A tree based eXtreme Gradient Boosting (XGBoost) machine learning model to forecast the annual rice production in Bangladesh.

In this study, we attempt to anticipate annual rice production in Bangladesh (1961-2020) using both the Autoregressive Integrated Moving Average (ARIMA) and the eXtreme Gradient Boosting (XGBoost) methods and compare their respective performances. On the basis of the lowest Corrected Akaike Information Criteria (AICc) values, a significant ARIMA (0, 1, 1) model with drift was chosen based on the findings. The drift parameter value shows that the production of rice positively trends upward. Thus, the ARIMA (0, 1, 1) model with drift was found to be significant. On the other hand, the XGBoost model for time series data was developed by changing the tunning parameters frequently with the greatest result. The four prominent error measures, such as mean absolute error (MAE), mean percentage error (MPE), root mean square error (RMSE), and mean absolute percentage error (MAPE), were used to assess the predictive performance of each model. We found that the error measures of the XGBoost model in the test set were comparatively lower than those of the ARIMA model. Comparatively, the MAPE value of the test set of the XGBoost model (5.38%) was lower than that of the ARIMA model (7.23%), indicating that XGBoost performs better than ARIMA at predicting the annual rice production in Bangladesh. Hence, the XGBoost model performs better than the ARIMA model in predicting the annual rice production in Bangladesh. Therefore, based on the better performance, the study forecasted the annual rice production for the next 10 years using the XGBoost model. According to our predictions, the annual rice production in Bangladesh will vary from 57,850,318 tons in 2021 to 82,256,944 tons in 2030. The forecast indicated that the amount of rice produced annually in Bangladesh will increase in the years to come.

Biobran/MGN-3, an Arabinoxylan Rice Bran, Protects against Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2): An In Vitro and In Silico Study.

Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), the causative agent of Coronavirus Disease 2019 (COVID-19), poses a serious global public health threat for which there is currently no satisfactory treatment. This study examines the efficacy of Biobran/MGN-3 against SARS-CoV-2. Biobran is an arabinoxylan rice bran that has been shown to significantly inhibit the related influenza virus in geriatric subjects. Here, Biobran's anti-SARS-CoV-2 activity was assessed using MTT and plaque reduction assays, RT-PCR, ELISA techniques, and measurements of SARS-CoV-2-related gene expression and protein levels. For Vero E6 cells infected with SARS-CoV-2, Biobran reduced the viral load by 91.9% at a dose of 100 µg/mL, it reduced viral counts (PFU/mL) by 90.6% at 50 µg/mL, and it exhibited a significant selectivity index (EC50/IC50) of 22.5. In addition, Biobran at 10 µg/mL inhibited papain-like proteinase (PLpro) by 87% and ACE2 SARS-CoV-2 S-protein RBD by 90.5%, and it significantly suppressed SARS-CoV-2 gene expression, down-regulating E-gene and RdRp gene expression by 93% each at a dose of 50 µg/mL and inhibiting the E-protein by 91.3%. An in silico docking study was also performed to examine the protein-protein interaction (PPI) between SARS-CoV-2 RBD and DC-SIGN as well as between serine carboxypeptidase and papain-like protease PLpro. Serine carboxypeptidase, an active ingredient in Biobran, was found to interfere with the binding of SARS-CoV-2 to its receptor DC-SIGN on Vero cells, thus preventing the cell entry of SARS-CoV-2. In addition, it impairs the viral replication cycle by binding to PLpro. We conclude that Biobran possesses potent antiviral activity against SARS-CoV-2 in vitro and suggest that Biobran may be able to prevent SARS-CoV-2 infection. This warrants further investigation in clinical trials.

Construction of rice supply chain supervision model driven by blockchain smart contract.

