{
  "abstract": "目的以陕西省延安市吴起县和志丹县的213个林地表层（0~20 cm）土壤样本为研究对象，采集可见-近红外（Vis-NIR）光谱及实测土壤有机碳（SOC）质量分数，探究非线性数学变换结合分数阶微分（FOD）处理对光谱特征挖掘及模型性能的影响，为提高黄土高原地表SOC质量分数的光谱估测精度及智能化辨识提供支持。方法对原始光谱（R）采取倒数（1/R）、对数（lg R）、对数倒数（1/lg R）、平方根（R）等4种非线性变换，及0~2阶（步长0.1）的FOD处理，利用竞争性自适应重加权采样（CARS）和连续投影算法（SPA）筛选特征波段，构建并对比偏最小二乘回归（PLSR）、随机森林（RF）和极限梯度提升（XGBoost）3种模型的反演效果。结果研究区林地土壤SOC质量分数为2.50~23.11 g/kg，平均值为7.70 g/kg。在原始反射光谱（R）中，SOC质量分数较高的样本整体反射率水平较低，光谱反射率随SOC升高呈整体降低趋势，光谱特征波段集中在550~800 nm及900 nm附近。相较于整数阶和>1.5的高阶微分，采用0.3~0.9阶的FOD数据预处理，能有效去除基线漂移并凸显细部光谱特征。对数与倒数的非线性变换可以显著提升光谱对SOC的辨识程度。相比SPA，CARS在测试集上R²平均提升0.052，RMSE平均降低0.147 g/kg，RPD平均提升0.132。在所有模型中，PLSR的预测性能整体优于RF和XGBoost，基于非线性变换与FOD处理的CARS-PLSR模型测试集R²可达0.843。结论研究证实，非线性变换结合中低阶分数阶微分及CARS-PLSR建模策略，可有效提升黄土高原土壤有机碳的光谱估测精度。",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "name": "刘璇皓"
    },
    {
      "name": "张晓萍"
    },
    {
      "name": "文艳"
    },
    {
      "name": "胡志斌"
    },
    {
      "name": "段辰"
    },
    {
      "name": "孙贯芳"
    },
    {
      "name": "陈庆伟"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/aggbpq8h0gszr.bib",
  "cited_by": 0,
  "doi": null,
  "fulltext_url": "http://www.stbcxb.com.cn/zh/article/doi/10.13870/j.cnki.stbcxb.2026.05.003/",
  "id": "aggbpq8h0gszr",
  "issns": [
    "1009-2242"
  ],
  "landing_url": "http://www.stbcxb.com.cn/zh/article/doi/10.13870/j.cnki.stbcxb.2026.05.003/",
  "language": "zh",
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "lcc",
      "GE1-350"
    ],
    [
      "lcc",
      "S"
    ]
  ],
  "openalex": null,
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-24",
  "publisher": "Editorial Department of Journal of Soil and Water Conservation",
  "ris": "https://research.draconitic.com/paper/aggbpq8h0gszr.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T13:44:46Z",
      "native_id": "997f75f0d6b94e3ebd194b4a953f7fec",
      "source": "doaj",
      "url": "http://www.stbcxb.com.cn/zh/article/doi/10.13870/j.cnki.stbcxb.2026.05.003/"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "lcc:GE1-350",
      "subfield": "environmental-science"
    }
  ],
  "title": "基于非线性变换与分数阶微分的土壤有机碳光谱估测",
  "title_text": "基于非线性变换与分数阶微分的土壤有机碳光谱估测",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T13:44:46Z",
  "url": "https://research.draconitic.com/paper/aggbpq8h0gszr",
  "venue": "Shuitu Baochi Xuebao",
  "versions": []
}