Enhancing soil texture classification with multivariate scattering correction and residual neural networks using visible near-infrared spectra.

Soil texture is one of the most important indicators of soil physical properties, which has traditionally been measured through laborious procedures. Approaches utilizing visible near-infrared spectroscopy, with their advantages in efficiency, eco-friendliness and non-destruction, are emerging as potent alternatives. Nevertheless, these approaches often suffer from limitations in classification accuracy, and the substantial impact of spectral preprocessing, model integration, and sample matrix effect is commonly disregarded. Here a novel 11-class soil texture classification strategy that address this challenge by combining Multiplicative Scatter Correction (MSC) with Residual Network (ResNet) models was presented, resulting in exceptional classification accuracy. Utilizing the LUCAS dataset, collected by the Land Use and Cover Area frame Statistical Survey project, we thoroughly evaluated eight spectral preprocessing methods. Our findings underscored the superior performance of MSC in reducing spatial complexity within spectral data, showcasing its crucial role in enhancing model precision. Through comparisons of three 1D CNN models and two ResNet models integrated with MSC, we established the superior performance of the MSC-incorporated ResNet model, achieving an overall accuracy of 98.97 % and five soil textures even reached 100.00 %. The ResNet model demonstrated a marked superiority in classifying datasets with similar features, as observed by the confusion matrix analysis. Moreover, we investigated the potential benefit of pre-categorization based on land cover type of the soil samples in enhancing the accuracy of soil texture classification models, achieving overall classification accuracies exceeding 99.39 % for woodland, grassland, and farmland with the 2-layer ResNet model. The proposed work provides a pioneering and efficient strategy for rapid and precise soil texture identification via visible near-infrared spectroscopy, demonstrating unparalleled accuracy compared to existing methods, thus significantly enhancing the practical application prospects in soil, agricultural and environmental science.

Enhancing soil nitrogen measurement via visible-near infrared spectroscopy: Integrating soil particle size distribution with long short-term memory models.

Good quality of soil nitrogen data, which is essential for the advancement of both enhanced agricultural management and ecological environment, traditionally depends on labor intensive chemical procedures. Visible near-infrared (Vis-NIR) spectroscopy, acknowledged for its efficiency, environmental compatibility and rapidity, merges as a promising alternative. However, the effectiveness of Vis-NIR measurement models are significantly compromised by soil particle size distribution (PSD), presenting a substantial challenge in improving the measurement accuracy and reliability. Here an innovative deep learning methodology that integrates PSD with Vis-NIR spectroscopy was proposed for the measurement of nitrogen content in soil samples. By leveraging the LUCAS dataset, different strategies for integrating PSD with Vis-NIR spectral data in deep learning models were explored, revealing that our proposed InSGraL framework, which incorporated mixed features of PSD and spectra as LSTM inputs achieves superior performance. Compared to models utilizing solely Vis-NIR data, InSGraL exhibits a 39.47 % reduction in RMSE and a 42.55 % decrease in MAE, and demonstrates robust performance across various land cover types, achieving an R2 of 0.94 on grassland samples. Moreover, Shapley Additive exPlanations (SHAP) analysis revealed that incorporating PSD modifies the spectral input importance distribution, effectively mitigating spectral interference from particle size while highlighting critical wavelengths previously obscured. This study provides an innovative modeling strategy to mitigate the influence of PSD by integrating it within deep learning framework using Vis-NIR, contributing a deeper understanding of the relationship between PSD and Vis-NIR spectra for the measurement of nitrogen content and offering an effective means to attain soil nitrogen data.

Identifying Freshness of Spinach Leaves Stored at Different Temperatures Using Hyperspectral Imaging.

Spinach is prone to spoilage in the course of preservation. Spinach leaves stored at different temperatures for different durations will have varying degrees of freshness. In order to monitor the freshness of spinach leaves during storage, a rapid and non-destructive method-hyperspectral imaging technology-was applied in this study. Visible near-infrared reflectance (Vis-NIR) (380-1030 nm) and near-infrared reflectance (NIR) (874-1734 nm) hyperspectral imaging systems were used. Spinach leaves preserved at different temperatures with different durations (0, 3, 6, 9 days at 4 °C and 0, 1, 2 days at 20 °C) were studied. Principal component analysis (PCA) was adopted as a qualitative analysis method. The second-order derivative spectra were utilized to select effective wavelengths. Partial least squares discriminant analysis (PLS-DA), support vector machine (SVM), and extreme learning machine (ELM) were used to build models based on full spectra and effective wavelengths. All three models achieved good results, with accuracies above 92% for both Vis-NIR spectra and NIR spectra. ELM obtained the best results, with all accuracies reaching 100%. The overall results indicate the possibility of the freshness identification of spinach preserved at different temperatures for different durations using two kinds of hyperspectral imaging systems.

Use of Visible-Near-Infrared (Vis-NIR) Spectroscopy to Detect Aflatoxin B1 on Peanut Kernels.

Current methods for detecting aflatoxin contamination of agricultural and food commodities are generally based on wet chemical analyses, which are time-consuming, destructive to test samples, and require skilled personnel to perform, making them impossible for large-scale nondestructive screening and on-site detection. In this study, we utilized visible-near-infrared (Vis-NIR) spectroscopy over the spectral range of 400-2500 nm to detect contamination of commercial, shelled peanut kernels (runner type) with the predominant aflatoxin B1 (AFB1). The artificially contaminated samples were prepared by dropping known amounts of aflatoxin standard dissolved in 50:50 (v/v) methanol/water onto peanut kernel surface to achieve different contamination levels. The partial least squares discriminant analysis (PLS-DA) models established using the full spectra over different ranges achieved good prediction results. The best overall accuracy of 88.57% and 92.86% were obtained using the full spectra when taking 20 and 100 parts per billion (ppb), respectively, as the classification threshold. The random frog (RF) algorithm was used to find the optimal characteristic wavelengths for identifying the surface AFB1-contamination of peanut kernels. Using the optimal spectral variables determined by the RF algorithm, the simplified RF-PLS-DA classification models were established. The better RF-PLS-DA models attained the overall accuracies of 90.00% and 94.29% with the 20 ppb and 100 ppb thresholds, respectively, which were improved compared to using the full spectral variables. Compared to using the full spectral variables, the employed spectral variables of the simplified RF-PLS-DA models were decreased by at least 94.82%. The present study demonstrated that the Vis-NIR spectroscopic technique combined with appropriate chemometric methods could be useful in identifying AFB1 contamination of peanut kernels.