Abstract Pesticide detection has been a long-running concern within the agricultural industry. Therefore, rapid and accurate detection techniques are required. Raman spectroscopy is favored by scientists due to the rapid detection without the need for the pretreatment or destruction of samples. However, the accuracy of the quantitative analysis that is based on Raman spectra is related to the detection model and analysis algorithm. In this study, random forest regression (RFR) was employed to construct a quantitative detection model that correlated the Raman spectral intensity of chlorpyrifos at 341 cm−1 and the chlorpyrifos concentration remaining on the pear surface. RFR performs better than partial least square regression (PLSR). The correlation coefficient (R2) of RFR was 0.9003 and 0.8495 for the training and test sets, respectively. In particular, the R2 value of the test sets was significantly higher than for PLSR (R2 of 0.6985). The intensity of the Raman spectra at 341 cm−1 was improved by four-fold using 100 nm gold nanoparticles. The results show that Raman spectroscopy combined with RFR achieves the rapid and accurate quantitative determination of pesticide residues.

中文翻译：

---

随机森林回归分析拉曼光谱法测定梨中毒死蜱

摘要 农药检测一直是农业领域长期关注的问题。因此，需要快速准确的检测技术。拉曼光谱因其快速检测而无需对样品进行预处理或破坏而受到科学家的青睐。然而，基于拉曼光谱的定量分析的准确性与检测模型和分析算法有关。在本研究中，随机森林回归 (RFR) 用于构建定量检测模型，该模型将 341 cm-1 处毒死蜱的拉曼光谱强度与梨表面残留的毒死蜱浓度相关联。RFR 的性能优于偏最小二乘回归 (PLSR)。训练集和测试集的 RFR 相关系数 (R2) 分别为 0.9003 和 0.8495。特别是，测试集的 R2 值明显高于 PLSR（R2 为 0.6985）。使用 100 nm 金纳米粒子后，341 cm-1 处的拉曼光谱强度提高了四倍。结果表明，拉曼光谱结合RFR实现了农药残留的快速准确定量测定。