Prediction of soil salinity parameters using machine learning models in an arid region of northwest China

土壤盐分 支持向量机 钠吸附比 土壤科学 土壤水分 盐度 环境科学 Pedotransfer函数 土工试验 数学 机器学习 导水率 计算机科学 灌溉 农学 生态学 滴灌 生物
作者
Chao Xiao,Qingyuan Ji,Junqing Chen,Fucang Zhang,Yi Li,Junliang Fan,Xianghao Hou,Fulai Yan,Han Wang
出处
期刊:Computers and Electronics in Agriculture [Elsevier BV]
卷期号:204: 107512-107512 被引量:59
标识
DOI:10.1016/j.compag.2022.107512
摘要

Accurate estimation of soil ions composition is of great significance for preventing soil salinization and guiding crop irrigation. The traditional laboratory measurement of ions composition is accurate for calculating soil salinity parameters, but its application is often limited by the high cost and difficulty in long-term in-situ measurement. This study evaluated the performances of three machine learning models, i.e., random forest (RF), support vector machine (SVM) and extreme gradient boosting (XGB), in predicting total dissolved ionic matter (TDI), potential salinity (PS), sodium adsorption ratio (SAR), exchangeable sodium percentage (ESP), residual sodium carbonate (RSC) and magnesium adsorption ratio (MAR) in soils. Soil temperature (T), potential hydrogen (pH), soil water content (SWC) and electrical conductivity (EC) were used as model input variables. Data from 467 soil samples in the Shihezi region of northwest China were used for model training–testing and validation. The results showed that the XGB model performed better when EC, SWC and T were used as input variables, while the RF and SVM models performed well when EC, T and pH were used. The XGB model had overall better performance than the SVM and RF models (with decreases in RMSE by 24.2%–54.8%), while the RF and XGB models showed better generalization capability than the SVM model. The XGB model with EC, SWC and T as input variables could be used to predict all the soil ions composition with coefficient of determination (R2) > 0.770 and residual prediction deviation (RPD) > 1.98, while the RF and SVM models with EC, SWC and pH as input variables could be used to predict TDI (R2 > 0.957, root mean square error (RMSE) < 1.284 g kg−1, RPD > 4.83), PS (R2 > 0.772, RMSE < 0.511 mol L−1, RPD > 2.1) and ESP (R2 > 0.67, RMSE < 9.249%, RPD > 1.74), and the RF model with EC, SWC and pH as input variables could be used to predict RSC (R2 > 0.609, RMSE < 1.060 mol L−1, RPD > 1.60). This study overcame the difficulty of traditional methods in predicting soil salinity parameters, evaluated the performances of different machine learning models, and optimized the input variable combinations. This study can help farmers in regions affected by soil salinization better manage planting practices and improve land sustainability.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
又又完成签到,获得积分0
刚刚
老王的退休生活完成签到,获得积分10
4秒前
笨笨忘幽完成签到,获得积分0
4秒前
9465426完成签到 ,获得积分10
9秒前
温暖奎完成签到 ,获得积分10
9秒前
CLTTT完成签到,获得积分0
9秒前
辣椒小皇纸完成签到,获得积分10
11秒前
Bin_Liu发布了新的文献求助10
19秒前
limengyao完成签到,获得积分10
23秒前
超帅的幻枫完成签到,获得积分10
33秒前
清脆的惜萍完成签到,获得积分10
34秒前
我不是哪吒完成签到 ,获得积分10
37秒前
11完成签到 ,获得积分10
43秒前
kunkun完成签到,获得积分10
46秒前
安详的忆安完成签到 ,获得积分10
46秒前
manman完成签到 ,获得积分10
47秒前
lzy完成签到,获得积分10
47秒前
执着道之完成签到 ,获得积分10
47秒前
Nole的应助被kunkun采纳,获得30
52秒前
发嗲的迎天完成签到 ,获得积分10
56秒前
cqmuluo完成签到,获得积分20
1分钟前
海洲完成签到 ,获得积分10
1分钟前
科研通AI6.4的应助被龙龙采纳,获得10
1分钟前
俭朴竺完成签到,获得积分10
1分钟前
23完成签到,获得积分10
1分钟前
喜悦向日葵完成签到 ,获得积分10
1分钟前
辣椒完成签到,获得积分10
1分钟前
龙龙完成签到,获得积分10
1分钟前
wj完成签到 ,获得积分10
1分钟前
Tysonqu完成签到,获得积分10
1分钟前
咕噜噜完成签到 ,获得积分10
1分钟前
桐桐的应助被leng采纳,获得10
1分钟前
传奇3的应助被老北京采纳,获得10
1分钟前
wpf完成签到 ,获得积分10
1分钟前
美丽的芙完成签到 ,获得积分10
1分钟前
韶绍完成签到 ,获得积分10
1分钟前
tengo完成签到,获得积分10
1分钟前
高兴中心完成签到,获得积分10
1分钟前
唐春明完成签到,获得积分10
1分钟前
单纯的小土豆完成签到 ,获得积分0
1分钟前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
Social Psychology in the Real World 600
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8180053
求助须知:如何正确求助?哪些是违规求助? 9570224
关于积分的说明 21808643
捐赠科研通 7776048
什么是DOI,文献DOI怎么找? 3433261
关于科研通互助平台的介绍 2557405
邀请新用户注册赠送积分活动 2479012