Data Analytics for Environmental Science and Engineering Research

Meta-analysis of wastewater microbiome for antibiotic resistance profiling

The microbial composition and stress molecules are main drivers influencing the development and spread of antibiotic resistance bacteria (ARBs) and genes (ARGs) in the environment. A reliable and rapid method for identifying associations between microbiome composition and resistome remains challenging. In the present study, secondary metagenome data of sewage and hospital wastewaters were assessed for differential taxonomic and ARG profiling. Subsequently, Random Forest (RF)-based ML models were used to predict ARG profiles based on taxonomic composition and model validation on hospital wastewaters. Total ARG abundance was significantly higher in hospital wastewaters (15 ppm) than sewage (5 ppm), while the resistance towards methicillin, carbapenem, and fluoroquinolone were predominant. Although, Pseudomonas constituted major fraction, Streptomyces, Enterobacter, and Klebsiella were characteristic of hospital wastewaters. Prediction modeling showed that the relative abundance of pathogenic genera Escherichia, Vibrio, and Pseudomonas contributed most towards variations in total ARG count. Moreover, the model was able to identify host-specific patterns for contributing taxa and related ARGs with >90% accuracy in predicting the ARG subtype abundance. More than >80% accuracy was obtained for hospital wastewaters, demonstrating that the model can be validly extrapolated to different types of wastewater systems. Findings from the study showed that the ML approach could identify ARG profile based on bacterial composition including 16S rDNA amplicon data, and can serve as a viable alternative to metagenomic binning for identification of potential hosts of ARGs. Overall, this study demonstrates the promising application of ML techniques for predicting the spread of ARGs and provides guidance for early warning of ARBs emergence.

Boosting Sinh Cosh Optimizer and arithmetic optimization algorithm for improved prediction of biological activities for indoloquinoline derivatives

Quantitative Structure Activity Relation (QSAR) models are mathematical techniques used to link structural characteristics with biological activities, thus considered a useful tool in drug discovery, hazard evaluation, and identifying potentially lethal molecules. The QSAR regulations are determined by the Organization for Economic Cooperation and Development (OECD). QSAR models are helpful in discovering new drugs and chemicals to treat severe diseases. In order to improve the QSAR model's predictive power for biological activities of naturally occurring indoloquinoline derivatives against different cancer cell lines, a modified machine learning (ML) technique is presented in this paper. The Arithmetic Optimization Algorithm (AOA) operators are used in the suggested model to enhance the performance of the Sinh Cosh Optimizer (SCHO). Moreover, this improvement functions as a feature selection method that eliminates superfluous descriptors. An actual dataset gathered from previously published research is utilized to evaluate the performance of the suggested model. Moreover, a comparison is made between the outcomes of the suggested model and other established methodologies. In terms of pIC50 values for different indoloquinoline derivatives against human MV4-11 (leukemia), human HCT116 (colon cancer), and human A549 (lung cancer) cell lines, the suggested model achieves root mean square error (RMSE) of 0.6822, 0.6787, 0.4411, and 0.4477, respectively. The biological application of indoloquinoline derivatives as possible anticancer medicines is predicted with a high degree of accuracy by the suggested model, as evidenced by these findings.

Predicting removal efficiency of organic pollutants by soil vapor extraction based on an optimized machine learning method

Soil vapor extraction (SVE) was a cost-effective technology for remediating volatile and semi-volatile organic contaminated soils. Many factors, including SVE parameters, soil properties, and contaminant characteristics, significantly influenced the remediation efficiency of SVE. The optimal conditions for organic pollutants removal efficiency were site-specific and varied among studies. Therefore, a generalized model was needed to predict the remediation efficiency of SVE in organic contaminated soils. This study employed machine learning to predict the removal efficiency of organic pollutants by SVE. The model's development was based on a trainset, and its predictive capabilities were evaluated using a testset. An XGBoost (XGB) model was derived from literature data (R2 = 0.9728). Time, pollutant type, and temperature were identified as the three most important features affecting SVE remediation efficiency. The accuracy (R2 = 0.9799) and universality of the model were enhanced through an optimization scheme. The developed XGB model demonstrated the ability to predict the removal efficiency of organic pollutants by considering all collected influential factors. The mechanism of multi-factor interaction on remediation efficiency was clarified. Overall, this study would contribute to evaluating the remediation potential of SVE for specific organic contaminated soils, aiding in maximizing the removal efficiency of organic pollutants under optimal conditions.

