Laboratory Visible and Near-Infrared Spectroscopy with Genetic Algorithm-Based Partial Least Squares Regression for Assessing the Soil Phosphorus Content of Upland and Lowland Rice Fields in Madagascar

Rapid In Situ Near-Infrared Assessment of Tetrahydrocannabinolic Acid in Cannabis Inflorescences before Harvest Using Machine Learning

Cannabis is cultivated for therapeutic and recreational purposes where delta-9 tetrahydrocannabinol (THC) is a main target for its therapeutic effects. As the global cannabis industry and research into cannabinoids expands, more efficient and cost-effective analysis methods for determining cannabinoid concentrations will be beneficial to increase efficiencies and maximize productivity. The utilization of machine learning tools to develop near-infrared (NIR) spectroscopy-based prediction models, which have been validated from accurate and sensitive chemical analysis, such as gas chromatography (GC) or liquid chromatography mass spectroscopy (LCMS), is essential. Previous research on cannabinoid prediction models targeted decarboxylated cannabinoids, such as THC, rather than the naturally occurring precursor, tetrahydrocannabinolic acid (THCA), and utilize finely ground cannabis inflorescence. The current study focuses on building prediction models for THCA concentrations in whole cannabis inflorescences prior to harvest, by employing non-destructive screening techniques so cultivators may rapidly characterize high-performing cultivars for chemotype in real time, thus facilitating targeted optimization of crossbreeding efforts. Using NIR spectroscopy and LCMS to create prediction models we can differentiate between high-THCA and even ratio classes with 100% prediction accuracy. We have also developed prediction models for THCA concentration with a R2 = 0.78 with a prediction error average of 13%. This study demonstrates the viability of a portable handheld NIR device to predict THCA concentrations on whole cannabis samples before harvest, allowing the evaluation of cannabinoid profiles to be made earlier, therefore increasing high-throughput and rapid capabilities.

A novel multi-model estimation of phosphorus in coal and its ash using FTIR spectroscopy

The level of phosphorus must be carefully monitored for proper and effective utilization of coal and coal ash. The phosphorus content needs to be assessed to optimize combustion efficiency and maintenance costs of power plants, ensure quality, and minimize the environmental impact of coal and coal ash. The detection of low levels of phosphorus in coal and coal ash is a significant challenge due to its complex chemical composition and low concentration levels. Effective monitoring requires accurate and sensitive equipment for the detection of phosphorus in coal and coal ash. X-ray fluorescence (XRF) is a commonly used analytical technique for the determination of phosphorus content in coal and coal ash samples but proves challenging due to their comparatively weak fluorescence intensity. Fourier Transform Infrared spectroscopy (FTIR) emerges as a promising alternative that is simple, rapid, and cost-effective. However, research in this area has been limited. Until now, only a limited number of research studies have outlined the estimation of major elements in coal, predominantly relying on FTIR spectroscopy. In this article, we explore the potential of FTIR spectroscopy combined with machine learning models (piecewise linear regression-PLR, partial least square regression-PLSR, random forest-RF, and support vector regression-SVR) for quantifying the phosphorus content in coal and coal ash. For model development, the methodology employs the mid-infrared absorption peak intensity levels of phosphorus-specific functional groups and anionic groups of phosphate minerals at various working concentration ranges of coal and coal ash. This paper proposes a multi-model estimation (using PLR, PLSR, and RF) approach based on FTIR spectral data to detect and rapidly estimate low levels of phosphorus in coal and its ash (R2 of 0.836, RMSE of 0.735 ppm, RMSE (%) of 34.801, MBE of - 0.077 ppm, MBE (%) of 5.499, and MAE of 0.528 ppm in coal samples and R2 of 0.803, RMSE of 0.676 ppm, RMSE (%) of 38.050, MBE of - 0.118 ppm, MBE (%) of 4.501, and MAE of 0.474 ppm in coal ash samples). Our findings suggest that FTIR combined with the multi-model approach combining PLR, PLSR, and RF regression models is a reliable tool for rapid and near-real-time measurement of phosphorus in coal and coal ash and can be suitably modified to model phosphorus content in other natural samples such as soil, shale, etc.

