基于GBDT的望奎县农田土壤有机碳主控因子研究

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (3337 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要利用多源公开数据,针对于2012年搜集到的农田土壤有机碳(SOC)数据,通过梯度增强决策树(GBDT)探究SOC的主控因子,揭示SOC空间分异机理.选择国家商品粮食生产基地县和全国产量大县-望奎县作为研究区域,结果表明,GBDT模型相较于一元线性回归模型在所有的自变量上均具有更好的预测效果,总体的R²为0.958,表明该模型能够很好地解释目标变量的变异;碱解氮、有效磷、气温、土壤微生物多样性、速效钾、土壤pH和降水量依次是影响有机碳含量最为显著的几个因素,其中碱解氮以33.85%的影响权重位居最高;7个环境协变量均观察到对SOC的阈值效应,且均具有两个阈值.研究发现任意两个变量都不是独立的,均存在相互作用的负值效应.表明环境变量对SOC含量的影响是一个复杂的交互作用,而不是简单的叠加.侧面证明了过度施肥并不会达到增加土壤肥力的作用,而会造成资源浪费和农田生态污染问题.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	祝元丽
	冯向阳
	闫庆武
	吴子豪

关键词 ：土壤有机碳, 农田, 梯度提升决策树, 主控因子, 黑土区, 非线性关系

Abstract：The nonlinear relationships between soil organic carbon (SOC) and environmental covariates have been extensively proved, the threshold and interaction effects of environmental covariates on SOC content are often ignored. This study, founded upon the SOC data collected in 2012, employs the Gradient Boosting Decision Tree (GBDT) to delve into the thresholds and interactive effects of SOC. It aims to discern the main controlling factors of SOC and unveil the spatial differentiation mechanism of SOC. The national commodity grain production base county, Wangkui County, which is also one of the high-yield counties in China, was selected as the study area. The GBDT model can more flexibly fit the complex nonlinear relationship between SOC and environmental variables, and shows superior predicting performance under all independent variables to the simple linear regression model. The model achieves an overall R² value of 0.958, indicating its ability to effectively explain the variations of the target variable. Alkali-hydrolyzed nitrogen, available phosphorus, temperature, soil microbial system diversity, available potassium, pH and precipitation in turn are the most significant factors influencing SOC content. Alkali-hydrolyzed nitrogen holds the highest influence weight of 33.85%. All 7environmental covariates had threshold effects on SOC with two distinct thresholds. It was found that any two covariates are not independent but exhibit interactive negative effects, indicating that the influence of environmental covariates on SOC concentration is a complex interaction rather than a simple superposition. The above results emphasize that threshold and interaction effects between environment variables should be considered in determining the effective range of environmental variables, the potential process of SOC spatial differentiation, and improving the explanatory power of SOC change in farmland. It indirectly proves the fact that excessive fertilization fails to enhance soil fertility but instead leads to resource wastage and the ecological pollution of farmlands.

Key words： soil organic carbon cultivated land gradient boosting decision tree main controlling factors black soil region nonlinear relationship

收稿日期: 2023-09-13

PACS:

X53

基金资助:国家自然科学基金资助项目(42201271,42201447)

作者简介: 祝元丽(1993-),女,山东烟台人,讲师,博士,主要从事土壤遥感与土地退化.发表论文15篇.6268@cumt.edu.cn.

引用本文:

祝元丽, 冯向阳, 闫庆武, 吴子豪. 基于GBDT的望奎县农田土壤有机碳主控因子研究[J]. 中国环境科学, 2024, 44(3): 1407-1417. ZHU Yuan-li, FENG Xiang-yang, YAN Qing-wu, WU Zi-hao. Spatial distribution and main controlling factors of soil organic carbon under cultivated land based on GBDT model in black soil region of Northeast China. CHINA ENVIRONMENTAL SCIENCECE, 2024, 44(3): 1407-1417.

