A Preprocessing Technique Using Diffuse Reflectance Spectroscopy to Predict the Soil Properties of Paddy Fields in Korea

Mid-infrared (MIR) spectroscopy is a powerful, eco-friendly, and cost-effective technique for predicting soil property. However, its predictive accuracy can be affected by factors such as moisture content, particle size, sensor variability, and the baseline noise. To address these limitations, this study investigated the impact of combining various preprocessing techniques with variable selection methods on the performance of partial least squares regression (PLSR) models. Soil samples from the Rhamna region of Morocco were analyzed to estimate key properties, including total nitrogen (TN), total carbon (TC), total organic carbon (TOC), clay, silt, sand, moisture content (MC), pH, phosphorus (P 2 O 5 ), and cation exchange capacity (CEC). Spectral data were preprocessed using methods such as standard normal variate (SNV), Savitzky–Golay smoothing (SG smoothing), first and second derivatives (SG1D and SG2D), and their combinations (e.g., SNV + SG2D). The best-performing preprocessing combinations were then used with variable selection approaches, interval PLS (iPLS), variable importance in projection (VIP), and selectivity ratio (SR). The results indicated that Savitzky–Golay (SG) derivatives combined with SNV generally improved model performance across most soil properties. In particular, total nitrogen (TN) prediction improved primarily with the first SG derivative, with R 2 cv increasing from 0.82 (raw spectra) to 0.88 (SG1D), while RMSEcv decreased from 0.03% to 0.01%. Further improvements were achieved through variable selection, with iPLS providing the most consistent enhancement across properties with a very low number of features compared to the other methods. Overall, the integration of optimal preprocessing and iPLS variable selection significantly improved the predictive accuracy and robustness of partial least squares regression (PLSR) models for soil property estimation compared with the full spectrum.

Assessment of calibration methods for nitrogen estimation in wet and dry soil samples with different wavelength ranges using near-infrared spectroscopy

The influence of vegetation cover on the spectroscopic estimation of soil properties

Dendrobium officinale is a valuable medicinal and edible homologous health food. It has immunomodulatory, antioxidant, and metabolism-regulating properties. However, its adulteration is widespread, seriously compromising product quality and safety. Traditional adulteration detection methods are complex, costly, and time-consuming, making it urgent to establish a rapid and non-destructive detection approach. This study developed a rapid identification and quantification method for adulterated D. officinale. The method combined near-infrared (NIR) spectroscopy with data-driven soft independent modeling of class analogy (DD-SIMCA) and partial least squares regression (PLSR) models. PCA, PLS-DA, and OPLS-DA were first used to visualize sample clustering and group differences. DT, SVM, ANN, and NB were used for classification. DD-SIMCA and PLSR were used for one-class modeling and quantitative analysis. Raw spectral data were preprocessed using multiplicative scatter correction (MSC), the standard normal variate (SNV), the first derivative, and Savitzky–Golay smoothing. In the identification analysis, the DD-SIMCA model achieved 100% sensitivity and 100% specificity in the validation set. Its overall accuracy in the independent test set was 99.2%, demonstrating excellent discrimination performance. In addition, SVM combined with NIR also achieved good accuracy. In the quantitative analysis of adulteration, the PLSR model predicted different adulteration levels. Most calibration and validation sets showed R2 values above 0.99 and RMSE values below 0.05, indicating excellent predictive performance. The results indicate that NIR combined with DD-SIMCA and PLSR can achieve rapid identification and accurate quantification of adulterated D. officinale samples. This approach provides strong support for quality control and regulatory supervision of high-value health foods.

