Detecting and Segregating Black Tip‐Damaged Wheat Kernels Using Visible and Near‐Infrared Spectroscopy

Detection of individual wheat kernels with black tip symptom (BTS) and black tip damage (BTD) was demonstrated with near‐infrared reflectance spectroscopy (NIRS) and silicon light‐emitting‐diode (LED) based instruments. The two instruments tested, a single‐kernel NIRS instrument (SKNIRS) and a silicon LED‐based single‐kernel high‐speed sorter (SiLED‐SKS) were both developed by the Stored Product Insect and Engineering Research Unit, Center for Grain and Animal Health Research, USDA Agricultural Research Service. BTD was classified into four levels for the study ranging from sound, symptomatic (BTS) at two levels, and damaged (BTD). Discriminant analysis models for the SKNIRS instrument could distinguish sound undamaged kernels well, correctly classifying kernels 80% of the time. Damaged kernels were classified with 67% accuracy and symptomatic kernels at about 44%. Higher classification accuracy (81–87%) was obtained by creating only two groupings: 1) combined sound and lightly symptomatic kernels and 2) combined heavily symptomatic and damaged kernels. A linear regression model was developed from the SiLED‐SKS sorted fractions to predict the percentage of combined BTS and BTD kernels in a sample. The model had an R² of 0.64 and a standard error of prediction of 7.4%, showing it had some measurement ability for BTS and BTD. The SiLED‐SKS correctly classified and sorted out 90% of BTD and 66% of BTS for all 28 samples after three passes through the sorter. These instruments can serve as important tools for plant breeders and grading facilities of the wheat industry that require timely and objective determination and sorting of different levels of black tip present in wheat samples.     

Selecting and Sorting Waxy Wheat Kernels Using Near‐Infrared Spectroscopy

An automated single kernel near‐infrared (NIR) sorting system was used to separate single wheat (Triticum aestivum L.) kernels with amylose‐free (waxy) starch from reduced‐amylose (partial waxy) or wild‐type wheat kernels. Waxy kernels of hexaploid wheat are null for the granule‐bound starch synthase alleles at all three Wx gene loci; partial waxy kernels have at least one null and one functional allele. Wild‐type kernels have three functional alleles. Our results demonstrate that automated single kernel NIR technology can be used to select waxy kernels from segregating breeding lines or to purify advanced breeding lines for the low‐amylose kernel trait. Calibrations based on either amylose content or the waxy trait performed similarly. Also, a calibration developed using the amylose content of waxy, partial waxy, and wild‐type durum (T. turgidum L. var durum) wheat enabled adequate sorting for hard red winter and hard red spring wheat with no modifications. Regression coefficients indicated that absorption by starch in the NIR region contributed to the classification models. Single kernel NIR technology offers significant benefits to breeding programs that are developing wheat with amylose‐free starches.     

Differentiating Vitreous and Nonvitreous Durum Wheat Kernels by Using Near‐Infrared Spectroscopy

The vitreousnss of durum wheat is used by the wheat industry as an indicator of milling and cooking quality. The current visual method of determining vitreousness is subjective, and classification results between inspectors and countries vary widely. Thus, the use of near‐infrared (NIR) spectroscopy to objectively classify vitreous and nonvitreous single kernels was investigated. Results showed that classification of obviously vitreous or nonvitreous kernels by the NIR procedure agreed almost perfectly with inspector classifications. However, when difficult‐to‐classify vitreous and nonvitreous kernels were included in the analysis, the NIR procedure agreed with inspectors on only 75% of kernels. While the classification of difficult kernels by NIR spectroscopy did not match well with inspector classifications, this NIR procedure quantifies vitreousness and thus may provide an objective classification means that could reduce inspector‐to‐inspector variability. Classifications appear to be due, at least in part, to scattering effects and to starch and protein differences between vitreous and nonvitreous kernels.     