The outbreak of the COVID-19 and the Russia Ukraine war has had a great impact on the rice supply chain. Compared with other grain supply chains, rice supply chain has more complex structure and data. Using digital means to realize the dynamic supervision of rice supply chain is helpful to ensure the quality and safety of rice. This study aimed to build a dynamic supervision model suited to the circulation characteristics of the rice supply chain and implement contractualization, analysis, and verification. First, based on an analysis of key information in the supervision of the rice supply chain, we built a dynamic supervision model framework based on blockchain and smart contracts. Second, under the logical framework of a regulatory model, we custom designed three types of smart contracts: initialization smart contract, model-verification smart contract, and credit-evaluation smart contract. To implement the model, we combined an asymmetric encryption algorithm, virtual regret minimization algorithm, and multisource heterogeneous fusion algorithm. We then analyzed the feasibility of the algorithm and the model operation process. Finally, based on the dynamic supervision model and smart contract, a prototype system is designed for example verification. The results showed that the dynamic supervision model and prototype system could achieve the real-time management of the rice supply chain in terms of business information, hazard information, and personnel information. It could also achieve dynamic and credible supervision of the rice supply chain's entire life cycle at the information level. This new research is to apply information technology to the digital management of grain supply chain. It can strengthen the digital supervision of the agricultural product industry.

Long-term blast control in high eating quality rice using multilines.

Combining genetic heterogeneity and crop homogeneity serves a dual purpose: disease control and maintaining harvest quality. Multilines, which consist of a genetically uniform mixture of plants, have the potential to suppress disease while maintaining eating quality, yet practical methods that facilitate commercial use over large geographical areas are lacking. Here, we describe effective rice multiline management based on seed mixture composition changes informed by monitoring virulent blast races in Niigata Prefecture, Japan. The most elite nonglutinous cultivar, Koshihikari, was converted into the multiline, Koshihikari BL (blast resistant lines) and planted on 94,000 ha in 2005. The most destructive rice disease, blast, was 79.4% and 81.8% less severe in leaves and panicles, respectively, during the 2005-2019 period compared to the year 2004. In addition, fungicidal application was reduced by two-thirds after the introduction of BL. Our results suggest that seed mixture diversification and rotation of resistant BL provides long-term disease control by avoiding virulent race evolution.

Molecular farming using transgenic rice endosperm.

Plant expression platforms are low-cost, scalable, safe, and environmentally friendly systems for the production of recombinant proteins and bioactive metabolites. Rice (Oryza sativa L.) endosperm is an ideal bioreactor for the production and storage of high-value active substances, including pharmaceutical proteins, oral vaccines, vitamins, and nutraceuticals such as flavonoids and carotenoids. Here, we explore the use of molecular farming from producing medicines to developing functional food crops (biofortification). We review recent progress in producing pharmaceutical proteins and bioactive substances in rice endosperm and compare this platform with other plant expression systems. We describe how rice endosperm could be modified to design metabolic pathways and express and store stable products and discuss the factors restricting the commercialization of transgenic rice products and future prospects.

Discovery of Epipodophyllotoxin-Derived B2 as Promising XooFtsZ Inhibitor for Controlling Bacterial Cell Division: Structure-Based Virtual Screening, Synthesis, and SAR Study.

The emergence of phytopathogenic bacteria resistant to antibacterial agents has rendered previously manageable plant diseases intractable, highlighting the need for safe and environmentally responsible agrochemicals. Inhibition of bacterial cell division by targeting bacterial cell division protein FtsZ has been proposed as a promising strategy for developing novel antibacterial agents. We previously identified 4'-demethylepipodophyllotoxin (DMEP), a naturally occurring substance isolated from the barberry species Dysosma versipellis, as a novel chemical scaffold for the development of inhibitors of FtsZ from the rice blight pathogen Xanthomonas oryzae pv. oryzae (Xoo). Therefore, constructing structure-activity relationship (SAR) studies of DMEP is indispensable for new agrochemical discovery. In this study, we performed a structure-activity relationship (SAR) study of DMEP derivatives as potential XooFtsZ inhibitors through introducing the structure-based virtual screening (SBVS) approach and various biochemical methods. Notably, prepared compound B2, a 4'-acyloxy DMEP analog, had a 50% inhibitory concentration of 159.4 µM for inhibition of recombinant XooFtsZ GTPase, which was lower than that of the parent DMEP (278.0 µM). Compound B2 potently inhibited Xoo growth in vitro (minimum inhibitory concentration 153 mg L-1) and had 54.9% and 48.4% curative and protective control efficiencies against rice blight in vivo. Moreover, compound B2 also showed low toxicity for non-target organisms, including rice plant and mammalian cell. Given these interesting results, we provide a novel strategy to discover and optimize promising bactericidal compounds for the management of plant bacterial diseases.

