基于哨兵光学的兴安盟土壤有机碳密度遥感反演研究

doi:10.14088/j.cnki.issn0439-8114.2025.11.024

湖北农业科学 ›› 2025, Vol. 64 ›› Issue (11): 175-181.doi: 10.14088/j.cnki.issn0439-8114.2025.11.024

基于哨兵光学的兴安盟土壤有机碳密度遥感反演研究

王欣欣¹, 余静^2,3,4, 朱华晨⁴, 赵珍妮⁴, 陈晓龙⁴

1.重庆交通大学智慧城市学院,重庆 400074;
2.重庆大学机械与运载工程学院,重庆 400044;
3.中国科学院大学重庆学院,重庆 400700;
4.重庆市地理信息和遥感应用中心,重庆 401120

收稿日期:2025-03-24 出版日期:2025-11-25 发布日期:2025-12-05
作者简介:王欣欣（2001-）,女,山西运城人,硕士,主要从事遥感数据分类与三维点云处理研究,（电话）18295956030（电子信箱）wxxmsn222@outlook.com;余静（1982-）,女,湖北武汉人,正高级工程师,在读博士研究生,主要从事数字城市、时空大数据、遥感监测应用研究,（电话）15923356226（电子信箱）37225009@qq.com。

A remote sensing retrieval study of soil organic carbon density in Xing'an League based on Sentinel optical data

WANG Xin-xin¹, YU Jing^2,3,4, ZHU Hua-chen⁴, ZHAO Zhen-ni⁴, CHEN Xiao-long⁴

1. School of Smart City, Chongqing Jiaotong University, Chongqing 400074, China;
2. College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing 400044, China;
3. Chongqing School, University of Chinese Academy of Sciences, Chongqing 400700, China;
4. Chongqing Geomatics and Remote Sensing Application Center, Chongqing 401120, China

Received:2025-03-24 Published:2025-11-25 Online:2025-12-05

摘要/Abstract

摘要： 通过遥感和地理信息技术对2023年内蒙古自治区兴安盟土壤有机碳密度进行空间估算。基于遥感数据、环境（地形、气候、土壤等）数据提取多种环境变量,以实地土壤采样获得的土壤属性数据作为响应变量。采用随机森林（RF）、极度梯度提升（XGBoost）和多层感知器（MLP）进行回归建模与精度比较。基于精度评价结果选择性能最佳的模型,最终完成研究区土壤有机碳密度的空间制图。结果表明,RF模型表现最佳（R²=0.86,RMSE=1.51 kg/m²）,XGBoost模型性能略逊于RF模型,但仍表现良好,而MLP模型在本任务中表现明显不佳,精度远低于另外2个模型。兴安盟土壤有机碳密度空间分布呈明显的南北差异,整体从西北向东南递减,从垂直分布看,有机碳密度随取样深度增加呈先减少后增加的趋势。

关键词: 土壤, 有机碳密度, 哨兵光学, 遥感, 反演, 兴安盟

Abstract: A spatial estimation of soil organic carbon density in Xing'an League of the Inner Mongolia Autonomous Region was conducted for the year 2023 using remote sensing and geographic information technologies. Multiple environmental variables were extracted based on remote sensing data and environmental data (e.g., terrain, climate, soil), with soil property data obtained from field soil sampling serving as the response variable. Regression modeling and accuracy comparison were performed using Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Multilayer Perceptron (MLP). Based on the accuracy evaluation results, the best-performing model was selected to ultimately complete the spatial mapping of soil organic carbon density in the study area. The results showed that the RF model performed the best (R² = 0.86, RMSE = 1.51 kg/m²), the XGBoost model performed slightly worse than the RF model but still well, while the MLP model performed significantly worse in this task, with its accuracy being much lower than the other two models. The spatial distribution of soil organic carbon density in Xing'an League showed obvious north-south differences, generally decreasing from northwest to southeast. In terms of vertical distribution, the organic carbon density first decreased and then increased with increasing sampling depth.

Key words: soil, organic carbon density, Sentinel optical, remote sensing, inversion, Xing'an League

中图分类号:

TP237

王欣欣, 余静, 朱华晨, 赵珍妮, 陈晓龙. 基于哨兵光学的兴安盟土壤有机碳密度遥感反演研究[J]. 湖北农业科学, 2025, 64(11): 175-181.