Detection of Scab‐Damaged Hard Red Spring Wheat Kernels by Near‐Infrared Reflectance

Scab (Fusarium head blight) is a fungal disease that has become increasingly prevalent in North American wheat during the past 15 years. It is of concern to growers, processors, and the consumers because of depressed yields, poor flour quality, and the potential for elevated concentrations of the mycotoxin, deoxynivalenol (DON). Both wheat breeder and wheat inspector must currently deal with the assessment of scab in harvested wheat by manual human inspection. The study described herein examined the accuracy of a semi‐automated wheat scab inspection system that is based on near‐infrared (NIR) reflectance (1,000–1,700 nm) of individual kernels. Using statistical classification techniques such as linear discriminant analysis and nonparametric (k‐nearest‐neighbor) classification, upper limits of accuracy for NIR‐based classification schemes of ≈88% (cross‐validation) and 97% (test) were determined. An exhaustive search of the most suitable wavelength pairs for the spectral difference, [log(1/R)_λ1 ‐ log(1/R)_λ2], revealed that the slope of the low‐wavelength side of a broad carbohydrate absorption band (centered at ≈1,200 nm) was very effective at discriminating between healthy and scab‐damaged kernels with test set accuracies of 95%. The achieved accuracy levels demonstrate the potential for the use of NIR spectroscopy in commercial sorting and inspection operations for wheat scab.     

Detection of Sprouted and Midge‐Damaged Wheat Kernels Using Near‐Infrared Hyperspectral Imaging

Sprout damage which results in poor breadmaking quality due to enzymatic activity of α‐amylase is one of the important grading factors of wheat in Canada. Potential of near‐infrared (NIR) hyperspectral imaging was investigated to detect sprouting of wheat kernels. Artificially sprouted, midge‐damaged, and healthy wheat kernels were scanned using NIR hyperspectral imaging system in the range of 1000–1600 nm at 60 evenly distributed wavelengths. Multivariate image analysis (MVI) technique based on principal components analysis (PCA) was applied to reduce the dimensionality of the hyperspectral data. Three wavelengths 1101.7, 1132.2, and 1305.1 nm were identified as significant and used in analysis. Statistical discriminant classifiers (linear, quadratic, and Mahalanobis) were used to classify sprouted, midge‐damaged, and healthy wheat kernels. The discriminant classifiers gave maximum accuracy of 98.3 and 100% for classifying healthy and damaged kernels, respectively.     

Near‐Infrared Hyperspectral Imaging of Fusarium‐Damaged Oats (Avena sativa L.)

The feasibility of hyperspectral imaging (HSI) to detect deoxynivalenol (DON) content and Fusarium damage in single oat kernels was investigated. Hyperspectral images of oat kernels from a Fusarium‐inoculated nursery were used after visual classification as asymptomatic, mildly damaged, and severely damaged. Uninoculated kernels were included as controls. The average spectrum from each kernel was paired with the reference DON value for the same kernel, and a calibration model was fitted by partial least squares regression (PLSR). To correct for the skewed distribution of DON values and avoid nonlinearities in the model, the DON values were transformed as DON* = [log(DON)]³. The model was optimized by cross‐validation, and its prediction performance was validated by predicting DON* values for a separate set of validation kernels. The PLSR model and linear discriminant analysis classification were further used on single‐pixel spectra to investigate the spatial distribution of infection in the kernels. There were clear differences between the kernel classes. The first component separated the uninoculated and asymptomatic from the severely damaged kernels. Infected kernels showed higher intensities at 1,925, 2,070, and 2,140 nm, whereas noninfected kernels were dominated by signals at 1,400, 1,626, and 1,850 nm. The DON* values of the validation kernels were estimated by using their average spectra, and the correlation (R) between predicted and measured DON* was 0.8. Our results show that HSI has great potential in detecting Fusarium damage and predicting DON in oats, but it needs more work to develop a model for routine application.     

Determining Vitreous Subclasses of Hard Red Spring Wheat Using Visible/Near‐Infrared Spectroscopy

The percentage of dark hard vitreous (DHV) kernels in hard red spring wheat is an important grading factor that is associated with protein content, kernel hardness, milling properties, and baking quality. The current visual method of determining DHV and non‐DHV (NDHV) wheat kernels is time‐consuming, tedious, and subject to large errors. The objective of this research was to classify DHV and NDHV wheat kernels, including kernels that were checked, cracked, sprouted, or bleached using visible/near‐infrared (Vis/NIR) spectroscopy. Spectra from single DHV and NDHV kernels were collected using a diode‐array NIR spectrometer. The dorsal and crease sides of the kernels were viewed. Three wavelength regions, 500–750 nm, 750–1,700 nm, and 500–1700 nm were compared. Spectra were analyzed by using partial least squares (PLS) regression. Results suggest that the major contributors to classifying DHV and NDHV kernels are light scattering, protein content, kernel hardness, starch content, and kernel color effects on the absorption spectrum. Bleached kernels were the most difficult to classify because of high lightness values. The sample set with bleached kernels yielded lower classification accuracies of 91.1–97.1% compared with 97.5–100% for the sample set without bleached kernels. More than 75% of misclassified kernels were bleached. For sample sets without bleached kernels, the classification models that included the dorsal side gave the highest classification accuracies (99.6–100%) for the testing sample set. Wavelengths in both the Vis/NIR regions or the NIR region alone yielded better classification accuracies than those in the visible region only.     

Discriminating Oat and Groat Kernels from Other Grains Using Near‐Infrared Spectroscopy

Oats and groats can be discriminated from other grains such as barley, wheat, rye, and triticale (nonoats) with near‐infrared spectroscopy. The two instruments tested herein were the manual version of the United States Department of Agriculture–Agricultural Research Service single‐kernel near‐infrared (SKNIR) instrument and the automated QualySense QSorter Explorer high‐speed sorter, both used in similar near‐infrared spectral ranges. Three linear discriminate self‐prediction models were developed: 1) oats versus groats + nonoats, 2) oats + groats versus nonoats, and 3) groats versus nonoats. For all three models, the SKNIR instrument showed high correct classification of oats or groats (94.5–100%), which was similar to results of the QSorter Explorer at 95.0–99.4%. The amount of nonoats that were misclassified as oats or groats was low for both instruments at 0–0.2% for the SKNIR instrument and 0.8–3.7% for the QSorter Explorer. Linear discriminate models from independent prediction and validation sets yielded classification accuracies of 91.6–99.3% (SKNIR) and 90.5–97.8% (QSorter Explorer). Small differences in classification accuracy were attributed to processing speeds between the two instruments: 3 kernels/s for the SKNIR instrument and 35 kernels/s for the QSorter Explorer. This indicated that both instruments are useful for quantifying grain sample compositions of oat and groat samples and that both could be useful tools for meeting consumer demand for gluten‐free or low‐gluten products. Discrimination between grains will help producers and manufacturers meet various regulatory requirements. Examples include requirements such as those from the U.S. Food and Drug Administration and the Commission of European Communities, in which gluten‐free oats or other products can only be labeled as nongluten if they contain gluten at less than 20 ppm, the established safe consumption limit for people with celiac disease. The QSorter Explorer is currently being used to meet these requirements.     

Predicting Wheat Quality Characteristics and Functionality Using Near‐Infrared Spectroscopy

The accuracy of using near‐infrared spectroscopy (NIRS) for predicting 186 grain, milling, flour, dough, and breadmaking quality parameters of 100 hard red winter (HRW) and 98 hard red spring (HRS) wheat and flour samples was evaluated. NIRS shows the potential for predicting protein content, moisture content, and flour color b* values with accuracies suitable for process control (R² > 0.97). Many other parameters were predicted with accuracies suitable for rough screening including test weight, average single kernel diameter and moisture content, SDS sedimentation volume, color a* values, total gluten content, mixograph, farinograph, and alveograph parameters, loaf volume, specific loaf volume, baking water absorption and mix time, gliadin and glutenin content, flour particle size, and the percentage of dark hard and vitreous kernels. Similar results were seen when analyzing data from either HRW or HRS wheat, and when predicting quality using spectra from either grain or flour. However, many attributes were correlated to protein content and this relationship influenced classification accuracies. When the influence of protein content was removed from the analyses, the only factors that could be predicted by NIRS with R² > 0.70 were moisture content, test weight, flour color, free lipids, flour particle size, and the percentage of dark hard and vitreous kernels. Thus, NIRS can be used to predict many grain quality and functionality traits, but mainly because of the high correlations of these traits to protein content.     

Protein Content of Bulk Wheat from Near‐Infrared Reflectance of Individual Kernels

Protein content of wheat by near‐infrared (NIR) reflectance of bulk samples is routinely practiced. New instrumentation that permits automated NIR analysis of individual kernels is now available, with the potential for rapid NIR‐based determinations of color, disease, and protein content, all on a single kernel (sk) basis. In the event that the protein content of the bulk sample is needed rather than that of the individual kernels, the present study examines the feasibility of estimating bulk sample protein from sk spectral readings. On the basis of 318 wheat samples of 10 kernels per sample, encompassing five U.S. wheat classes, the study demonstrates that with as few as 300 kernels bulk sample protein content may be estimated by sk NIR reflectance spectra at an accuracy equivalent to conventional bulk kernel NIR instrumentation.     