Cyanidin-3-O-glucoside and Peonidin-3-O-glucoside-Rich Fraction of Black Rice Germ and Bran Suppresses Inflammatory Responses from SARS-CoV-2 Spike Glycoprotein S1-Induction In Vitro in A549 Lung Cells and THP-1 Macrophages via Inhibition of the NLRP3 Inflammasome Pathway.

Black rice is a functional food that is high in anthocyanin content, primarily C3G and P3G. It possesses nutraceutical properties that exhibit a range of beneficial effects on human health. Currently, the spike glycoprotein S1 subunit of SARS-CoV-2 (SP) has been reported for its contribution to pathological inflammatory responses in targeting lung tissue and innate immune cells during COVID-19 infection and in the long-COVID phenomenon. Our objectives focused on the health benefits of the C3G and P3G-rich fraction of black rice germ and bran (BR extract) on the inhibition of inflammatory responses induced by SP, as well as the inhibition of NF-kB activation and the NLRP3 inflammasome pathway in an in vitro model. In this study, BR extract was identified for its active anthocyanins, C3G and P3G, using the HPLC technique. A549-lung cells and differentiated THP-1 macrophages were treated with BR extract, C3G, or P3G prior to exposure to 100 ng/mL of SP. Their anti-inflammatory properties were then determined. BR extract at concentrations of 12.5-100 µg/mL exhibited anti-inflammation activity for both A549 and THP-1 cells through the significant suppression of NLRP3, IL-1ß, and IL-18 inflammatory gene expressions and IL-6, IL-1ß, and IL-18 cytokine secretions in a dose-dependent manner (p < 0.05). It was determined that both cell lines, C3G and P3G (at 1.25-10 µg/mL), were compatibly responsible for the significant inhibition of SP-induced inflammatory responses for both gene and protein levels (p < 0.05). With regard to the anti-inflammation mechanism, BR extract, C3G, and P3G could attenuate SP-induced inflammation via counteraction with NF-kB activation and downregulation of the inflammasome-dependent inflammatory pathway proteins (NLRP3, ASC, and capase-1). Overall, the protective effects of anthocyanins obtained from black rice germ and bran can be employed in potentially preventive strategies that use pigmented rice against the long-term sequelae of COVID-19 infection.

Assessment of the effects of COVID-19 lockdown period on groundwater quality of a significant rice land in an urban area of Türkiye.

In the current research, the impact of the COVID-19 lockdown period on groundwater quality of Lower Meriç Plain (Thrace Region of Türkiye) was evaluated. Some significant nutrient characteristics (NO3-, NO2-, and PO43-), salinity characteristics (EC, TDS, and salinity), and physical characteristics (temperature, DO, pH, and turbidity) were investigated in groundwater samples collected from 45 sampling points in pre-lockdown and lockdown periods. Water quality index (WQI) and nutrient pollution index (NPI), Pearson correlation index (PCI), cluster analysis (CA), one-way ANOVA test (OWAT), and factor analysis (FA) were applied to assess ecological risk. Excluding recorded statistical differences in temperature and DO due to climatic conditions (p < 0.05), levels of all the investigated water quality parameters show no statistically significant differences and no significant reduction in pollutants measured in the lockdown period. On the contrary, the WQI and NPI scores have increased between the rates of 4.76-27.10% during the lockdown period. In the lockdown period, although the reduction of industry or limited production of many industrial facilities reduced the inorganic contaminant releases to the environment, ongoing agricultural activities and domestic wastes caused to prevent the reduction of organic pollutants in groundwater of the region during the lockdown period.

