Machine Learning for a Low-cost Air Pollution Network
This addresses the issue of poor decision-making due to invalid predictions from low-cost sensors in resource-limited settings, but it is incremental as it applies existing probabilistic methods to a specific domain.
The paper tackled the problem of biased measurements from low-cost sensors in air pollution networks, especially in economically constrained countries, by using probabilistic machine learning to model sensor calibration as distributions or Gaussian processes over time, resulting in mitigation of technical constraints.
Data collection in economically constrained countries often necessitates using approximate and biased measurements due to the low-cost of the sensors used. This leads to potentially invalid predictions and poor policies or decision making. This is especially an issue if methods from resource-rich regions are applied without handling these additional constraints. In this paper we show, through the use of an air pollution network example, how using probabilistic machine learning can mitigate some of the technical constraints. Specifically we experiment with modelling the calibration for individual sensors as either distributions or Gaussian processes over time, and discuss the wider issues around the decision process.