Application of Machine Learning Methods for an Analysis of E-Nose Multidimensional Signals in Wastewater Treatment.

The work represents a successful attempt to combine a gas sensors array with instrumentation (hardware), and machine learning methods as the basis for creating numerical codes (software), together constituting an electronic nose, to correct the classification of the various stages of the wastewater treatment process. To evaluate the multidimensional measurement derived from the gas sensors array, dimensionality reduction was performed using the t-SNE method, which (unlike the commonly used PCA method) preserves the local structure of the data by minimizing the Kullback-Leibler divergence between the two distributions with respect to the location of points on the map. The k-median method was used to evaluate the discretization potential of the collected multidimensional data. It showed that observations from different stages of the wastewater treatment process have varying chemical fingerprints. In the final stage of data analysis, a supervised machine learning method, in the form of a random forest, was used to classify observations based on the measurements from the sensors array. The quality of the resulting model was assessed based on several measures commonly used in classification tasks. All the measures used confirmed that the classification model perfectly assigned classes to the observations from the test set, which also confirmed the absence of model overfitting.

Environmental Engineering Applications of Electronic Nose Systems Based on MOX Gas Sensors.

Nowadays, the electronic nose (e-nose) has gained a huge amount of attention due to its ability to detect and differentiate mixtures of various gases and odors using a limited number of sensors. Its applications in the environmental fields include analysis of the parameters for environmental control, process control, and confirming the efficiency of the odor-control systems. The e-nose has been developed by mimicking the olfactory system of mammals. This paper investigates e-noses and their sensors for the detection of environmental contaminants. Among different types of gas chemical sensors, metal oxide semiconductor sensors (MOXs) can be used for the detection of volatile compounds in air at ppm and sub-ppm levels. In this regard, the advantages and disadvantages of MOX sensors and the solutions to solve the problems arising upon these sensors' applications are addressed, and the research works in the field of environmental contamination monitoring are overviewed. These studies have revealed the suitability of e-noses for most of the reported applications, especially when the tools were specifically developed for that application, e.g., in the facilities of water and wastewater management systems. As a general rule, the literature review discusses the aspects related to various applications as well as the development of effective solutions. However, the main limitation in the expansion of the use of e-noses as an environmental monitoring tool is their complexity and lack of specific standards, which can be corrected through appropriate data processing methods applications.

Rapid Method of Wastewater Classification by Electronic Nose for Performance Evaluation of Bioreactors with Activated Sludge.

Currently, e-noses are used for measuring odorous compounds at wastewater treatment plants. These devices mimic the mammalian olfactory sense, comprising an array of multiple non-specific gas sensors. An array of sensors creates a unique set of signals called a "gas fingerprint", which enables it to differentiate between the analyzed samples of gas mixtures. However, appropriate advanced analyses of multidimensional data need to be conducted for this purpose. The failures of the wastewater treatment process are directly connected to the odor nuisance of bioreactors and are reflected in the level of pollution indicators. Thus, it can be assumed that using the appropriately selected methods of data analysis from a gas sensors array, it will be possible to distinguish and classify the operating states of bioreactors (i.e., phases of normal operation), as well as the occurrence of malfunction. This work focuses on developing a complete protocol for analyzing and interpreting multidimensional data from a gas sensor array measuring the properties of the air headspace in a bioreactor. These methods include dimensionality reduction and visualization in two-dimensional space using the principal component analysis (PCA) method, application of data clustering using an unsupervised method by Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, and at the last stage, application of extra trees as a supervised machine learning method to achieve the best possible accuracy and precision in data classification.

Comparison of the Moist Material Relative Permittivity Readouts Using the Non-Invasive Reflectometric Sensors and Microwave Antenna.

