目前，在各种大气污染物的模拟中，独立痕量气体（SO2 和 O3）的模拟受到关键遥感产品分辨率不足的制约，导致模拟可靠性不足。本研究将空间采样和参数卷积相结合，利用地面观测、遥感产品、气象数据、援助数据和随机 ID 优化 LightGBM。通过上述技术和大气污染物序列模拟，我们得到了 2015-2020 年中国大部分地区 PM2.5、SO2 和 O3 每日 1 公里分辨率的无缝产品。通过随机抽样、随机站点抽样、特定区域验证、不同模型比较以及不同研究的横向比较，我们验证了我们对多种大气污染物空间分布的模拟是可靠和有效的。随机样本的 CV 值为：PM2.5 的 R2 为 0.88，均方根误差为 9.91 µg/m3；SO2 的 R2 为 0.89，均方根误差为 4.62 µg/m3；O3 的 R2 为 0.91，均方根误差为 6.88 µg/m3。结合 SHapley Additive exPlanations（SHAP）方法，明确了模拟过程中不同参数的作用，并证实了参数卷积的积极作用。我们利用数据集评估了 COVID-19 爆发前后中国空气污染指数（API）的变化，结果表明这些变化相对较小，表明 2020 年的疫情控制措施是有效的。该研究表明，利用所提出的模型生成的多污染物数据集对于长期、大规模和区域范围的空气污染监测和预测以及人群健康评估具有重要价值。
", "ds_source": "本研究使用的数据包括中国PM2.5、SO2和03的日常地面监测数据，此外还使用了遥感数据、气象数据和辅助数据。
", "ds_process_way": "基于随机ID的多污染物通用机器学习模型、空间采用、参数卷积和其他方法的多污染物通用机器学习模型，用于改进 在预测大气污染物浓度变化时考虑多种因素，并优化对污染物空间分布的估计。浓度变化时对多种因素的考虑，并优化对污染物空间分布的估计。
", "ds_quality": "数据质量良好。
", "ds_acq_start_time": "2015-01-01 00:00:00", "ds_acq_end_time": "2018-03-18 00:00:00", "ds_acq_place": "中国", "ds_acq_lon_east": null, "ds_acq_lat_south": null, "ds_acq_lon_west": null, "ds_acq_lat_north": null, "ds_acq_alt_low": null, "ds_acq_alt_high": null, "ds_share_type": "open-access", "ds_total_size": 49907647678, "ds_files_count": 1174, "ds_format": "GeoTIFF", "ds_space_res": "1000", "ds_time_res": "1day", "ds_coordinate": "WGS84", "ds_projection": "", "ds_thumbnail": "4b3fc46e-5ecd-4422-ab78-e7685866ee63.png", "ds_thumb_from": 0, "ds_ref_way": "", "paper_ref_way": "", "ds_ref_instruction": "用户在使用数据时请在正文中明确声明数据的来源，并在参考文献部分引用本元数据提供的引用方式。", "ds_from_station": null, "organization_id": "0a4269e1-65f4-45f1-aeba-88ea3068eebf", "ds_serv_man": "敏玉芳", "ds_serv_phone": "0931-4967596", "ds_serv_mail": "ncdc@lzb.ac.cn", "doi_value": "", "subject_codes": [ "170.45" ], "quality_level": 3, "publish_time": "2024-08-29 09:03:00", "last_updated": "2025-06-30 16:18:32", "protected": false, "protected_to": null, "lang": "zh", "cstr": "11738.11.NCDC.ZENODO.DB6663.2024", "i18n": { "en": { "title": "Spatial distribution of various air pollutants in China at 1 km(PM2.5 2015-01-01:2018-03-18)", "ds_format": "GeoTIFF", "ds_source": "The data used in this study include daily ground monitoring data for PM2.5, SO2, and O3 in China. Additionally, remote sensing data, meteorological data, and auxiliary data are used.
", "ds_quality": "The data quality is good.
", "ds_ref_way": "", "ds_abstract": "Currently, in the modeling of various atmospheric pollutants, the simulation of independent trace gases (SO2 and O3) is constrained by the insufficient resolution of key remote sensing products, resulting in insufficient simulation reliability. In this study, spatial sampling and parameter convolution are combined to optimize LightGBM by utilizing ground observations, remote sensing products, meteorological data, assistance data, and random ID. Through the above techniques and an sequentialsimulation of air pollutants, we produce seamless daily 1-km-resolution products of PM2.5, SO2 and O3 for most parts of China from 2015 to 2020. Through random sampling, random site sampling, area-specific validation, comparisons of different models, and a cross-sectional comparison of different studies, we verified that our simulations of the spatial distribution of multiple atmospheric pollutants are reliable and effective. The CV of the random sample yielded an R2 of 0.88 and an RMSE of 9.91 µg/m3 for PM2.5, an R2 of 0.89 and an RMSE of 4.62 µg/m3 for SO2, and an R2 of 0.91 and an RMSE of 6.88 µg/m3 for O3. Combined with the SHapley Additive exPlanations (SHAP) approach, the roles of different parameters in the simulation process were clarified, and the positive role of parameter convolution was confirmed. Our dataset was used to assess the changes in the Air Pollution Index (API) in China before and after the outbreak of COVID-19, and the results indicate that these changes were relatively small huge, suggesting that the epidemic control measures in 2020 were effective. The study demonstrates that the multipollutant datasets produced with the proposed models are of great value for long-term, large-scale, and regional-scale air pollution monitoring and prediction, as well as population health evaluation.
", "ds_time_res": "1day", "ds_acq_place": "China", "ds_space_res": "1000", "ds_projection": "", "ds_process_way": "A general machine learning model for multiple pollutants based on random ID, spatial adoption, parameter convolution, and other methods is used to improve the consideration of multiple factors in the prediction of changes in atmospheric pollutant concentrations and optimize estimates of the spatial distributions of pollutants
", "ds_ref_instruction": "When using data, users should clearly declare the source of the data in the main text and cite the citation method provided by this metadata in the reference section." } }, "submit_center_id": "ncdc", "data_level": 0, "license_type": "https://creativecommons.org/licenses/by/4.0/", "doi_reg_from": "reg_outside", "cstr_reg_from": "reg_outside", "doi_not_reg_reason": null, "cstr_not_reg_reason": null, "is_paper_in_submitting": false, "ds_topic_tags": [ "大气污染物", "PM2.5", "SO2", "O3" ], "ds_subject_tags": [ "地理学" ], "ds_class_tags": [], "ds_locus_tags": [ "中国" ], "ds_time_tags": [ 2015, 2016, 2017, 2018 ], "ds_contributors": [ { "true_name": "池毓锋", "email": "418338906@139.com", "work_for": "三明学院信息工程学院", "country": "中国" }, { "true_name": "叶红", "email": "hye@iue.ac.cn", "work_for": "中国科学院城市环境研究所", "country": "中国" } ], "ds_meta_authors": [ { "true_name": "池毓锋", "email": "418338906@139.com", "work_for": "三明学院信息工程学院", "country": "中国" }, { "true_name": "叶红", "email": "hye@iue.ac.cn", "work_for": "中国科学院城市环境研究所", "country": "中国" } ], "ds_managers": [ { "true_name": "池毓锋", "email": "418338906@139.com", "work_for": "三明学院信息工程学院", "country": "中国" }, { "true_name": "叶红", "email": "hye@iue.ac.cn", "work_for": "中国科学院城市环境研究所", "country": "中国" } ], "category": "生态" }