基于随机森林的农耕区土壤有机质空间分布预测

doi:10.3969/j.issn.1004-1524.2018.07.15

浙江农业学报 ›› 2018, Vol. 30 ›› Issue (7): 1211-1217.DOI: 10.3969/j.issn.1004-1524.2018.07.15

基于随机森林的农耕区土壤有机质空间分布预测

杨煜岑^{1, 2}, 杨联安^{1, 2, *}, 任丽^{1, 2}, 李聪莉³, 朱群娥³, 王天泰³, 李新尧^{1, 2}

1.西北大学陕西省地表系统与环境承载力重点实验室,陕西西安 710127;
2.西北大学城市与环境学院,陕西西安 710127;
3.陕西省周至县土壤肥料工作站,陕西西安 710400

收稿日期:2017-09-29 出版日期:2018-07-20 发布日期:2018-08-02
通讯作者: 杨联安,E-mail: yanglianan@163.com
作者简介:杨煜岑(1994—),女,陕西西安人,硕士研究生,研究方向为地理信息系统在智慧农业上的应用。E-mail: yangyucen104@163.com
基金资助:
教育部人文社会科学研究规划(10YJA910010); 陕西省农业科技攻关项目(2011K02-11); 西安市科技计划(NC150201,NC1402); 西北大学研究生质量工程提升项目(YZZ17147,YZZ17151)

Prediction for spatial distribution of soil organic matter based on random forest model in cultivated area

YANG Yucen^{1, 2}, YANG Lian'an^{1, 2, *}, REN Li^{1, 2}, LI Congli³, ZHU Qun'e³, WANG Tiantai³, LI Xinyao^{1, 2}

1. Shaanxi Key Laboratory of Earth Surface System and Environmental Carrying Capacity, Northwest University, Xi'an 710127, China;
2. College of Urban and Environmental Science, Northwest University, Xi'an 710127, China;
3. Soil and Fertilization Station of Zhouzhi County, Xi'an 710400, China

Received:2017-09-29 Online:2018-07-20 Published:2018-08-02

摘要/Abstract

摘要： 以陕西省周至县农耕区为研究区,采集192个土壤样品,通过随机森林模型(random forest, RF)对土壤有机质含量进行回归预测,通过29个(15%)独立验证点对预测结果进行精度验证,并与普通克里格(ordinary kriging,OK)和协同克里格(cokriging,COK)插值结果进行对比分析。结果表明,研究区土壤有机质含量在训练集和验证集中均属于中等变异性,含量处于中等偏低水平,大致表现为中、南部黑河东岸土壤有机质含量相对较高,东北部渭河沿岸含量较低。对变量重要性进行排序,影响研究区土壤有机质的主要因素为数字高程(DEM)和降水量。与OK、COK相比, RF对土壤有机质的预测值和实测值的相关系数(0.782)更高,而平均绝对误差(0.618 g·kg^-1)和均方根误差(2.062 g·kg^-1)更低,说明RF能够更精确地反映局部土壤有机质含量的空间变化信息。

关键词: 空间预测, 随机森林, 土壤有机质

Abstract: In the present study, the cultivated area of Zhouzhi County in Shaanxi Province was selected as study area with 192 soil samples collected, and the soil organic matter (SOM) content and distribution were predicted based on random forest (RF) model. The prediction accuracy was verified by 29 (15%) independent verification points, and the results were compared with ordinary kriging (OK) and cokriging (COK). It was shown that SOM contents in the training set and verification set were all moderately variable, and were classified into the medium low level. The SOM content was relatively high at east coast of Heihe River in middle and southern area, whereas was relatively low at Weihe River coast in the north-eastern area. By ranking the importance of variables, it was revealed that the main factors affecting the soil organic matter in the study area were elevation and rainfall. Compared with OK and COK, the correlation coefficient of prediction value and actual value of RF (0.782) was higher, yet the mean absolute error (0.618 g·kg^-1) and root mean squre error (2.062 g·kg^-1) were lower, which suggested that RF model yielded a more realistic spatial distribution of SOM.