Impacts of Extreme Climate Events on Future Rice Yields in Global Major Rice-Producing Regions.

Under the dual impacts of climate change and COVID-19, there are great risks to the world's food security. Rice is one of the three major food crops of the world. Assessing the impact of climate change on future rice production is very important for ensuring global food security. This article divides the world's main rice-producing regions into four regions and uses a multivariate nonlinear model based on historical economic and climatic data to explore the impacts of historical extreme climatic events and economic factors on rice yield. Based on these historical models, future climatic data, and economic data under different shared socioeconomic pathways (SSPs), the yields of four major rice-producing regions of the world under different climate change scenarios (SSP126, SSP245, and SSP585) are predicted. The research results reveal that under different climate change scenarios, extreme high-temperature events (Tx90p) and extreme precipitation events (Rx5day, R99pTOT) in the four major rice-producing regions have an upward trend in the future. Extreme low-temperature events (Tn10p) have a downward trend. In the rice-producing regions of Southeast Asia and South America, extreme precipitation events will increase significantly in the future. The prediction results of this model indicate that the rice output of these four major rice-producing regions will show an upward trend in the future. Although extreme precipitation events will have a negative impact on rice production, future increases in rice planting areas, economic development, and population growth will all contribute to an increase in rice production. The increase in food demand caused by population growth also brings uncertainty to global food security. This research is helpful for further understanding climate change trends and risks to global rice-production areas in the future and provides an important reference for global rice-production planning and risk management.

Elementomics combined with dd-SIMCA and K-NN to identify the geographical origin of rice samples from China, India, and Vietnam.

The COVID-19 pandemic has impacted the food industry and consumers, with production gaps, shipping delays, and changes in supply and demand leading to an increased risk of food fraud. Rice has a high probability for adulteration by food fraudsters, being a staple commodity for more than half the global population, making the assessment of geographical origins of rice for authenticity important in terms of protecting businesses and consumers. In this study, we describe ICP-MS elemental profiling coupled with elementomic modelling to identify the geographical indications of Indian, Chinese, and Vietnamese rice. A PLS-DA model exhibited good discrimination (R2 = 0.8393, Q2 = 0.7673, accuracy = 1.0). Data-driven soft independent modelling of class analogy (dd-SIMCA) and K-nearest neighbours (K-NN) models have good sensitivity (98%) and specificity (100%).

Preparation, Characterization and Antimicrobial Properties of Nanosized Silver-Containing Carbon/Silica Composites from Rice Husk Waste.

Rice husk, one of the main side products in the rice production, and its sustainable management represent a challenge in many countries. Herein, we describe the use of this abundant agricultural bio-waste as feedstock for the preparation of silver-containing carbon/silica nano composites with antimicrobial properties. The synthesis was performed using a fast and cheap methodology consisting of wet impregnation followed by pyrolysis, yielding C/SiO2 composite materials doped with varying amounts of silver from 28 to 0.001 wt %. The materials were fully characterized and their antimicrobial activity against ESKAPE pathogens, namely E. faecium, S. aureus, K. pneumoniae, A. baumannii, P. aeruginosa, and E. coli, and the pathogenic yeast C. albicans was investigated. Sensitivities of these strains against the prepared materials were demonstrated, even with exceptional low amounts of 0.015 m% silver. Hence, we report a straightforward method for the synthesis of antimicrobial agents from abundant sources which addresses urgent questions like bio-waste valorization and affordable alternatives to increasingly fewer effective antibiotics.

Rice quality and its impacts on food security and sustainability in Bangladesh.

Rice market efficiency is important for food security in countries where rice is a staple. We assess the impact of rice quality on rice prices, food security, and environmental sustainability in Bangladesh. We find that while price varies as expected for most quality attributes, it is unaffected by a broken percentage below 24.9 percent. This reveals a potential inefficiency, considering the average 5 percent broken rate observed in the market. An increase in the broken rate of milled rice within the limits supported by our findings can, ceteris paribus, increase rice rations by 4.66 million a year, or conversely, yield the current number of rice rations using 170.79 thousand fewer hectares and cutting emissions by 1.48 million metric tons of CO2 equivalent. Thus, producing rice based on quality assessment can improve food security and its sustainability.

