{
    "created": "2026-06-24 17:15:10",
    "updated": "2026-06-24 12:24:02",
    "id": "626fdfb5-61ef-4ef4-8563-305b4078911b",
    "version": 2,
    "ds_topic": null,
    "title_cn": "中国高分辨率逐日 CO₂ 数据集 (2016–2020年)",
    "title_en": "A High-Resolution daily CO₂ Dataset for China (2016–2020)",
    "ds_abstract": "<p>&emsp;&emsp;高分辨率柱平均干空气 CO<sub>2</sub>摩尔分数（XCO<sub>2</sub>）数据对于表征碳源汇特征、推进碳循环研究，以及支撑碳达峰、碳中和等气候政策目标至关重要。然而，受云量和气溶胶干扰，当前卫星反演结果往往存在空间碎片化和时间不连续的问题。为弥补这些不足，本研究采用经贝叶斯优化的 XGBoost 模型（XGBoost-BO），构建了大气 XCO<sub>2</sub>浓度与多源辅助参数之间的稳健映射关系。尤为关键的是，研究引入了 SHAP（沙普利可加性解释）方法以增强模型可解释性，确保重建结果能够捕捉中国范围内具有物理意义的时空动态。重建后的 XCO₂数据集与 OCO-2 卫星观测具有高度一致性，决定系数（R<sup>2</sup>）达 0.98，均方根误差（RMSE）为 0.58 ppm，平均绝对百分比误差（MAPE）为 0.07%。经中国地区地面 TCCON 观测进一步验证，模型可靠性得到确认：合肥站 R<sup>2</sup> 为 0.92（RMSE = 1.16 ppm，MAPE = 0.2%），香河站 R<sup>2</sup> 为 0.70（RMSE = 2.00 ppm，MAPE = 0.4%）。\n<p>&emsp;&emsp;内容详见数据关联论文。",
    "ds_source": "",
    "ds_process_way": "",
    "ds_quality": "",
    "ds_acq_start_time": "2016-01-01 00:00:00",
    "ds_acq_end_time": "2020-12-31 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": 493964267,
    "ds_files_count": 0,
    "ds_format": "NetCDF",
    "ds_space_res": "0.1°*0.1°",
    "ds_time_res": "日",
    "ds_coordinate": "无",
    "ds_projection": "",
    "ds_thumbnail": "626fdfb5-61ef-4ef4-8563-305b4078911b.png",
    "ds_thumb_from": 0,
    "ds_ref_way": "",
    "paper_ref_way": "",
    "ds_ref_instruction": "",
    "ds_from_station": null,
    "organization_id": "0a4269e1-65f4-45f1-aeba-88ea3068eebf",
    "ds_serv_man": null,
    "ds_serv_phone": null,
    "ds_serv_mail": null,
    "doi_value": "",
    "subject_codes": [
        "170.15"
    ],
    "quality_level": 0,
    "publish_time": "2026-06-24 17:28:01",
    "last_updated": "2026-06-24 17:28:01",
    "protected": false,
    "protected_to": null,
    "lang": "zh",
    "cstr": "11738.11.ncdc.atmosphere.db7467.2026",
    "i18n": {
        "en": {
            "title": "A High-Resolution daily CO₂ Dataset for China (2016–2020)",
            "ds_format": "NetCDF",
            "ds_source": "",
            "ds_quality": "",
            "ds_ref_way": "",
            "ds_abstract": "<p>&emsp;High-resolution column-averaged dry-air CO<sub>2</sub> mole fraction (XCO<sub>2</sub>) data are essential for characterizing carbon sources and sinks, advancing carbon cycle research, and supporting climate policy goals such as carbon peaking and carbon neutrality. However, current satellite retrievals are often spatially fragmented and temporally discontinuous due to cloud cover and aerosol interference. To address these limitations, this study utilizes an XGBoost model optimized via Bayesian optimization (XGBoost-BO) to construct a robust mapping relationship between atmospheric XCO<sub>2</sub> concentrations and multi-source auxiliary parameters. Crucially, the incorporation of the SHAP (SHapley Additive exPlanations) methodology enhances model interpretability, ensuring that the reconstruction captures physically meaningful spatiotemporal dynamics across China. The reconstructed XCO<sub>2</sub> dataset exhibits high consistency with OCO-2 satellite observations, achieving a coefficient of determination (R²) of 0.98, a Root Mean Square Error (RMSE) of 0.58 ppm, and a Mean Absolute Percentage Error (MAPE) of 0.07%. The model’s reliability is further validated against ground-based TCCON measurements in China, achieving an R<sup>2</sup> of 0.92 (RMSE = 1.16 ppm, MAPE = 0.2%) at the Hefei site and an R<sup>2</sup> of 0.70 (RMSE = 2.00 ppm, MAPE = 0.4%) at the Xianghe site.\r\n<p>&emsp;For detailed information, please refer to the associated data paper.",
            "ds_time_res": "",
            "ds_acq_place": "China",
            "ds_space_res": "",
            "ds_projection": "",
            "ds_process_way": "",
            "ds_ref_instruction": ""
        }
    },
    "submit_center_id": "ncdc",
    "data_level": 0,
    "recommendation_value": 0,
    "license_type": "https://creativecommons.org/licenses/by/4.0/",
    "doi_reg_from": "reg_local",
    "cstr_reg_from": "reg_local",
    "doi_not_reg_reason": null,
    "cstr_not_reg_reason": null,
    "is_paper_in_submitting": false,
    "belong_to_nieer": false,
    "ds_topic_tags": [
        "CO₂",
        "CO₂摩尔分数",
        "XGBoost 模型",
        "SHAP"
    ],
    "ds_subject_tags": [
        "大气科学"
    ],
    "ds_class_tags": [],
    "ds_locus_tags": [
        "中国"
    ],
    "ds_time_tags": [
        2016,
        2017,
        2018,
        2019,
        2020
    ],
    "ds_contributors": [
        {
            "true_name": "杨爱霞",
            "email": "yangax@radi.ac.cn",
            "work_for": "中国科学院空天信息创新研究院",
            "country": "中国"
        }
    ],
    "ds_meta_authors": [
        {
            "true_name": "杨爱霞",
            "email": "yangax@radi.ac.cn",
            "work_for": "中国科学院空天信息创新研究院",
            "country": "中国"
        }
    ],
    "ds_managers": [
        {
            "true_name": "杨爱霞",
            "email": "yangax@radi.ac.cn",
            "work_for": "中国科学院空天信息创新研究院",
            "country": "中国"
        }
    ],
    "category": "气象"
}