WANG Xin-xin, YU Jing, ZHU Hua-chen, ZHAO Zhen-ni, CHEN Xiao-long. A remote sensing retrieval study of soil organic carbon density in Xing'an League based on Sentinel optical data[J]. HUBEI AGRICULTURAL SCIENCES, 2025, 64(11): 175-181.

参考文献

[1] 陈月,胡艳燕,杨丽军,等.重庆市中心城区公园绿地土壤有机碳含量及密度分布特征[J].南方农业,2024,18(21):80-83,89.
[2] 樊子豪,崔鸿侠,沈琛琛,等.神农架林区天然次生林土壤有机碳分布及影响因素[J].生态学报,2024,44(16):7130-7139.
[3] 张楚磊,田耀武.河南省土壤有机碳储量及影响因素[J].环境监测管理与技术,2024,36(4):71-76.
[4] 李敏. 森林土壤碳储量研究综述[J].林业调查规划,2018, 43(4):21-24,50.
[5] MITRA A, BANERJEE K, SETT S.Spatial variation in organic carbon density of mangrove soil in Indian sundarbans[J]. National academy science letters, 2012, 35(3): 147-154.
[6] LEE J, HOPMANS J W, ROLSTON D E, et al.Determining soil carbon stock changes: Simple bulk density corrections fail[J]. Agricultureecosystems & environment, 2009, 134(3-4): 251-256.
[7] BAUER A, BLACK A L.Soil carbon, nitrogen, and bulk density comparisons in two cropland tillage systems after 25 years and in virgin grassland[J]. Soil science society of America journal, 1981, 45(6): 1166-1170.
[8] ZABOWSKI D, CHAMBREAU D, ROTRAMEL N, et al.Long-term effects of stump removal to control root rot on forest soil bulk density, soil carbon and nitrogen content[J]. Forest ecology and management, 2008, 255(3-4): 720-727.
[9] FALAHATKAR S, HOSSEINI S M, AYOUBI S, et al.Predicting soil organic carbon density using auxiliary environmental variables in northern Iran[J]. Archives of agronomy and soil science, 2016, 62(3): 375-393.
[10] 张启月,张国徽.吉林省森林碳储量及经济价值核算研究[J].山东农业大学学报(自然科学版),2025,56(1):21-31.
[11] LOBSEY C R, VISCARRA ROSSEL R A. Sensing of soil bulk density for more accurate carbon accounting[J]. European journal of soil science, 2016, 67(4): 504-513.
[12] 刘文辉,董林泉.兰州—白银地区1987年与2014年表层土壤有机碳储量和碳密度变化趋势及影响因素探讨[J].甘肃地质,2023,32(2):48-55.
[13] 谷欣逾,赵明松,王世航,等.近40年安徽省土壤有机碳密度时空变化及驱动力分析[J/OL].环境科学,2025:1-14(2025-03-10).https://kns.cnki.net/kcms2/article/abstract?v=IPzr95zWmwQkAJdI1lr5KyXA2GR_wNTJbYkXvMJDFMunokidwcPrNS-1Cv9j27Rnv2LvF8zjUkk96GU0bGvgRBdzIh54iWlo6Qk_0BXr8q0v_jj214sorY-0ctiS5JBg6AjSX9tSLkAlpQa5EQBzU9JLFYLEfR2YHSqKnUokUJ2_2hQJVwMICQ==&uniplatform=NZKPT&language=CHS.
[14] 杜倩,王岩,万祖梁,等.基于随机森林模型的呼中冻土区土壤碳空间分布特征[J].森林工程,2025,41(1):100-107.
[15] 郭艳杰,毕华兴,赵丹阳,等.不同密度油松林地土壤水碳分布特征及其耦合关系[J].应用生态学报,2025,36(1):50-58.
[16] 张艺,梁超.“双碳”视域下内蒙古地区农业生态效率时空演进特征及影响因素研究[J].中国农业资源与区划,2025, 46(6):90-99.
[17] 李鸿源,张建华.热解法脱除工业废盐中总有机碳的工艺研究[J].无机盐工业,2024,56(10):95-102.
[18] 赵琳盈. 哨兵1号&2号卫星多时相遥感影像的时空表征与变化检测[D].武汉:武汉大学,2023.
[19] FRASER R S, FERRARE R A, KAUFMAN Y J, et al.Algorithm for atmospheric corrections of aircraft and satellite imagery[J]. International journal of remote sensing, 1992, 13(3): 541-557.
[20] WILFORD J, DE CARITAT P, BUI E.Predictive geochemical mapping using environmental correlation[J]. Applied geochemistry, 2016, 66: 275-288.
[21] BREIMAN L.Random forests[J]. Machine learning,2001,45(1):5-32.
[22] YU J W, YOON Y W, BAEK W K, et al.Forest vertical structure mapping using two-seasonal optic images and LiDAR DSM acquired from UAV platform through random forest, XGBoost, and support vector machine approaches[J]. Remote sensing, 2021, 13(21): 4282.