The article concerns the issue of non-invasive moisture sensing in building materials. Two techniques that enable evaluating the value of the relative permittivity of the material, being the measure of porous material moisture, have been utilized for the research. The first is the microwave technique that utilizes the non-contact measurement of velocity of microwave radiation across the tested material and the second is the time domain reflectometry (TDR) technique based on the measurement of electromagnetic pulse propagation time along the waveguides, being the elements of sensor design. The tested building material involved samples of red ceramic brick that differed in moisture, ranging between 0% and 14% moisture by weight. The main goal of the research was to present the measuring potential of both techniques for moisture evaluation as well as emphasize the advantages and disadvantages of each method. Within the research, it was stated that both methods provide similar measuring potential, with a slight advantage in favor of a microwave non-contact sensor over surface TDR sensor designs.

Determination of Time Domain Reflectometry Surface Sensors Sensitivity Depending on Geometry and Material Moisture.

The article concerns the electric techniques of moisture detection that are based on the evaluation of the apparent permittivity of the tested medium. The main goal of the research was to evaluate the non-invasive Time Domain Reflectometry (TDR) sensors' sensitivity by measuring the span of elements and material moisture. To that aim, two non-invasive sensor designs were investigated for their sensitivity in the evaluation of the apparent permittivity value of aerated concrete. Sensors A and B were characterized by the spacing between the measuring elements equal to 30 mm and 70 mm, respectively. The tested samples differed in moisture, ranging between 0 and 0.3 cm3/cm3 volumetric water content. Within the research, it was stated that in the case of the narrower sensor (A), the range of the sensor equals about 30 mm, and in the case of the wider design (B), it equals about 50 mm. Additionally, it was stated that material moisture influences the range of sensor influence. In the case of the dry and low-saturated material, it was not possible to evaluate the range of sensor sensitivity using the adopted method, whereas the range of sensor signal influence was visible for the moist material.

Soft Sensor Application in Identification of the Activated Sludge Bulking Considering the Technological and Economical Aspects of Smart Systems Functioning.

The paper presented the methodology for the construction of a soft sensor used for activated sludge bulking identification. Devising such solutions fits within the current trends and development of a smart system and infrastructure within smart cities. In order to optimize the selection of the data-mining method depending on the data collected within a wastewater treatment plant (WWTP), a number of methods were considered, including: artificial neural networks, support vector machines, random forests, boosted trees, and logistic regression. The analysis conducted sought the combinations of independent variables for which the devised soft sensor is characterized with high accuracy and at a relatively low cost of determination. With the measurement results pertaining to the quantity and quality of wastewater as well as the temperature in the activated sludge chambers, a good fit can be achieved with the boosted trees method. In order to simplify the selection of an optimal method for the identification of activated sludge bulking depending on the model requirements and the data collected within the WWTP, an original system of weight estimation was proposed, enabling a reduction in the number of independent variables in a model-quantity and quality of wastewater, operational parameters, and the cost of conducting measurements.

The Impact of Different Powdered Mineral Materials on Selected Properties of Aerobic Granular Sludge.

This study aimed to evaluate and compare the physical, chemical and biological properties of aerobic granular sludge from reactors with the addition of different powdered mineral materials. These properties have a significant impact on the efficiency of systems in which the biomass in granular form is used. Four identical granular sequencing batch reactors (GSBRs) were adopted for the research performed on a laboratory scale (R1-control reactor; R2, R3 and R4-with materials, PK, PG and PL respectively). The results indicate that the addition of powdered mineral materials improved the properties of biomass in reactors. The SVI5/SVI30 ratio values were significantly lower in the reactors with added materials (approx. 1.3 ± 0.3). The mean values of the sludge volume index at 30 min were the lowest in the R2 (39.8 ± 8.6 mL/g) and R4 (32.8 ± 10.7 mL/g) reactors. The settling velocity of biomass was the highest in the R2 reactor (15.4 ± 6.1 m/h). In the early days of the study, the highest extracellular polymeric substances (EPS) content was found in the biomass from the reactors to which the materials with higher Ca and Mg content were added (380.18-598.30 mg/g MLVSS). The rate of specific oxygen uptake (SOUR) by biomass indicated an insufficient biomass content in the R1 reactor-to 7.85 mg O2/(g MLVSS∙h)-while in the reactors with materials, the SOUR values were at the higher levels.

The Influence of COD Fraction Forms and Molecules Size on Hydrolysis Process Developed by Comparative OUR Studies in Activated Sludge Modelling.

