AirQo sensor kit: A particulate matter air quality sensing kit custom designed for low-resource settings.

Air pollution remains a major public health risk. People living in urban spaces are among those most affected by exposure to unhealthy levels of air pollution. However, many urban spaces especially in low- and middle-income countries lack high resolution and long-term data on the state of air quality. Without high resolution air quality data on the different spaces in a city, citizens and authorities are unable to quantify the challenge and act. This is in part attributed to the high cost of air quality monitoring equipment that are expensive to set up, maintain and not designed for local operating conditions that characterise environments in such contexts. In this paper, we describe AirQo sensor kit, a low-cost sensing hardware system designed for and custom made to work in low-resource settings and outdoor urban environments. We describe the design of the air quality sensing device, 3D-printed enclosure, installation-mount, fabrication and deployment configurations. We demonstrate that the low-cost sensing hardware provides a complete solution comparable to the traditional monitoring system and inspires action to tackle air pollution issues. The sensor kit presented in this paper has been widely deployed in cities in Eastern, Western and Central African countries.

Seeing the air in detail: Hyperlocal air quality dataset collected from spatially distributed AirQo network.

Air pollution is a major global challenge associated with an increasing number of morbidity and mortality from lung cancer, cardiovascular and respiratory diseases, among others. However, there is scarcity of ground monitoring air quality data from Sub-Saharan Africa that can be used to quantify the level of pollution. This has resulted in limited targeted air pollution research and interventions e.g. health impacts, key drivers and sources, economic impacts, among others; ultimately hindering the establishment of effective management strategies. This paper presents a dataset of air quality observations collected from 68 spatially distributed monitoring stations across Uganda. The dataset includes hourly PM2 . 5 and PM10 data collected from low-cost air quality monitoring devices and one reference grade monitoring device over a period ranging from 2019 to 2020. This dataset contributes towards filling some of the data gaps witnessed over the years in ground level monitored ambient air quality in Sub-Saharan Africa and it can be useful to various policy makers and researchers.

Characterization of Ambient Air Quality in Selected Urban Areas in Uganda Using Low-Cost Sensing and Measurement Technologies.

Air pollution is prevalent in cities and urban centers in developing countries including sub-Saharan Africa, but ground monitoring data on local pollution remain inadequate, hindering effective mitigation. We employed low-cost sensing and measurement technologies to quantify pollution levels based on particulate matter (PM2.5), NO2, and O3 over a 6 month period for selected urban centers in three of the four macroregions in Uganda. PM2.5 diurnal profiles exhibited consistent patterns across all monitoring locations with higher pollution levels manifesting from 18:00 to 00:00 and from 06:00 to 09:00; while the periods from 00:00 to 05:00 and from 09:00 to 17:00 had the lowest levels. Daily PM2.5 varied widely between 34 and 107 µg/m3 over a 7 day period, well within unhealthy levels (55.5-150.4 µg/m3) for short-term exposure. The inconsistent daily trend are instructive for multiple pollutant assessment to aid specific policy initiatives. The results also show inverse relations between seasonal particulate levels and precipitation, that is, R (correlation coefficient) = -0.93 and -0.62 for Kampala and Wakiso, R = -0.49 and -0.44 for the Eastern region, and R = -0.65 and -0.96 for the Western region. NO2 monthly concentrations replicated PM2.5 spatial levels, whereas O3 exhibited inverse relations probably due to a higher retention time in less-urbanized environments. Both PM2.5 and NO2 correlated positively with the resident population. Our findings show significant spatiotemporal variations and exceedances of health guidelines by about 4-6 times across most study locations (with two exceptions) for longer-term exposure. This paper demonstrably highlights the practicability and potential of low-cost approaches for air quality monitoring, with strong prospects for citizen science. This paper also provides novel information regarding air pollution that is needed to improve control strategies for reducing exposures.

A land use regression model using machine learning and locally developed low cost particulate matter sensors in Uganda.

The application of land use regression (LUR) modeling for estimating air pollution exposure has been used only rarely in sub-Saharan Africa (SSA). This is generally due to a lack of air quality monitoring networks in the region. Low cost air quality sensors developed locally in sub-Saharan Africa presents a sustainable operating mechanism that may help generate the air monitoring data needed for exposure estimation of air pollution with LUR models. The primary objective of our study is to investigate whether a network of locally developed low-cost air quality sensors can be used in LUR modeling for accurately predicting monthly ambient fine particulate matter (PM2.5) air pollution in urban areas of central and eastern Uganda. Secondarily, we aimed to explore whether the application of machine learning (ML) can improve LUR predictions compared to ordinary least squares (OLS) regression. We used data for the entire year of 2020 from a network of 23 PM2.5 low-cost sensors located in urban municipalities of eastern and central Uganda. Between January 1, 2020 and December 31, 2020, these sensors collected highly time-resolved measurement data of PM2.5 air concentrations. We used monthly-averaged PM2.5 concentration data for LUR prediction modeling of monthly PM2.5 concentrations. We used eight different ML base-learner algorithms as well as ensemble modeling. We applied 5-fold cross validation (80% training/20% test random splits) to evaluate the models with resampling and Root mean squared error (RMSE). The relative explanatory power and accuracy of the ML algorithms were evaluated by comparing coefficient of determination (R2) and RMSE, using OLS as the reference approach. The overall average PM2.5 concentration during the study period was 52.22 µg/m3 (IQR: 38.11, 62.84 µg/m3)-well above World Health Organization PM2.5 ambient air guidelines. From the base-learner and ensemble models, RMSE and R2 values ranged between 7.65 µg/m3 - 16.85 µg/m3 and 0.24-0.84, respectively. Extreme gradient boosting (xgbTree) performed best out of the base learner algorithms (R2 = 0.84; RMSE = 7.65 µg/m3). Model performance from ensemble modeling with Lasso and Elastic-Net Regularized Generalized Linear Models (glmnet) did not outperform xgbTree, but prediction performance was comparable to that of xgbTree. The most important temporal and spatial predictors of monthly PM2.5 levels were monthly precipitation, percent of the population using solid fuels for cooking, distance to Lake Victoria, and greenspace (NDVI) within a 500-m buffer of air monitors. In conclusion, data from locally developed low-cost PM sensors provide evidence that they can be used for spatio-temporal prediction modeling of air pollution exposures in Uganda. Moreover, the non-parametric ML and ensemble approaches to LUR modeling clearly outperformed OLS regression algorithm for the prediction of monthly PM2.5 concentrations. Deploying low-cost air quality sensors in concert with implementation of data quality control measures, can help address the critical need for expanding and improving air quality monitoring in resource-constrained settings of sub-Saharan Africa. These low-cost sensors, in conjunction with non-parametric ML algorithms, may provide a rapid path forward for PM2.5 exposure assessment and to spur air pollution epidemiology research in the region.