Exploring relationship of soil PTE geochemical and "VIS-NIR spectroscopy" patterns near Cu-Mo mine (Armenia)

PTE contamination of soils remains one of the global environmental concerns. The ways of detecting and monitoring PTE concentrations in soils varies including traditional field sampling accompanied by sample preparation and chemical analysis and state of the art visible and near-infrared (Vis-NIR) spectroscopic approaches. Among the different Machine Learning (ML) to extract soil information from spectra and to explore the relationship between spectral reflectance data and soil PTE content PLSR method is a well-established one to construct a soil PTE estimation model. This study aimed to explore the relationship of soil PTE geochemical and VIS-NIR spectroscopy characteristics in agricultural soils near Cu-Mo mine area in Armenia. PLSR method is applied to identify the links between the spectra and agricultural soil Ti, V, Cr, Mn, Fe, Co, Ba, Pb, Zn, Cu, Sr, Zr and Mo contents to reveal the potential of VIS-NIR spectroscopy in ex-situ monitoring of Kajaran soils. The results show that different portions of VIS-NIR spectra are responsible for Ti (1100-1200 nm, 2350-2500 nm), V (350-500 nm, 700-750 nm, 1000-1100 nm, 1400-2500 nm), Cr (1300-1400 nm, 1900-2100 nm) and Ba (450-500 nm, 600-800 nm, 1050-1700 nm, 2000-2100 nm, 2350-2400 nm) estimations through PLSR correspondingly. However, among the studied PTEs Ti and V, which shows significant negative correlations in VIS-NIR spectra registered at around 400-600 nm and 850-1150 nm regions, are remarkable and promising with the PLSR estimation results using VIS-NIR spectra Ti (R²_Test = 0.74), V (R²_Test = 0.71). This study shows that VIS-NIR spectroscopy has a high potential for the estimation of at least several PTE in soils and PLSR modelis reliable for deriving information from there.

Vis-NIR Spectroscopy Combined with GAN Data Augmentation for Predicting Soil Nutrients in Degraded Alpine Meadows on the Qinghai-Tibet Plateau

Soil nutrients play vital roles in vegetation growth and are a key indicator of land degradation. Accurate, rapid, and non-destructive measurement of the soil nutrient content is important for ecological conservation, degradation monitoring, and precision farming. Currently, visible and near-infrared (Vis-NIR) spectroscopy allows for rapid and non-destructive monitoring of soil nutrients. However, the performance of Vis-NIR inversion models is extremely dependent on the number of samples. Limited samples may lead to low prediction accuracy of the models. Therefore, modeling and prediction based on a small sample size remain a challenge. This study proposes a method for the simultaneous augmentation of soil spectral and nutrient data (total nitrogen (TN), soil organic matter (SOM), total potassium oxide (TK₂O), and total phosphorus pentoxide (TP₂O₅)) using a generative adversarial network (GAN). The sample augmentation range and the level of accuracy improvement were also analyzed. First, 42 soil samples were collected from the pika disturbance area on the QTP. The collected soils were measured in the laboratory for Vis-NIR and TN, SOM, TK₂O, and TP₂O₅ data. A GAN was then used to augment the soil spectral and nutrient data simultaneously. Finally, the effect of adding different numbers of generative samples to the training set on the predictive performance of a convolutional neural network (CNN) was analyzed and compared with another data augmentation method (extended multiplicative signal augmentation, EMSA). The results showed that a GAN can generate data very similar to real data and with better diversity. A total of 15, 30, 60, 120, and 240 generative samples (GAN and EMSA) were randomly selected from 300 generative samples to be included in the real data to train the CNN model. The model performance first improved and then deteriorated, and the GAN was more effective than EMSA. Further shortening the interval for adding GAN data revealed that the optimal ranges were 30-40, 50-60, 30-35, and 25-35 for TK₂O, TN, TP₂O₅, and SOM, respectively, and the validation set accuracy was maximized in these ranges. Therefore, the above method can compensate to some extent for insufficient samples in the hyperspectral prediction of soil nutrients, and can quickly and accurately estimate the content of soil TK₂O, TN, TP₂O₅, and SOM.