Hardness Measurement of Bulk Wheat by Single‐Kernel Visible and Near‐Infrared Reflectance Spectroscopy

Reflectance spectra (400 to 1700 nm) of single wheat kernels collected using the Single Kernel Characterization System (SKCS) 4170 were analyzed for wheat grain hardness using partial least squares (PLS) regression. The wavelengths (650 to 700, 1100, 1200, 1380, 1450, and 1670 nm) that contributed most to the ability of the model to predict hardness were related to protein, starch, and color differences. Slightly better prediction results were observed when the 550–1690 nm region was used compared with 950–1690 nm region across all sample sizes. For the 30‐kernel mass‐averaged model, the hardness prediction for 550–1690 nm spectra resulted in a coefficient of determination (R²) = 0.91, standard error of cross validation (SECV) = 7.70, and relative predictive determinant (RPD) = 3.3, while the 950–1690 nm had R² = 0.88, SECV = 8.67, and RPD = 2.9. Average hardness of hard and soft wheat validation samples based on mass‐averaged spectra of 30 kernels was predicted and compared with the SKCS 4100 reference method (R² = 0.88). Compared with the reference SKCS hardness classification, the 30‐kernel (550–1690 nm) prediction model correctly differentiated (97%) between hard and soft wheat. Monte Carlo simulation technique coupled with the SKCS 4100 hardness classification logic was used for classifying mixed wheat samples. Compared with the reference, the prediction model correctly classified mixed samples with 72–100% accuracy. Results confirmed the potential of using visible and near‐infrared reflectance spectroscopy of whole single kernels of wheat as a rapid and nondestructive measurement of bulk wheat grain hardness.     

Near‐Infrared Spectroscopic Method for Identification of Fusarium Head Blight Damage and Prediction of Deoxynivalenol in Single Wheat Kernels

Fusarium Head Blight (FHB), or scab, can result in significant crop yield losses and contaminated grain in wheat (Triticum aestivum L.). Growing less susceptible cultivars is one of the most effective methods for managing FHB and for reducing deoxynivalenol (DON) levels in grain, but breeding programs lack a rapid and objective method for identifying the fungi and toxins. It is important to estimate proportions of sound kernels and Fusarium‐damaged kernels (FDK) in grain and to estimate DON levels of FDK to objectively assess the resistance of a cultivar. An automated single kernel near‐infrared (SKNIR) spectroscopic method for identification of FDK and for estimating DON levels was evaluated. The SKNIR system classified visually sound and FDK with an accuracy of 98.8 and 99.9%, respectively. The sound fraction had no or very little accumulation of DON. The FDK fraction was sorted into fractions with high or low DON content. The kernels identified as FDK by the SKNIR system had better correlation with other FHB assessment indices such as FHB severity, FHB incidence and kernels/g than visual FDK%. This technique can be successfully employed to nondestructively sort kernels with Fusarium damage and to estimate DON levels of those kernels. Single kernels could be predicted as having low (<60 ppm) or high (>60 ppm) DON with ≈96% accuracy. Single kernel DON levels of the high DON kernels could be estimated with R² = 0.87 and standard error of prediction (SEP) of 60.8 ppm. Because the method is nondestructive, seeds may be saved for generation advancement. The automated method is rapid (1 kernel/sec) and sorting grains into several fractions depending on DON levels will provide breeders with more information than techniques that deliver average DON levels from bulk seed samples.     

Development and Evaluation of a Near‐Infrared Instrument for Single‐Seed Compositional Measurement of Wheat Kernels

A single‐kernel, near‐infrared reflectance instrument was designed, built, and tested for its ability to measure composition and traits in wheat kernels. The major objective of the work was targeted at improving an existing design concept of an instrument used for larger seeds such as soybeans and corn but in this case designed for small seeds. Increases in throughput were sought by using a vacuum to convey seeds without compromising measurement accuracy. Instrument performance was evaluated by examining measurement accuracy of wheat kernel moisture, protein content, and kernel mass. Spectral measurements were obtained on individual wheat kernels as they were conveyed by air through an illuminated tube. Partial least squares (PLS) prediction models for these constituents were then developed and evaluated. PLS single‐kernel moisture predictions had a root mean square error of prediction (RMSEP) around 0.5% MC wet basis; protein prediction models had an RMSEP near 0.70%. Prediction of mass was not as good but still provided a reasonable estimate of single‐kernel mass, with RMSEP values of 2.8–4 mg. Data showed that kernel mass and protein content were not correlated, in contrast to some previous research. Overall, results showed the instrument performed comparably to other single‐seed instruments or methods based on accuracy but with an increased throughput at a rate of at least 4 seeds/s.     

