Grantee Research Project Results
2024 Progress Report: MINTS: Multi-scale intelligent sensing
EPA Grant Number: SU840570Title: MINTS: Multi-scale intelligent sensing
Investigators: Lary, David J , Patra, Rittik , Sooriyaarachchi, Vinu , Dewage, Prabuddha , Balagopal, Gokul , Waczak, John
Institution: The University of Texas at Dallas , Paul Quinn College , Downwinders at Risk Education Fund
EPA Project Officer: Page, Angela
Phase: I
Project Period: August 1, 2023 through April 23, 2025
Project Period Covered by this Report: August 1, 2023 through July 31,2024
Project Amount: $24,999
RFA: 19th Annual P3 Awards: A National Student Design Competition Focusing on People, Prosperity and the Planet Request for Applications (RFA) (2022) RFA Text | Recipients Lists
Research Category: Air , P3 Awards
Objective:
- Technical Innovation: The deployment of low-cost sensors to monitor air pollution (e.g., the airborne particulate size distribution from 0.1 to 10 µm and PM1, PM2.5, PM5 and PM10) and calibrate them using EPA-approved reference instruments. The sensors were powered by solar energy and communicate via LoRaWAN, a wireless network that allows wide-area coverage.
- Environmental Justice: The project addressed the lack of air quality monitoring in Dallas neighborhoods, particularly in communities facing environmental justice issues historically affected by industrial pollution. Community engagement ensured residents and live online portals ensured the communities can access and use the data for informed decision-making and policy advocacy.
- Societal Impact: The sensors provide open-source, real-time data for residents, policymakers, and educational institutions, promoting transparency and enabling local communities to take action to improv
Progress Summary:
The MINTS (Multi-scale Intelligent Sensing) project had two main components: First, manufacturing and deploying affordable, solar-powered air quality sensors throughout Dallas neighborhoods, particularly in areas affected by environmental justice concerns related to industrial pollution. These sensors provided consistent, real-time air quality data, available live at http://sharedairdfw.com. This data was critical for tracking local pollution, improving public health, and supporting environmental justice efforts. The project also improved the accuracy of pollution measurements by combining sensor data with satellite observations and machine learning techniques. Second, using remote sensed based data to infer surface level particulates. We used a combination of ground-based sensors and satellite data to track pollution levels over time and across different locations. By using Internet of Things (IoT) sensors and satellite information, we were able to produce more detailed and accurate maps of air quality, especially in the Dallas-Fort Worth area, where local sensors collected data every second.
Measuring airborne particles, particularly in the range of 0.1-10 µm, is crucial for assessing public health risks [1] related to air quality (Figure 1). The smaller particles in this size range can travel deep into the respiratory system, reaching the lungs, and even entering the bloodstream. Fine particles (PM2.5) and ultra-fine particles (less than 0.1 µm) are especially concerning because they are linked to various health issues, including cardiovascular diseases, respiratory conditions (such as asthma and bronchitis), and even impacts on cognitive function and fetal development [2, 3]. Accurate monitoring of these particles is essential for understanding their distribution and concentration, which is vital for public health surveillance and creating strategies to reduce exposure in high-risk areas. This information plays a key role in shaping public health policies and preventive measures to reduce the harmful effects of air pollution.
Improving how we assess cumulative environmental exposures allows us to better understand the link between exposure and its long-term impact, such as the 'wear and tear' that pollution can cause on the body. This includes physical, physiological, and mental decline over time. A promising approach is the exposome framework, which examines the complex relationships between environment, behavior, biology, and disease throughout an individual's life [4].
Fig 1. The observed health consequences that are often associated with exposures to various particulate matter size fractions, the depth of penetration of these size fractions into the lungs, a size chart for the typical sizes of various types of particles, and their visibility to the naked eye.
Moreover, we exceeded our project goals by investigating how the body's autonomic responses can detect inhaled particles (including their size distribution) and various gas concentrations -- effectively using the human body as a sensor. This is discussed in detail in the papers 4-6 listed below.