Machine-learning-driven discovery of metal-organic framework adsorbents for hexavalent chromium removal from aqueous environments

HYPOTHESIS

Metal-organic frameworks (MOFs) have been widely studied for Cr(VI) adsorption in water. Theoretically, numerous MOFs can be synthesised by assembling diverse metals and ligands. However, the traditional manual experimentation for screening high-performance MOFs is resource-intensive and inefficient.

EXPERIMENTS

A screening strategy for MOFs based on machine learning was proposed for the adsorption and removal of Cr(VI) from water. By collecting the characteristics of MOFs and the experimental parameters of Cr(VI) adsorption from the literature, a dataset was constructed to predict the adsorption performance. Among the six regression models, the model trained by the extreme gradient boosted tree algorithm had the best performance and was used to simulate the adsorption and screen potential high-performance adsorbents.

FINDINGS

Structure-property analysis indicated that prepared MOF adsorbents with properties of 0.37 < largest cavity diameter < 0.71 nm, 0.18 < pore volume < 0.57 cm3/g, 412 < specific surface area < 1588 m2/g, 0.43 < void fraction < 0.62 will achieve enhanced adsorption of Cr(VI) in water. High-performance adsorbents were successfully screened using a combination of machine-learning prediction and analysis. Experiments were conducted to verify the exceptional adsorption capacity of UiO-66 and MOF-801. This method effectively identified adsorbents and accelerated the development of new MOF adsorbents for contaminant removal, providing a novel approach for the discovery of superior adsorbents.

Enhancing compound confidence in suspect and non-target screening through machine learning-based retention time prediction

The retention time (RT) of contaminants of emerging concern (CECs) in liquid chromatography-high-resolution mass spectrometry (LC-HRMS) is crucial for database matching in non-targeted screening (NTS) analysis. In this study, we developed a machine learning (ML) model to predict RTs of CECs in NTS analysis. Using 1051 CEC standards, we evaluated Random Forest (RF), XGBoost, Support Vector Regression (SVR), and Artificial Neural Network (ANN) with molecular fingerprints and chemical descriptors to establish an optimal model. The SVR model utilizing chemical descriptors resulted in good predictive capacity with R2ext = 0.850 and r2 = 0.925. The model was further validated through laboratory NTS compound characterization. When applied to examine CEC occurrence in a large wastewater treatment plant, we identified 40 level S1 CECs (confirmed structure by reference standard) and 234 level S2 compounds (probable structure by library spectrum match). The model predicted RTs for level S2 compounds, leading to the classification of 153 level S2 compounds with high confidence (ΔRT <2 min). The model served as a robust filtering mechanism within the analytical framework. This study emphasizes the importance of predicted RTs in NTS analysis and highlights the potential of prediction models. Our research introduces a workflow that enhances NTS analysis by utilizing RT prediction models to determine compound confidence levels.

