Adam Aker

The goal of this study is to describe a design architecture for a self-powered IoT (Internet of Things) sensor network that is currently being deployed at various locations throughout the Dallas-Fort Worth metroplex to measure and report on Particulate Matter (PM) concentrations. This system leverages diverse low-cost PM sensors, enhanced by machine learning for sensor calibration, with LoRaWAN connectivity for long-range data transmission. Sensors are GPS-enabled, allowing precise geospatial mapping of collected data, which can be integrated with urban air quality forecasting models and operational forecasting systems. To achieve energy self-sufficiency, the system uses a small-scale solar-powered solution, allowing it to operate independently from the grid, making it both cost-effective and suitable for remote locations. This novel approach leverages multiple operational modes based on power availability to optimize energy efficiency and prevent downtime. By dynamically adjusting system behavior according to power conditions, it ensures continuous operation while conserving energy during periods of reduced supply. This innovative strategy significantly enhances performance and resource management, improving system reliability and sustainability. This IoT network provides localized real-time air quality data, which has significant public health benefits, especially for vulnerable populations in densely populated urban environments. The project demonstrates the synergy between IoT sensor data, machine learning-enhanced calibration, and forecasting methods, contributing to scientific understanding of microenvironments, human exposure, and public health impacts of urban air quality. In addition, this study emphasizes open source design principles, promoting transparency, data quality, and reproducibility by exploring cost-effective sensor calibration techniques and adhering to open data standards. The next iteration of the sensors will include edge processing for short-term air quality forecasts. This work underscores the transformative role of low-cost sensor networks in urban air quality monitoring, advancing equitable policy development and empowering communities to address pollution challenges.

This study calibrates an affordable, solar-powered LoRaWAN air quality monitoring prototype using the research-grade Palas Fidas Frog sensor. Motivated by the need for sustainable air quality monitoring in smart city initiatives, this work integrates low-cost, self-sustaining sensors with research-grade instruments, creating a cost-effective hybrid network that enhances both spatial coverage and measurement accuracy. To improve calibration precision, the study leverages the Super Learner machine learning technique, which optimally combines multiple models to achieve robust PM (Particulate Matter) monitoring in low-resource settings. Data was collected by co-locating the Palas sensor and LoRaWAN devices under various climatic conditions to ensure reliability. The LoRaWAN monitor measures PM concentrations alongside meteorological parameters such as temperature, pressure, and humidity. The collected data were calibrated against precise PM concentrations and particle count densities from the Palas sensor. Various regression models were evaluated, with the stacking-based Super Learner model outperforming traditional approaches, achieving an average test R² value of 0.96 across all target variables, including 0.99 for PM_2.5 and 0.91 for PM_10.0. This study presents a novel approach by integrating Super Learner-based calibration with LoRaWAN technology, offering a scalable solution for low-cost, high-accuracy air quality monitoring. The findings demonstrate the feasibility of deploying these sensors in urban areas such as the Dallas-Fort Worth metroplex, providing a valuable tool for researchers and policymakers to address air pollution challenges effectively.

This study calibrates an affordable, solar-powered LoRaWAN air quality monitoring prototype using the research-grade Palas Fidas Frog sensor. By leveraging the Super Learner machine learning technique, it develops cost-effective sensors for accurate PM (Particulate Matter) monitoring in low-resource settings. Data was collected by co-locating the Palas sensor and LoRaWAN devices under various climatic conditions over multiple days to ensure reliable calibration. The LoRaWAN air quality monitor integrates sensors that measure PM concentrations and meteorological parameters, including temperature, pressure, and humidity. The collected data were calibrated using precise PM concentrations and particle count density measured by the Palas sensor. Various regression models were evaluated, with the stacking model (Super Learner) demonstrating superior performance. By combining simple and complex models, the stacking model achieved the most accurate predictions, with an average test R2 value of 0.96 across all target variables. Specifically, it achieved R2 values of 0.99 for PM2.5 and 0.91 for PM10.0, demonstrating near-research-grade accuracy and underscoring the robustness of the calibration. This study offers a practical and scalable solution for cost-effective air quality monitoring, with significant potential for deployment in the Dallas-Fort Worth metroplex and similar urban areas.

The air we breathe consists of contaminants such as particulate matter (PM), carbon dioxide (CO2), nitrogen dioxide (NO2), nitric oxide (NO) which when inhaled brings about several changes in the autonomous responses of our body. Our previous work showed that we can use the human body as a sensor by making use of autonomous responses (or biometrics) such as changes in electrical activity in the brain measured using electroencephalogram (EEG) and physiological changes such as skin temperature, Galvanic Skin Response (GSR), blood oxygen saturation (SpO2) and few others can be used to estimate pollutants, in particular, PM1 and CO2 with high degree of accuracy using machine learning. In this study, we introduce a novel approach to obtain the power spectral density (PSD) from the timeseries of EEG developed by Astrapi called the Astrapi Spectrum Analyzer (ASA). The physiological responses of a participant cycling outdoors is measured using a biometric suite and ambient CO2, NO2 and NO is measured simultaneously. We made use of physiological responses and combined it with the PSD from an EEG timeseries using Welch Method (WM) and then with the PSD using ASA to estimate the inhaled concentration of CO2, NO2 and NO. This work shows that, indeed the PSD obtained from ASA combined with other physiological responses provides much better result (RMSE=9.28 ppm in an independent test set) in estimating inhaled CO2 compared to making use of the same physiological responses and PSD from WM (RMSE=17.55 ppm in an independent test set). Small improvements are also seen in the estimation of NO2 and NO when using physiological responses and PSD from ASA, which can be further confirmed by making use of large number of data collection.