The activated sludge models (ASMs) commonly used by the International Water Association (IWA) task group are based on chemical oxygen demand (COD) fractionations. However, the proper evaluation of COD fractions, which is crucial for modelling and especially oxygen uptake rate (OUR) predictions, is still under debate. The biodegradation of particulate COD is initiated by the hydrolysis process, which is an integral part of an ASM. This concept has remained in use for over 30 years. The aim of this study was to verify an alternative, more complex, modified (Activated Sludge Model No 2d) ASM2d for modelling the OUR variations and novel procedure for the estimation of a particulate COD fraction through the implementation of the GPS-X software (Hydromantis Environmental Software Solutions, Inc., Hamilton, ON, Canada) in advanced computer simulations. In comparison to the original ASM2d, the modified model more accurately predicted the OUR behavior of real settled wastewater (SWW) samples and SWW after coagulation-flocculation (C-F). The mean absolute relative deviations (MARDs) in OUR were 11.3-29.5% and 18.9-45.8% (original ASM2d) vs. 9.7-15.8% and 11.8-30.3% (modified ASM2d) for the SWW and the C-F samples, respectively. Moreover, the impact of the COD fraction forms and molecules size on the hydrolysis process rate was developed by integrated OUR batch tests in activated sludge modelling.

A Noninvasive TDR Sensor to Measure the Moisture Content of Rigid Porous Materials.

The article presents the potential application of the time domain reflectometry (TDR) technique to measure moisture transport in unsaturated porous materials. The research of the capillary uptake phenomenon in a sample of autoclaved aerated concrete (AAC) was conducted using a TDR sensor with the modified construction for non-invasive testing. In the paper the basic principles of the TDR method as a technique applied in metrology, and its potential for measurement of moisture in porous materials, including soils and porous building materials are presented. The second part of the article presents the experiment of capillary rise process in the AAC sample. Application of the custom sensor required its individual calibration, thus a unique model of regression between the readouts of apparent permittivity of the tested material and its moisture was developed. During the experiment moisture content was monitored in the sample exposed to water influence. Monitoring was conducted using the modified TDR sensor. The process was additionally measured using the standard frequency domain (FD) capacitive sensor in order to compare the readouts with traditional techniques of moisture detection. The uncertainty for testing AAC moisture, was expressed as RMSE (0.013 cm³/cm³) and expanded uncertainty (0.01⁻0.02 cm³/cm³ depending on moisture) was established along with calibration of the applied sensor. The obtained values are comparable to, or even better than, the features of the traditional invasive sensors utilizing universal calibration models. Both, the TDR and capacitive (FD) sensor enabled monitoring of capillary uptake phenomenon progress. It was noticed that at the end of the experiment the TDR readouts were 4.4% underestimated and the FD readouts were overestimated for 12.6% comparing to the reference gravimetric evaluation.

Evaluation of Hydrocarbon Soil Pollution Using E-Nose.

The possibility of detecting low levels of soil pollution by petroleum fuel using an electronic nose (e-nose) was studied. An attempt to distinguish between pollution caused by petrol and diesel oil, and its relation to the time elapsed since the pollution event was simultaneously performed. Ten arable soils, belonging to various soil groups from the World Reference Base (WRB), were investigated. The measurements were performed on soils that were moistened to field capacity, polluted separately with both hydrocarbons, and then allowed to dry slowly over a period of 180 days. The volatile fingerprints differed throughout the course of the experiment, and, by its end, they were similar to those of the unpolluted soils. Principal component analysis (PCA) and artificial neural network (ANN) analysis showed that the e-nose results could be used to detect soil contamination and distinguish between pollutants and contamination levels.

Short-term Influence of Two Types of Drilling Fluids on Wastewater Treatment Rate and Eukaryotic Organisms of Activated Sludge in Sequencing Batch Reactors.