Selection of the Effective Characteristic Spectra Based on the Chemical Structure and Its Application in Rapid Analysis of Ethanol Content in Gasoline

Near-infrared (NIR) spectroscopy analysis is one of the most rapid detection methods for determining ethanol content in gasoline. Wavelength selection is a key step in the multivariate calibration analysis of NIR spectroscopy. To improve detection accuracy of ethanol content in gasoline and provide a simpler interpretation, we established NIR spectroscopy, a rapid analysis method based on the effective characteristic spectra. Five effective characteristic spectral bands were used according to the molecular structure of ethanol, followed by the development of four modeling schemes. The four modeling schemes spectra, NIR full spectra, and variable importance projection (VIP) spectra were used for modeling and analysis. The model was established based on the effective characteristic spectra without the interference spectra of aromatic hydrocarbons, achieving the best model performance. In addition, the model was further evaluated by internal cross-validation and external validation. The model's evaluation parameters were as follows: the root mean square error of cross-validation (RMSECV) was 0.6193, the correlation coefficient of internal cross-validation (R CV 2) was 0.9995, the root mean square error of prediction (RMSEP) was 0.5572, and the correlation coefficient of external prediction validation (R P 2) was 0.9995. The effective characteristic spectra model had smaller RMSEP and RMSECV values, and larger R CV 2 and R P 2 values compared to the full spectra and VIP spectra models. In conclusion, the effective characteristic spectra model had the highest accuracy and could provide rapid analysis of the ethanol content in gasoline.

Rapid Detection of Different Types of Soil Nitrogen Using Near-Infrared Hyperspectral Imaging

Rapid and accurate determination of soil nitrogen supply capacity by detecting nitrogen content plays an important role in guiding agricultural production activities. In this study, near-infrared hyperspectral imaging (NIR-HSI) combined with two spectral preprocessing algorithms, two characteristic wavelength selection algorithms and two machine learning algorithms were applied to determine the content of soil nitrogen. Two types of soils (laterite and loess, collected in 2020) and three types of nitrogen fertilizers, namely, ammonium bicarbonate (ammonium nitrogen, NH4-N), sodium nitrate (nitrate nitrogen, NO3-N) and urea (urea nitrogen, urea-N), were studied. The NIR characteristic peaks of three types of nitrogen were assigned and regression models were established. By comparing the model average performance indexes after 100 runs, the best model suitable for the detection of nitrogen in different types was obtained. For NH4-N, R2p = 0.92, RMSEP = 0.77% and RPD = 3.63; for NO3-N, R2p = 0.92, RMSEP = 0.74% and RPD = 4.17; for urea-N, R2p = 0.96, RMSEP = 0.57% and RPD = 5.24. It can therefore be concluded that HSI spectroscopy combined with multivariate models is suitable for the high-precision detection of various soil N in soils. This study provided a research basis for the development of precision agriculture in the future.

