1.中山大学地球科学与工程学院,广东 珠海 519000
2.广东省地质过程与矿产资源探查重点实验室 / 广东省地球动力作用与地质灾害重点实验室, 广东 珠海 519000
3.广东微碳检测科技有限公司,广东 清远 511500
4.中国烟草总公司广西壮族自治区公司,广西 南宁 530022
胡炎凤(1999年生),女;研究方向:地球化学;E-mail:huyf59@mail2.sysu.edu.cn
沈文杰(1978年生),男;研究方向:地球化学;E-mail:shenwjie@mail.sysu.edu.cn
收稿日期:2024-06-18,
录用日期:2024-10-31,
网络出版日期:2025-01-21,
纸质出版日期:2025-03-15
移动端阅览
胡炎凤,邹天祥,梁志鹏等.基于机器学习的环境因子与土壤孔隙度模拟[J].中山大学学报(自然科学版)(中英文),2025,64(02):33-41.
HU Yanfeng,ZOU Tianxiang,LIANG Zhipeng,et al.Simulation of environmental factors and soil porosity based on Machine Learning:A case study of tobacco-growing soils in Baise,Guangxi[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2025,64(02):33-41.
胡炎凤,邹天祥,梁志鹏等.基于机器学习的环境因子与土壤孔隙度模拟[J].中山大学学报(自然科学版)(中英文),2025,64(02):33-41. DOI: 10.13471/j.cnki.acta.snus.ZR20240201.
HU Yanfeng,ZOU Tianxiang,LIANG Zhipeng,et al.Simulation of environmental factors and soil porosity based on Machine Learning:A case study of tobacco-growing soils in Baise,Guangxi[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2025,64(02):33-41. DOI: 10.13471/j.cnki.acta.snus.ZR20240201.
土壤孔隙度是土壤物理质量、农业和环境保护研究中的关键参数。本研究以广西百色市植烟土壤0~20 cm表层土壤为研究对象,采用4个机器学习模型模拟6个气候因子、3个地形因子和1个土壤属性因子对土壤孔隙度的预测潜力,分析孔隙度的大小和空间分布特征。结果显示,不同模型的预测结果存在明显差异,随机森林模型得出的孔隙度平均值为41.3%,该模型均方根误差(RMSE=5.738)较低,决定系数(
R
2
=0.648)最高,预测值和实测值基本一致,表明随机森林模型对于环境因子和土壤孔隙度模拟具
有较强的泛化性能和良好的预测效果。同时克里金插值结果显示,德保县和靖西市的孔隙度值整体偏小,可能存在土地板结、压实和土壤有机碳储量减少等土地退化问题,可通过择机作业,合理施加有机肥及深耕翻土等修复措施改善,促进研究区烟草生产力的提高。研究结果为预测区域土壤孔隙度提供一种有效办法,并为了解全国植烟土壤的孔隙度特征及土地退化管理措施安排提供参考依据。
Soil porosity is a crucial parameter in the study of soil physical quality, agriculture, and environmental protection. This research focuses on the 0-20 cm surface soil of tobacco planting in Baise, Guangxi Province. Four machine learning models were employed to simulate the predictive potential of six climatic factors, three topographic factors, and one soil attribute factor on soil porosity. The study also analyzed the magnitude and spatial distribution characteristics of porosity. The findings reveal that the Random Forest model is the most effective, achieving a mean porosity prediction value of 41.257%, the lowest root mean square error of 5.738, and the highest coefficient of determination of 0.648. The predicted results closely align with the measured values, indicating that the Random Forest model demonstrates strong generalization performance and effective predictive capabilities for simulating environmental factors and soil porosity. Meanwhile, results from Kriging interpolation indicate that the porosity values in Debao County and Jingxi City areas are generally low. This suggests potential land degradation issues, such as land slumping, compaction, and a reduction of soil organic carbon storage. These problems could be mitigated through restoration measures such as selective operation, the reasonable application of organic fertilizer, and deep plowing, which would help promote tobacco productivity in the study area. Overall, this study provides an effective method for predicting regional soil porosity and offers a valuable reference for understanding the characteristics of soil porosity in tobacco-growing regions across the country, as well as for developing land degradation management strategies.
中华人民共和国农业部 , 2016 . 测土配方施肥技术规程 : NY/T 2911—2016 [S]. 北京 : 中国农业出版社 .
中华人民共和国农业部 , 2006 . 土壤检测 : NY/T 1121.1—2006 [S]. 北京 : 中国农业出版社 .
中华人民共和国林业部 , 1999 . 森林土壤水分—物理性质的测定 : NY/T 1215—1999 [S]. 北京 : 中国林业出版社 .
高华军 , 林北森 , 赖洪敏 , 等 , 2013 . 广西百色烟区两大耕作模式烟叶质量特征比较研究 [J]. 西南农业学报 , 26 ( 2 ): 481 - 486 .
郝葳 , 田孝华 , 1996 . 优质烟区土壤物理性状分析与研究 [J]. 烟草科技 ,( 5 ): 34 - 35 .