This work presents the results of studies on the impact of spent drilling fluids cotreated with municipal wastewater on the rate of the wastewater treatment process and the structure of the community of eukaryotic organisms inhabiting an activated sludge. The studies were conducted under laboratory conditions in sequencing batch reactors. The effect of added polymer-potassium drilling fluid (DF1) and polymer drilling fluid (DF2) at dosages of 1 and 3% of wastewater volume on the rate of removal of total suspended solids, turbidity, chemical oxygen demand, and the content of total and ammonium nitrogen were analyzed, taking into account the values of these parameters measured at the end of each operating cycle. In addition to the impacts on the aforementioned physicochemical indices, the influence of drilling fluid on the biomass of various groups of eukaryotes in activated sludge was analyzed. The impact of the drilling fluid was highly dependent on its type and dosage. A noticeable slowdown in the rate of the wastewater treatment process and a negative effect on the organisms were observed after the addition of DF2. This effect intensified after an increase in fluid dose. However, no statistically significant negative changes were observed after the introduction of DF1. Conversely, the removal rate of some of the analyzed pollutant increased.

Short-term Influence of Drilling Fluid on Ciliates from Activated Sludge in Sequencing Batch Reactors.

Spent drilling muds are the liquid residues of rock drilling operations. Due to a high concentration of suspended solids and potentially detrimental chemical properties, they can negatively affect microorganisms participating in wastewater treatment processes. We evaluated the addition of a potassium-polymer drilling fluid (DF) to activated sludge in laboratory sequencing batch reactors (SBRs) for municipal wastewater treatment. Ciliate assemblage, the most dynamic component of eukaryotes in activated sludge, and which is highly sensitive to changes in the system, was evaluated. The average ciliate abundance dropped by about 51% (SBR 2; 1% DF added) and 33% (SBR 3; 3% DF added) in comparison to the control (SBR 1; wastewater only). A decrease in the total number of ciliate species during the experiment was observed, from 25 to 24 in SBR 2 and from 17 to 13 in SBR 3. Moreover, a drop in the number of dominant (>100 individuals mL) ciliate species was observed during the experiment-from eight in the control to five in SBR 2 and four in SBR 3-signaling noticeable changes in the quantitative structure of ciliate species. The species analyzed showed different responses to DF addition. The most sensitive was , which is bacteriovorus. In contrast, two predators, and , showed no reaction to DF addition. Our results indicate that addition of potassium-polymer DF, in doses of 1 to 3% of the treated wastewater volume, had no toxic effects on ciliates, but qualitative and quantitative changes in their community were observed.

Evaluating Soil Moisture Status Using an e-Nose.

The possibility of distinguishing different soil moisture levels by electronic nose (e-nose) was studied. Ten arable soils of various types were investigated. The measurements were performed for air-dry (AD) soils stored for one year, then moistened to field water capacity and finally dried within a period of 180 days. The volatile fingerprints changed during the course of drying. At the end of the drying cycle, the fingerprints were similar to those of the initial AD soils. Principal component analysis (PCA) and artificial neural network (ANN) analysis showed that e-nose results can be used to distinguish soil moisture. It was also shown that different soils can give different e-nose signals at the same moistures.

Application of gas sensor arrays in assessment of wastewater purification effects.

A gas sensor array consisting of eight metal oxide semiconductor (MOS) type gas sensors was evaluated for its ability for assessment of the selected wastewater parameters. Municipal wastewater was collected in a wastewater treatment plant (WWTP) in a primary sedimentation tank and was treated in a laboratory-scale sequential batch reactor (SBR). A comparison of the gas sensor array (electronic nose) response to the standard physical-chemical parameters of treated wastewater was performed. To analyze the measurement results, artificial neural networks were used. E-nose-gas sensors array and artificial neural networks proved to be a suitable method for the monitoring of treated wastewater quality. Neural networks used for data validation showed high correlation between the electronic nose readouts and: (I) chemical oxygen demand (COD) (r = 0.988); (II) total suspended solids (TSS) (r = 0.938); (III) turbidity (r = 0.940); (IV) pH (r = 0.554); (V) nitrogen compounds: N-NO3 (r = 0.958), N-NO2 (r = 0.869) and N-NH3 (r = 0.978); (VI) and volatile organic compounds (VOC) (r = 0.987). Good correlation of the abovementioned parameters are observed under stable treatment conditions in a laboratory batch reactor.