This study aims to determine the optimal frequency for monitoring airborne pollutants in densely populated urban areas to effectively capture their temporal variations. While environmental organizations worldwide typically update air quality data hourly, there is no global consensus on the ideal monitoring frequency to adequately resolve pollutant (Particulate Matter) time series. By applying temporal variogram analysis to particulate matter (PM) data over time, we identified specific measurement intervals that accurately reflect fluctuations in pollution levels. Using January 2023 air quality data from the Joppa neighborhood of Dallas, TX, Temporal Variogram analysis was conducted on three distinct days with varying PM2.5 pollution levels. For the most polluted day, the optimal sampling interval for PM2.5 was determined to be 12.25 seconds. This analysis shows that highly polluted days are associated with shorter sampling intervals, highlighting the need for highly granular observations to accurately capture variations in PM levels. Using the variogram analysis results from the most polluted day, we trained Machine Learning models that can predict the sampling time using meteorological parameters. Feature importance analysis revealed that humidity, temperature and wind speed could significantly impact the measurement time for PM2.5. The study also extends to the other size fractions measured by the air quality monitor. Our findings highlight how local conditions influence the frequency required to reliably track changes in air quality.

The goal of this study is to describe a design architecture for a self-powered IoT (Internet of Things) sensor network that is currently being deployed at various locations throughout the Dallas-Fort Worth metroplex to measure and report on Particulate Matter (PM) concentrations. This system leverages diverse low-cost PM sensors, enhanced by machine learning for sensor calibration, with LoRaWAN connectivity for long-range data transmission. Sensors are GPS-enabled, allowing precise geospatial mapping of collected data, which can be integrated with urban air quality forecasting models and operational forecasting systems. To achieve energy self-sufficiency, the system uses a small-scale solar-powered solution, allowing it to operate independently from the grid, making it both cost-effective and suitable for remote locations. This novel approach leverages multiple operational modes based on power availability to optimize energy efficiency and prevent downtime. By dynamically adjusting system behavior according to power conditions, it ensures continuous operation while conserving energy during periods of reduced supply. This innovative strategy significantly enhances performance and resource management, improving system reliability and sustainability. This IoT network provides localized real-time air quality data, which has significant public health benefits, especially for vulnerable populations in densely populated urban environments. The project demonstrates the synergy between IoT sensor data, machine learning-enhanced calibration, and forecasting methods, contributing to scientific understanding of microenvironments, human exposure, and public health impacts of urban air quality. In addition, this study emphasizes open source design principles, promoting transparency, data quality, and reproducibility by exploring cost-effective sensor calibration techniques and adhering to open data standards. The next iteration of the sensors will include edge processing for short-term air quality forecasts.

Unmanned aerial vehicles equipped with hyperspectral imagers have emerged as an essential technology for the characterization of inland water bodies. The high spectral and spatial resolutions of these systems enable the retrieval of a plethora of optically active water quality parameters via band ratio algorithms and machine learning methods. However, fitting and validating these models requires access to sufficient quantities of in situ reference data which are time-consuming and expensive to obtain. In this study, we demonstrate how Generative Topographic Mapping (GTM), a probabilistic realization of the self-organizing map, can be used to visualize high-dimensional hyperspectral imagery and extract spectral signatures corresponding to unique endmembers present in the water. Using data collected across a North Texas pond, we first apply GTM to visualize the distribution of captured reflectance spectra, revealing the small-scale spatial variability of the water composition. Next, we demonstrate how the nodes of the fitted GTM can be interpreted as unique spectral endmembers. Using extracted endmembers together with the normalized spectral similarity score, we are able to efficiently map the abundance of nearshore algae, as well as the evolution of a rhodamine tracer dye used to simulate water contamination by a localized source.

Unmanned Aerial Vehicles (UAVs) equipped with hyperspectral imagers have emerged as an essential technology for the characterization of inland water bodies. The high spectral and spatial resolutions of these systems enable the retrieval of a plethora of optically-active water quality parameters via band ratio algorithms and machine learning methods. However, fitting and validating these models requires access to sufficient quantities of in situ reference data which are time-consuming and expensive to obtain. In this study, we demonstrate how the Generative Topographic Mapping (GTM), a Bayesian realization of the Self-organizing Map, can be used to visualize high-dimensional hyperspectral imagery and extract spectral signatures corresponding to unique endmembers present in the water. Using data collected across a North Texas pond, we first apply the GTM to visualize the distribution of captured reflectance spectra revealing small-scale spatial variability of water composition. Next, we demonstrate how the nodes of the fitted GTM can be interpreted as unique spectral endmembers. Using extracted endmembers together with the normalized spectral similarity score, we are able to efficiently map the abundance of near shore algae as well as the evolution of a rhodamine tracer dye used to simulate water contamination by a localized source.