Scholarlink

<p>Soil and plant analyser development (SPAD) is a key indicator of plant nutritional status and nitrogen stress, reflecting crop growth. During potato tuber formation, multispectral and thermal infrared sensors were used to monitor leaf chlorophyll content. Four data sources—texture indices (TIs), vegetation indices (VIs), thermal infrared vegetation indices (TVIs), and texture features (TFs)—were analysed for correlation with SPAD values. The correlation coefficient was calculated, and the feature variables were screened. Then, the selected features were randomly combined with the ground measured data to construct random forest (RF), support vector machine (SVM), and partial least squares regression (PLSR) models. Results showed that among TIs, the ratio texture index (RTI) had the highest correlation with SPAD (<i>R</i> = 0.703). Among VIs, the visible light difference vegetation index (VDVI) correlated best (<i>R</i> = 0.576). Among TVIs, normalised canopy temperature (NRCT) showed the strongest correlation (<i>R</i> = 0.640). Nearly half of TFs reached significant levels (<i>P</i> &lt; 0.01). VIs provided the highest accuracy (<i>R</i><sup>2</sup> = 0.741) in chlorophyll monitoring, with TIs improving prediction accuracy by up to 17.81% compared to TFs. Multi-source fusion (VIs + TIs + TVIs) achieved the highest model accuracy (<i>R</i><sup>2</sup> = 0.854), a 15.2% improvement over traditional VIs input, with mean square error (RMSE) reduced by 40.8% and mean relative error (MRE) by 77.7%. RF models outperformed others under identical input conditions. This study offers a robust methodology for UAV-based multi-source remote sensing to monitor potato leaf chlorophyll, supporting precision agriculture practices.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Estimation of Chlorophyll Content in Potato Leaves Based on UAV Multi-Spectral and Thermal Infrared Images

  • 期刊论文

  • 发表日期：

    2025年11月8日

查看全文
  • Ming Jin,
  • Juanli Ju,
  • Siqi Li,
  • Xiaochi Liu,
  • Xiangyang Huang,
  • Tao Sun,
  • Zijun Tang,
  • Youzhen Xiang,
  • Zhijun Li,
  • Fucang Zhang

摘要

Soil and plant analyser development (SPAD) is a key indicator of plant nutritional status and nitrogen stress, reflecting crop growth. During potato tuber formation, multispectral and thermal infrared sensors were used to monitor leaf chlorophyll content. Four data sources—texture indices (TIs), vegetation indices (VIs), thermal infrared vegetation indices (TVIs), and texture features (TFs)—were analysed for correlation with SPAD values. The correlation coefficient was calculated, and the feature variables were screened. Then, the selected features were randomly combined with the ground measured data to construct random forest (RF), support vector machine (SVM), and partial least squares regression (PLSR) models. Results showed that among TIs, the ratio texture index (RTI) had the highest correlation with SPAD (R = 0.703). Among VIs, the visible light difference vegetation index (VDVI) correlated best (R = 0.576). Among TVIs, normalised canopy temperature (NRCT) showed the strongest correlation (R = 0.640). Nearly half of TFs reached significant levels (P < 0.01). VIs provided the highest accuracy (R2 = 0.741) in chlorophyll monitoring, with TIs improving prediction accuracy by up to 17.81% compared to TFs. Multi-source fusion (VIs + TIs + TVIs) achieved the highest model accuracy (R2 = 0.854), a 15.2% improvement over traditional VIs input, with mean square error (RMSE) reduced by 40.8% and mean relative error (MRE) by 77.7%. RF models outperformed others under identical input conditions. This study offers a robust methodology for UAV-based multi-source remote sensing to monitor potato leaf chlorophyll, supporting precision agriculture practices.