Low-cost sensors (LCSs) for air quality monitoring have enormous potential to improve air quality data coverage in resource-limited parts of the world such as sub-Saharan Africa. LCSs, however, are ...affected by environment and source conditions. To establish high-quality data, LCSs must be collocated and calibrated with reference grade PM2.5 monitors. From March 2020, a low-cost PurpleAir PM2.5 monitor was collocated with a Met One Beta Attenuation Monitor 1020 in Accra, Ghana. While previous studies have shown that multiple linear regression (MLR) and random forest regression (RF) can improve accuracy and correlation between PurpleAir and reference data, MLR and RF yielded suboptimal improvement in the Accra collocation (R 2 = 0.81 and R 2 = 0.81, respectively). We present the first application of Gaussian mixture regression (GMR) to air quality data calibration and demonstrate improvement over traditional methods by increasing the collocated PM2.5 correlation and accuracy to R 2 = 0.88 and MAE = 2.2 μg m–3. Gaussian mixture models (GMMs) are a probability density estimator and clustering method from which nonlinear regressions that tolerate missing inputs can be derived. We find that even when given missing inputs, GMR provides better correlation than MLR and RF performed with complete data. GMR also allows us to estimate calibration certainty. When evaluated, 95% confidence intervals agreed with reference PM2.5 data 96% of the time, suggesting that the model accurately assesses its own confidence. Additionally, clustering within the GMM is consistent with climate characteristics, providing confidence that the calibration approach can learn underlying relationships in data.
There is a notable lack of continuous monitoring of air pollutants in the Global South, especially for measuring chemical composition, due to the high cost of regulatory monitors. Using our ...previously developed low-cost method to quantify black carbon (BC) in fine particulate matter (PM2.5) by analyzing reflected red light from ambient particle deposits on glass fiber filters, we estimated hourly ambient BC concentrations with filter tapes from beta attenuation monitors (BAMs). BC measurements obtained through this method were validated against a reference aethalometer between August 2 and 23, 2023 in Addis Ababa, Ethiopia, demonstrating a very strong agreement (R 2 = 0.95 and slope = 0.97). We present hourly BC for three cities in sub-Saharan Africa (SSA) and one in North America: Abidjan (Côte d’Ivoire), Accra (Ghana), Addis Ababa (Ethiopia), and Pittsburgh (USA). The average BC concentrations for the measurement period at the Abidjan, Accra, Addis Ababa Central summer, Addis Ababa Central winter, Addis Ababa Jacros winter, and Pittsburgh sites were 3.85 μg/m3, 5.33 μg/m3, 5.63 μg/m3, 3.89 μg/m3, 9.14 μg/m3, and 0.52 μg/m3, respectively. BC made up 14–20% of PM2.5 mass in the SSA cities compared to only 5.6% in Pittsburgh. The hourly BC data at all sites (SSA and North America) show a pronounced diurnal pattern with prominent peaks during the morning and evening rush hours on workdays. A comparison between our measurements and the Goddard Earth Observing System Composition Forecast (GEOS-CF) estimates shows that the model performs well in predicting PM2.5 for most sites but struggles to predict BC at an hourly resolution. Adding more ground measurements could help evaluate and improve the performance of chemical transport models. Our method can potentially use existing BAM networks, such as BAMs at U.S. Embassies around the globe, to measure hourly BC concentrations. The PM2.5 composition data, thus acquired, can be crucial in identifying emission sources and help in effective policymaking in SSA.
Particulate matter air pollution is a leading cause of global mortality, particularly in Asia and Africa. Addressing the high and wide-ranging air pollution levels requires ambient monitoring, but ...many low- and middle-income countries (LMICs) remain scarcely monitored. To address these data gaps, recent studies have utilized low-cost sensors. These sensors have varied performance, and little literature exists about sensor intercomparison in Africa. By colocating 2 QuantAQ Modulair-PM, 2 PurpleAir PA-II SD, and 16 Clarity Node-S Generation II monitors with a reference-grade Teledyne monitor in Accra, Ghana, we present the first intercomparisons of different brands of low-cost sensors in Africa, demonstrating that each type of low-cost sensor PM2.5 is strongly correlated with reference PM2.5, but biased high for ambient mixture of sources found in Accra. When compared to a reference monitor, the QuantAQ Modulair-PM has the lowest mean absolute error at 3.04 μg/m3, followed by PurpleAir PA-II (4.54 μg/m3) and Clarity Node-S (13.68 μg/m3). We also compare the usage of 4 statistical or machine learning models (Multiple Linear Regression, Random Forest, Gaussian Mixture Regression, and XGBoost) to correct low-cost sensors data, and find that XGBoost performs the best in testing (R 2: 0.97, 0.94, 0.96; mean absolute error: 0.56, 0.80, and 0.68 μg/m3 for PurpleAir PA-II, Clarity Node-S, and Modulair-PM, respectively), but tree-based models do not perform well when correcting data outside the range of the colocation training. Therefore, we used Gaussian Mixture Regression to correct data from the network of 17 Clarity Node-S monitors deployed around Accra, Ghana, from 2018 to 2021. We find that the network daily average PM2.5 concentration in Accra is 23.4 μg/m3, which is 1.6 times the World Health Organization Daily PM2.5 guideline of 15 μg/m3. While this level is lower than those seen in some larger African cities (such as Kinshasa, Democratic Republic of the Congo), mitigation strategies should be developed soon to prevent further impairment to air quality as Accra, and Ghana as a whole, rapidly grow.