Concentration and risk assessment of metals in snow cover monitoring in urban and rural areas.

INTRODUCTION AND OBJECTIVE: Snow cover serves as a unique indicator of environmental pollution in both urban and rural areas. As a seasonal cover, it accumulates various pollutants emitted into the atmosphere, thus providing insight into air pollution types and the relative contributions of different pollution sources. The aim of the study is to analyze the distribution of trace elements in snow cover to assess the anthropogenic influence on pollution levels, and better understand ecological threats. MATERIAL AND METHODS: The study was conducted in rural areas around the village of Wólka in the Lublin Province of eastern Poland, and in urban districts of the city of Lublin, capital of the Province. Samples were analyzed using Inductively Coupled Plasma-Mass Spectrometry, the Enrichment Factor (EF), and ecological risk indices (RI), were calculated to evaluate the contamination and potential ecological risks posed by the metals. RESULTS: The findings indicate higher concentrations of metals like sodium and iron in urban areas, likely due to road salt use and industrial activity, respectively. Enrichment factors showed significant anthropogenic contributions, particularly for metals like sodium, zinc, and cadmium, which had EF values substantially above natural levels. The potential ecological risk assessment highlighted a considerable ecological threat in urban areas compared to rural settings, primarily due to higher concentrations of metals. CONCLUSIONS: The variation in metal concentrations between urban and rural snow covers reflects the impact of human activities on local environments. Urban areas showed higher pollution levels, suggesting the need for targeted pollution control policies to mitigate the adverse ecological impacts. This study underscores the importance of continuous monitoring and comprehensive risk assessments to effectively manage environmental pollution.

Determining the shelf life and quality changes of potatoes (Solanum tuberosum) during storage using electronic nose and machine learning.

The activities of alpha-amylase, beta-amylase, sucrose synthase, and invertase enzymes are under the influence of storage conditions and can affect the structure of starch, as well as the sugar content of potatoes, hence altering their quality. Storage in a warehouse is one of the most common and effective methods of storage to maintain the quality of potatoes after their harvest, while preserving their freshness and sweetness. Smart monitoring and evaluation of the quality of potatoes during the storage period could be an effective approach to improve their freshness. This study is aimed at assessing the changes in the potato quality by an electronic nose (e-nose) in terms of the sugar and carbohydrate contents. Three potato cultivars (Agria, Santé, and Sprite) were analyzed and their quality variations were separately assessed. Quality parameters (i.e. sugar and carbohydrate contents) were evaluated in six 15-day periods. The e-nose data were analyzed by means of chemometric methods, including principal component analysis (PCA), linear data analysis (LDA), support vector machine (SVM), and artificial neural network (ANN). Quadratic discriminant analysis (QDA) and multivariate discrimination analysis (MDA) offer the highest accuracy and sensitivity in the classification of data. The accuracy of all methods was higher than 90%. These results could be applied to present a new approach for the assessment of the quality of stored potatoes.

Macrophyte communities as bioindicator of stormwater pollution in rivers: a quantitative analysis.

Macrophytes are one of the important indicators used in assessing the anthropic impact on aquatic ecosystems. The structure of macrophyte communities of two rivers were compared by species composition, dominant species and projective cover using statistical methods. It is shown that the influence of storm runoff on these rivers is manifested in the form of a change in the dominant species composition. Based on the statistical analysis carried out, it can be argued that, despite the peculiarities of the flora composition of each of the rivers, the influence of storm runoffs largely neutralizes this specificity, determining the situation in local areas immediately below the runoff. In the area of the effluent discharge the dominance of individual species and an increase in the area overgrown with macrophytes was observed. In the area of stormwater discharge on the Psel River, species were usually present: Nuphar lutea, Ceratophyllum demersum, Myriophyllum spicatum and on the Bystrica River-Glyceria maxima, Sagitaria sagittiformis, Stuckenia pectinata and Potamogeton crispus. The use of the NMDS method has been found to provide good insight into the structural rearrangements in macrophyte communities affected by runoff from stormwater systems.