Hyperspectral technology has been widely applied to the retrieval of soil properties, such as soil organic matter (SOM) and particle size distribution (PSD). However, most previous studies have focused on hyperspectral data acquired from the nadir direction, and the influence of viewing geometry on hyperspectral-based soil property retrieval remains unclear. In this study, bidirectional reflectance factors (BRFs) were collected at 48 different viewing angles for 154 soil samples with varying SOM contents and PSDs. SOM and PSD were then retrieved using combinations of ten spectral preprocessing methods (raw reflectance, Savitzky–Golay filter (SG), first derivative (D1), second derivative (D2), standard normal variate (SNV), multiplicative scatter correction (MSC), SG + D1, SG + D2, SG + SNV, and SG + MSC), one sensitive wavelength selection method, and three retrieval algorithms (partial least squares regression (PLSR), support vector machine (SVM), and convolutional neural networks (CNNs)). The influence of viewing geometry on the selection of spectral preprocessing methods, retrieval algorithms, sensitive wavelengths, and retrieval accuracy was systematically analyzed. The results showed that soil BRFs are influenced by both soil properties and viewing angles. The viewing geometry had limited effects on the choice of preprocessing method and retrieval algorithm. Among the preprocessing methods, D1, SG + D1, and SG + D2 outperformed the others, while PLSR achieved a higher accuracy than SVM and CNN when retrieving soil properties. The selected sensitive wavelengths for both SOM and PSD varied slightly with viewing angle and were mainly located in the near-infrared region when using BRFs from multiple viewing angles. Compared with single-angle data, multi-angle BRFs significantly improved retrieval performance, with the R2 increasing by 11% and 15%, and RMSE decreasing by 16% and 30% for SOM and PSD, respectively. The optimal viewing zenith angle ranged from 10° to 20° for SOM and around 40° for PSD. Additionally, backward viewing directions were more favorable than forward directions, with the optimal viewing azimuth angles being 0° for SOM and 90° for PSD. These findings provide useful insights for improving the accuracy of soil property retrieval using multi-angle hyperspectral observations.

The disappearance of EPTC (ethyl N,N-di-n-propylthiolcarbamate) from soils was studied by steam distilling the remaining EPTC from the soil samples and analyzing the distillates. The most important factor affecting the loss of EPTC from soil was the amount of moisture in the soil. During the first 15 minutes after spraying on the soil surface, 20% of the applied EPTC disappeared from dry soil, 27% from moist soil and 44% from wet soil. The loss was 23, 49, and 69% after one day and 44, 68, and 90% after six days on dry, moist, and wet soils, respectively. No significant loss of EPTC occurred the first few hours after applying granular EPTC to dry soil or soil containing 4 to 6% moisture, but on soil at 15% moisture the loss from granules was 60% in two hours. There appeared to be a critical moisture level for each soil, above which large losses of EPTC occurred after application to the surface or after shallow incorporation. Depth of incorporation was the second most important factor in EPTC loss from soils. Incorporation to at least 2 to 3 inches was necessary to prevent large losses of EPTC when light rain or sprinkler irrigation followed treatment. EPTC was lost at a faster rate on sunny days than cloudy days. Increasing the temperature from 32 to 60 F, increased the rate of EPTC vaporization from moist soil but had no effect on the loss from dry soil.

Ammonia-oxidizing archaea and bacteria (AOA, AOB) catalyze the first and rate-limiting step of nitrification. To examine their differential responses to the wetting of dry and salty arid soil, AOA and AOB amoA genes (encoding subunit A of the ammonia monooxygenase) and transcripts were enumerated in dry (summer) and wet (after the first rainfall) soil under the canopy of halophytic shrubs and between the shrubs. AOA and AOB were more abundant under shrub canopies than between shrubs in both the dry and wetted soil. Soil wetting caused a significant decrease in AOB abundance under the canopy and an increase of AOA between the shrubs. The abundance of the archaeal amoA gene transcript was similar for both the wet and dry soil, and the transcript-to-gene ratios were < 1 independent of niche or water content. In contrast, the bacterial amoA transcript-to-gene ratios were between 78 and 514. The lowest ratio was in dry soil under the canopy and the highest in the soil between the shrubs. The results suggest that the AOA are more resilient to stress conditions and maintain a basic activity in arid ecosystems, while the AOB are more responsive to changes in the biotic and abiotic conditions.

