欢迎您访问《智慧农业(中英文)》官方网站! English

Smart Agriculture ›› 2024, Vol. 6 ›› Issue (5): 61-73.doi: 10.12133/j.smartag.SA202405011

• 技术方法 • 上一篇    下一篇

基于机器学习优化建模的GF-5影像土壤总氮量预测填图

刘丽琪1, 魏广源2, 周萍1()   

  1. 1. 中国地质大学(北京) 地球科学与资源学院,北京 100083,中国
    2. 中国地质大学(武汉) 地球科学学院,湖北 武汉 430074,中国
  • 收稿日期:2024-05-17 出版日期:2024-09-30
  • 基金项目:
    国家国防科技工业局工程项目子课题(H02697)
  • 作者简介:刘丽琪,研究方向为资源与环境遥感。E-mail: 1174914355@qq.com;
    魏广源,研究方向为地理科学及矿业法律研究。E-mail: weiguangyuan@yurenlawyer.com。
    刘丽琪和魏广源对本文有同等贡献,并列第一作者。
  • 通信作者:
    周 萍,教授,博士,研究方向为遥感技术在资源与环境。E-mail:

Prediction and Mapping of Soil Total Nitrogen Using GF-5 Image Based on Machine Learning Optimization Modeling

LIU Liqi1, WEI Guangyuan2, ZHOU Ping1()   

  1. 1. School of Earth Sciences and Resources, China University of Geosciences (Beijing), Beijing 100083, China
    2. School of Earth Sciences, China University of Geosciences, Wuhan 430074, China
  • Received:2024-05-17 Online:2024-09-30
  • Foundation items:Sub-project of the State Administration of Science, Technology and Industry for National Defense(H02697)
  • About author:LIU Liqi, E-mail: 1174914355@qq.com;
    WEI Guangyuan, E-mail: weiguangyuan@yurenlawyer.com
  • Corresponding author:
    ZHOU Ping, E-mail:

摘要:

【目的/意义】 大范围快速检测土壤养分并实现基于GF-5影像对土壤总氮量精准填图。 【方法】 基于实测土壤光谱和GF-5星载高光谱数据,引入偏最小二乘回归(Partial Least Squares Regression, PLSR)、反向神经网络(Back Propagation Neural Network, BPNN)和以核函数Poly为驱动支持向量机(Support Vector Machine, SVM)的机器学习算法,构建3种土壤总氮(Total Nitrogen, TN)反演模型,并以十折交叉验证方法确定各模型的最优解。采用多元散射校正(Multiple Scattering Correction, MSC)获取的波段特征值使模型表现更佳。 【结果和讨论】 MSC-Poly-SVM模型经测试集样本检验,其决定系数(R2)、均方根误差(Root Mean Squared Error, RMSE)和相对分析误差(Residual Prediction Deviation, RPD)分别是0.863、0.203和2.147。将该模型用于星载GF-5号影像数据进行土壤总氮含量的反演填图。由填图结果可见,黑龙江省富锦市建三江垦区86.1%的土地总氮量均在2.0 g/kg以上,土地氮含量以一等地块和二等地块为主,而三等地块和四等级地块仅占总面积的11.83%。研究区内土壤氮要素储备充足,总氮高背景值主要集中在中部靠近河流两岸、呈北东东向分布。本研究土壤总氮预测成图结果与前人1∶25万地球化学插值和航空高光谱影像(Compact Airborne Spectrographic Imager, CASI)和(Shortwave Infrared Airborne Spectrographic Imager, SASI)填图效果具有很好的一致性。 【结论】 研究表明星载GF-5高光谱数据在土壤全氮含量监测填图和可视化分析上具有极高的潜力,本研究提出方法可为今后大范围开展定量检测土壤养分状况以及合理施肥提供技术支撑。

关键词: GF-5高光谱数据, 土壤总氮, 偏最小二乘回归法, 反向神经网络, 多元散射校正, 机器学习

Abstract:

[Objective] Nitrogen in soil is an absolutely crucial element for plant growth. Insufficient nitrogen supply can severely affect crop yield and quality, while excessive use of nitrogen fertilizers can lead to significant environmental issues such as water eutrophication and groundwater pollution. Therefore, large-scale, rapid detection of soil nitrogen content and precise fertilization are of great importance for smart agriculture. In this study, the hyperspectral data from the GF-5 satellite was emploied, and the various machine learning algorithms introduced to establish a prediction model for soil total nitrogen (TN) content and a distribution map of soil TN content was generated in the study area, aiming to provide scientific evidence for intelligent monitoring in smart agriculture. [Method] The study area was the Jian Sanjiang Reclamation Area in Fujin city, Heilongjiang province. Fieldwork involved the careful collection of 171 soil samples, obtaining soil spectral data, chemical analysis data of soil TN content, and the GF-5 hyperspectral data. Among these samples, 140 were randomly selected as the modeling sample set for calibration, and the remaining 31 samples were used as the test sample set. Three machine learning algorithms were introduced: Partial least squares regression (PLSR), backpropagation neural network (BPNN), and support vector machine (SVM) driven by a polynomial kernel function (Poly). Three distinct soil TN inversion models were constructed using these algorithms. To optimize model performance, ten-fold cross-validation was employed to determine the optimal parameters for each model. Additionally, multiple scatter correction (MSC) was applied to obtain band characteristic values, thus enhancing the model's prediction capability. Model performance was evaluated using three indicators: Coefficient of determination (R²), root mean square error (RMSE), and relative prediction deviation (RPD), to assess the prediction accuracy of different models. [Results and Discussions] MSC-Poly-SVM model exhibited the best prediction performance on the test sample set, with an R² of 0.863, an RMSE of 0.203, and an RPD of 2.147. This model was used to perform soil TN content inversion mapping using GF-5 satellite hyperspectral data. In accordance with the stringent requirements of land quality geochemical evaluation, the GF-5 hyperspectral land organic nitrogen parameter distribution map was drawn based on the "Determination of Land Quality Geochemical Evaluation". The results revealed that 86.1% of the land in the Jian Sanjiang study area had a total nitrogen content of more than 2.0 g/kg, primarily concentrated in first and second-grade plots, while third and fourth-grade plots accounted for only 11.83% of the total area. The study area exhibited sufficient soil nitrogen reserves, with high TN background values mainly concentrated along the riverbanks in the central part, distributed in a northeast-east direction. Specifically, in terms of soil spectral preprocessing, the median filtering method performed best in terms of smoothness and maintaining spectral characteristics. The spectra extracted from GF-5 imagery were generally quite similar to ground-measured spectral data, despite some noise, which had a minimal overall impact. [Conclusions] This study demonstrates the clear feasibility of using GF-5 satellite hyperspectral remote sensing data and machine learning algorithm for large-scale quantitative detection and visualization analysis of soil TN content. The soil TN content distribution map generated based on GF-5 hyperspectral remote sensing data is detailed and consistent with results from other methods, providing technical support for future large-scale quantitative detection of soil nutrient status and rational fertilization.

Key words: GF-5 hyperspectral image, soil total nitrogen, partial least-squares method, back propagation neural network, multiple scattering correction, machine learning

中图分类号: