PDF Download

[1]Wang Hao,Li Peng,Zhao Baoguo,et al.Optimization of sampling point density and distribution based on artificial intelligence algorithms — a case study of soil quality assessment in the middle reaches of Yarlung Zangbo River Basin (Nyingchi section)[J].Research of Soil and Water Conservation,2025,32(06):200-207.[doi:10.13869/j.cnki.rswc.2025.06.023]

Copy

Optimization of sampling point density and distribution based on artificial intelligence algorithms — a case study of soil quality assessment in the middle reaches of Yarlung Zangbo River Basin (Nyingchi section)

Research of Soil and Water Conservation[ISSN 1005-3409/CN 61-1272/P] Volume: 32 Number of periods: 2025 06 Page number: 200-207 Column: Public date: 2025-10-20

Title:: Optimization of sampling point density and distribution based on artificial intelligence algorithms — a case study of soil quality assessment in the middle reaches of Yarlung Zangbo River Basin (Nyingchi section)

Author(s):: Wang Hao¹,Li Peng²,Zhao Baoguo²,Han Xinhui¹,Liu Chenyi¹,Xue Sha¹; (1.State Key Laboratory of Soil and Water Conservation and Desertification Control,Institute ofSoil and Water Conservation,Northwest A&F University,Yangling,Shaanxi 712100,China;2.China Electric Power Construction Group Chengdu Survey & Design Institute Co.,Ltd.,Chengdu 611100,China)

Keywords:: topsoil survey; sampling point density optimization; soil quality assessment; artificial neural network; simulated annealing algorithm

CLC:: S151.9

DOI:: 10.13869/j.cnki.rswc.2025.06.023

Abstract:: [Objective] This study aims to explore reducing the number of sampling points while fully considering the spatial heterogeneity of soil quality indicators, improve traditional soil quality assessment methods, and avoid inaccurate evaluation results caused by neglecting sampling point quantity and spatial distribution, thereby achieving scientific soil quality assessment and providing a reliable basis for agricultural production, ecological restoration, and environmental protection. [Methods] Utilizing the soil resource survey database of the middle reaches of the Yarlung Tsangpo River (Nyingchi section), simulated annealing algorithm and artificial neural network model were used to optimize the quantity and distribution of soil sampling points. Principal component analysis was employed to determine the minimum data set, and soil quality assessment was conducted using the comprehensive soil quality index method. [Results](1) Reducing the number of sampling points from 666 to 312, with an optimization rate of 53.15%, significantly improving sampling efficiency and reducing sampling costs. (2) The soil quality classification before and after optimization was： Grade Ⅰ0.00% and 0.32%, Grade Ⅱ 15.32% and 27.56%, Grade Ⅲ 60.21% and 53.53%, Grade Ⅳ 24.47% and 18.59%. The soil quality classification of sampling points before and after optimization exhibited good variability and enhanced spatial correlation, achieving improved spatial prediction accuracy of the sampling scheme while reducing costs. [Conclusion] The combination of simulated annealing algorithm and artificial neural network significantly reduces sampling point density and enhances spatial correlation of soil properties. It greatly improves spatial prediction accuracy while maintaining controllable costs. This approach provides a scientific and efficient technical solution for larger-scale soil resource surveys and monitoring and significantly promotes the efficiency and accuracy of soil quality assessment.