Particulate matter air pollution is a leading cause of global mortality, particularly in Asia and Africa. Addressing the high and wide-ranging air pollution levels requires ambient monitoring, but ...many low- and middle-income countries (LMICs) remain scarcely monitored. To address these data gaps, recent studies have utilized low-cost sensors. These sensors have varied performance, and little literature exists about sensor intercomparison in Africa. By colocating 2 QuantAQ Modulair-PM, 2 PurpleAir PA-II SD, and 16 Clarity Node-S Generation II monitors with a reference-grade Teledyne monitor in Accra, Ghana, we present the first intercomparisons of different brands of low-cost sensors in Africa, demonstrating that each type of low-cost sensor PM
is strongly correlated with reference PM
, but biased high for ambient mixture of sources found in Accra. When compared to a reference monitor, the QuantAQ Modulair-PM has the lowest mean absolute error at 3.04 μg/m
, followed by PurpleAir PA-II (4.54 μg/m
) and Clarity Node-S (13.68 μg/m
). We also compare the usage of 4 statistical or machine learning models (Multiple Linear Regression, Random Forest, Gaussian Mixture Regression, and XGBoost) to correct low-cost sensors data, and find that XGBoost performs the best in testing (
: 0.97, 0.94, 0.96; mean absolute error: 0.56, 0.80, and 0.68 μg/m
for PurpleAir PA-II, Clarity Node-S, and Modulair-PM, respectively), but tree-based models do not perform well when correcting data outside the range of the colocation training. Therefore, we used Gaussian Mixture Regression to correct data from the network of 17 Clarity Node-S monitors deployed around Accra, Ghana, from 2018 to 2021. We find that the network daily average PM
concentration in Accra is 23.4 μg/m
, which is 1.6 times the World Health Organization Daily PM
guideline of 15 μg/m
. While this level is lower than those seen in some larger African cities (such as Kinshasa, Democratic Republic of the Congo), mitigation strategies should be developed soon to prevent further impairment to air quality as Accra, and Ghana as a whole, rapidly grow.
•Both decomposed and regular food waste can be used in briquette fuel production.•Decomposed food waste briquettes have higher bulk density and net calorific value.•Decomposed food waste briquettes ...achieve lower burning rate and flame temperature.•Mixing food waste to tree-based raw materials improves the briquette quality.•Compared to compost, briquette ash contains less N and P and more K and ca.
This study investigated the potential of using locally available municipal solid wastes (MSW) (such as food wastes from restaurants, charcoal dust, coconut husk and shell, and sawdust) as feedstock to produce non-carbonized fuel briquettes. A low-cost briquetting machine sourced from Alfaster Industries in Kenya served to demonstrate the concept. Using decomposed food waste resulted in briquettes with higher bulk density (+4%), greater net calorific value (+18%) and lower burning rate (-24%), compared to the use of regular food waste. There was no significant difference in ash content from the two briquette types. The results also indicate that decomposing food waste and mixing it with tree-based raw materials such as coconut waste, charcoal waste or sawdust improves the quality of briquettes, and enhances the temperatures achieved during combustion. This recycling solution has the potential to serve multiple benefits in MSW management for sustainable cities while reducing rural land degradation and deforestation.
Building embodied AI systems that can follow arbitrary language instructions in any 3D environment is a key challenge for creating general AI. Accomplishing this goal requires learning to ground ...language in perception and embodied actions, in order to accomplish complex tasks. The Scalable, Instructable, Multiworld Agent (SIMA) project tackles this by training agents to follow free-form instructions across a diverse range of virtual 3D environments, including curated research environments as well as open-ended, commercial video games. Our goal is to develop an instructable agent that can accomplish anything a human can do in any simulated 3D environment. Our approach focuses on language-driven generality while imposing minimal assumptions. Our agents interact with environments in real-time using a generic, human-like interface: the inputs are image observations and language instructions and the outputs are keyboard-and-mouse actions. This general approach is challenging, but it allows agents to ground language across many visually complex and semantically rich environments while also allowing us to readily run agents in new environments. In this paper we describe our motivation and goal, the initial progress we have made, and promising preliminary results on several diverse research environments and a variety of commercial video games.