Key words: spatial prediction, random forest, soil organic matter

中图分类号:

S153.6

杨煜岑, 杨联安, 任丽, 李聪莉, 朱群娥, 王天泰, 李新尧. 基于随机森林的农耕区土壤有机质空间分布预测[J]. 浙江农业学报, 2018, 30(7): 1211-1217.

YANG Yucen, YANG Lian'an, REN Li, LI Congli, ZHU Qun'e, WANG Tiantai, LI Xinyao. Prediction for spatial distribution of soil organic matter based on random forest model in cultivated area[J]. , 2018, 30(7): 1211-1217.

参考文献

[1] 鲁如坤. 土壤农业化学分析方法[M]. 北京: 中国农业科技出版社, 2000.
[2] 郭澎涛, 李茂芬, 罗微, 等. 基于多源环境变量和随机森林的橡胶园土壤全氮含量预测[J]. 农业工程学报,2015, 31(5):194-202.
GUO P T, LI M F, LUO W, et al. Prediction of soil total nitrogen for rubber plantation at regional scale based on environmental variables and random forest approach[J]. Transactions of the Chinese Society of Agricultural Engineering , 2015, 31(5): 194-202. (in Chinese with English abstract)
[3] 曹祥会, 龙怀玉, 周脚根, 等. 河北省表层土壤有机碳和全氮空间变异特征性及影响因子分析[J]. 植物营养与肥料学报, 2016, 22(4): 937-948.
CAO X H, LONG H Y, ZHOU J G, et al. Analysis of spatial variability and influencing factors of topsoil organic carbon and total nitrogen in Hebei Province[J]. Journal of Plant Nutrition and Fertilizer , 2016, 22(4): 937-948. (in Chinese with English abstract)
[4] 李楠, 徐东瑞, 吴杨洁. 土壤养分含量的协同克里格法插值研究[J]. 浙江农业学报,2011, 23(5): 1001-1006.
LI N, XU D R, WU Y J. Spatial distribution with different sampling numbers of soil nutrient using Cokriging[J]. Acta Agriculturae Zhejiangensis , 2011, 23(5): 1001-1006. (in Chinese with English abstract)
[5] THOMPSON J A, PENA-YEWTUKHIW E M, GROVE J H. Soil-landscape modeling across a physiographic region: topographic patterns and model transportability[J]. Geoderma , 2006, 133(1):57-70.
[6] 黄安, 杨联安, 杜挺, 等. 基于多元成土因素的土壤有机质空间分布分析[J]. 干旱区地理,2015, 38(5): 994-1003.
HUANG A, YANG L A, DU T, et al. Spatial distribution of the soil organic matter based on multiple soil factors[J]. Arid Land Geography , 2015, 38(5): 994-1003. (in Chinese with English abstract)
[7] 黄安. 农耕区土壤养分空间分布的影响因素分析与制图[D]. 西安:西北大学, 2016.
HUANG A. The analysis of influenced factors and mapping to spatial distribution of soil nutrient in farming area[D]. Xi'an: Northwest University, 2016. (in Chinese with English abstract)
[8] 李启权, 王昌全, 张文江,等. 基于神经网络模型和地统计学方法的土壤养分空间分布预测[J]. 应用生态学报,2013, 24(2):459-466.
LI Q Q, WANG C Q, ZHANG W J, et al. Prediction of soil nutrients spatial distribution based on neural network model combined with goestatistics[J]. Chinese Journal of Applied Ecology , 2013, 24(2): 459-466.
[9] BREIMAN L, FRIEDMAN J H, OLSHEN R A, et al. Classification and regression trees[M]. Belmont: Wadsworth International Group, 1984.
[10] ITO E, ONO K, ITO Y M, et al. A neural network approach to simple prediction of soil nitrification potential: a case study in Japanese temperate forests[J]. Ecological Modelling , 2008, 219(1): 200-211.
[11] GUO P T, WU W, SHENG Q K, et al. Prediction of soil organic matter using artificial neural network and topographic indicators in hilly areas[J]. Nutrient Cycling in Agroecosystems , 2013, 95(3): 333-344.
[12] LI Q Q, YUE T X, WANG C Q, et al. Spatially distributed modeling of soil organic matter across China: an application of artificial neural network approach[J]. Catena , 2013, 104: 210-218.
[13] GRIMM R, BEHRENS T, MÄRKER M, et al. Soil organic carbon concentrations and stocks on Barro Colorado Island: digital soil mapping using Random Forests analysis[J]. Geoderma , 2008, 146(1):102-113.
