Surface ozone (O3) pollution is a severe environmental problem that endangers human health. It is necessary to obtain high spatiotemporal resolution O3 data to provide support for pollution monitoring and prevention. For this purpose, this study makes comprehensive use of remote sensing data, reanalysis data, and ground station observations and develops an enhanced geographically and temporally weighted neural network (EGTWNN) model to acquire high spatial and temporal resolutions of O3 data. The EGTWNN model is nested by two neural networks (NNs). The first NN automatically learns the spatiotemporal proximity relationship to obtain spatiotemporal weights for the samples, and the spatiotemporal weights are then inputted into the second NN to conduct weighted modeling of the relationship between O3 and influencing variables. The contribution of the proposed model is that the first NN replaces the traditional empirical weighting method and represents the spatiotemporal proximity relationship more accurately to improve estimation accuracy. Results indicate that the cross-validation R2R^{2} and the root mean square error (RMSE) of EGTWNN are 0.81 and 21.24 μg21.24 \ \mu \text{g} /m3, respectively, which are increased by 0.02 and decreased by ∼1 μg\sim 1 \ \mu \text{g} /m3 relative to those of the traditional empirical weighting method-based geographically and temporally weighted NN model. The results also show that, compared with the geographically and temporally weighted regression model, the proposed model achieves superior performance. In addition, the spatiotemporal weights obtained by the first NN of EGTWNN are highly consistent with those obtained by the traditional empirical weighting method, indicating that the results of NNs are highly interpretable.

中文翻译：

---

用于地表臭氧遥感估算的增强型地理和时间加权神经网络


地表臭氧（O3）污染是危害人类健康的严重环境问题。需要获取高时空分辨率的O3数据，为污染监测和防治提供支撑。为此，本研究综合利用遥感数据、再分析数据和地面站观测，开发了增强型地理和时间加权神经网络（EGTWNN）模型来获取O3数据的高空间和时间分辨率。 EGTWNN 模型由两个神经网络 (NN) 嵌套。第一个神经网络自动学习时空邻近关系以获得样本的时空权重，然后将时空权重输入到第二个神经网络对O3与影响变量之间的关系进行加权建模。该模型的贡献在于，第一个神经网络取代了传统的经验加权方法，更准确地表示时空邻近关系，从而提高了估计精度。结果表明，EGTWNN的交叉验证R2R^{2}和均方根误差（RMSE）分别为0.81和21.24 μg21.24 \ \mu \text{g} /m3，分别增加了0.02和降低相对于传统的基于经验加权方法的地理和时间加权神经网络模型，提高了∼1 μg\sim 1 \ \mu \text{g} /m3。结果还表明，与地理和时间加权回归模型相比，所提出的模型具有优越的性能。此外，EGTWNN的第一个神经网络得到的时空权重与传统经验加权方法得到的时空权重高度一致，表明神经网络的结果具有很强的可解释性。