor outcome (antibiotic failure or AF). Substantial differences in microbiome were observed in AF versus AS patients and healthy controls. There was significantly decreased alpha diversity and increased relative abundances of Pseudomonas , Achromobacter , Stenotrophomonas and Ralstonia in AF patients. Conversely, Prevotella , Peptostreptococcus , Leptotrichia and Selenomonas were depleted. The prevalence of Selenomonas was markedly reduced in AF versus AS patients (9.1 % versus 60.0 %, P = 0.004). The AF patients with similar microbiome profiles in general responded well to the same new antibiotics in the adjusted therapy, indicating sputum microbiome may help guide the adjustment of antibiotics. Random forest analysis identified five microbiome operational taxonomic units together with C-reactive protein, procalcitonin and blood neutrophil count showing best predictability for antibiotic treatment outcome (area under curve 0.885). Functional inference revealed an enrichment of microbial genes in xenobiotic metabolism and antimicrobial resistance in AF patients, whereas genes in DNA repair and amino acid metabolism were depleted. Sputum microbiome may determine the clinical outcome of initial antibiotic treatment and be considered in the risk management of antibiotics in AECOPD. [ABSTRACT FROM AUTHOR]