Prediction of bioavailability and toxicity of complex chemical mixtures through machine learning models.

Empirical data from a 6-month mesocosms experiment were used to assess the ability and performance of two machine learning (ML) models, including artificial neural network (NN) and random forest (RF), to predict temporal bioavailability changes of complex chemical mixtures in contaminated soils amended with compost or biochar. From the predicted bioavailability data, toxicity response for relevant ecological receptors was then forecasted to establish environmental risk implications and determine acceptable end-point remediation. The dataset corresponds to replicate samples collected over 180 days and analysed for total and bioavailable petroleum hydrocarbons and heavy metals/metalloids content.

Linking bioavailability and toxicity changes of complex chemicals mixture to support decision making for remediation endpoint of contaminated soils.

A six-month laboratory scale study was carried out to investigate the effect of biochar and compost amendments on complex chemical mixtures of tar, heavy metals and metalloids in two genuine contaminated soils. An integrated approach, where organic and inorganic contaminants bioavailability and distribution changes, along with a range of microbiological indicators and ecotoxicological bioassays, was used to provide multiple lines of evidence to support the risk characterisation and assess the remediation end-point. Both compost and biochar amendment (p = 0.

Insights into mixed contaminants interactions and its implication for heavy metals and metalloids mobility, bioavailability and risk assessment.

Mobility of heavy metals at contaminated sites is mainly influenced by the soil physicochemical properties and environmental conditions, therefore assessing heavy metals (HMs) and metalloids fractionation can provide insights into their potential risk and the mechanisms that regulate bioavailability. A 12-months mesocosms experiment was setup to investigate the effect of physicochemical factors (pH, moisture, and temperature) and weathering (time) on HMs and metalloids fractionation in three different multi-contaminated soil matrices (low, medium, and high contamination) collected from a soil treatment facility located in the United Kingdom, and two rural contaminated soil samples. The study demonstrates that even though Pb and Zn were found associated with the exchangeable fraction in the soil with the highest contamination (total average Pb 3400 mg/kg, and total average Zn 2100 mg/kg in Soil C), neither the condition applied nor the weathering caused an increase in their mobility.