High‐Throughput Near‐Infrared Reflectance Spectroscopy for Predicting Quantitative and Qualitative Composition Phenotypes of Individual Maize Kernels

Near‐infrared reflectance (NIR) spectroscopy can be used for fast and reliable prediction of organic compounds in complex biological samples. We used a recently developed NIR spectroscopy instrument to predict starch, protein, oil, and weight of individual maize (Zea mays) seeds. The starch, protein, and oil calibrations have reliability equal or better to bulk grain NIR analyzers. We also show that the instrument can differentiate quantitative and qualitative seed composition mutants from normal siblings without a specific calibration for the constituent affected. The analyzer does not require a specific kernel orientation to predict composition or to differentiate mutants. The instrument collects a seed weight and a spectrum in 4–6 sec and can collect NIR data alone at a 20‐fold faster rate. The spectra are acquired while the kernel falls through a glass tube illuminated with broad spectrum light. These results show significant improvements over prior single‐kernel NIR systems, making this instrument a practical tool to collect quantitative seed phenotypes at high throughput. This technology has multiple applications for studying the genetic and physiological influences on seed traits.     

Authentication of Rice Using Near‐Infrared Reflectance Spectroscopy

The authentication of rice (Korean domestic rice vs. foreign rice) has been attempted using near‐infrared spectroscopy (NIRS). Two sample sets (n₁ = 280 and n₂ = 200) were used to obtain calibration equations and the spectral regions used for this study were 500–600 nm, 700–900nm, and 980–2,498 nm. Modified partial least square (MPLS) regression was used to develop the prediction model. The standard error of cross validation (SECV) and the r² were 0.165 and 0.91 respectively for 1st calibration set and 0.165 and 0.93 for 2nd calibration set respectively. The results of the independent validation (n₃ = 80) showed that all of 80 samples were identified correctly. Even though authentication of rice was performed successfully using NIRS, the calibration statistics in this study showed that further effort is needed for implementation of NIRS for authentication of rice for industry purposes.     

Wavelength Selection for Classifying Paddy Rice by Near‐Infrared Spectroscopy

Using five paddy rice cultivars grown in Central, Eastern, and Southern Taiwan and harvested in the summers of 1997, 1998, and 1999, eight calibrated models were established by discriminant analysis and back‐propagation neural network with four wavelength selection methods. Randomly adding 80 samples of the 2000 year crop in the three‐crop‐year calibrated models for annual recalibration, eight models were used to classify paddy rice harvested in the summer of 2000. With 351 wavelengths of models 1 and 2, the average classification rates by discriminant analysis and backpropagation neural network were 98.1 and 92.5%, respectively. With 69 wavelengths selected by stepwise discrimination of models 3 and 4, the average classification rates by discriminant analysis and backpropagation neural network were 98.5 and 85.5%, respectively. With 69 wavelengths selected by correlation matrix of models 5 and 6, the average classification rates by discriminant analysis and neural network were 72.0 and 72.2%, respectively. With 69 wavelengths from loading values in the first and second principal components of models 7 and 8, the average classification rates by discriminant analysis and neural network were 69.1 and 60.6%, respectively. Model 3 would be recommended for classifying paddy rice to set trading prices because of its highest classification rate (98.5%).     

Comparison of Near‐Infrared Reflectance Spectroscopy and Texture Analyzer for Measuring Wheat Bread Changes in Storage

Bread staling affects bread texture properties and is one of the most common problems in bread storage. Bread firmness, as measured in compression mode by a texture analyzer (TA) has been commonly used to measure bread staling. This study investigated the potential of visible and near‐infrared reflectance spectroscopy (NIRS) to detect bread changes during storage by comparing NIRS results with those obtained by TA. Twenty‐five loaves of commercial wheat white pan bread from one batch were studied over five days. NIRS and TA measurements were made on the same slice at approximately the same time. The experiment was repeated five times using the same kind of commercial samples from five different batches. NIRS measurements of slices, loaf averages, and daily averages were compared with TA measurements. NIRS spectra had a high correlation to TA firmness. NIRS measurements correlated better with the actual storage time and had smaller standard deviations than the TA measurements. The batch differences had less effect on NIRS measurements than on the TA measurements. The results indicate that NIRS could follow bread changes during storage more accurately than the TA. NIRS is probably based on both physical and chemical changes during bread staling, unlike the TA method that only measures bread firmness, which is only one aspect of the staling phenomenon.     

