Air Quality Data from Regulatory AQMS and Low-Cost Sensors in Bulevar Sur, Valencia (July 08 - November 18, 2023)

This dataset contains parallel time-series data for air quality and meteorological parameters, collected for the purpose of calibrating a low-cost air quality sensor (LCS) against a regulatory-grade reference monitoring station. The data was collected continuously for 165 days, from June 8, 2023, to November 20, 2023, at the Bulevar Sur air quality station in Valencia, Spain. The dataset is divided into two main sources: Reference Data (GVA): The gva_*.csv files originate from an official Valencian AQ Monitoring Network (VAQMN) station, managed by the Generalitat Valenciana (GVA). This data represents the high-accuracy "ground truth" measurements from professional, regulatory-grade instruments. The selected reference station is located at (lat: 39.45037852, lon: -0.39631399), and is identified by its code 46250050 Low-Cost Sensor Data (LCS): The lcs_*.csv files contain raw data collected by an IoT node equipped with a ZPHS01B multi-sensor module. This node was co-located with the official GVA station to ensure measurements were taken under identical ambient conditions. The raw sensor data has been processed and aggregated into synchronized time intervals of 10, 30, and 60 minutes to facilitate direct comparison and the training of machine learning models. This dataset was used to develop and evaluate machine learning algorithms to improve the accuracy of raw ozone (O3) readings from the low-cost sensor, as detailed in the related publication.本数据集包含空气质量与气象参数的并行时序数据，采集目的是针对低成本空气质量传感器（low-cost air quality sensor, LCS）与合规级基准监测站开展校准。数据于2023年6月8日至2023年11月20日连续采集165天，采集点位位于西班牙巴伦西亚的布莱瓦尔苏尔空气质量监测站。 本数据集分为两大来源： 参考数据（GVA）："gva_*.csv"文件源自巴伦西亚官方空气质量监测网络（Valencian AQ Monitoring Network, VAQMN）站点，由巴伦西亚自治区（Generalitat Valenciana, GVA）运营管理。该数据为专业合规级仪器采集的高精度「地面真值」测量结果。 选定的基准监测站坐标为（纬度：39.45037852，经度：-0.39631399），站点编号为46250050。 低成本传感器数据（LCS）："lcs_*.csv"文件包含搭载ZPHS01B多传感器模块的物联网（Internet of Things, IoT）节点采集的原始数据。该节点与GVA官方站点共址部署，以确保二者在完全一致的环境条件下开展测量。 原始传感器数据已完成处理与聚合，被整理为10分钟、30分钟及60分钟的同步时间间隔，以支持直接对比分析与机器学习模型训练。本数据集曾用于开发并评估机器学习算法，以提升低成本传感器的原始臭氧（O₃）读数精度，相关细节已在关联发表的学术论文中详述。