链接本文:

http://www.zghjkx.com.cn/CN/ 或 http://www.zghjkx.com.cn/CN/Y2024/V44/I3/1407

[1] 韩晓增,邹文秀.我国东北黑土地保护与肥力提升的成效与建议[J]. 中国科学院院刊, 2018,33:206-212. Han X Z, Zou W X. Effects and suggestions of black soil protection and soil fertility increase in northeast China[J]. Proceedings of the Chinese Academy of Sciences, 2018,33:206-212.
[2] 韩晓增,李娜.中国东北黑土地研究进展与展望[J]. 地理科学, 2018,38(7):1032-1041. Han X Z, Li N. Research progress of black soil in northeast China[J]. Scientia Geographica Sinica, 2018,38(7):1032-1041.
[3] 汪景宽,徐香茹,裴久渤,等.东北黑土地区耕地质量现状与面临的机遇和挑战[J]. 土壤通报, 2021,52(3):695-701. Wang J K, Xu X R, Pei J B, et al. Current situations of black soil quality and facing opportunities and challenges in northeast China[J]. Chinese Journal of Soil Science, 2021,52(3):695-701.
[4] 阎百兴,杨育红,刘兴土,等.东北黑土区土壤侵蚀现状与演变趋势[J]. 中国水土保持, 2008,12:26-30. Yan B X, Yang Y H, Liu X T, et al. Present situation and evolution trend of soil erosion in Northeast black soil region[J]. Soil and Water Conservation in China, 2008,12:26-30.
[5] Li M, Han X Z, Du S L, et al. Profile stock of soil organic carbon and distribution in croplands of Northeast China[J]. Catena, 2019,174:285-292.
[6] Chen D Y, Xue M Y, Duan X W, et al. Changes in topsoil organic carbon from 1986to 2010in a mountainous plateau region in Southwest China[J]. Land Degradation & Development, 2020,31(6):734-747.
[7] 胡贵贵,杨联安,封涌涛,等.基于地理探测器的宝鸡市农田土壤养分影响因子分析[J]. 土壤通报, 2020,51(1):71-78. Hu G G, Yang L A, Feng Y T, et al. Influencing factors of soil nutrients in farmland of Baoji based on geographical detector[J]. Chinese Journal of Soil Science, 2020,51(1):71-78.
[8] Jian J S, Du X, Reiter M S, et al. A meta-analysis of global cropland soil carbon changes due to cover cropping[J]. Soil Biology and Biochemistry, 2020,143:107735.
[9] Zhou Y, Hartemink A E, Shi Z, et al. Land use and climate change effects on soil organic carbon in North and Northeast China[J]. Science of the Total Environment, 2019,647:1230-1238.
[10] Jebari A, del Prado A, Pardo G, et al. Modeling regional effects of climate change on soil organic carbon in Spain[J]. Journal of Environmental Quality, 2018,47(4):644-653.
[11] 李金全,李兆磊,江国福,等.中国农田耕层土壤有机碳现状及控制因素[J]. 复旦学报(自然科学版), 2016,55(2):247-256,266. Li J Q, Li Z L, Jaing G F, et al. A study on soil organic carbon in plough layer of Chinaxs arable land[J]. Fudan Journal(Natural Science), 2016,55(2):247-256,266.
[12] Wang D, Yan Y, Li X, et al. Influence of climate on soil organic carbon in Chinese paddy soils[J]. Chinese GeograpHical Science, 2017,27(5):1-11.
[13] Yu H X, Wei X S, Tan W B. High nitrogen enrichment increases the allocation of new organic carbon to deep soil layers[J]. Geoderma, 2022,406:115515.
[14] Li J H, Zhang R, Cheng B H, et al. Effects of nitrogen and phosphorus additions on decomposition and accumulation of soil organic carbon in alpine meadows on the Tibetan Plateau[J]. Land Degradation & Development, 2020,32(3):1467-1477.
[15] Yuan G Y, Huan, W W, Song, H. Effects of straw incorporation and potassium fertilizer on crop yields, soil organic carbon, and active carbon in the rice-wheat system[J]. Soil and tillage research, 2021, 209:104958.
[16] Pittman R, Hu B, Webster K. Improvement of soil property mapping in the great clay belt of northern ontario using multi-source remotely sensed data[J]. Geoderma, 2021,381:114761.
