Benefits of fusion approaches for visible to near (vis-NIR) and mid-infrared (MIR) chemometric modelling have been studied to some extent for laboratory-based soil studies, but little is known about the usefulness and limitations for in situ studies. Objectives were to compare laboratory-based and in situ vis-NIR and MIR partial least squares (PLS) and bagging-PLS regression approaches and to explore the potentials of combining both types of spectral data for the quantification of soil organic carbon (SOC). We applied different established low-level (spectra concatenation, outer product fusion approach) and high-level (averaging of vis-NIR and MIR modelling results) data fusion methods. The studied set comprised a total of 186 soil samples collected in Saxony-Anhalt and northern Saxony, Central Germany. One subset (Querfurt Plateau) covered 90 finely-textured soils originating from the Chernozem soil region, another (Düben Heath) with 96 samples was characterized by a wider pedological variety. Vis-NIR and MIR diffuse reflectance spectra were measured in situ on the soil surface and in the laboratory on pre-treated (dried and finely ground) soil material with the ASD FieldSpec 4 and the Agilent 4300 Handheld FTIR instruments. We found a regionally stratified approach to be beneficial for accurate estimations for both laboratory and in situ data. For laboratory spectra, MIR outperformed vis-NIR data in both regions (Querfurt Plateau: r² = 0.85 vs. 0.65, RMSE = 0.11 (in % SOC) vs. 0.17; Düben Heath: 0.77 vs. 0.69 (r²) and 0.27 vs. 0.40 (RMSE)). Ranking for in situ data was the same, but accuracies decreased markedly. With MIR, r² amounted to 0.58 and RMSE was 0.20 for the Querfurt Plateau (vis-NIR: r² = 0.26, RMSE = 0.27); for Düben Heath, r² was 0.60 and RMSE was 0.39 for MIR data, while vis-NIR resulted in an r² of 0.53 and an RMSE of 0.43. For the studied samples, which had medium to low water contents (0.68 to 16.8 wt%, median at 5.4 wt%), we found accuracies with both spectral datasets to be similarly affected by in situ conditions. Model ensemble averaging based on bagging-PLS regression was the most efficient approach to improve SOC estimation accuracies with in situ spectral data, whereas model averaging was in general of little effect for laboratory data. Improvements were most marked for the in situ data of the Düben Heath region, where r² increased to a value of 0.77 and RMSE decreased to 0.28. Low-level data fusion methods did not yield any improvements compared to model ensemble averaging. For the latter, we identified averaging with weights derived sample-wise from uncertainties in the bootstrap-based modelling as being most accurate, but with little benefits compared to a simple (unweighted) averaging of vis-NIR and MIR estimates. Our results suggest that already a simple averaging procedure has the potential to advance multi-sensor applications integrating vis-NIR and MIR data for in situ or on-site soil spectroscopy. This applies especially to regions with heterogeneous soil conditions, tied to spectral variablity, as this increases the probability of complementary vis-NIR and MIR information and their prospective fusion.

对于基于实验室的土壤研究，融合方法对可见光到近光 (vis-NIR) 和中红外 (MIR) 化学计量建模的好处已经在某种程度上进行了研究，但对原位研究的有用性和局限性知之甚少。目的是比较基于实验室和原位 vis-NIR 和 MIR 偏最小二乘法 (PLS) 和装袋-PLS 回归方法，并探索将两种类型的光谱数据结合起来量化土壤有机碳 (SOC) 的潜力。我们应用了不同的已建立的低级（光谱串联、外积融合方法）和高级（vis-NIR 和 MIR 建模结果的平均）数据融合方法。研究组包括在德国中部萨克森-安哈尔特州和萨克森州北部收集的总共 186 个土壤样品。一个子集（Querfurt Plateau）覆盖了源自黑钙土区域的 90 个质地细腻的土壤，另一个（Düben Heath）包含 96 个样本，其特征是更广泛的土壤多样性。Vis-NIR 和 MIR 漫反射光谱是在土壤表面原位测量的，并在实验室中使用 ASD 对预处理（干燥和细磨）的土壤材料进行测量 FieldSpec  4 和 Agilent 4300 手持式 FTIR 仪器。我们发现区域分层方法有利于准确估计实验室和原位数据。对于实验室光谱，MIR 在两个区域（Querfurt Plateau：r ²  = 0.85 vs. 0.65，RMSE = 0.11（% SOC）vs. 0.17；Düben Heath：0.77 vs. 0.69 (r ² ) 和 0.27）的表现都优于可见光-近红外数据与 0.40（RMSE））。原位数据的排名相同，但准确度显着下降。对于 MIR，Querfurt 高原的r ²为 0.58，RMSE 为 0.20（vis-NIR：r ²  = 0.26，RMSE = 0.27）；对于 Düben Heath，MIR 数据的r ²为 0.60，RMSE 为 0.39，而 vis-NIR 导致 r ²0.53 和 0.43 的 RMSE。对于具有中至低水含量（0.68 至 16.8 重量％，中值为 5.4 重量％）的研究样品，我们发现两个光谱数据集的准确性受原位条件的影响类似。基于 bagging-PLS 回归的模型集成平均是利用原位光谱数据提高 SOC 估计精度的最有效方法，而模型平均对实验室数据的影响通常很小。Düben Heath 地区的原位数据的改进最为显着，其中 r ²增加到 0.77 的值，RMSE 减少到 0.28。与模型集成平均相比，低级数据融合方法没有产生任何改进。对于后者，我们确定使用从基于引导程序的建模中的不确定性抽样得出的权重进行平均是最准确的，但与简单（未加权）平均 vis-NIR 和 MIR 估计相比几乎没有好处。我们的结果表明，已经是一个简单的平均程序有可能推进多传感器应用，将可见近红外和中红外数据集成到原位或现场土壤光谱学中。这尤其适用于土壤条件异质的区域，与光谱可变性相关，因为这增加了互补可见近红外和中红外信息及其预期融合的可能性。