POPs identification using simple low-code machine learning

Effectively identifying persistent organic pollutants (POPs) with extensive organic chemical datasets poses a formidable challenge but is of utmost importance. Leveraging machine learning techniques can enhance this process, but previous models often demanded advanced programming skills and high-end computing resources. In this study, we harnessed the simplicity of PyCaret, a Python-based package, to construct machine-learning models for POP screening based on 2D molecular descriptors. We compared the performance of these models against a deep convolutional neural network (DCNN) model. Utilising minimal Python code, we generated several models that exhibited superior or comparable performance to the DCNN. The most outstanding performer, the Light Gradient Boosting Machine (LGBM), achieved an accuracy of 96.20 %, an AUC of 97.70 %, and an F1 score of 82.58 %. This model outshone the DCNN model. Furthermore, it excelled in identifying POPs within the REACH PBT and compiled industrial chemical lists. Our findings highlight the accessibility and simplicity of PyCaret, requiring only a few lines of code, rendering it suitable for non-computing professionals in environmental sciences. The ability of low code machine learning tools (e.g. PyCaret) to facilitate model comparison and interpretation holds promise, encouraging prompt assessment and management of chemical substances.

Estuarine environmental flow assessment based on the flow-ecological health index relation model: a case study in Yangtze River Estuary, China

Environmental flow (e-flow) is the water demand of one given ecosystem, which can become the flow regulation target for protection and restoration of river or estuarine ecosystems. In this study, an e-flow assessment based on the flow-ecological health index (EHI) relation model was conducted to improve ecosystem health of the Yangtze River Estuary (YRE). Monitoring data of hydrology, biology, and water environment in the last decades were used for the model establishment. For the description of the YRE ecosystem, an EHI system was developed by cumulative frequency distribution curves and adaption of national standards. After preprocessing original flow values into proportional flow values, the generalized additive model and Monte Carlo random sampling were used for the establishment of the flow-EHI relation model. From the model calculation, the e-flow assessment results were that, in proportional flow values, the suitable flow range was 1.05-1.35, and the optimum flow range was 1.15-1.25 (flows in Yangtze River Datong Station). For flow regulation in two crucial periods, flows of 42,630-65,545 m3/s or over 14,675 m3/s are needed for the suitable flow of YRE in summer (June-August) or January, respectively. An adaptive management framework of ecological health-based estuarine e-flow assessment for YRE was contrived due to the limitation of current established model when facing the extreme drought in summer, 2022. The methodology and framework in this study are expected to provide valuable management and data support for the sustainable development of estuarine ecosystems and to bring inspiration for further studies at even continental or global levels.

Optimizing the development of contaminated land in China: Exploring machine-learning to identify risk markers

Often available for use, previously developed land, which includes residential and commercial/industrial areas, presents a significant challenge due to the risk to human health. China's 2018 release of health risk assessment standards for land reuse aimed to bridge this gap in soil quality standards. Despite this, the absence of representative indicators strains risk managers economically and operationally. We improved China's land redevelopment approach by leveraging a dataset of 297,275 soil samples from 352 contaminated sites, employing machine learning. Our method incorporating soil quality standards from seven countries to discern patterns for establishing a cost-effective evaluative framework. Our research findings demonstrated that detection costs could be curtailed by 60% while maintaining consistency with international soil standards (prediction accuracy = 90-98%). Our findings deepen insights into soil pollution, proposing a more efficient risk assessment system for land redevelopment, addressing the current dearth of expertise in evaluating land development in China.

Using machine learning to explore oxyanion adsorption ability of goethite with different specific surface area

In this study, we developed prediction models for the adsorption of divalent and trivalent oxyanions on goethite based on machine learning algorithms. After verifying the reliability of the models, the importance of goethite specific surface area (SSA) and the average oxyanion adsorption capacities of goethite with different SSAs were calculated by shapley additive explanations (SHAP) importance analysis and partial dependence (PD) analysis. Despite there were differences in the feature importance of divalent and trivalent oxyanions, the contribution of goethite's SSA to the adsorption amount ranked the fourth based on SHAP importance, indicating SSA played the important role in oxyanion adsorption. Meanwhile, the PD values of SSA and the optimized complexation constants from surface complexation modeling (SCM) both indicated a non-monotonic relationship between the goethite with different SSA and its oxyanions binding capacity. When the total site concentration and crystal face composition were used as the machine learning model input features, the SHAP importance values of crystal faces and the PD decomposition results indicated that the (001) face showed the crucial influence on oxyanions adsorption amount. These findings demonstrated the important role of crystal face composition in goethite's adsorption ability, and provided a theoretical explanation for the variations of oxyanions adsorption amount on different SSA goethite.