Determination of Rapid Visco Analyser Parameters in Rice by Near‐Infrared Spectroscopy

The objective of these studies was to find alternative Rapid Visco Analyser (RVA) viscoelastic parameters that are predictable by near‐infrared spectroscopy (NIRS). Currently, RVA instruments are widely used in assessing cooking and processing characteristics in rice. The ability to predict RVA parameters by NIRS would be useful in rapidly determining rice pasting qualities, but NIRS does not correlate with the traditional parameters (peak viscosity, final viscosity, breakdown, consistency, and setback). Alternative RVA parameters were sought by collecting RVA and NIRS data for a total of 86 short, medium, and long grain rice cultivars. The amylose contents were 0.41–24.90% (w/w) and protein concentrations were 8.47–11.35% (w/w). Partial least squares (PLS) regression models generated for the entire NIR spectrum against the RVA curve showed viscosity at 212–228 sec (80°C ± 1) varied linearly with NIR spectra (1,100 to ‐2,500 nm). Regression coefficient values were R = 0.961 for 212 sec and R = 0.903 for 228 sec. The PLS correlation coefficient for the prediction of amylose at 212–228 sec decreases along with the NIRS correlation to the same time frame. An opposite trend was observed for the correlation with protein at 212–228 sec. This comparison suggests the importance of amylose and protein in water absorption during this time frame.     

Quantitative Analysis of Fat Content in Rice by Near‐Infrared Spectroscopy Technique

Fat content in rice is one of the most important nutritional quality properties. But the chemical analysis of fat content is time‐consuming and costly and could result in poor reproduction between replicates. Near‐infrared spectroscopy (NIRS) can solve those problems by providing a rapid, nondestructive, and quantitative analysis. Based on the NIRS technique and partial least squares (PLS) algorithm, four calibration models were established to quantitatively analyze fat content in brown rice grain and flour and milled rice grain and flour with 248 representative samples. The determination coefficients (R²) of these calibration models were 0.79, 0.84, 0.89, and 0.91, respectively, with the corresponding root mean square errors 0.16, 0.14, 0.09, and 0.08%. The R² were 0.73, 0.81, 0.81, and 0.89 with the corresponding root mean square errors 0.17, 0.15, 0.12, and 0.09%, respectively, in cross validation. The R² were 0.62, 0.80, 0.81, and 0.87, respectively, with the root mean square errors 0.25, 0.31, 0.28, and 0.30% in external validation. These results indicate that the method of NIRS has relatively high accuracy in the prediction of rice fat content. The four calibration models established in the present study should be useful for nutrient quality improvement in rice breeding.     

Rapid Variety Identification of Pure Rough Rice by Fourier‐Transform Near‐Infrared Spectroscopy

Rice variety is considered as an important factor influencing cooking and processing quality because of variations in size, shape, and constitution. Difficulty in management of rough rice with lower varietal purity becomes a significant problem in rice production and can result in the reduction of rice quality. Fourier‐transform near‐infrared (FT‐NIR) spectroscopy was used to identify the variety of rough rice through whole‐grain techniques. Moist rough rice samples (n = 259) comprising five varieties (Khao Dawk Mali 105 [KDML105], Pathum Thani 1, Suphan Buri 60, Chainat 1, and Pitsanulok 2) were gathered from different locations around Thailand and scanned in the NIR region of 9088–4000 cm^–1 in reflectance mode. Soft independent modeling of class analogies (SIMCA) and partial least squares discriminant analysis (PLSDA) methods were used for identification by utilizing preprocessed spectra. The highest identification accuracy achieved was 74.42% by the SIMCA model and 99.22% by the PLSDA model. The best PLSDA model demonstrated approximately 97% correct identification for KDML105 samples and 100% for the others. This study raises the possibility of applying FT‐NIR spectroscopy as a nondestructive technique for rapidly identifying moist rough rice varieties in routine quality assurance testing.