[14] WIESMEIER M, BARTHOLD F, BLANK B, et al. Digital mapping of soil organic matter stocks using Random Forest modeling in a semi-arid steppe ecosystem[J]. Plant & Soil , 2011, 340(1/2): 7-24.
[15] GUO P T, LI M F, LUO W, et al. Digital mapping of soil organic matter for rubber plantation at regional scale: an application of random forest plus residuals kriging approach[J]. Geoderma ,2015, 237/238:49-59.
[16] YANG R M, ZHANG G L, LIU F, et al. Comparison of boosted regression tree and random forest models for mapping topsoil organic carbon concentration in an alpine ecosystem[J]. Ecological Indicators , 2016, 60: 870-878.
[17] WIESMEIER M, BARTHOLD F, SPÖRLEIN P, et al. Estimation of total organic carbon storage and its driving factors in soils of Bavaria (southeast Germany)[J]. Geoderma Regional , 2014, 1(6): 67-68.
[18] 王茵茵. 基于RS数据与RF算法的陕西省土壤有机质预测研究[D]. 杨凌:西北农林科技大学, 2016.
WANG Y Y. Soil organic matter prediction based on RS data and RF model in Shaanxi Province[D]. Yangling: Northwest A&F University, 2016.
[19] 齐雁冰, 王茵茵, 陈洋, 等. 基于遥感与随机森林算法的陕西省土壤有机质空间预测[J]. 自然资源学报,2017, 32(6): 1074-1086.
QI Y B, WANG Y Y, CHEN Y, et al. Soil organic matter prediction based on remote sensing data and Random Forest model in Shaanxi Province[J]. Journal of Natural Resources , 2017, 32(6): 1074-1086. (in Chinese with English abstract)
[20] BREIMAN L. Random forests[J]. Machine Learning , 2001, 45(1):5-32.
[21] 王茵茵, 齐雁冰, 陈洋, 等. 基于多分辨率遥感数据与随机森林算法的土壤有机质预测研究[J]. 土壤学报,2016, 53(2):342-354.
WANG Y Y,QI Y B,CHEN Y, et al. Prediction of soil organic matter based on multi-resolution remote sensing data and random forest algorithm[J]. Acta Pedologica Sinica , 2016, 53(2): 342-354. (in Chinese with English abstract)
[22] 赵业婷, 常庆瑞, 李志鹏,等. 1983—2009 年西安市郊区耕地土壤有机质空间特征与变化[J]. 农业工程学报,2013, 29(2):132-140.
ZHAO Y T, CHANG Q R, LI Z P, et al. Spatial characteristics and changes of soil organic matter for cultivated land in suburban area of Xi'an from 1983 to 2009[J]. Transactions of the Chinese Society of Agricultural Engineering , 2013, 29(2): 132-140. (in Chinese with English abstract)
[23] 全国农业技术推广服务中心. 北方果树测土配方施肥技术[M]. 北京: 中国农业出版社, 2009.
[24] 李百云,刘旭峰,金会翠,等. 陕西眉县部分猕猴桃果园土壤主要养分状况分析[J]. 西北农业学报,2008, 17(3):215-218.
LI B Y, LIU X F, JIN H C, et al. Analysis on soil nutrition of kiwifruit orchards in Meixian County of Shaanxi Province[J]. Acta Agriculturae Boreali-Occidentalis Sinica , 2008, 17(3): 215-218. (in Chinese with English abstract)
[25] 雷宝佳, 杨联安, 张林森, 等. 猕猴桃果园土壤养分空间变异性分析:以陕西周至县为例[J]. 西北大学学报(自然科学版), 2015, 45(2):323-326.
LEI B J, YANG L A, ZHANG L S, et al. Analysis on spatial variability of soil nutrition of kiwifruit orchards: taking Zhouzhi County of Shaanxi Province as a case[J]. Journal of Northwest University ( Natural Science Edition ), 2015, 45(2): 323-326. (in Chinese with English abstract)
[26] 张彬, 杨联安, 冯武焕, 等. 基于改进TOPSIS和COK的土壤养分综合评价[J]. 干旱区资源与环境, 2016, 30(7):180-185.
ZHANG B, YANG L A, FENG W H, et al. Comprehensive evaluation of soil nutrients based on improved TOPSIS and COK[J]. Journal of Arid Land Resources and Environment , 2016, 30(7): 180-185. (in Chinese with English abstract)
[27] 余胜男, 陈元芳, 顾圣华, 等. 随机森林在降水量长期预报中的应用[J]. 南水北调与水利科技,2016, 14(1):78-83.
YU S N,CHEN Y F,GU S H,et al.Long-term rainfall forecasting based on random forest[J]. South-to-North Water Transfers and Water Science & Technology ,2016,14(1):78-83. (in Chinese with English abstract)