Visible and near-infrared (VNIR) diffuse reflectance spectroscopy (DRS) has proven to be effective tools of estimation of soil properties. Regression models are usually calibrated on the entire datasets without its stratification. This paper discusses how clustering of the soil spectra improves prediction of basic soil properties: contents of sand, clay, soil organic carbon (SOC) and total nitrogen, as well as the cation exchange capacity (CEC) and total exchangeable bases (TEB). The analysis was performed on a set of 212 soil samples collected from surface horizons throughout the area of arable lands in Poland. Spectral measurements were done using ASD Fildspec PRO with attached Source Probe Mug-Lite in the wavelength range of 350-2500 nm. First, partial least squares (PLS) regression models using the raw spectra and their first derivatives were calibrated on the entire dataset. Then, the observations (soil samples) were clustered using the Ward and K-mean methods based both on the raw and the transformed spectral data. The PLS regression modeling fitted separately within each cluster was performed. Our findings indicate that clustering is potentially useful to enhance the prediction of soil properties based on the DSR data when using the PLS regression modeling. In a practical application to a given set of soil samples, one needs to implement a two-step procedure recommended in this paper. In the first step, one runs a cross-validation analysis in order to identify the best combination of the spectra transformation, the type of the clustering method, and the number of clusters. In the second step, the best combination is applied to the whole dataset for prediction purposes. The improvement achieved by the described procedure ranges from 24 to 49 % reduction in the cross validation root mean squared error.

Total viable count (TVC) is often used as an important indicator for chicken freshness evaluation. In this study, 112 fresh chicken flesh samples were acquired after slaughtered and their hyperspectral images were collected in the LW-NIR (900-1700 nm) range. The full LW-NIR spectra (486 wavebands) within the images were extracted and applied to related to reference TVC values measured in different storage period, using partial least squares regression (PLSR) algorithm, resulting in high correlation coefficients (R) and low root mean square errors (RMSE), for either raw spectra or pretreatment spectra. By using regression coefficients (RC) method, 20, 18, 17 and 20 optimal wavebands were respectively selected from raw spectra, baseline correction (BC) spectra, Savitzky-Golay convolution smoothing (SGCS) spectra and standard normal variate (SNV) spectra and applied for the optimization of original full waveband PLSR model. By comparison, RC-PLSR model based on the SGCS spectra showed a better performance in TVC prediction with RC of 0.98 and RMSEC of 0.35 log10 CFU/g in calibration set, and RP of 0.98 and RMSEP of 0.44 log10 CFU/g in prediction set. At last, by transferring the best RC-PLSR model, the dynamic TVC change during the storage was visualized by color maps to indicate the TVC spoilage degree. The overall study revealed that LW-NIR hyperspectral imaging combined with PLSR could be used to predict the freshness of chicken flesh. Keywords: hyperspectral imaging, chicken, TVC, partial least square regression (PLSR) DOI: 10.25165/j.ijabe.20191203.4444 Citation: H Wang, H J He, H J Ma, F S Chen, Z L Kang, M M Zhu, et al. LW-NIR hyperspectral imaging for rapid prediction of TVC in chicken flesh. Int J Agric & Biol Eng, 2019; 12(3): 180–186.

Local modeling approaches for estimating soil properties in selected Indian soils using diffuse reflectance data over visible to near-infrared region

Multi-factor fusion models for soluble solid content detection in pear (Pyrus bretschneideri ‘Ya’) using Vis/NIR online half-transmittance technique

Content uniformity of pharmaceutical solid dosage forms by near infrared hyperspectral imaging: A feasibility study