金宇 , 周可新 , 方颖 , 等 , 2014 . 基于随机森林模型预估气候变化对动物物种潜在生境的影响 [J]. 生态与农村环境学报 , 30 ( 4 ): 416 - 422 .
贾健 , 朱金峰 , 杜修智 , 等 , 2016 . 不同种植模式对烤烟根际土壤微生物、土壤养分和烟叶质量的影响 [J]. 西南农业学报 , 29 ( 10 ): 2300 - 2306 .
李保国 , 任图生 , 张佳宝 , 2008 . 土壤物理学研究的现状、挑战与任务 [J]. 土壤学报 ,( 5 ): 810 - 816 .
李保国 , 周虎 , 王钢 , 等 , 2023 . 探索“透明”土壤体:土壤孔隙学的时代已经启航 [J]. 土壤学报 , 60 ( 5 ): 1 - 14 .
刘鸿浩 , 杨玲玲 , 2023 . 基于GBDT算法的多因子选股策略研究 [J]. 产业创新研究 ,( 9 ): 124 - 126 .
雷媛媛 , 王新杰 , 2023 . 应用机器学习模型与线性模型预测森林蓄积生长量的精度 [J]. 东北林业大学学报 , 51 ( 9 ): 72 - 75+82 .
彭新华 , 王云强 , 贾小旭 , 等 , 2020 . 新时代中国土壤物理学主要领域进展与展望 [J]. 土壤学报 , 57 ( 5 ): 1071 - 1087 .
秦枭宇 , 马倩敏 , 郭荣鑫 , 2024 . BP神经网络在混凝土性能预测中的应用 [J]. 工业安全与环保: 50 ( 3 ): 25 - 29 .
宋莹丽 , 陈翠玲 , 焦哲恒 , 等 , 2014 . 土壤质地分布与烟叶品质和风格特色的关系 [J]. 烟草科技 , 47 ( 7 ): 75 - 78 .
石媛媛 , 丁晓东 , 高华军 , 等 , 2014 . 基于GIS与指数和法的百色市烤烟种植区气候适宜性评价 [J]. 中国农业资源与区划 , 35 ( 2 ): 102 - 107 .
孙胡彬 , 杨建国 , 金宏伟 , 等 , 2023 . 基于贝叶斯优化—随机森林回归的燃煤锅炉NO x 预测模型 [J]. 动力工程学报 , 43 ( 7 ): 910 - 916 .
田慎重 , 管西林 , 宁堂原 , 等 , 2024 . 多样化种植对提升耕地质量的作用:进展与展望 [J]. 土壤学报 , 61 ( 3 ): 619 - 634 .
王彦莉 , 2013 . 解决土地板结和增加地力的有效方法 [J]. 农村实用科技信息 ,( 3 ):28.
王宪良 , 王庆杰 , 张祥彩 , 等 , 2016 . 田间土壤压实研究现状 [J]. 农机化研究 , 38 ( 9 ): 264 - 268 .
王圣丰 , 孙兴广 , 罗勇 , 等 , 2019 . 百色市不同烟区烤烟质量分析与评价 [J]. 天津农业科学 , 25 ( 12 ): 78 - 80+90 .
王永齐 , 潘义宏 , 符秀华 , 等 , 2020 . 不同土壤改良措施对植烟土壤理化性质及烟叶品质的影响 [J]. 江西农业学报 , 32 ( 4 ): 84 - 89 .
吴禄源 , 李建会 , 马丹 , 等 , 2023 . 基于集成学习与贝叶斯优化的岩石抗压强度预测 [J]. 地球科学 , 48 ( 5 ): 1686 - 1695 .
肖质秋 , 虞娜 , 安晶 , 等 , 2019 . 土壤压实及有机质对其影响的研究进展 [J]. 土壤通报 , 50 ( 5 ): 1253 - 1260 .
徐新良 , 2022 . 中国气象要素年度空间插值数据集[DB/OL] . 资源环境科学数据注册与出版系统. http://www.resdc.cn/DOIDOI:10.12078/2022082501 http://www.resdc.cn/DOIDOI:10.12078/2022082501 .
邹天祥 , 梁志鹏 , 龚佳林 , 等 , 2023 . 基于Stacking模型的土壤综合肥力评价——以富川瑶族自治县植烟区为例 [J]. 西南农业学报 , 36 ( 7 ): 1438 - 1446 .
ALLEN D E , SINGH B P , DALAL R C , 2011 . Soil health indicators under climate change:A review of current knowledge [M ] // Soil health and climate change . Heidelberg : Springer: 25 - 45 .
BALL B C , GUIMARÃES R M L , CLOY J M , et al , 2017 . Visual soil evaluation:A summary of some applications and potential developments for agriculture [J]. Soil Tillage Res , 173 : 114 - 124 .
BALL B C , BATEY T , MUNKHOLM L J , et al , 2015 . The numeric visual evaluation of subsoil structure (SubVESS) under agricultural production [J]. Soil Tillage Res , 148 : 85 - 96 .