Integrating molecular descriptors for enhanced prediction: Shedding light on the potential of pH to model hydrated electron reaction rates for organic compounds

Hydrated electron reaction rate constant (ke-aq) is an important parameter to determine reductive degradation efficiency and to mitigate the ecological risk of organic compounds (OCs). However, OC species morphology and the concentration of hydrated electrons (e-aq) in water vary with pH, complicating OC fate assessment. This study introduced the environmental variable of pH, to develop models for ke-aq for 701 data points using 3 descriptor types: (i) molecular descriptors (MD), (ii) quantum chemical descriptors (QCD), and (iii) the combination of both (MD + QCD). Models were screened using 2 descriptor screening methods (MLR and RF) and 14 machine learning (ML) algorithms. The introduction of QCDs that characterized the electronic structure of OCs greatly improved the performance of models while ensuring the need for fewer descriptors. The optimal model MLR-XGBoost(MD + QCD), which included pH, achieved the most satisfactory prediction: R2tra = 0.988, Q2boot = 0.861, R2test = 0.875 and Q2test = 0.873. The mechanistic interpretation using the SHAP method further revealed that QCDs, polarizability, volume, and pH had a great influence on the reductive degradation of OCs by e-aq. Overall, the electrochemical parameters (QCDs, pH) related to the solvent and solute are of significance and should be considered in any future ML modeling that assesses the fate of OCs in aquatic environment.

Machine Learning in Environmental Research: Common Pitfalls and Best Practices

Machine learning (ML) is increasingly used in environmental research to process large data sets and decipher complex relationships between system variables. However, due to the lack of familiarity and methodological rigor, inadequate ML studies may lead to spurious conclusions. In this study, we synthesized literature analysis with our own experience and provided a tutorial-like compilation of common pitfalls along with best practice guidelines for environmental ML research. We identified more than 30 key items and provided evidence-based data analysis based on 148 highly cited research articles to exhibit the misconceptions of terminologies, proper sample size and feature size, data enrichment and feature selection, randomness assessment, data leakage management, data splitting, method selection and comparison, model optimization and evaluation, and model explainability and causality. By analyzing good examples on supervised learning and reference modeling paradigms, we hope to help researchers adopt more rigorous data preprocessing and model development standards for more accurate, robust, and practicable model uses in environmental research and applications.

Integrating low-cost sensor monitoring, satellite mapping, and geospatial artificial intelligence for intra-urban air pollution predictions

There is a growing need to apply geospatial artificial intelligence analysis to disparate environmental datasets to find solutions that benefit frontline communities. One such critically needed solution is the prediction of health-relevant ambient ground-level air pollution concentrations. However, many challenges exist surrounding the size and representativeness of limited ground reference stations for model development, reconciling multi-source data, and interpretability of deep learning models. This research addresses these challenges by leveraging a strategically deployed, extensive low-cost sensor (LCS) network that was rigorously calibrated through an optimized neural network. A set of raster predictors with varying data quality and spatial scales was retrieved and processed, including gap-filled satellite aerosol optical depth products and airborne LiDAR-derived 3D urban form. We developed a multi-scale, attention-enhanced convolutional neural network model to reconcile the LCS measurements and multi-source predictors for estimating daily PM2.5 concentration at 30-m resolution. This model employs an advanced approach by using the geostatistical kriging method to generate a baseline pollution pattern and a multi-scale residual method to identify both regional patterns and localized events for high-frequency feature retention. We further used permutation tests to quantify the feature importance, which has rarely been done in DL applications in environmental science. Finally, we demonstrated one application of the model by investigating the air pollution inequality issue across and within various urbanization levels at the block group scale. Overall, this research demonstrates the potential of geospatial AI analysis to provide actionable solutions for addressing critical environmental issues.

