Unveiling the Predictive Capabilities of Machine Learning in Air Quality Data Analysis: A Comparative Evaluation of Different Regression Models

Air quality is a critical concern for public health and environmental regulation. The Air Quality Index (AQI), a widely adopted index by the US Environmental Protection Agency (EPA), serves as a crucial metric for reporting site-specific air pollution levels. Accurately predicting air quality, as measured by the AQI, is essential for effective air pollution management. In this study, we aim to identify the most reliable regression model among linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), logistic regression, and K-nearest neighbors (KNN). We conducted four different regression analyses using a machine learning approach to determine the model with the best performance. By employing the confusion matrix and error percentages, we selected the best-performing model, which yielded prediction error rates of 22%, 23%, 20%, and 27%, respectively, for LDA, QDA, logistic regression, and KNN models. The logistic regression model outperformed the other three statistical models in predicting AQI. Understanding these models' performance can help address an existing gap in air quality research and contribute to the integration of regression techniques in AQI studies, ultimately benefiting stakeholders like environmental regulators, healthcare professionals, urban planners, and researchers.

Effects of Increasing Rainfall Depths and Impervious Areas on the Hydrologic Responses

Hydrologic modeling is a popular tool for estimating the hydrological response of a watershed. However, modeling processes are becoming more complex due to land-use changes such as urbanization, industrialization, and the expansion of agricultural activities. The primary goal of the research was to use the HEC-HMS model to evaluate the impact of impervious soil layers and the increase in rainfall-runoff processes on hydrologic processes. For these purposes, the Watershed Modelling System (WMS) and Hydrologic Engineering Center’s-Hydrologic Modeling System (HEC-HMS) models were used in this study to simulate the rainfall-runoff process. To compute runoff rate, runoff volume, base flow, and flow routing methods SCS curve number, SCS unit hydrograph, recession, and loss routing methods were selected for the research, respectively. To reduce the processing time and computational complexity, a small section of the Pipestem Creek Watershed was selected to understand the methods and concepts associated with the hydrologic simulation model building. A DEM along with other required data such as land use land cover data, soil type data, and meteorological data was utilized to delineate the watershed in WMS. The output of WMS was utilized to run the HEC-HMS model for five different scenario analyses. All the relevant data were plugged in to the model to get the desired map. Subsequently, outlets at appropriate locations were selected for the sub-basin delineation for further analysis. Finally, the model was parametrized to get successful simulation results. Overall, peak discharges and runoff volumes were increased with increasing storm depths and impervious areas. Peak discharges were increased to 36% and 51% when rainfall depths were increased by 10% and 20% from the initial rainfall depth, respectively. Runoff volumes were also increased to 35% and 49% for the same scenarios, respectively. Peak discharges were increased to 12% and 78% with a 10% and 20%, respectively, increase in impervious areas. The runoff volumes were increased by 12% and 76% when impervious areas were increased by 10% and 20%, respectively. The simulation models responded well, and the peak discharges and runoff volumes increased with increasing storm depths and impervious areas.

Sensors and Methods for Measuring Greenhouse Gas Emissions from Different Components of Livestock Production Facilities

Greenhouse gas monitoring on a broader scale is necessary to ensure that a cap-and-trade system is effective, reduces measurement uncertainty, and detects fraudulent or illegal activities. The recent strict air quality regulation in livestock production facilities has accelerated the need for accurate on-farm determination of greenhouse gas (GHG) emission rates (ERs) from livestock operations in the United States under a wide range of production, management, and climate conditions. The estimation of GHG emissions from different ground-level sources or at a property line is a very complicated process, and such measurements require multidirectional expertise including engineering, micrometeorology, agronomy, applied physics, and chemistry. Accurate measurement of gaseous concentration from an emitting source is a prerequisite and of paramount importance for estimating emissions rates (ERs) using any micro-meteorological and sampling device-based method. This paper provides an overview of the state-of-the-art sensors and analyzers used to measure GHG concentrations. Sensor and analyzer selection and their performance in the laboratory and field were discussed. In addition, protocols for data quality control (QC) and quality assurance (QA) when deploying sensors in the area for long-term use were also discussed. In addition, the preparation of measurement systems, coupling of air samplers with sensing systems for measuring gaseous concentrations, and uncertainties inherent to such measurement methods as a whole to estimate ERs were discussed in this paper.