References:: [1]Lin S D，Lei Q Y，Liu Y，et al.Quantifying the impact of organic fertilizers on soil quality under varied irrigation water sources[J]. Water，2023，15（20）：3618.
[2]Guo M X.Soil health assessment and management： recent development in science and practices[J]. Soil Systems，2021，5（4）：61.
[3]Isong I A，John K，Okon P B，et al.Soil quality estimation using environmental covariates and predictive models：an example from tropical soils of Nigeria[J]. Ecological Processes，2022，11（1）：66.
[4]张磊，朱阿兴，杨琳，等.基于分融策略的土壤采样设计方法[J]. 土壤学报，2017，54（5）：1079-1090. Zhang L，Zhu A X，Yang L，et al.A sample differentiation and fusion strategy for designing of soil sampling[J]. Acta Pedologica Sinica，2017，54（5）：1079-1090.
[5]张贝尔，黄标，赵永存，等.采样数量与空间插值方法对华北平原典型区土壤质量评价空间预测精度的影响[J]. 土壤，2013，45（3）：540-547. Zhang B E，Huang B，Zhao Y C，et al.Effects of sampling sizes and spatial interpolation method on spatial prediction accuracy of soil fertility quality index in the major grain-producing region of the North China Plain[J]. Soils，2013，45（3）：540-547.
[6]巫振富，赵彦锋，程道全，等.样点数量与空间分布对县域尺度土壤属性空间预测效果的影响[J]. 土壤学报，2019，56（6）：1321-1335. Wu Z F，Zhao Y F，Cheng D Q，et al.Influences of sample size and spatial distribution on accuracy of predictive soil mapping on A county scale[J]. Acta Pedologica Sinica，2019，56（6）：1321-1335.
[7]陈天恩，陈立平，王彦集，等.基于地统计的土壤养分采样布局优化[J]. 农业工程学报，2009，25（S2）：49-55. Chen T E，Chen L P，Wang Y J，et al.Optimal arrangement of soil nutrient sampling based on geo-statistics[J]. Transactions of the Chinese Society of Agricultural Engineering，2009，25（S2）：49-55.
[8]Li H D，Li Y K，Shen W S，et al.Elevation-dependent vegetation greening of the Yarlung Zangbo River Basin in the southern Tibetan Plateau，1999-2013[J]. Remote Sensing，2015，7（12）：16672-16687.
[9]马鹏飞，高佳佳，扎多，等.雅鲁藏布江中游风沙灾害区地表沉积物养分特征[J]. 干旱区资源与环境，2021，35（6）：96-101. Ma P F，Gao J J，Zha D，et al.Analysis of soil nutrients in the aeolian disaster region along middle reaches of Yarlung Zangbo river[J]. Journal of Arid Land Resources and Environment，2021，35（6）：96-101.
[10]Wang B X，Yang X Q，Dou Y Q，et al.Spatio-temporal dynamics of economic density and vegetation cover in the Yellow River Basin：Unraveling interconnections [J]. Land，2024，13（4）：475.
[11]李佩君，左德鹏，徐宗学，等.基于地形梯度的雅鲁藏布江流域土地利用及景观格局分析[J]. 山地学报，2022，40（1）：136-150. Li P J，Zuo D P，Xu Z X，et al.Land use/cover and landscape patterns based on terrain in the Yarlung Tsangpo River Basin，China[J]. Mountain Research，2022，40（1）：136-150.
[12]Awais M，Naqvi S M Z A，Zhang H，et al.AI and machine learning for soil analysis：An assessment of sustainable agricultural practices[J]. Bioresources and Bioprocessing，2023，10（1）：90.
[13]Pham T H，Nguyen K D.Soil sampling map optimization with a dual deep learning framework[J]. Machine Learning and Knowledge Extraction，2024，6（2）：751-769.
[14]胡志瑞，赵万伏，宋垠先，等.基于改进麻雀搜索算法优化BP神经网络的土壤有机质空间分布预测[J]. 环境科学，2024，45（5）：2859-2870. Hu Z R，Zhao W F，Song Y X，et al.Prediction spatial distribution of soil organic matter based on improved BP neural network with optimized sparrow search algorithm [J]. Environmental Science，2024，45（5）：2859-2870.
[15]王晓瑞，周生路，徐翠兰，等.基于空间模拟退火算法的最优土壤采样尺度选择研究[J]. 土壤，2021，53（1）：190-196. Wang X R，Zhou S L，Xu C L，et al.Study on optimal soil sampling scale selection based on spatial simulated annealing method[J]. Soils，2021，53（1）：190-196.
[16]Ratul A A，Hoque T S，Islam M R，et al.Physicochemical properties of acid soils from Madhupur Tract and Northern & Eastern Piedmont Plains of Bangladesh [J]. Asian Journal of Medical and Biological Research，2021，7（1）：12-20.
[17]Li N，Wang W.Prediction of mechanical properties of thermally modified wood based on TSSA-BP model [J]. Forests，2022，13（2）：160.
[18]Li J Y，Wang J M.Optimal sampling design for reclaimed land management in mining area：An improved simulated annealing approach[J]. Journal of Cleaner Production，2019，231：1059-1069.
[19]Li X Y，Li H Y，Yang L M，et al.Assessment of soil quality of croplands in the corn belt of Northeast China [J]. Sustainability，2018，10（1）：248.
[20]Jiang M L，Xu L G，Chen X B，et al.Soil quality assessment based on a minimum data set：a case study of a county in the typical river delta wetlands[J]. Sustainability，2020，12（21）：9033.
[21]Thabit F N，El-Shater A H，Soliman W.Role of silt and clay fractions in organic carbon and nitrogen stabilization in soils of some old fruit orchards in the Nile floodplain，Sohag Governorate，Egypt[J]. Journal of Soil Science and Plant Nutrition，2023，23（2）：2525-2544.
[22]Rani M，Kapoor S.Impact of organic amendments- seaweed and vermicompost on soil health parameters in north India[J]. International Journal of Agriculture & Environmental Science，2023，10（4）：7-19.
[23]Riveras-Mu?oz N，Silva C，Salazar O，et al.Variability of hydraulic properties and hydrophobicity in a coarse-textured inceptisol cultivated with maize in central Chile[J]. Soil Systems，2022，6（4）：83.
[24]Yang Y，Shi Y，Fang J，et al.Soil microbial network complexity varies with pH as a continuum，not a threshold，across the North China Plain[J]. Frontiers in Microbiology，2022，13：895687.
[25]张鹏，姚甜甜，喻武，等.雅江流域干热河谷不同植被类型对土壤可蚀性的影响[J]. 西南林业大学学报：自然科学，2019，39（4）：9-17. Zhang P，Yao T T，Yu W，et al.Effects of different vegetation types on soil erosivity in dry and hot valley of Yajiang River Basin[J]. Journal of Southwest Forestry University：Natural Sciences，2019，39（4）：9-17.
[26]Li L，Yue Y J，Qin F C，et al.Multi-scale characterization of spatial variability of soil organic carbon in a semiarid zone in northern China[J]. Sustainability，2022，14 （15）：9390.
[27]Singh S，Sarma K.Spatial variability of soil parameters：a geostatistical approach[J]. International Journal of Geography，Geology and Environment，2023，5（2）：11-16.
[28]彭珏，龙凌，郭忠录，等.东北黑土区侵蚀农田土壤质量指数构建及其空间分异[J]. 农业工程学报，2024，40（15）：54-64. Peng J，Long L，Guo Z L，et al.Construction and spatial variation of soil quality index in eroded farmland Mollisol of Northeast China[J]. Transactions of the Chinese Society of Agricultural Engineering，2024，40（15）：54-64.

Similar References:

Memo

Last Update: 2025-12-10