Future Activities:
Innovative Aspects
- Machine Learning: The sensors used machine learning for accurate calibration against EPA reference instruments, allowing for long-term data reliability.
- Collaboration: The project engaged local universities, community organizations, and residents to ensure wide participation and integration of the data into public policy and educational curricula.
- Replicability: The project can be scaled and replicated in other cities and communities facing similar environmental challenges.
Journal Articles on this Report : 8 Displayed | Download in RIS Format
| Other project views: | All 8 publications | 8 publications in selected types | All 8 journal articles |
|---|
| Type | Citation | ||
|---|---|---|---|
|
|
Fernando BA, Talebi S, Wijeratne L, Waczak J, Sooriyaarachchi V, Ruwali S, Hathurusinghe P, Lary DJ, Sadler J, Lary T, Lary M. Data-driven environmental health:unraveling particulate matter trends with biometric signals. Medical Research Archives 2024;12(1). |
SU840570 (2024) |
Exit |
|
|
Ruwali S, Fernando B, Talebi S, Wijeratne L, Waczak J, Madusanka PM, Lary DJ, Sadler J, Lary T, Lary M, Aker A. Estimating inhaled nitrogen dioxide from the human biometric response. Advances in Environmental and Engineering Research 2024;5(2):1-2. |
SU840570 (2024) |
Exit |
|
|
Waczak J, Lary DJ. Generative simplex mapping:non-linear endmember extraction and spectral unmixing for hyperspectral imagery. Remote Sensing 2024;16(22):4316. |
SU840570 (2024) |
Exit |
|
|
Dewage PM, Wijeratne LO, Yu X, Iqbal M, Balagopal G, Waczak J, Fernando A, Lary MD, Ruwali S, Lary DJ. Providing fine temporal and spatial resolution analyses of airborne particulate matter utilizing complimentary in situ IoT sensor network and remote sensing approaches. Remote Sensing 2024;16(13):2454. |
SU840570 (2024) |
Exit |
|
|
Ruwali S, Talebi S, Fernando A, Wijeratne LO, Waczak J, Dewage PM, Lary DJ, Sadler J, Lary T, Lary M, Aker A. Quantifying inhaled concentrations of particulate matter, carbon dioxide, nitrogen dioxide, and nitric oxide using observed biometric responses with machine learning. BioMedInformatics 2024;4(2):1019-1046. |
SU840570 (2024) |
Exit |
|
|
Waczak J, Aker A, Wijeratne LO, Talebi S, Fernando A, Dewage PM, Iqbal M, Lary M, Schaefer D, Balagopal G, Lary DJ. Unsupervised dharacterization of water composition with Uav-based hyperspectral imaging and generative topographic mapping. Remote Sensing 2024;16(13):2430. |
SU840570 (2024) |
Exit |
|
|
Wijeratne LO, Kiv D, Waczak J, Dewage P, Balagopal G, Iqbal M, Aker A, Fernando B, Lary M, Sooriyaarachchi V, Patra R. The design and deployment of a self-powered, LoRaWAN-based IoT environment sensor ensemble for integrated air quality sensing and simulation. Air 2025;3(1):9. |
SU840570 (2024) |
Exit |
|
|
Sooriyaarachchi V. Causality-driven feature selection for calibrating low-cost air quality sensors using machine learning. Preprints 2024 [Epub ahead of print] doi:10.20944/preprints202410.0680.v1. |
SU840570 (2024) |
Exit |
Supplemental Keywords:
Aerosol optical depth, air pollution, autonomic responses, biometric observations, causality, CO2, endmember extraction, exposome, generative topographic mapping, hyperspectral imaging, IOT sensor, machine learning, microenvironment, NO, NO2, particulate matter, remote sensing, sensor calibration, source apportionment, spectral unmixing, unsupervised classification, unsupervised machine learning.Relevant Websites:
Shared Air DFW Project Page Exit
The perspectives, information and conclusions conveyed in research project abstracts, progress reports, final reports, journal abstracts and journal publications convey the viewpoints of the principal investigator and may not represent the views and policies of ORD and EPA. Conclusions drawn by the principal investigators have not been reviewed by the Agency.