Evaluation of Near-Infrared Reflectance and Transflectance Sensing System for Predicting Manure Nutrients

Livestock manure is widely applied onto agriculture soil to fertilize crops and increase soil fertility. However, it is difficult to provide real-time manure nutrient data based on traditional lab analyses during application. Manure sensing using near-infrared (NIR) spectroscopy is an innovative, rapid, and cost-effective technique for inline analysis of animal manure. This study investigated a NIR sensing system with reflectance and transflectance modes to predict N speciation in dairy cow manure using a spiking method. In this study, 20 dairy cow manure samples were collected and spiked to achieve four levels of ammoniacal nitrogen (NH4-N) and organic nitrogen (Org-N) concentrations that resulted in 100 samples in each spiking group. All samples were scanned and analyzed using a NIR system with reflectance and transflectance sensor configurations. NIR calibration models were developed using partial least square regression analysis for NH4-N, Org-N, total solid (TS), ash, and particle size (PS). Coefficient of determination (R2) and root mean square error (RMSE) were selected to evaluate the models. A transflectance probe with a 1 mm path length had the best performance for analyzing manure constituents among three path lengths. Reflectance mode improved the calibration accuracy for NH4-N and Org-N, whereas transflectance mode improved the model predictability for TS, ash, and PS. Reflectance provided good prediction for NH4-N (R2 = 0.83; RMSE = 0.65 mg mL−1) and approximate predictions for Org-N (R2 = 0.66; RMSE = 1.18 mg mL−1). Transflectance was excellent for TS predictions (R2 = 0.97), and provided good quantitative predictions for ash and approximate predictions for PS. The correlations between the accuracy of NH4-N and Org-N calibration models and other manure parameters were not observed indicating the predictions of N contents were not affected by TS, ash, and PS.

Evaluating Calibration and Spectral Variable Selection Methods for Predicting Three Soil Nutrients Using Vis-NIR Spectroscopy

Soil nutrients, including soil available potassium (SAK), soil available phosphorous (SAP), and soil organic matter (SOM), play an important role in farmland soil productivity, food security, and agricultural management. Spectroscopic analysis has proven to be a rapid, nondestructive, and effective technique for predicting soil properties in general and potassium, phosphorous, and organic matter in particular. However, the successful estimation of soil nutrient content by visible and near-infrared (Vis-NIR) reflectance spectroscopy depends on proper calibration methods (including preprocessing transformation methods and multivariate methods for regression analysis) and the selection of appropriate variable selection techniques. In this study, raw spectrum and 13 preprocessing transformations combined with 2 variable selection methods (competitive adaptive reweighted sampling (CARS) and the successive projections algorithm (SPA)) and 2 regression algorithms (support vector machine (SVM) and partial least squares regression (PLSR)), for a total of 56 calibration methods, were investigated for modeling and predicting the above three soil nutrients using hyperspectral Vis-NIR data (400–2450 nm). The results show that first-order derivatives based on logarithmic and inverse transformations (FD-LGRs) can provide better predictions of soil available potassium and phosphorous, and the best form of soil organic matter transformation is SG+MSC. CARS was superior to the SPA in selecting effective variables, and the PLSR model outperformed the SVM models. The best estimation accuracies (R2, RMSE) for soil available potassium, phosphorous, and organic matter were 0.7532, 32.3090 mg/kg; 0.7440, 6.6910 mg/kg; and 0.9009, 3.2103 g/kg, respectively, and their corresponding calibration methods were (FD-LGR)/SPA/PLSR, (FD-LGR)/SPA/PLSR, and SG+MSC/CARS/SVM, respectively. Overall, for the prediction of the soil nutrient content, organic matter was superior to available phosphorous, followed by available potassium. It was concluded that the application of hyperspectral images (Vis-NIR data) was an efficient method for mapping and monitoring soil nutrients at the regional scale, thus contributing to the development of precision agriculture.

