Abstract:
Land use regression (LUR) models have been extensively used to predict air pollution exposure in epidemiological and environmental studies. The lack of dense routine monitoring networks in big cities places increased emphasis on the need for LUR models to be developed using purpose-designed neighborhood-scale monitoring data. However, the unsatisfactory model transferability limits these neighborhood LUR models to be then applied to other intra-urban areas in predicting air pollution exposure. In this study, we tackled this issue by proposing a method to develop transferable neighborhood NO2 LUR models with comparable predictive power based on only micro-scale predictor variables for modeling intra-urban ambient air pollution exposure. Taking Auckland metropolis, New Zealand, as a case study, the proposed method was applied to three neighborhoods (urban, central business district, and dominion road) and compared with the corresponding counterpart models developed using pools of (a) only macro-scale predictor variables and (b) a mixture of both micro- and macro-scale predictor variables (traditional method). The results showed that the models using only macro-scale variables achieved the lowest accuracy (R2: 0.388-0.484) and had the worst direct (R2: 0.0001-0.349) and indirect transferability (R2: 0.07-0.352). Those models using the traditional method had the highest model fitting R2 (0.629-0.966) with lower cross-validation R2 (0.495-0.941) and slightly better direct transferability (R2: 0.0003-0.386) but suffered poor model interpretability when indirectly transferred to new locations. Our proposed models had comparable model fitting R2 (0.601-0.966) and the best cross-validation R2 (0.514-0.941). They also had the strongest direct transferability (R2: 0.006-0.590) and moderate-to-good indirect transferability (R2: 0.072-0.850) with much better model interpretability. This study advances our knowledge of developing transferable LUR models for the very first time from the perspective of the scale of the predictor variables used in the model development and will significantly benefit the wider application of LUR approaches in epidemiological and environmental studies.
摘要:
在流行病学和环境研究中,土地利用回归(LUR)模型已被广泛用于预测空气污染暴露。大城市缺乏密集的常规监测网络,越来越强调需要使用专门设计的邻域尺度监测数据开发LUR模型。然而,不令人满意的模型可转移性限制了这些邻域LUR模型,然后将其应用于其他城市内地区以预测空气污染暴露。在这项研究中,我们通过提出一种方法来开发可转移的邻域NO2LUR模型,该模型具有可比的预测能力,仅基于微观尺度预测变量,用于对城市内环境空气污染暴露进行建模。以奥克兰大都市为例,新西兰,作为一个案例研究,所提出的方法应用于三个社区(城市,中央商务区,和统治道路),并与使用(a)仅宏观预测变量和(b)微观和宏观预测变量的混合(传统方法)开发的相应对应模型进行比较。结果表明,仅使用宏观变量的模型精度最低(R2:0.388-0.484),直接(R2:0.0001-0.349)和间接可转移性(R2:0.07-0.352)最差。使用传统方法的那些模型具有最高的模型拟合R2(0.629-0.966),具有较低的交叉验证R2(0.495-0.941)和稍好的直接可转移性(R2:0.0003-0.386),但是当间接转移到新位置时,遭受较差的模型可解释性。我们提出的模型具有可比的模型拟合R2(0.601-0.966)和最佳交叉验证R2(0.514-0.941)。它们还具有最强的直接转移性(R2:0.006-0.590)和中等至良好的间接转移性(R2:0.072-0.850),具有更好的模型可解释性。这项研究从模型开发中使用的预测变量的规模的角度首次提高了我们开发可转移LUR模型的知识,并将大大有利于LUR方法在流行病学和环境研究中的广泛应用。