Glyphosate Separating and Sensing for Precision Agriculture and Environmental Protection in the Era of Smart Materials

The present article critically and comprehensively reviews the most recent reports on smart sensors for determining glyphosate (GLP), an active agent of GLP-based herbicides (GBHs) traditionally used in agriculture over the past decades. Commercialized in 1974, GBHs have now reached 350 million hectares of crops in over 140 countries with an annual turnover of 11 billion USD worldwide. However, rolling exploitation of GLP and GBHs in the last decades has led to environmental pollution, animal intoxication, bacterial resistance, and sustained occupational exposure of the herbicide of farm and companies' workers. Intoxication with these herbicides dysregulates the microbiome-gut-brain axis, cholinergic neurotransmission, and endocrine system, causing paralytic ileus, hyperkalemia, oliguria, pulmonary edema, and cardiogenic shock. Precision agriculture, i.e., an (information technology)-enhanced approach to crop management, including a site-specific determination of agrochemicals, derives from the benefits of smart materials (SMs), data science, and nanosensors. Those typically feature fluorescent molecularly imprinted polymers or immunochemical aptamer artificial receptors integrated with electrochemical transducers. Fabricated as portable or wearable lab-on-chips, smartphones, and soft robotics and connected with SM-based devices that provide machine learning algorithms and online databases, they integrate, process, analyze, and interpret massive amounts of spatiotemporal data in a user-friendly and decision-making manner. Exploited for the ultrasensitive determination of toxins, including GLP, they will become practical tools in farmlands and point-of-care testing. Expectedly, smart sensors can be used for personalized diagnostics, real-time water, food, soil, and air quality monitoring, site-specific herbicide management, and crop control.

Machine learning-assisted data filtering and QSAR models for prediction of chemical acute toxicity on rat and mouse

Machine learning (ML) methods provide a new opportunity to build quantitative structure-activity relationship (QSAR) models for predicting chemicals' toxicity based on large toxicity data sets, but they are limited in insufficient model robustness due to poor data set quality for chemicals with certain structures. To address this issue and improve model robustness, we built a large data set on rat oral acute toxicity for thousands of chemicals, then used ML to filter chemicals favorable for regression models (CFRM). In comparison to chemicals not favorable for regression models (CNRM), CFRM accounted for 67% of chemicals in the original data set, and had a higher structural similarity and a smaller toxicity distribution in 2-4 log₁₀ (mg/kg). The performance of established regression models for CFRM was greatly improved, with root-mean-square deviations (RMSE) in the range of 0.45-0.48 log₁₀ (mg/kg). Classification models were built for CNRM using all chemicals in the original data set, and the area under receiver operating characteristic (AUROC) reached 0.75-0.76. The proposed strategy was successfully applied to a mouse oral acute data set, yielding RMSE and AUROC in the range of 0.36-0.38 log₁₀ (mg/kg) and 0.79, respectively.

Accurate prediction of huanglongbing occurrence in citrus plants by machine learning-based analysis of symbiotic bacteria

Huanglongbing (HLB), the most prevalent citrus disease worldwide, is responsible for substantial yield and economic losses. Phytobiomes, which have critical effects on plant health, are associated with HLB outcomes. The development of a refined model for predicting HLB outbreaks based on phytobiome markers may facilitate early disease detection, thus enabling growers to minimize damages. Although some investigations have focused on differences in the phytobiomes of HLB-infected citrus plants and healthy ones, individual studies are inappropriate for generating common biomarkers useful for detecting HLB on a global scale. In this study, we therefore obtained bacterial information from several independent datasets representing hundreds of citrus samples from six continents and used these data to construct HLB prediction models based on 10 machine learning algorithms. We detected clear differences in the phyllosphere and rhizosphere microbiomes of HLB-infected and healthy citrus samples. Moreover, phytobiome alpha diversity indices were consistently higher for healthy samples. Furthermore, the contribution of stochastic processes to citrus rhizosphere and phyllosphere microbiome assemblies decreased in response to HLB. Comparison of all constructed models indicated that a random forest model based on 28 bacterial genera in the rhizosphere and a bagging model based on 17 bacterial species in the phyllosphere predicted the health status of citrus plants with almost 100% accuracy. Our results thus demonstrate that machine learning models and phytobiome biomarkers may be applied to evaluate the health status of citrus plants.

