The Key Laboratory of Metalorganic Prediction of Nonferrous Metals and Geological Environment Monitoring, School of Geosciences and Info-Physic Central South University, Changsha, Hunan 410083, China.
The Key Laboratory of Metalorganic Prediction of Nonferrous Metals and Geological Environment Monitoring, School of Geosciences and Info-Physic Central South University, Changsha, Hunan 410083, China; Chinese National Engineering Research Center for Control & Treatment of Heavy Metal Pollution, Changsha, Hunan 410083, China.
Sci Total Environ. 2019 Jun 15;669:964-972. doi: 10.1016/j.scitotenv.2019.03.186. Epub 2019 Mar 14.
Visible and near-infrared reflectance (VNIR) spectroscopy is considered to be a potential and efficient means for monitoring soil arsenic (As) contamination. While current studies mainly focus on the evaluation of models' performance when training and verification samples are collected from the same region, whether the model developed at a specific region can be transferred to other regions is still unclear. To answer this question, this study collected a total of 247 samples for training and verification from regions with different geographical conditions, which are Yuanping and Baoding in northern China, Chenzhou and Hengyang in southern China. Afterward, we proposed a transfer component analysis (TCA) based spectroscopic diagnosis model, which aims at adapting a model learned from one region to other regions. This model was compared with the traditional modeling method in terms of the prediction accuracy by four experiments. The results show that: (1) The traditional modeling method trained by specific regional samples has no transfer capability to different regions, since the coefficient of determination (R) and the ratio of prediction to deviation (RPD) were 0.02 and 0.65 for the first pair of study areas, 0.01 and 1.01 for the second pair of study areas; (2) A transfer model with favorable predictability can be constructed with the aid of TCA spectral transformation and a small amount off-site samples (R and RPD were improved to 0.68 and 1.54 for the first pair of study areas, 0.64 and 1.66 for the second pair of study areas). Results suggest that it is promising to develop potential implementations of transferable spectroscopic diagnosis models for estimating soil As concentrations in large area with lower cost.
可见近红外反射光谱（VNIR）被认为是监测土壤砷（As）污染的一种有潜力且高效的手段。虽然目前的研究主要集中在评估模型在从同一区域采集训练和验证样本时的性能，但开发的模型是否可以从特定区域转移到其他区域仍不清楚。为了回答这个问题，本研究从地理条件不同的地区（中国北方的原平和保定、中国南方的郴州和衡阳）共采集了 247 个样本进行训练和验证。之后，我们提出了一种基于转移成分分析（TCA）的光谱诊断模型，旨在将从一个地区学习到的模型应用于其他地区。通过四个实验，我们比较了该模型与传统建模方法在预测精度方面的差异。结果表明：（1）特定区域样本训练的传统建模方法没有向不同区域的转移能力，因为第一对研究区域的决定系数（R）和预测偏差比（RPD）分别为 0.02 和 0.65，第二对研究区域的分别为 0.01 和 1.01；（2）借助 TCA 光谱变换和少量异地样本，可以构建具有良好预测能力的转移模型（第一对研究区域的 R 和 RPD 分别提高到 0.68 和 1.54，第二对研究区域的 R 和 RPD 分别提高到 0.64 和 1.66）。结果表明，开发用于在大面积范围内以较低成本估算土壤 As 浓度的可转移光谱诊断模型具有很大的应用潜力。
