Monitored natural attenuation is commonly used to manage petroleum hydrocarbon-contaminated groundwater. However, it requires periodic, costly grab sampling. We propose a cost-effective, real-time groundwater monitoring proof-of-concept machine learning (ML) framework using in-situ sensors—pH, dissolved oxygen, electrical conductivity, and redox potential—to detect benzene, ethylbenzene, and xylenes (BEX). We built upon the established correlations between hydrocarbon concentrations and in-situ water quality parameters (iWQPs). Due to limited field data, we validated the framework using datasets at virtual wells within a simulated aquifer from our previously developed reactive transport model. In this application, we detected the spreading of pollution downstream of the established pollution plume. The used framework is a binary classification system that flags contamination at virtual downstream wells. We compared five ML classifiers, i.e. Logistic Regression, Random Forest, XGBoost, Multi-layer Perceptron, and Support Vector Classifier, for early warning when BEX reached or exceeded the regulatory threshold of 5 μg/L. The models were trained on virtual wells at and near the source zone and predicted contamination before BEX reached the threshold at downstream virtual wells. This reflects the spatial variability in flow and reaction dynamics that altered BEX-iWQP relationships. Scenario analyses revealed the ML models' sensitivity to aquifer properties, i.e., hydraulic conductivity, electrical conductivity, and electron acceptor availability. We also assessed the impact of sensor noise and seasonal fluctuations on iWQPs. We found that even moderate levels of noise (10–20 %) can significantly affect model accuracy, particularly when the noise was introduced into the test data. Therefore, we recommended to combine hardware stabilization with adaptive smoothing techniques. With these approaches, our proposed framework remains promising for providing early warnings of plume migration toward sensitive receptors.

Petroleum products have contaminated groundwater with harmful organic compounds, such as benzene, toluene, ethylbenzene, and xylenes (BTEX). Collecting and analyzing polluted groundwater samples is expensive and undertaken infrequently. However, quick remedial action in case of unexpected events requires continuous monitoring. In-situ water quality sensors (pH, EC, DO, ORP) may show correlations with the components of dissolved petroleum hydrocarbon (PHC) such as aromatics and non-volatile mobile fractions. Correlations are prerequisite to ultimately develop real-time prediction models. Since suitable field data sets are limited, we simulated the fate of hydrocarbons in groundwater under various realistic conditions using a reactive transport model as novel approach to explore when, where, and why correlations occur. A stationary oil source zone continuously dissolved at the top of a heterogeneous and shallow sandy aquifer over a two-dimensional cross-section. Our model considered transient conditions (fluctuating water table) and spatially uniform hydrogeochemical composition. We observed a strong correlation between PHCs and water quality sensors (rolling Spearman's correlation > |0.8|) at varying periods. These correlations are strongly affected by the location of observation wells, the aquifer's hydraulic conductivity, and the availability of calcite and oxide minerals, and other electron acceptors. DO and ORP are significant for the early detection of hydrocarbon contamination, whereas pH and EC are important features for the long-term monitoring of hydrocarbons. Our findings lay the foundation for the subsequent development of a data analysis model to detect and estimate in real time PHC levels in groundwater using in-situ water quality sensors.

To assist reaching net-zero emissions, the dissolved carbon in the ocean can be extracted to enable an indirect air capture. An electrochemical bipolar membrane electrodialysis (BPMED) is a sustainable method for such capture. The BPMED enables a pH-swing that manipulates the oceanic carbonate-equilibrium using electricity. However, at alkaline-pH, an in-situ process suffers from inorganic fouling within the stack, increasing the cost of capture. In the current work, we investigate fouling management strategies including fouling control (i.e., membrane- configuration and current-flow rate optimization) and fouling removal methods. Fouling removal methods including air and CO₂(g) sparging, dissolved CO₂ (aq) cleaning, back-pressure, flow rate increase, and acid-wash are investigated under accelerated fouling conditions. The stack configuration containing the BPM-AEM pairs shows 4 × lower fouling than the BPM-CEM stack, while the carbonate-extraction and faradaic efficiency are similar for both configurations. From the scaling removal methods, only the acid wash combined with the back-pressure removed all the inorganic fouling, recovering both the cell voltage and pressure drop to their initial values. Upon the air sparging, the total cell voltage and pressure drop increased even more due to the trapped gas inside the netted spacers. Cleaning via dissolved and gaseous CO₂ decreases the cell pH, dissolving hydroxide/carbonate-based fouling, but decreases the carbonate-removal significantly which is not preferred. Applying the back-pressure and higher flow rates decelerated the scaling buildup but was not enough to remove the fouling. Using BPM-AEM stacks in combination with periodic acid cleaning has potential as resilient oceanic carbon removal via BPMED.

Bipolar membrane electrodialysis (BPMED) can provide a sustainable route to capture the oceanic-dissolved inorganic carbon (DIC) using an electrochemical pH-swing concept. Previous works demonstrated how gaseous CO₂ (through acidification) can be obtained from ocean water, and how carbonate minerals can be provided via ex situ alkalinization. In this work, we present, for the first time, the in situ mineralization via the alkalinization route using both real and synthetic seawater. An in situ pH-swing, inside of the BPMED cell, allows reducing the energy consumption of the oceanic-DIC capture. We demonstrate that, by accurately controlling the applied current density and cell residence time, the energy required for the process can be indeed lowered through facilitating an optimized pH in the cell (i.e., base-pH 9.6–10). Within this alkaline pH-window, we capture between 60% (for real seawater) up to 85% (for synthetic seawater) of the DIC from the feed, together with minor Mg(OH)₂ precipitates. The CaCO₃(s) production increases linearly with the applied current density, with a theoretical maximum extraction of 97 %. The energy consumption is dominated by the ohmic losses and BPM-overpotential. Through tuning the current density and flow rate, we optimised the energy consumption by applying a mild in situ pH-swing of ca. pH 3.2 – 9.75 (for real seawater). As a result, aragonite was extracted by using of 318 ± 29 kJ mol⁻¹ CaCO₃(s) (i.e., ca. 0.88 kWh kg⁻¹ CaCO₃(s)) from real seawater in a cell containing ten bipolar – cation exchange membrane cell pairs, which is less than half of the previously lowest energy consumption for carbonate mineralization from (synthetic) seawater.

The practical energy required for water dissociation reaction in bipolar membrane (BPM) is still substantially higher compared to the thermodynamic equivalent. This required energy is determined by the bipolar membrane voltage, consisting of (1) thermodynamic potential and (2) undesired voltage losses. Since the pH gradient over the BPM affects both voltage components, in this work, pH gradient is leveraged to decrease the BPM-voltage. We investigate the effect of four flow orientations: 1) co-flow, 2) counter-flow, 3) co-recirculation, and 4) counter-recirculation, on the pH gradient and BPM-voltage, using an analytical model and chronopotentiometry experiments. The analytical model predicts the experimentally obtained pH accurately and confirms the importance of the flow orientation in determining the longitudinal pH gradient profile over the BPM in the bulk solution. However, in contrast to the simulated results, our observations show the effect of flow orientations on the BPM-voltage to be insignificant under practical operating conditions. When the water dissociation reaction in the BPM is dominant, the internal local pH inside of the membrane determines its final voltage, shadowing the effect of the external pH-gradient in the bulk solution. Therefore, although changing the flow orientation affects the bulk pH, it does not influence the local pH at the BPM junction layer and hence the BPM-voltage. Instead, opportunities for reducing the membrane voltage are in the realm of improved catalysts and ion exchange layers of the BPM.