Using a One-Dimensional Convolutional Neural Network on Visible and Near-Infrared Spectroscopy to Improve Soil Phosphorus Prediction in Madagascar

As a proximal soil sensing technique, laboratory visible and near-infrared (Vis-NIR) spectroscopy is a promising tool for the quantitative estimation of soil properties. However, there remain challenges for predicting soil phosphorus (P) content and availability, which requires a reliable model applicable for different land-use systems to upscale. Recently, a one-dimensional convolutional neural network (1D-CNN) corresponding to the spectral information of soil was developed to considerably improve the accuracy of soil property predictions. The present study investigated the predictive ability of a 1D-CNN model to estimate soil available P (oxalate-extractable P; Pox) content in soils by comparing it with partial least squares (PLS) and random forest (RF) regressions using soil samples (n = 318) collected from natural (forest and non-forest) and cultivated (upland and flooded rice fields) systems in Madagascar. Overall, the 1D-CNN model showed the best predictive accuracy (R2 = 0.878) with a highly accurate prediction ability (ratio of performance to the interquartile range = 2.492). Compared to the PLS model, the RF and 1D-CNN models indicated 4.37% and 23.77% relative improvement in root mean squared error values, respectively. Based on a sensitivity analysis, the important wavebands for predicting soil Pox were associated with iron (Fe) oxide, organic matter (OM), and water absorption, which were previously known wavelength regions for estimating P in soil. These results suggest that 1D-CNN corresponding spectral signatures can be expected to significantly improve the predictive ability for estimating soil available P (Pox) from Vis-NIR spectral data. Rapid and accurate estimation of available P content in soils using our results can be expected to contribute to effective fertilizer management in agriculture and the sustainable management of ecosystems. However, the 1D-CNN model will require a large dataset to extend its applicability to other regions of Madagascar. Thus, further updates should be tested in future studies using larger datasets from a wide range of ecosystems in the tropics.

Evaluation of Near Infrared Spectroscopy (NIRS) for Estimating Soil Organic Matter and Phosphorus in Mediterranean Montado Ecosystem

The Montado is an agro-silvo-pastoral ecosystem characteristic of the Mediterranean region. Pasture productivity and, consequently, the possibilities for intensifying livestock production depend on soil fertility. Soil organic matter (SOM) and phosphorus (P2O5) are two indicators of the evolution of soil fertility in this ecosystem. However, their conventional analytical determination by reference laboratory methods is costly, time consuming, and laborious and, thus, does not meet the needs of current production systems. The aim of this study was to evaluate an alternative approach to estimate SOM and soil P2O5 based on near infrared spectroscopy (NIRS) combined with multivariate data analysis. For this purpose, 242 topsoil samples were collected in 2019 in eleven fields. These samples were subjected to reference laboratory analysis and NIRS analysis. For NIRS, 165 samples were used during the calibration phase and 77 samples were used during the external validation phase. The results of this study showed significant correlation between NIRS calibration models and reference methods for quantification of these soil parameters. The coefficient of determination (R2, 0.85 for SOM and 0.76 for P2O5) and the residual predictive deviation (RPD, 2.7 for SOM and 2.2 for P2O5) obtained in external validation indicated the potential of NIRS to estimate SOM and P2O5, which can facilitate farm managers’ decision making in terms of dynamic management of animal grazing and differential fertilizer application.

An Evaluation of Different NIR-Spectral Pre-Treatments to Derive the Soil Parameters C and N of a Humus-Clay-Rich Soil

Near-infrared reflectance spectroscopy (NIRS) was successfully used in this study to measure soil properties, mainly C and N, requiring spectral pre-treatments. Calculations in this evaluation were carried out using multivariate statistical procedures with preceding pre-treatment procedures of the spectral data. Such transformations could remove noise, highlight features, and extract essential wavelengths for quantitative predictions. This frequently significantly improved the predictions. Since selecting the appropriate transformation was not straightforward due to the large numbers of available methods, more comprehensive insight into choosing appropriate and optimized pre-treatments was required. Therefore, the objectives of this study were (i) to compare various pre-processing transformations of spectral data to determine their suitability for modeling soil C and N using NIR spectra (55 pre-treatment procedures were tested), and (ii) to determine which wavelengths were most important for the prediction of C and N. The investigations were carried out on an arable field in South Germany with a soil type of Calcaric Fluvic Relictigleyic Phaeozem (Epigeoabruptic and Pantoclayic), created in the flooding area of the Isar River. The best fit and highest model accuracy for the C (Ct, Corg, and Ccarb) and N models in the calibration and validation modes were achieved using derivations with Savitzky–Golay (SG). This enabled us to calculate the Ct, Corg, and N with an R² higher than 0.98/0.86 and an ratio of performance to the interquartile range (RPIQ) higher than 10.9/4.1 (calibration/validation).

