Air quality has become a central issue in public health and urban planning management, due to the proven adverse effects of airborne pollutants. Considering temporary mobility restriction measures used to face low air quality episodes, the capability of foreseeing pollutant concentrations is crucial. We thus present SOCAIRE (Spanish acronim for “operational forecast system for air quality”), an operational tool based on a Bayesian and spatiotemporal ensemble of neural and statistical nested models. SOCAIRE integrates endogenous and exogenous information in order to predict and monitor future distributions of the concentration for the main pollutants. It focuses on modeling available components which affect air quality: past concentrations of pollutants, human activity, and numerical pollution and weather predictions. This tool is currently in operation in Madrid, producing daily air quality predictions for the next 48 h and anticipating the probability of the activation of the measures included in the city's official air quality NO₂ protocols through probabilistic inferences about compound events.

由于空气污染物的不利影响已被证实，空气质量已成为公共卫生和城市规划管理的核心问题。考虑到用于应对低空气质量事件的临时行动限制措施，预测污染物浓度的能力至关重要。因此，我们提出了 SOCAIRE（西班牙语“空气质量运行预测系统”的首字母缩写词），这是一种基于贝叶斯和神经和统计嵌套模型的时空集合的运行工具。SOCAIRE 整合内源性和外源性信息，以预测和监测主要污染物浓度的未来分布。它侧重于对影响空气质量的可用组件进行建模：过去的污染物浓度、人类活动以及数值污染和天气预报。₂协议通过关于复合事件的概率推断。