Operational parameter prediction of electrocoagulation system in a rural decentralized water treatment plant by interpretable machine learning model

Electrocoagulation (EC) is a promising alternative for decentralized drinking water treatment in rural areas as a chemical-free technology. However, seasonal fluctuations of water quality in influent remain a significant challenge for rural decentralized water supply, which was a potential threat to water safety. The frequent operation was required to ensure the effluent water quality by the experienced technicians, who were in shortage in rural areas. If the operational parameters prediction model based on water quality could be established, it might reduce the dependence on technicians. Therefore, an artificial neural network (ANN) model combined with genetic algorithm (GA) was used to establish a prediction model for unattended intelligent operation. Data on water quality and operational parameters were collected from a practical EC system in a decentralized water treatment plant. Seven water quality parameters (e.g., turbidity, temperature, pH and conductivity) were selected as input variables and the operational current was employed as the output. A non-linear relationship between water quality parameters and the operational current was verified by correlation analysis and principal component analysis (PCA). The mean squared error (MSE) and coefficient of determination (R²) were used as evaluation indexes to optimize the structure of the GA-ANN model. Influent turbidity was identified to be crucial in the GA-ANN model by model interpretation using sensitivity analysis and scenario analysis. The Garson weight of turbidity in the seven input variables achieved 45.4%. The predictive accuracy of the GA-ANN model sharply declined from 90% to 67.1% when influent turbidity data were absent. In addition, it was estimated that energy consumption savings of the GA-ANN method declined by 14.2% in comparison with the gradient control method. This study verifies the feasibility and stability of machine learning strategy for unattended operation in the rural decentralized water treatment plant.

Global net biome CO2 exchange predicted comparably well using parameter-environment relationships and plant functional types

Accurate estimation and forecasts of net biome CO₂ exchange (NBE) are vital for understanding the role of terrestrial ecosystems in a changing climate. Prior efforts to improve NBE predictions have predominantly focused on increasing models' structural realism (and thus complexity), but parametric error and uncertainty are also key determinants of model skill. Here, we investigate how different parameterization assumptions propagate into NBE prediction errors across the globe, pitting the traditional plant functional type (PFT)-based approach against a novel top-down, machine learning-based "environmental filtering" (EF) approach. To do so, we simulate these contrasting methods for parameter assignment within a flexible model-data fusion framework of the terrestrial carbon cycle (CARDAMOM) at a global scale. In the PFT-based approach, model parameters from a small number of select locations are applied uniformly within regions sharing similar land cover characteristics. In the EF-based approach, a pixel's parameters are predicted based on underlying relationships with climate, soil, and canopy properties. To isolate the role of parametric from structural uncertainty in our analysis, we benchmark the resulting PFT-based and EF-based NBE predictions with estimates from CARDAMOM's Bayesian optimization approach (whereby "true" parameters consistent with a suite of data constraints are retrieved on a pixel-by-pixel basis). When considering the mean absolute error of NBE predictions across time, we find that the EF-based approach matches or outperforms the PFT-based approach at 55% of pixels-a narrow majority. However, NBE estimates from the EF-based approach are susceptible to compensation between errors in component flux predictions and predicted parameters can align poorly with the assumed "true" values. Overall, though, the EF-based approach is comparable to conventional approaches and merits further investigation to better understand and resolve these limitations. This work provides insight into the relationship between terrestrial biosphere model performance and parametric uncertainty, informing efforts to improve model parameterization via PFT-free and trait-based approaches.