基于哨兵光学的兴安盟土壤有机碳密度遥感反演研究

A remote sensing retrieval study of soil organic carbon density in Xing'an League based on Sentinel optical data

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	陈晓文, 荀佳常, 刘昌永, 张鹤缤, 王晓娅. 地貌敏感区土壤保持的长期演变及其气候时空响应机制——以山西省为例[J]. 湖北农业科学, 2025, 64(9): 27-35.
[2]	顾僖鸿, 刘江龙, 胡桂清, 张文太. 准噶尔西部山区地形序列土壤水力性质及其影响因素[J]. 湖北农业科学, 2025, 64(9): 36-43.
[3]	周奕恺, 姚怡彩, 高源, 张警予, 张斌, 满振团, 王明道, 崔光周. 植物促生菌：从作用机制到绿色农业[J]. 湖北农业科学, 2025, 64(9): 56-65.
[4]	叶晶, 赵亚荣, 钱波, 叶晴, 彭立军. 中国土壤铅环境标准的国际定位与启示——基于15个典型国家与地区的对比分析[J]. 湖北农业科学, 2025, 64(9): 179-184.
[5]	李杰, 董峦. 温宿县台兰河灌区作物的EAA-UNet遥感分类研究[J]. 湖北农业科学, 2025, 64(9): 213-219.
[6]	李亚强, 曹俊涛, 常宇飞, 孟成真, 张珺, 刀剑, 赵春雷, 权畅. GEE与多源遥感在冬小麦自动样本生成与分类中的应用——以邯郸市为例[J]. 湖北农业科学, 2025, 64(9): 220-228.
[7]	陈治宇, 窦世卿. 基于无人机多光谱数据的柑橘叶面积指数反演[J]. 湖北农业科学, 2025, 64(8): 24-30.
[8]	贺瀅霖, 李文龙, 池汝安, 时珺玮, 李建芬, 秦振华. 磷石膏、水稻秸秆和鸡粪联合堆肥及其改良土壤的效果[J]. 湖北农业科学, 2025, 64(8): 73-78.
[9]	杨立荣, 胡桂清, 张文太. 伊犁河谷土壤储水量及其影响因素[J]. 湖北农业科学, 2025, 64(8): 104-109.
[10]	叶灵, 相殿国, 苗锋, 纪明妹, 刘珊, 王胜蕊. 不同栽培模式下小麦养分生产效率及土壤环境风险[J]. 湖北农业科学, 2025, 64(6): 28-32.
[11]	任泉静, 卢宗琪, 李宇航, 顾海萍, 杨毅, 任伟征. 不同植物驯化的土壤微生物对小麦生长的影响[J]. 湖北农业科学, 2025, 64(6): 33-38.
[12]	赵希梅, 裴霄敏, 李奥明洋, 刘天雅, 张政, 李梦蝶, 李继福. 模拟水旱轮作条件下土壤磷素含量对秸秆还田的响应及变化规律[J]. 湖北农业科学, 2025, 64(6): 39-44.
[13]	莫明浩, 刘昭, 石芬芬, 严志伟, 王嘉. 基于土柱模拟的红壤坡耕地耕作土体构型对土壤水运移特征的影响[J]. 湖北农业科学, 2025, 64(6): 45-52.
[14]	杜菲, 黄润生, 杨永花, 杨波. 克拉玛依市石油出口处土壤细菌的鉴定及耐药性[J]. 湖北农业科学, 2025, 64(6): 59-64.
[15]	班若楠, 董峦. 基于深度学习的盐碱地遥感影像反演模型构建[J]. 湖北农业科学, 2025, 64(6): 185-189.