[17] Siewert M. High-resolution digital mapping of soil organic carbon in permafrost terrain using machine-learning:A case study in a sub- Arctic peatland environment[J]. Biogeosciences, 2018,15:1663-82.
[18] Siewert M B. High-resolution digital mapping of soil organic carbon in permafrost terrain using machine-learning:A case study in a sub- Arctic peatland environment[J]. Biogeosciences Discussions, 2016, 15(6):1663-1682.
[19] Jiang H, Rusuli Y, Amuti T, et al. Quantitative assessment of soil salinity using multi-source remote sensing data based on the support vector machine and artificial neural network[J]. International Journal of Remote Sensing, 2019,40(1):284-306.
[20] 袁玉琦,陈瀚阅,张黎明等.基于多变量与RF算法的耕地土壤有机碳空间预测研究-以福建亚热带复杂地貌区为例[J]. 土壤学报, 2021,58(4):887-899. Yuan Y Q, Chen H Y, Zhang L M, et al. Prediction of spatial distribution of soil organic carbon in farmland based on multi- variables and random forest algorithm-a case study of a subtropical complex geomorphic region in fujian as an example[J]. Acta Pedologica Sinica, 2021,58(4):887-899.
[21] 望奎县人民政府.望奎概况[EB/OL]. Wangkui County People's Government. General situation of Wangkui[EB/OL].
[22] Friedman, J H. Greedy function approximation:A gradient boosting machine[J]. Annals of Statistics, 2001,29(5):1189-1232.
[23] 闫霈,张友静,张元.利用增强型水体指数(EWI)和GIS去噪音技术提取半干旱地区水系信息的研究[J]. 遥感信息, 2007,(6):62-67. Yan P, Zhang Y J, Zhang Y. Study on water system information extraction in semi-arid region by enhanced water index (EWI) and GIS noise removal technology[J]. Remote Sensing Information, 2007, (6):62-67.
[24] 郑超磊,贾立,赵天杰.全球1公里分辨率地表土壤湿度数据集(2000~2020)[DB/OL]. 国家青藏高原科学数据中心, 2022. Zheng C L, Jia L, Zhao T J. Global 1-km resolution soil moisture dataset (2000~2020)[DB/OL]. National Tibetan Plateau Science Data Center, 2022.
[25] Qin R Z, Zhang F. HRLT:A high-resolution(1day, 1km) and long- term(1961~2019) gridded dataset for temperature and precipitation across China[DB/OL]. PANGAEA, 2022.
[26] 马宁,Jozsef Szilagyi,张寅生,等.中国陆地实际蒸散发数据集(1982~2017)[DB/OL]. 国家青藏高原科学数据中心, 2019. Ma N, Jozsef S, Zhang Y S, et al. China land evapotranspiration dataset (1982~2017)[DB/OL]. National Tibetan Plateau Science Data Center, 2019.
[27] 吴志杰,赵书河.基于TM图像的"增强的指数型建筑用地指数"研究[J]. 国土资源遥感, 2012,2:50-55. Wu Z J, Zhao Z H. A study of enhanced index-based built-up index based on Landsat TM imagery[J]. Remote Sensing for land resources, 2012,2:50-55.
[28] Liu J J, Sui Y Y, Yu Z H, et al. High throughput sequencing analysis of biogeographical distribution of bacterial communities in the black soils of northeast China[J]. Soil Biology and Biochemistry, 2014, 70:113-122.
[29] Zhang Y, Guo L, Chen Y, et al. Prediction of soil organic carbon based on Landsat 8monthly NDVI data for the Jianghan plain in Hubei province, China[J]. Remote Sensing, 2019,11(14):1683.
[30] Wang J M, Sun R, Zhang H L, et al. New global musyq GPP/NPP remote sensing products from 1981to 2018[DB/OL]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021,14:5596-5612.
[31] Wang M J, Sun R, Zhu A R, et al. Evaluation and comparison of light use efficiency and gross primary productivity using three different approaches[J]. Remote Sensing, 2020,12(6):1003.
[32] Yu T, Sun R, Xiao Z Q, et al. Estimation of global vegetation productivity from global land surface satellite data[J]. Remote Sensing, 2018,10(2):327.
[33] Crowther T W, Riggs C, Lind E M, et al. Sensitivity of global soil carbon stocks to combined nutrient enrichment[J]. Ecology Letters, 2019,22(6):936-945.
