欢迎访问《中国农学通报》,

中国农学通报 ›› 2023, Vol. 39 ›› Issue (13): 87-94.doi: 10.11924/j.issn.1000-6850.casb2022-0997

• 资源·环境·生态·土壤·气象 • 上一篇    下一篇

云南山地胶园土壤有机质高光谱估算

陈桂良(), 刘忠妹(), 许木果, 黎小清, 丁华平, 杨春霞   

  1. 云南省热带作物科学研究所,云南景洪 666100
  • 收稿日期:2022-11-27 修回日期:2023-03-22 出版日期:2023-05-05 发布日期:2023-04-27
  • 通讯作者: 刘忠妹,女,1988年出生,云南景谷人,助理研究员,本科,研究方向:土壤与植物营养。通信地址:666100 云南省景洪市宣慰大道99号 云南省热带作物科学研究所,Tel:0691-2120323,E-mail:718717454@qq.com
  • 作者简介:

    陈桂良,男,1984年出生,江西上栗人,助理研究员,硕士,研究方向:植物营养与3S技术应用。通信地址:666100 云南省景洪市宣慰大道99号 云南省热带作物科学研究所,Tel:0691-2120323,E-mail:

  • 基金资助:
    云南省应用研究基础计划-青年项目“基于高光谱信息的胶园土壤养分含量估算模型研究”(2019FD006); 省所热带作物科技创新专项资金“热带作物栽培技术服务平台优化与应用”(RF2023-6)

Hyper-spectral Estimation for Soil Organic Matter in Yunnan Mountainous Rubber Plantations

Guiliang CHEN(), Zhongmei LIU(), Muguo XU, Xiaoqing LI, DING Huaping, YANG Chunxia   

  1. Yunnan Institute of Tropical Crops, Jinghong, Yunnan 666100
  • Received:2022-11-27 Revised:2023-03-22 Online:2023-05-05 Published:2023-04-27

摘要:

有机质是反映橡胶园土壤养分状况的重要指标,其含量快速、高精度估算模型的建立,可以更好地指导胶园精细化生产管理。本研究从景洪市东风农场采集到225个橡胶园土壤样品,并获取土壤样品的光谱反射率和有机质含量数据,对光谱反射率进行噪声波段去除和重采样后,应用3种方法[log(1/R)、MSC、SNV]对重采样后的光谱反射率R进行光谱变换处理,然后对光谱反射率R以及3种变换形式光谱数据进行SG平滑或导数变换模式优选,得到最佳的光谱变换模式为log(1/R)结合SG平滑变换,其中,SG平滑变换模式为导数阶数0、SG滤波窗口5、多项式次数2或3。基于最佳光谱变换光谱数据与土壤有机质含量数据,选择CARS、SPA、CARS-SPA等3种方法提取特征波长,并采用MLR、PLSR和SVR 3种方法构建土壤有机质高光谱估算模型。结果显示,CARS-SVR模型估算精度最高,R2RMSERPD分别为0.897、3.990 g/kg、2.947。建立的云南山地胶园土壤有机质含量高光谱最优估算模型,RPD位于2.5~3.0之间,具有很好的估算能力。

关键词: 橡胶园, 土壤有机质, 高光谱, 竞争适应重加权采样, 支持向量回归

Abstract:

Organic matter is an important indicator of soil nutrient status in rubber plantations. The establishment of a fast and highly precise estimation model for organic matter content can better guide the fine production management of rubber plantations. In this study, 225 rubber plantation soil samples were collected from Dongfeng Farm in Jinghong City, and the spectral reflectance and organic matter content data of the soil samples were obtained. After noise band removal and resampling of the spectral reflectance, three methods [log(1/R), MSC and SNV] were applied to perform spectral transformation processing on resampled spectral reflectance R, and then SG smoothing or derivative transformation modes were used to optimize the spectral reflectance R and the spectral data of three transform forms. The best spectral transformation mode was obtained as log(1/R) combined with SG smoothing transformation. The SG smoothing transformation mode had the derivative order, SG filtering window, and polynomial degree of 0, 5, and 2 or 3, respectively. Based on the best spectral transformation data and soil organic matter content data, three methods including CARS, SPA and CARS-SPA were selected to extract characteristic wavelength, and the hyper-spectral estimation model for soil organic matter was constructed by MLR, PLSR and SVR. The results showed that the estimation accuracy of CARS-SVR model was the highest. The R2, RMSE and RPD were respectively 0.897, 3.990 g/kg and 2.947. Therefore, the established hyper-spectral optimal estimation model for soil organic matter content in Yunnan mountainous rubber plantations, with RPD between 2.5 and 3.0, has good estimation ability.

Key words: rubber plantation, soil organic matter, hyper-spectral, competitive adaptive reweighted sampling, support vector regression