PDF HTML阅读 XML下载 导出引用 引用提醒 太湖流域丘陵区两种土地利用类型土壤水分分布控制因素 DOI: 10.5846/stxb201405181019 作者: 作者单位: 中科院南京地理与湖泊研究所,中科院南京地理与湖泊研究所,中科院南京地理与湖泊研究所,中科院南京地理与湖泊研究所 作者简介: 通讯作者: 中图分类号: 基金项目: 国家自然科学基金(41271109, 41301234); 中国科学院南京地理与湖泊研究所"一三五"重点项目(NIGLAS2012135005) The controlling factors of soil moisture distribution under two typical land-use hillslopes in a hilly region of Taihu Lake basin Author: Affiliation: Nanjing Institute of Geography and Limnology, Chinese Academy of Sciences,,Nanjing Institute of Geography and Limnology, Chinese Academy of Sciences,Nanjing Institute of Geography and Limnology, Chinese Academy of Sciences Fund Project: 摘要 | 图/表 | 访问统计 | 参考文献 | 相似文献 | 引证文献 | 资源附件 | 文章评论 摘要:为探究太湖流域丘陵区典型土地利用类型(如竹林地和茶园)土壤水分的控制因素,在不同深度土壤水分定期观测的基础上,根据前7d降雨量将研究时段划分为干旱状态和湿润状态,利用分类与回归树(CART)方法得出不同干湿状态下土壤水分分布的主控因子,并借助典范对应分析(CCA)定量分析不同土地利用类型、不同土壤深度土壤水分格局与环境因子关系。结果表明:(1)高程、土地利用类型和土层厚度对土壤水分分布的相对贡献率最大,但在不同干湿状态下其影响程度存在差异; (2)干旱状态时土壤水分主要受高程、坡度、地形湿度指数(TWI)和剖面曲率等地形因素的作用,而土层厚度和粘粒也分别为0-20 cm和20-40 cm深度土壤水分的主控因子; (3)在湿润状态下,茶园0-20 cm土壤水分的主控因素为地形因子,在20-40 cm则以土壤性质为主,竹林地两个深度的土壤水分受地形和土壤性质的作用都很强,其中20-40 cm深度土壤水分与环境因子的关系较0-20 cm深度更为复杂。 Abstract:Soil moisture is one of the most important factors in terrestrial ecosystems. Adequate knowledge of its spatio-temporal variability is critical to many scientific and practical applications. We explored the factors controlling moisture distribution in soils under typical land-use types (i.e., bamboo forest and tea garden) in a hilly region of Taihu Lake basin. In situ soil moisture measurements were made at different depths, and these were classified as dry or wet conditions, based on the precipitation during the previous 7 d. The main controlling factors were identified by using the classification and regression tree (CART) method. Canonical correspondence analysis (CCA) was then applied to quantitatively analyze the relationships between soil moisture and environmental factors under different land-uses at different soil depths. The results show that: (1) the relative influences of elevation, land use, and soil thickness on soil moisture distribution were larger than those of other environmental factors in most cases. Together these accounted for more than 50% of the total variation in soil moisture. However, their relative contributions differed between dry and wet conditions. (2) In dry conditions soil moisture was mainly affected by topographic indices such as elevation, slope, topographic wetness index (TWI) and profile curvature. Soil thickness and clay content also significantly affected soil moisture at 0-20 and 20-40 cm depths, respectively. The main factors controlling soil moisture in dry conditions varied with soil depth, but not with land-use type. This finding was different from that of a previous study, in which the study area had similar landforms and climatic conditions. This may be due to the effects of spatial scale. (3) In wet conditions, topographic indices and soil properties were the main factors controlling soil moisture in tea gardens at 0-20 and 20-40 cm depths, respectively. Both topographic indices and soil properties were the main controlling factors of soil moisture in a bamboo forest at these two depths. It is noted that the relationship between soil moisture and environmental factors at 20-40 cm depth is more complicated than that at 0-20 cm depth in bamboo forest. In contrast to dry conditions, both soil depth and land-use type had a significant impact on the environmental factors that control soil moisture distribution. This study is of great relevance to the sustainable utilization of water and soil resources and to the management of water and fertilizer in agriculture in this region. 参考文献 相似文献 引证文献

