裴志福, 沈钦国, 范若渝, 包明哲, 张月鲜, 红 梅. 基于中红外光谱的内蒙古区域农田土壤有机碳预测模型研究[J]. 土壤通报, 2024, 55(5): 1264 − 1272. DOI: 10.19336/j.cnki.trtb.2023072301
引用本文: 裴志福, 沈钦国, 范若渝, 包明哲, 张月鲜, 红 梅. 基于中红外光谱的内蒙古区域农田土壤有机碳预测模型研究[J]. 土壤通报, 2024, 55(5): 1264 − 1272. DOI: 10.19336/j.cnki.trtb.2023072301
PEI Zhi-fu, SHEN Qin-guo, FAN Ruo-yu, BAO Ming-zhe, ZHANG Yue-xian, HONG Mei. Prediction Model of Organic Carbon in Farmland Soil in Inner Mongolia Based on Middle Infrared Spectroscopy[J]. Chinese Journal of Soil Science, 2024, 55(5): 1264 − 1272. DOI: 10.19336/j.cnki.trtb.2023072301
Citation: PEI Zhi-fu, SHEN Qin-guo, FAN Ruo-yu, BAO Ming-zhe, ZHANG Yue-xian, HONG Mei. Prediction Model of Organic Carbon in Farmland Soil in Inner Mongolia Based on Middle Infrared Spectroscopy[J]. Chinese Journal of Soil Science, 2024, 55(5): 1264 − 1272. DOI: 10.19336/j.cnki.trtb.2023072301

基于中红外光谱的内蒙古区域农田土壤有机碳预测模型研究

Prediction Model of Organic Carbon in Farmland Soil in Inner Mongolia Based on Middle Infrared Spectroscopy

  • 摘要:
    目的 探究中红外光谱在预测内蒙古区域农田土壤有机碳含量的潜力。
    方法 以中国内蒙古地区农田土壤为研究对象,在内蒙古东部、中部和西部主要农田分布区域采集了411个土壤样品作为测试样本,基于不同预处理组合筛选评价,分别建立偏最小二乘回归(PLSR)和支持向量机回归(SVR)土壤有机碳预测模型,来比较中红外光谱对不同区域和整体土壤有机碳的预测精度。
    结果 ①从整体预测效果来看,PLSR所对应的不同预处理方法组合中预测精度表现最佳的为归一化处理(Normalization)(R2 = 0.8360,RMSEP = 1.7928 g kg−1,RPD = 2.4816),SVR所对应最佳预处理组合为多元散射校正(MSC) + MA平滑 + 中心化处理(Centralization)(R2 = 0.7557,RMSEP = 2.1881 g kg−1,RPD = 2.0332)。②从不同区域预测效果来看,两种建模方法均表现为对东部农田土壤有机碳预测效果最好(SVR优于PLSR),其次为中部,对西部农田土壤有机碳预测效果最差(PLSR优于SVR),这主要由于土壤类型和碳含量差异导致。此外,我们发现SVR更适合对东部高有机碳农田土壤预测,而PLSR对西部、中部农田和整体土壤有机碳的预测效果更为准确。
    结论 农田土壤类型、土壤碳含量差异和预处理方法选择对中红外光谱的预测效果均具有较大影响。基于中红外光谱技术建立的Normalization-PLSR定量预测模型对区域农田土壤有机碳具有较好的预测效果(R2 > 0.80),可为该地区精准农业发展提供重要的理论支撑。

     

    Abstract:
    Objective The aim was to explore the potential of mid infrared spectroscopy in predicting soil organic carbon (SOC) content in farmland in Inner Mongolia region.
    Methods This study focused on farmland soil in Inner Mongolia, China. Soil samples (411) were collected from the main farmland distribution areas in eastern, central and western Inner Mongolia as test samples. Based on different preprocessing combinations, SOC prediction models of partial least squares regression (PLSR) and support vector machine regression (SVR) were established to compare the accuracy of mid infrared spectroscopy in predicting OSC in the region.
    Results ①From the overall prediction performance, among the different preprocessing methods corresponding to PLSR, the best prediction accuracy was achieved through normalization (R2=0.8360, RMSEP=1.7928 g kg−1, RPD=2.4816); while the best preprocessing combination for SVR was multivariate scattering correction (MSC) + MA smoothing + centralization (R2=0.7557, RMSEP=2.1881 g kg−1, RPD=2.0332). ② From the perspective of prediction performance in different regions, both modeling methods showed the best prediction effect on SOC in eastern farmland (SVR is better than PLSR), followed by the central region, and the worst in western farmland (PLSR is better than SVR), mainly due to differences in soil type and SOC content. In addition, We found that the SVR was more suitable for predicting SOC in high SOC farmland in the east, while PLSR had a more accurate prediction effect on SOC in western, central farmland, and overall soil.
    Conclusion The farmland soil type, the difference of SOC content and the selection of pretreatment methods have a great impact on the prediction effect of mid infrared spectrum. Normalization PLSR quantitative prediction model based on mid infrared spectrum technology has a good prediction effect on regional farmland SOC (R2>0.80), which can provide important theoretical support for the development of precision agriculture in this region.

     

/

返回文章
返回