Using machine learning models to predict the effects of seasonal fluxes on Plesiomonas shigelloides population density

Seasonal variations (SVs) affect the population density (PD), fate, and fitness of pathogens in environmental water resources and the public health impacts. Therefore, this study is aimed at applying machine learning intelligence (MLI) to predict the impacts of SVs on P. shigelloides population density (PDP) in the aquatic milieu. Physicochemical events (PEs) and PDP from three rivers acquired via standard microbiological and instrumental techniques across seasons were fitted to MLI algorithms (linear regression (LR), multiple linear regression (MR), random forest (RF), gradient boosted machine (GBM), neural network (NN), K-nearest neighbour (KNN), boosted regression tree (BRT), extreme gradient boosting (XGB) regression, support vector regression (SVR), decision tree regression (DTR), M5 pruned regression (M5P), artificial neural network (ANN) regression (with one 10-node hidden layer (ANN10), two 6- and 4-node hidden layers (ANN64), and two 5- and 5-node hidden layers (ANN55)), and elastic net regression (ENR)) to assess the implications of the SVs of PEs on aquatic PDP. The results showed that SVs significantly influenced PDP and PEs in the water (p < 0.0001), exhibiting a site-specific pattern. While MLI algorithms predicted PDP with differing absolute flux magnitudes for the contributing variables, DTR predicted the highest PDP value of 1.707 log unit, followed by XGB (1.637 log unit), but XGB (mean-squared-error (MSE) = 0.0025; root-mean-squared-error (RMSE) = 0.0501; R² =0.998; medium absolute deviation (MAD) = 0.0275) outperformed other models in terms of regression metrics. Temperature and total suspended solids (TSS) ranked first and second as significant factors in predicting PDP in 53.3% (8/15) and 40% (6/15), respectively, of the models, based on the RMSE loss after permutations. Additionally, season ranked third among the 7 models, and turbidity (TBS) ranked fourth at 26.7% (4/15), as the primary significant factor for predicting PDP in the aquatic milieu. The results of this investigation demonstrated that MLI predictive modelling techniques can promisingly be exploited to complement the repetitive laboratory-based monitoring of PDP and other pathogens, especially in low-resource settings, in response to seasonal fluxes and can provide insights into the potential public health risks of emerging pathogens and TSS pollution (e.g., nanoparticles and micro- and nanoplastics) in the aquatic milieu. The model outputs provide low-cost and effective early warning information to assist watershed managers and fish farmers in making appropriate decisions about water resource protection, aquaculture management, and sustainable public health protection.

Application of Isotopically Labeled Engineered Nanomaterials for Detection and Quantification in Soils via Single-Particle Inductively Coupled Plasma Time-of-Flight Mass Spectrometry

Finding and quantifying engineered nanomaterials (ENMs) in soil are challenging because of the abundance of natural nanomaterials (NNMs) with the same elemental composition, for example, TiO₂. Isotopically enriched ENMs may be distinguished from NNMs with the same elemental composition using single-particle inductively coupled plasma time-of-flight mass spectrometry (spICP-TOF-MS) to measure multiple isotopes simultaneously within each ENM and NNM in soil, but the minimum isotope enrichment needed for detection of ENMs in soil is not known. Here, we determined the isotope enrichment needed for ⁴⁷Ti-enriched TiO₂ ENMs to be detectable in soil and assessed the effects of weathering on those requirements for less soluble TiO₂ and more soluble CuO ENMs. The isotope-enriched ENMs were dosed into two different soils and were extracted and measured by spICP-TOF-MS after 1, 7, and 30 days. Isotope-enriched ENMs were recovered and detected for all three time points. The ⁴⁷Ti-enriched TiO₂ ENMs were detectable in Lufa 2.2 soil at a nominal dosed concentration of 10 mg-TiO₂ kg^-1 which is an environmentally relevant concentration in biosolid-amended soils. For distinguishing an ∼70 nm diameter TiO₂ ENM from TiO₂ NNMs in Lufa 2.2 soil, an ∼10 wt % ⁴⁷Ti isotope-enrichment was required, and this enrichment requirement increases as the particle size decreases. This study is the first to evaluate the tracking ability of isotope-enriched ENMs at an individual particle level in soil and provides guidance on the isotope enrichment requirements for quantification of ENMs made from Earth-abundant elements in soils.