A simplified method for determining potential heavy metal leached from sediments of stormwater and combined sewer systems - importance for public health.

INTRODUCTION AND OBJECTIVE: The identification and understanding of interactions between contaminants present in sediments from stormwater and combined sewer systems is a prerequisite for their proper management, and provides a basis for developing effective strategies to minimize their negative impact on humans and the environment. The studypresents the method described in PN-EN 12457-2:2006 as a possible technique for studying the mobility of heavy metals in sediments from stormwater and combined sewer systems. MATERIAL AND METHODS: The presented PN-EN 12457-2:2006 method is a relatively simple technique for preparing extracts for the determination of heavy metals in sediments from stormwater and combined sewer systems, consisting of one-step leaching, which is quick to perform. In addition, it allows determination of the characteristics of the samples to be analyzed, and indicates procedures and tests for evaluating hazardous substances released from solid waste. RESULTS: The results of the concentrations of leached heavy metals: chromium, copper, nickel, lead and zinc, obtained in the study, corresponded to the concentrations of the exchange fraction of sludge when using the recommended method with sequential extraction (Student's t-test, p=0.263). In the literature review conducted, no papers were found on the application of the leaching method to prepare extracts for the determination of heavy metals in sediments from stormwater and combined sewer systems. CONCLUSIONS: The PN-EN 12457-2:2006 method is capable of providing important data on the potential risks to humans and the environment from the presence of contaminants in sewage sludge.

Comparison of leaching behaviour of heavy metals from sediments sampled in sewer systems - environmental and public health aspect.

INTRODUCTION AND OBJECTIVE: The article analyzes the content of heavy metals and standard physical as well as chemical pollution indicators in different types of sediments from stormwater, combined sewer and sanitary sewer systems. MATERIAL AND METHODS: Nickel, lead, chromium, copper, zinc and cadmium, as well as standard physical and chemical pollution indicators, were determined in sewage sediments. Aqueous extracts of sediments samples, taken from storm water sewer inlet sediments traps, storm sewers, sanitary sewers and combined sewers, were prepared in accordance with PN-EN 12457-2:2006. After mineralization, the concentrations of the metals: nickel, lead, chromium, copper, zinc and cadmium in the extracts were determined using the inductively coupled plasma emission spectroscopy technique. RESULTS: The results were analyzed with a non-metric multidimensional scaling algorithm. The heavy metal content was variable depending on the sediments collection site. The heavy metals nickel, lead, chromium, copper, zinc and cadmium were found in the sediments from stormwater inlets, storm sewer and sanitary sewer channels, with variability in the concentration of individual metals. The sediments from the flushing of sanitary sewers and combined sewers did not contain cadmium. CONCLUSIONS: The content of heavy metals in sediments varied depending on the sampling location and type of sewer system, indicating the need for detailed monitoring to identify the sources of emissions. Sediments from stormwater sewers have higher concentrations of heavy metals, with those from sewer inlets showing zinc concentrations exceeding regulatory limits, highlighting the variability and potential environmental impact of different sewer systems.

Adhesion of Modified Epoxy Resin to a Concrete Surface.

The protection of building elements exposed to the weather using hydrocarbon-based agents is a comprehensive group of analyses. These agents are characterized by very high chemical resistance, waterproofness, as well as adhesion to surfaces made of various materials, i.e., concrete, steel, ceramics and wood. Modification of adhesion, which ultimately leads to an increase in the durability of a protective/face coating made of such a material, can lead to a longer life of these layers and a less frequent need for replacement or restoration. The following paper describes an experimental research program on the possibility of increasing the adhesion and durability of epoxy resin modified with the use of powder fillers. The resin can be used as a protective or top coat on the surface of concretes or mortars. The main objective of the study was to increase the adhesion of the resin to the concrete substrate, modified by grinding and sandblasting to increase the roughness. For the series studied, both the changes in physicochemical parameters, which determine how the resin penetrates the irregularities of the substrate and mechanical parameters, which mainly determine the durability of the layer made in this way, were identified. A modified version of the pull-off test was used as a method to directly evaluate the effectiveness of the modified resins.