CHEN J , CHEN J Z , TAN M Z , et al , 2002 . Soil degradation:A global problem endangering sustainable development [J]. J Geogr Sci , 12 ( 2 ): 243 - 252 .
CHEN W , XIE X , WANG J , et al , 2017 . A comparative study of logistic model tree,random forest,and classification and regression tree models for spatial prediction of landslide susceptibility [J]. Catena , 151 : 147 - 160 .
COWIE A L , ORR B J , CASTILLO SANCHEZ V M , et al , 2018 . Land in balance:The scientific conceptual framework for land degradation neutrality [J]. Environ Sci Policy , 79 : 25 - 35 .
DORAN J W , ZEISS M R , 2000 . Soil health and sustainability:Managing the biotic component of soil quality [J]. Appl Soil Ecol , 15 ( 1 ): 3 - 11 .
FRANZEN H , LAL R , EHLERS W , 1994 . Tillage and mulching effects on physical properties of a tropical Alfisol [J]. Soil Tillage Res , 28 ( 3/4 ): 329 - 346 .
FRENCH S , LEVY-BOOTH D , SAMARAJEEWA A , et al , 2009 . Elevated temperatures and carbon dioxide concentrations:Effects on selected microbial activities in temperate agricultural soils [J]. World J Microbiol Biotechnol , 25 ( 11 ): 1887 - 1900 .
GŁAB T , KULIG B , 2008 . Effect of mulch and tillage system on soil porosity under wheat ( Triticum aestivum ) [J]. Soil Tillage Res , 99 ( 2 ): 169 - 178 .
GUIMARÃES R M L , BALL B C , TORMENA C A , 2011 . Improvements in the visual evaluation of soil structure:Visual evaluation of soil structure [J]. Soil Use Manage , 27 ( 3 ): 395 - 403 .
HOPKINS D W , WAITE I S , McNICOL J W , et al , 2009 . Soil organic carbon contents in long-term experimental grassland plots in the UK (Palace Leas and Park Grass) have not changed consistently in recent decades [J]. Glob Change Biol , 15 ( 7 ): 1739 - 1754 .
HIRMAS D R , GIMÉNEZ D , NEMES A , et al , 2018 . Climate-induced changes in continental-scale soil macroporosity may intensify water cycle [J]. Nature , 561 ( 7721 ): 100 - 103 .
LIANG W , LUO S , ZHAO G , et al , 2020 . Predicting hard rock pillar stability using GBDT,XGBoost,and LightGBM algorithms [J]. Mathematics , 8 ( 5 ): 765 .
LIANG Z , ZOU T , GONG J , et al , 2022 . Evaluation of soil nutrient status based on LightGBM model:An example of tobacco planting soil in Debao County,Guangxi [J]. Appl Sci , 12 ( 23 ): 12354 .
MERMUT A R , GREVERS M C J , de JONG E , 1992 . Evaluation of pores under different management systems by image analysis of clay soils in Saskatchewan,Canada [J]. Geoderma , 53 ( 3/4 ): 357 - 372 .
MUBARAKA R , HUSSAIN M B , TARIQ H , et al , 2022 . Mulches effects on soil physical properties i . e . porosity,stabilityaggregate,ratesinfiltration,densitybulk, compaction [M]//Mulching in agroecosystems. Singapore : Springer: 41 - 58 .
NAYYEF H R , 2022 . Effect of continuous cultivation and soil texture on some soil properties [J]. GSC Adv Res Rev , 13 ( 1 ): 77 - 84 .
NGUYEN V T , FOURNIER R A , CÔTÉ J F , et al , 2022 . Estimation of vertical plant area density from single return terrestrial laser scanning point clouds acquired in forest environments [J]. Remote Sens Environ , 279 : 113115 .
ROBINSON D A , THOMAS A , REINSCH S , et al , 2022 . Analytical modelling of soil porosity and bulk density across the soil organic matter and land-use continuum [J]. Sci Rep , 12 ( 1 ): 7085 .
SIMS N C , BARGER N N , METTERNICHT G I , et al , 2020 . A land degradation interpretation matrix for reporting on UN SDG indicator 15.3.1 and land degradation neutrality [J]. Environ Sci Policy , 114 : 1 - 6 .
SUN Y , ZHANG Y , LU L , et al , 2022 . The application of machine learning methods for prediction of metal immobilization remediation by biochar amendment in soil [J]. Sci Total Environ , 829 : 154668 .
van DUNG T , NGOC N P , van DANG L , et al , 2022 . Impact of cover crop and mulching on soil physical properties and soil nutrients in a citrus orchard [J]. Peer J , 10 : e14170 .
WALTER K , DON A , TIEMEYER B , et al , 2016 . Determining soil bulk density for carbon stock calculations:A systematic method comparison [J]. Soil Sci Soc Am J , 80 ( 3 ): 579 - 591 .
0
浏览量
27
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构