Predicting the abundance of metal resistance genes in subtropical estuaries using amplicon sequencing and machine learning

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.

Enhancing Data Integration, Interoperability, and Reuse to Address Complex and Emerging Environmental Health Problems

Environmental health sciences (EHS) span many diverse disciplines. Within the EHS community, the National Institute of Environmental Health Sciences Superfund Research Program (SRP) funds multidisciplinary research aimed to address pressing and complex issues on how people are exposed to hazardous substances and their related health consequences with the goal of identifying strategies to reduce exposures and protect human health. While disentangling the interrelationships that contribute to environmental exposures and their effects on human health over the course of life remains difficult, advances in data science and data sharing offer a path forward to explore data across disciplines to reveal new insights. Multidisciplinary SRP-funded teams are well-positioned to examine how to best integrate EHS data across diverse research domains to address multifaceted environmental health problems. As such, SRP supported collaborative research projects designed to foster and enhance the interoperability and reuse of diverse and complex data streams. This perspective synthesizes those experiences as a landscape view of the challenges identified while working to increase the FAIR-ness (Findable, Accessible, Interoperable, and Reusable) of EHS data and opportunities to address them.

Data-Driven Machine Learning in Environmental Pollution: Gains and Problems

The complexity and dynamics of the environment make it extremely difficult to directly predict and trace the temporal and spatial changes in pollution. In the past decade, the unprecedented accumulation of data, the development of high-performance computing power, and the rise of diverse machine learning (ML) methods provide new opportunities for environmental pollution research. The ML methodology has been used in satellite data processing to obtain ground-level concentrations of atmospheric pollutants, pollution source apportionment, and spatial distribution modeling of water pollutants. However, unlike the active practices of ML in chemical toxicity prediction, advanced algorithms such as deep neural networks in environmental process studies of pollutants are still deficient. In addition, over 40% of the environmental applications of ML go to air pollution, and its application range and acceptance in other aspects of environmental science remain to be increased. The use of ML methods to revolutionize environmental science and its problem-solving scenarios has its own challenges. Several issues should be taken into consideration, such as the tradeoff between model performance and interpretability, prerequisites of the machine learning model, model selection, and data sharing.

Identifying Functional Groups that Determine Rates of Micropollutant Biotransformations Performed by Wastewater Microbial Communities

The goal of this research was to identify functional groups that determine rates of micropollutant (MP) biotransformations performed by wastewater microbial communities. To meet this goal, we performed a series of incubation experiments seeded with four independent wastewater microbial communities and spiked them with a mixture of 40 structurally diverse MPs. We collected samples over time and used high-resolution mass spectrometry to estimate biotransformation rate constants for each MP in each experiment and to propose structures of 46 biotransformation products. We then developed random forest models to classify the biotransformation rate constants based on the presence of specific functional groups or observed biotransformations. We extracted classification importance metrics from each random forest model and compared them across wastewater microbial communities. Our analysis revealed 30 functional groups that we define as either biotransformation promoters, biotransformation inhibitors, structural features that can be biotransformed based on uncharacterized features of the wastewater microbial community, or structural features that are not rate-determining. Our experimental data and analysis provide novel insights into MP biotransformations that can be used to more accurately predict MP biotransformations or to inform the design of new chemical products that may be more readily biodegradable during wastewater treatment.