Exploring the Potential of HySpex Hyperspectral Imagery for Extraction of Copper Content

Detritus geochemical information has been proven through research to be an effective prospecting method in mineral exploration. However, the traditional detritus metal content monitoring methods based on field sampling and laboratory chemical analysis are time-consuming and may not meet the requirements of large-scale metal content monitoring. In this study, we obtained 95 detritus samples and seven HySpex hyperspectral imagery scenes with a spatial resolution of 1 m from Karatag Gobi area, Xinjiang, China, and used partial least squares and wavebands selection methods to explore the usefulness of super-low-altitude HySpex hyperspectral images in estimating detritus feasibility and effectiveness of Cu element content. The results show that: (1) among all the inversion models of transformed spectra, power-logarithm transformation spectrum was the optimal prediction model (coefficient of determination(R²) = 0.586, mean absolute error(MAE) = 21.405); (2) compared to the genetic algorithm (GA) and continuous projection algorithm (SPA), the competitive weighted resampling algorithm (CARS) was the optimal feature band-screening method. The R² of the inversion model was constructed based on the characteristic bands selected by CARS reaching 0.734, which was higher than that of GA (0.519) and SPA (0.691), and the MAE (19.926) was the lowest. Only 20 bands were used in the model construction, which is lower than that of GA (105) and SPA (42); (3) The power-logarithm transforms, and CARS combined with the model of HySpex hyperspectral images and the Cu content distribution in the study area were obtained, consistent with the actual survey results on the ground. Our results prove that the method incorporating the HySpex hyperspectral data to invert copper content in detritus is feasible and effective, and provides data and a reference method for obtaining geochemical element distribution in a large area and for reducing key areas of geological exploration in the future.

Combining Laser-Induced Breakdown Spectroscopy (LIBS) and Visible Near-Infrared Spectroscopy (Vis-NIRS) for Soil Phosphorus Determination

Conventional wet chemical methods for the determination of soil phosphorus (P) pools, relevant for environmental and agronomic purposes, are labor-intensive. Therefore, alternative techniques are needed, and a combination of the spectroscopic techniques—in this case, laser-induced breakdown spectroscopy (LIBS)—and visible near-infrared spectroscopy (vis-NIRS) could be relevant. We aimed at exploring LIBS, vis-NIRS and their combination for soil P estimation. We analyzed 147 Danish agricultural soils with LIBS and vis-NIRS. As reference measurements, we analyzed water-extractable P (Pwater), Olsen P (Polsen), oxalate-extractable P (Pox) and total P (TP) by conventional wet chemical protocols, as proxies for respectively leachable, plant-available, adsorbed inorganic P, and TP in soil. Partial least squares regression (PLSR) models combined with interval partial least squares (iPLS) and competitive adaptive reweighted sampling (CARS) variable selection methods were tested, and the relevant wavelengths for soil P determination were identified. LIBS exhibited better results compared to vis-NIRS for all P models, except for Pwater, for which results were comparable. Model performance for both the LIBS and vis-NIRS techniques as well as the combined LIBS-vis-NIR approach was significantly improved when variable selection was applied. CARS performed better than iPLS in almost all cases. Combined LIBS and vis-NIRS models with variable selection showed the best results for all four P pools, except for Pox where the results were comparable to using the LIBS model with CARS. Merging LIBS and vis-NIRS with variable selection showed potential for improving soil P determinations, but larger and independent validation datasets should be tested in future studies.