[34] Lu X, Gilliam F S, Guo J, et al. Decrease in soil pH has greater effects than increase in above-ground carbon inputs on soil organic carbon in terrestrial eco-systems of China under nitrogen enrichment[J]. Journal of Applied Ecology, 2022,59:768-778.
[35] Lu X, Vitousek P M, Mao Q, et al. Nitrogen deposition accelerates soil carbon sequestration in tropical forests[J]. Proceedings of the National Academy of Sciences of the United States of America, 2021,118:e2020790118.
[36] Song X D, Yang F, Wu H Y, et al. Significant loss of soil inorganic carbon at the continental scale[J]. National Science Review, 2022, 9(2):13-20.
[37] Liang Z Z, Cao B B, Jiao Y P, et al. Effect of the combined addition of mineral nitrogen and crop residue on soil respiration, organic carbon sequestration, and exogenous nitrogen in stable organic matter[J]. Applied Soil Ecology, 2022,171:104324.
[38] Zhou Z C, Gan Z T, Shang G Z P, et al. Effects of long-term repeated mineral and organic fertilizer applications on soil organic carbon and total nitrogen in a semi-arid cropland[J]. European Journal of Agronomy, 2013,45:20-26.
[39] 朱树伟.耕作方式与施氮量对土壤有机碳积累和小麦玉米产量的影响[D]. 泰安:山东农业大学, 2022. Zhu S W. Effects of tillage methods and nitrogen application rates on soil organic carbon accumulation and yield of wheat and maize[D].Taian, Shandong Agricultural University, 2022.
[40] Feng J G, Zhu B. A global meta-analysis of soil respiration and its components in response to phosphorus addition[J]. Soil Biology & Biochemistry, 2019,135:38-47.
[41] Hou E Q, Luo Y Q, Kuang Y W, et al. Global meta-analysis shows pervasive phosphorus limitation of aboveground plant production in natural terrestrial ecosystems[J]. Nature Communications, 2020,11(1):637.
[42] Zeng W, Wang W. Combination of nitrogen and phosphorus fertilization enhance ecosystem carbon sequestration in a nitrogen- limited temperate plantation of Northern China[J]. Forest Ecology and Management, 2015,341:59-66.
[43] Du E Z, Terrer C, Pellegrini A F A, et al. Global patterns of terrestrial nitrogen and phosphorus limitation[J]. Nature Geoscience, 2020,13(3):221-226.
[44] Ye Y C, Jiang Y F, Kuang L H, et al. Predicting spatial distribution of soil organic carbon and total nitrogen in a typical human impacted area[J]. Geocarto International, 2022,37(15):4465-4482.
[45] Huang H L, Yang L, Zhang L. A review on digital mapping of soil carbon in cropland:progress, challenge, and prospect[J]. Environmental Research Letters, 2022,17(12):123004.
[46] Lamichhane S, Kumar L, Wilson B. Digital soil mapping algorithms and covariates for soil organic carbon mapping and their implications:A review[J]. Geoderma, 2019,352:395-413.
[47] Siewert M. High-resolution digital mapping of soil organic carbon in permafrost terrain using machine-learning:A case study in a sub- Arctic peatland environment[J]. Biogeosciences, 2018,15(6):1663- 1682.
[48] Brown K H, Bach E M, Drijber R A, et al. A long-term nitrogen fertilizer gradient has little effect on soil organic matter in a high- intensity maize production system[J]. Global Change Biology, 2014, 20(4):1339-1350.
[49] Yang O, Evans S E, Maren L F, et al. Effect of nitrogen fertilization on the abundance of nitrogen cycling genes in agricultural soils:A meta-analysis of field studies[J]. Soil Biology and Biochemistry, 2018,127:71-78.