Monitoring air pollution is of vital importance to the overall health of the population. Unfortunately, devices that can measure air quality can be expensive, and many cities in low and middle-income countries have to rely on a sparse allocation of them. In this paper, we investigate the use of Gaussian Processes for both nowcasting the current air-pollution in places where there are no sensors and forecasting the air-pollution in the future at the sensor locations. In particular, we focus on the city of Kampala in Uganda, using data from AirQo's network of sensors. We demonstrate the advantage of removing outliers, compare different kernel functions and additional inputs. We also compare two sparse approximations to allow for the large amounts of temporal data in the dataset.

When Shamim Nabuuma Kaliisa first had chest pain, she was in the second year of her medical degree at Makerere University (Kampala, Uganda). She was diagnosed with breast cancer when she was barely in her 20s. "Being told that you have cancer is one of the worst things anyone can hear", she told The Lancet Oncology. "It comes with a feeling of not having a future, with the imagination of pain until death." Luckily, at stage I, her breast cancer was treatable, but the pain she went through during the long treatment process was unbearable.

Concerned that the majority of air quality issues affected those in low-income countries, the team developed a solution called AirQo, an initiative that combines human ingenuity, AI models, and boxes packed with air monitoring technology to predict pollution patterns in Kampala. Air sensors on buildings and moto-taxis collect swathes of pollution data, and cloud-based AI software swiftly analyses it to make air quality forecasts. These predictions are passed to government agencies, who can work to improve air quality and reduce the risk of exposure within local communities. The research team hopes that one day this technology will reduce pollution on streets across the continent so that this generation and the next will know what it means to breathe fresh air.

Along with a dedicated team of students, Engineer installs air sensors on top of buildings and the backs of motorbike taxis ― known as boda bodas and one of the city's most common forms of transportation ― to collect pollution data from all over the city. The team then uses cloud-based AI software to analyze air particle data in real-time and predict local pollution. These forecasts offer Kampala's communities a way to reduce their risk of exposure and are being used by government agencies to improve air quality on the ground. Engineer and the team at Makerere University are one of 20 organizations selected from more than 2,600 applicants to receive a grant through the Google AI Impact Challenge: the Google.org Through this program, the Makerere team also received coaching and mentorship from Google and DeepMind AI experts over the course of a 9-month AI accelerator.

In episode nine of season three we chat about the difference between models and algorithms, take a listener question about summer schools and learning in person as opposed to learning digitally, and we chat with John Quinn of the United Nations Global Pulse lab in Kampala, Uganda and Makerere University's Artificial Intelligence Research group. See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

Drones soon will be used in Tanzania to deliver medicines to health facilities across the East African country, continuing a trend of African governments embracing drone networks to deliver critical services.