Two-Stage Machine Learning-Based Approach to Predict Points of Departure for Human Noncancer and Developmental/Reproductive Effects.

Chemical points of departure (PODs) for critical health effects are crucial for evaluating and managing human health risks and impacts from exposure. However, PODs are unavailable for most chemicals in commerce due to a lack of in vivo toxicity data. We therefore developed a two-stage machine learning (ML) framework to predict human-equivalent PODs for oral exposure to organic chemicals based on chemical structure. Utilizing ML-based predictions for structural/physical/chemical/toxicological properties from OPERA 2.9 as features (Stage 1), ML models using random forest regression were trained with human-equivalent PODs derived from in vivo data sets for general noncancer effects (n = 1,791) and reproductive/developmental effects (n = 2,228), with robust cross-validation for feature selection and estimating generalization errors (Stage 2). These two-stage models accurately predicted PODs for both effect categories with cross-validation-based root-mean-squared errors less than an order of magnitude. We then applied one or both models to 34,046 chemicals expected to be in the environment, revealing several thousand chemicals of moderate concern and several hundred chemicals of high concern for health effects at estimated median population exposure levels. Further application can expand by orders of magnitude the coverage of organic chemicals that can be evaluated for their human health risks and impacts.

Potential for Machine Learning to Address Data Gaps in Human Toxicity and Ecotoxicity Characterization.

Machine Learning (ML) is increasingly applied to fill data gaps in assessments to quantify impacts associated with chemical emissions and chemicals in products. However, the systematic application of ML-based approaches to fill chemical data gaps is still limited, and their potential for addressing a wide range of chemicals is unknown. We prioritized chemical-related parameters for chemical toxicity characterization to inform ML model development based on two criteria: (1) each parameter's relevance to robustly characterize chemical toxicity described by the uncertainty in characterization results attributable to each parameter and (2) the potential for ML-based approaches to predict parameter values for a wide range of chemicals described by the availability of chemicals with measured parameter data. We prioritized 13 out of 38 parameters for developing ML-based approaches, while flagging another nine with critical data gaps. For all prioritized parameters, we performed a chemical space analysis to assess further the potential for ML-based approaches to predict data for diverse chemicals considering the structural diversity of available measured data, showing that ML-based approaches can potentially predict 8-46% of marketed chemicals based on 1-10% with available measured data. Our results can systematically inform future ML model development efforts to address data gaps in chemical toxicity characterization.

Modelling micropollutant fate in sewer systems - A new systematic approach to support conceptual model construction based on in-sewer hydraulic retention time.

Conceptual sewer models are useful tools to assess the fate of micropollutants (MPs) in integrated wastewater systems. However, the definition of their model structure is highly subjective, and obtaining a realistic simulation of the in-sewer hydraulic retention time (HRT) is a major challenge without detailed hydrodynamic information or with limited measurements from the sewer network. This study presents an objective approach for defining the structure of conceptual sewer models in view of modelling MP fate in large urban catchments. The proposed approach relies on GIS-based information and a Gaussian mixture model to identify the model optimal structure, providing a multi-catchment conceptual model that accounts for HRT variability across urban catchment. This approach was tested in a catchment located in a highly urbanized Italian city and it was compared against a traditional single-catchment conceptual model (using a single average HRT) for the fate assessment of reactive MPs. Results showed that the multi-catchment model allows for a successful simulation of dry weather flow patterns and for an improved simulation of MP fate compared to the classical single-catchment model. Specifically, results suggested that a multi-catchment model should be preferred for (i) degradable MPs with half-life lower than the average HRT of the catchment and (ii) MPs undergoing formation from other compounds (e.g. human metabolites); or (iii) assessing MP loads entering the wastewater treatment plant from point sources, depending on their location in the catchment. Overall, the proposed approach is expected to ease the building of conceptual sewer models, allowing to properly account for HRT distribution and consequently improving MP fate estimation.

Modelling the fate of micropollutants in integrated urban wastewater systems: Extending the applicability to pharmaceuticals.

Pharmaceutical active compounds (PhACs) are a category of micropollutants frequently detected across integrated urban wastewater systems. Existing modelling tools supporting the evaluation of micropollutant fate in such complex systems, such as the IUWS_MP model library (which acronym IUWS stands for Integrated Urban Wastewater System), do not consider fate processes and fractions that are typical for PhACs. This limitation was overcome by extending the existing IUWS_MP model library with new fractions (conjugated metabolites, sequestrated fraction) and processes (consumption-excretion, deconjugation). The performance of the extended library was evaluated for five PhACs (carbamazepine, ibuprofen, diclofenac, paracetamol, furosemide) in two different integrated urban wastewater systems where measurements were available. Despite data uncertainty and the simplicity of the modelling approach, chosen to minimize data requirements, model prediction uncertainty overlapped with the measurements ranges across both systems, stressing the robustness of the proposed modelling approach. Possible applications of the extended IUWS_MP model library are presented, illustrating how this tool can support urban water managers in reducing environmental impacts from PhACs discharges.