Soil health is a major environmental concern. Biochars are a promising solution to address both soil contamination and amendment. They represent a sustainable valorisation alternative for solid wastes produced in huge amounts, namely agroforestry residues and sludge from wastewater treatment plants. Biochar’s superior properties, enhanced pore structure and high specific surface area can contribute to restoring soil quality, by adsorbing several pollutants (e.g., pharmaceutical compounds, pesticides, and metals) from water and soil, enhancing water retention capacity, improving soil aggregation, regulating pH, and reducing the need for synthetic fertilisers. Multiple studies have reported removal efficiencies exceeding 70% for metals and 60% for organic compounds in soils, as well as over 40% for both organic compounds and metals in waters. These efficiencies depend on factors such as feedstock, pyrolysis conditions, modification strategies, and target contaminants. Recent advancements in the field have introduced both chemical and physical modifications that can enhance adsorption selectivity. This review provides a comprehensive analysis of the fundamentals of biochar production, modification strategies, and their environmental applications in soil remediation and water treatment. By comparing unmodified and modified biochars, this review highlights the crucial factors that influence the performance of this highly versatile and cost-effective solution.

Wastewater treatment plants operate under highly variable influent conditions, challenging process control and regulatory compliance. This study proposes a machine learning framework based on threshold artificial neural networks optimised with genetic algorithms (ANN-GA) to model effluent quality in a municipal treatment plant located in northern Portugal. Unlike conventional ANN approaches, the threshold structure divides the data into two operational regimes, enabling the model to capture regime-dependent behaviour in treatment performance. The three-year dataset included influent characteristics, operational parameters, and effluent quality indicators. Correlation analysis and principal component analysis were applied to characterise data variability and guide feature selection. Despite high influent variability, the system effectively removed organic matter and solids and reduced seasonal fluctuations, whereas nutrient removal remained limited. The ANN-GA models effectively described the removal of all regulated pollutants (R² values of 0.78-0.87 and RMSE of 0.94-12.5 mg L^-1), capturing non-linear and regime-dependent behaviours and outperforming simpler models. GA optimised pollutant-specific ANN structures, improving both accuracy and interpretability. The models consistently identified influent chemical oxygen demand, ammonium-nitrogen and aeration as key variables controlling pollutant removal. Organic matter removal was strongly influenced by the balance between influent composition, aeration and hydraulic conditions. Distinct operational regimes were identified, with influent suspended solids, aeration and flow rate governing nitrogen, phosphorus and chemical oxygen demand dynamics, respectively. Thus, the proposed framework enabled the identification of key drivers and operational thresholds influencing effluent quality, supporting improved process understanding and optimisation of wastewater treatment processes.