&amp;lt;p&amp;gt;Fire is an important element of the ecosystems, nevertheless, high severity fires can have negative impacts on the ecosystems as consequence of the high temperatures reaches. High temperatures normally have detrimental impacts on soil properties. The objective of this work was to determine the relationship of spectral reflectance and soil pH, electrical conductivity (EC), carbonates (CaCO&amp;lt;sub&amp;gt;3&amp;lt;/sub&amp;gt;) and total carbon (TC) content after a medium to high severity wildfire occurred in Croatia using linear and nonlinear calibration models.&amp;lt;/p&amp;gt;&amp;lt;p&amp;gt;Soils were sampled 2 days after a medium to high severity wildfire in Zadar County, Croatia. A total of 120 soil samples (0-5 cm) were collected from three different treatments (n= 40 per treatment): control (C), mean severity (MS), high severity (HS). Soil pH, EC, CaCO&amp;lt;sub&amp;gt;3&amp;lt;/sub&amp;gt; and TC content were determined using standard laboratory methods. &amp;amp;#160;Soil spectral measurements were carried out using a portable spectroradiometer (20 per treatment, 60 in total). Linear statistical model - partial least squares regression (PLSR) and non-linear - artificial neural network (ANN) were generated to estimate changes in soil pH, EC, CaCO&amp;lt;sub&amp;gt;3&amp;lt;/sub&amp;gt; and TC content based on the original spectral reflectance and its first derivative in form of principal components (PC). One-way ANOVA revealed pH values were significantly different in all three treatments. EC, CaCO&amp;lt;sub&amp;gt;3&amp;lt;/sub&amp;gt; and TC were significantly higher in HS plots compared with the other treatments.&amp;lt;/p&amp;gt;&amp;lt;p&amp;gt;Different wildfire severity indicated very collinear soil spectral response, but with certain variations of reflectance intensity. Control samples showed a higher reflectance than MS and HS samples. This is attributed to the low pH and TC content. Low reflectance of MS and HS samples could be explained by their increased pH and TC values. Soil pH was the only parameter that showed a high R&amp;lt;sup&amp;gt;2&amp;lt;/sup&amp;gt; and low root mean squared error (RMSE) after Savitzky Golay smoothing and the first derivation. In PLSR model, strong to very strong correlation and low RMSE were obtained. ANN model also showed a high R&amp;lt;sup&amp;gt;2&amp;lt;/sup&amp;gt; and lower RMSE for all properties except pH. Both models showed satisfactory results for prediction of the studied soil properties. ANN model predicted EC, CaCO&amp;lt;sub&amp;gt;3&amp;lt;/sub&amp;gt;, and TC better, while PLSR proved to be a better model for pH prediction.&amp;lt;/p&amp;gt;&amp;lt;p&amp;gt;&amp;lt;strong&amp;gt;Key words:&amp;lt;/strong&amp;gt; soil reflectance, fire severity, principal components, partial least squares regression, neural networks&amp;lt;/p&amp;gt;&amp;lt;p&amp;gt;Acknowledgements&amp;lt;/p&amp;gt;&amp;lt;p&amp;gt;This work was supported by Croatian Science Foundation through the project &amp;quot;Soil erosion and degradation in Croatia&amp;quot; (UIP-2017-05-7834) (SEDCRO).&amp;lt;/p&amp;gt;

One of the most important food safety issues is the detection of mycotoxins, the ubiquitous, natural contaminants in cereals. Hyperspectral imaging (HSI) is a new method in food science, it can be used to predict non-destructively the changes in composition and distribution of compounds. That is why, in the last decade, the potential of HSI has been evaluated in many fields of food science, including mycotoxin research.The aim of the recent study was to test the feasibility of HSI for the differentiation according to the toxin content of cornmeal samples inoculated with Fusarium graminearum, Fusarium verticillioides and Fusarium culmorum and samples with natural levels of mycotoxins. Samples were measured in the near infrared wavelength range of 900–1,700 nm and mean spectra of selected regions of interest of each image were pre-treated using Savitzky-Golay smoothing and standard normal variate (SNV) method. On the spectra, partial least squares discriminant analysis (PLS-DA) was carried out according to the level of contamination. Partial least squares regression (PLSR) method was used to predict deoxynivalenol (DON) content of samples and the cumulative toxin content: the sum of fumonisins (FB1, FB2) and DON content of samples. Based on the promising results of the study, HSI has the potential to be used as a preliminary testing method for mycotoxin content in feed materials.