Hyperspectral Estimation of Soil Organic Matter Content using Different Spectral Preprocessing Techniques and PLSR Method

Soil organic matter (SOM) is the main source of soil nutrients, which are essential for the growth and development of agricultural crops. Hyperspectral remote sensing is one of the most efficient ways of estimating the SOM content. Visible, near infrared, and mid-infrared reflectance spectroscopy, combined with the partial least squares regression (PLSR) method is considered to be an effective way of determining soil properties. In this study, we used 54 different spectral pretreatments to preprocess soil spectral data. These spectral pretreatments were composed of three denoising methods, six data transformations, and three dimensionality reduction methods. The three denoising methods included no denoising (ND), Savitzky–Golay denoising (SGD), and wavelet packet denoising (WPD). The six data transformations included original spectral data, R; reciprocal, 1/R; logarithmic, log(R); reciprocal logarithmic, log(1/R); first derivative, R’; and first derivative of reciprocal, (1/R)’. The three dimensionality reduction methods included no dimensionality reduction (NDR), sensitive waveband dimensionality reduction (SWDR), and principal component analysis (PCA) dimensionality reduction (PCADR). The processed spectra were then employed to construct PLSR models for predicting the SOM content. The main results were as follows—(1) the wavelet packet denoising (WPD)-R’ and WPD-(1/R)’ data showed stronger correlations with the SOM content. Furthermore, these methods could effectively limit the correlation between the adjacent bands and, thus, prevent “overfitting”. (2) Of the 54 pretreatments investigated, WPD-(1/R)’-PCADR yielded the model with the highest accuracy and stability. (3) For the same denoising method and spectral transformation data, the accuracy of the SOM content estimation model based on SWDR was higher than that of the model based on NDR. Furthermore, the accuracy in the case of PCADR was higher than that for SWDR. (4) Dimensionality reduction was effective in preventing data overfitting. (5) The quality of the spectral data could be improved and the accuracy of the SOM content estimation model could be enhanced effectively, by using some appropriate preprocessing methods (one combining WPD and PCADR in this study).

Exploring the Influence of Spatial Resolution on the Digital Mapping of Soil Organic Carbon by Airborne Hyperspectral VNIR Imaging

Accurate digital mapping of soil organic carbon (SOC) is important in understanding the global carbon cycle and its implications in mitigating climate change. Visible and near-infrared hyperspectral imaging technology provides an alternative for mapping SOC efficiently and accurately, especially at regional and global scales. However, there is a lack of understanding of the impacts of spatial resolution of hyperspectral images and spatial autocorrelation of spectral information on the accuracy of SOC retrievals. In this study, the hyperspectral images (380–1700 nm) with a spatial resolution of 1 m were acquired by Headwall Micro-Hyperspec airborne sensors. Then, hyperspectral images were resampled into three different spatial resolutions of 10 m, 30 m, and 60 m by near neighbor (NN), bilinear interpolation (BI), and cubic convolution (CC) resampling methods. The geographically weighted regression (GWR) model was used to explore the role of spatial autocorrelation in predicting SOC contrast with the partial least squares regression (PLSR) model. Results showed that (1) the hyperspectral images can be used to predict SOC and the spatial autocorrelation can improve the prediction accuracy, as the ratio of performance to interquartile range (RPIQ) values of PLSR and GWR were 1.957 and 2.003; (2) The SOC prediction accuracy decreased with the degradation of spatial resolution, and the RPIQ values of PLSR were from 1.957 to 1.134, and of GWR were from 2.003 to 1.136; (3) Three resampling methods had a much weaker influence than spatial resolution on SOC predictions because the differences of RPIQ values of NN, BI, and CC resampling methods were 0.146, 0.175, and 0.025 in the spatial resolutions of 10 m, 30 m, and 60 m, respectively; (4) Finally, the Global Moran’s I and the Anselin Local Moran’s I proved the existence of the spatial autocorrelation in SOC maps. We hope that this study can offer valuable information for digital soil mapping by satellite hyperspectral images in the near future.