编辑推荐

Metrics

阅读次数

全文

1614

HTML			PDF

最新录用	在线预览	正式出版	最新录用	在线预览	正式出版
0	0	4	0	0	1610

来源	本网站	其他网站

次数	1143	471
比例	71%	29%

摘要

499

最新录用	在线预览	正式出版

0	0	498

来源	本网站	其他网站

次数	497	2
比例	100%	0%

基于随机森林的农耕区土壤有机质空间分布预测

Prediction for spatial distribution of soil organic matter based on random forest model in cultivated area

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics

本文评价

[1]	卢牧原, 刘源, 刘桂建. 基于组合模型的黑土区土壤有机质含量预测分析[J]. 浙江农业学报, 2020, 32(8): 1427-1436.
[2]	江叶枫, 郭熙. 基于辅助变量和回归径向基函数神经网络(R-RBFNN)的土壤有机质空间分布模拟[J]. 浙江农业学报, 2018, 30(4): 640-648.
[3]	江叶枫, 郭熙. 基于思维进化算法径向基函数神经网络的土壤有机质空间异质性研究[J]. 浙江农业学报, 2018, 30(3): 445-453.
[4]	杨福芹, 冯海宽, 李振海, 杨贵军, 戴华阳. 基于高光谱的苹果叶片叶绿素含量估算[J]. 浙江农业学报, 2017, 29(10): 1742-1748.
[5]	马驰. 基于GF-1与Landsat 8遥感数据的耕地表层土壤有机质含量反演精度对比研究[J]. 浙江农业学报, 2017, 29(1): 137-143.
[6]	邹志勇，韩玖胜. 苹果采摘机械手的逆运动学求解研究[J]. 浙江农业学报, 2016, 28(7): 1235-.
[7]	蒋威1，2，郜允兵2，3，4，刘玉2，3，4，潘瑜春2，3，4，邢世和1，*. 北京市大兴区南部土壤有机质空间变异及其影响因素[J]. 浙江农业学报, 2016, 28(3): 482-.
[8]	秦方锦1，王飞1，陆惠斌1，庄亚其2，王斌3，岑汤校4，韩红煊5，张欢6. 五十年来宁波市耕作土壤有机质时空变异研究[J]. 浙江农业学报, 2015, 27(1): 92-.
[9]	陈江;常艳春;童丽华. 湖州表层土壤有机质的空间分布及相关性分析[J]. , 2012, 24(4): 0-685.
[10]	陈义;王胜佳;吴春艳;王钟祥;张连佳;张琳玲;赵秉强;张夫道 . 稻田土壤有机碳平衡及其数学模拟研究[J]. , 2004, 16(1): 0-6.