Abstract This study exploits the potential of near infrared (NIR) spectroscopy to deliver a measurement for each sampling point. Furthermore, it provides a protocol for the modelling of the spatial pattern of analytical constituents. On the basis of these two aspects, the methodology proposed in this work offers an opportunity to provide a real-time monitoring system to evaluate raw materials, easing and optimising the existing procedures for sampling and analysing products transported in bulk. In this paper, Processed Animal Proteins (PAPs) were selected as case study, and two types of quality/safety issues were tested in PAP lots —induced by moisture and cross-contamination. A simulation study, based on geostatistical analysis and the use of a set of sampling protocols, made a qualitative analysis possible to compare the representation of the spatial surfaces produced by each design. Moreover, the Root Mean Square Error of Prediction (RMSEP), calculated from the differences between the analytical values and the geostatistical predictions at unsampled locations, was used to measure the performance in each case. Results show the high sensitivity of the process to the sampling plan used — understood as the sampling design plus the sampling intensity. In general, a gradual decrease in the performance can be observed as the sampling intensity decreases, so that unlike for higher intensities, the too low ones resulted in oversmoothed surfaces which did not manage to represent the actual distribution. Overall, Stratified and Simple Random samplings achieved the best results in most cases. This indicated that an optimal balance between the design and the intensity of the sampling plan is imperative to perform this methodology.

中文翻译：

---

散装原材料质量安全控制采样设计的性能比较：基于近红外光谱数据和地质统计分析的模拟研究

摘要 本研究利用近红外 (NIR) 光谱的潜力对每个采样点进行测量。此外，它还为分析成分的空间模式建模提供了一个协议。在这两个方面的基础上，这项工作中提出的方法提供了一个机会，可以提供一个实时监控系统来评估原材料，简化和优化现有的对散装运输产品进行采样和分析的程序。在本文中，加工动物蛋白 (PAP) 被选为案例研究，并在 PAP 批次中测试了两种类型的质量/安全问题 - 由水分和交叉污染引起。基于地质统计分析和使用一组采样协议的模拟研究，使定性分析成为可能，以比较每个设计产生的空间表面的表现。此外，根据分析值与未采样位置的地质统计预测之间的差异计算得出的预测均方根误差 (RMSEP) 用于衡量每种情况下的性能。结果表明该过程对所使用的抽样计划具有很高的敏感性——理解为抽样设计加上抽样强度。一般来说，随着采样强度的降低，可以观察到性能的逐渐下降，因此与较高的强度不同，过低的强度会导致表面过于光滑，无法代表实际分布。总体而言，分层和简单随机抽样在大多数情况下取得了最好的结果。