There is a very extensive literature on the design and test of models of environmental pollution, especially in the atmosphere. Current and recent models, however, are focused on explaining the causes and their temporal relationships, but do not explore, in full detail, the performances of pure forecasting models. We consider here three years of data that contain hourly nitrogen oxides concentrations in the air; exposure to high concentrations of these pollutants has been indicated as potential cause of numerous respiratory, circulatory, and even nervous diseases. Nitrogen oxides concentrations are paired with meteorological and vehicle traffic data for each measure. We propose a methodology based on exactness and robustness criteria to compare different pollutant forecasting models and their characteristics. 1DCNN, GRU and LSTM deep learning models, along with Random Forest, Lasso Regression and Support Vector Machines regression models, are analyzed with different window sizes. As a result, our best models offer a 24-hours ahead, very reliable prediction of the concentration of pollutants in the air in the considered area, which can be used to plan, and implement, different kinds of interventions and measures to mitigate the effects on the population.

有大量关于环境污染模型的设计和测试的文献，特别是在大气中。然而，当前和最近的模型侧重于解释原因及其时间关系，但并未详细探讨纯预测模型的性能。我们在这里考虑了包含空气中每小时氮氧化物浓度的三年数据；暴露于高浓度的这些污染物已被证明是导致许多呼吸系统、循环系统甚至神经系统疾病的潜在原因。氮氧化物浓度与每项措施的气象和车辆交通数据配对。我们提出了一种基于准确性和稳健性标准的方法来比较不同的污染物预测模型及其特征。1DCNN，GRU 和 LSTM 深度学习模型，以及随机森林、套索回归和支持向量机回归模型，在不同的窗口大小下进行分析。因此，我们的最佳模型可提前 24 小时提供对所考虑区域空气中污染物浓度的非常可靠的预测，可用于规划和实施不同类型的干预措施和措施以减轻影响在人口上。