Combined application of biochar and nitrogen fertilizer promotes the activity of starch metabolism enzymes and the expression of related genes in rice in a dual cropping system.

BACKGROUND: Overuse of chemical fertilizer highly influences grain filling rate and quality of rice grain. Biochar is well known for improving plant growth and grain yield under lower chemical fertilization. Therefore field trials were conducted in the early and late seasons of 2019 at Guangxi University, China to investigate the effects of combined biochar (B) and nitrogen (N) application on rice yield and yield components. There were a total of eight treatments: N1B0, 135 kg N ha- 1+ 0 t B ha- 1; N2B0,180 kg N ha- 1+ 0 t B ha- 1; N1B1,135 kg N ha- 1+ 10 t B ha- 1; N1B2,135kg N ha- 1+ 20 t B ha- 1; N1B3,135 kg N ha- 1+ 30 t B ha- 1; N2B1,180 kg N ha- 1+ 10 t B ha- 1; N2B2,180 kg N ha- 1+ 20 t B ha- 1; and N2B3,180 kg N ha- 1+ 30 t B ha- 1. RESULTS: Biochar application at 30 t ha- 1combined with low N application (135 kg ha- 1) increased the activity of starch-metabolizing enzymes (SMEs) during the early and late seasons compared with treatments without biochar. The grain yield, amylose concentration, and starch content of rice were increased in plots treated with 30 t B ha-1and low N. RT-qPCR analysis showed that biochar addition combined with N fertilizer application increased the expression of AGPS2b, SSS1, GBSS1, and GBSE11b, which increased the activity of SMEs during the grain-filling period. CONCLUSION: Our results suggest that the use of 20 to 30 t B ha- 1coupled with 135 kg N ha- 1 is optimal for improving the grain yield and quality of rice.

The Role of Micronutrients and Toxic Metals in the Management of Epidemics in Cambodia.

The illegal trade of wildlife in SE Asia has been identified as the likely cause of the COVID-19 pandemic. We reviewed 198 papers on the current COVID pandemic in Cambodia, diseases such as avian influenza and Nipah virus, most likely to develop into a new pandemic in Cambodia, and common features of disease that require mitigation. Artisanal goldmining uses pure mercury in the areas where wildlife is smuggled to China. Moreover, 30-40% of Cambodians are zinc deficient. High levels of arsenic in irrigation water (>1000 µg/L) are associated with very low levels of zinc in rice (5 µg/g) and rice is the primary staple food for the region. Brown rice from nine of 15 paddy fields in the arsenic zone of Cambodia had double the new guidelines of 100 µg/kg inorganic arsenic for children's food in the EU and USA. The combination of deficiencies of essential micronutrients like zinc and pervasive presence of arsenic and mercury has the potential to compromise the immunity of many Cambodians. Innovative solutions are suggested to improve micronutrient nutrition. Toxins that suppress the immune system must be better managed to reduce the virulence of pathogens. Cambodia was not likely the source of the COVID-19 but does have problems that could result in a new pandemic.

Rice SUT and SWEET Transporters.

Sugar transporters play important or even indispensable roles in sugar translocation among adjacent cells in the plant. They are mainly composed of sucrose-proton symporter SUT family members and SWEET family members. In rice, 5 and 21 members are identified in these transporter families, and some of their physiological functions have been characterized on the basis of gene knockout or knockdown strategies. Existing evidence shows that most SUT members play indispensable roles, while many SWEET members are seemingly not so critical in plant growth and development regarding whether their mutants display an aberrant phenotype or not. Generally, the expressions of SUT and SWEET genes focus on the leaf, stem, and grain that represent the source, transport, and sink organs where carbohydrate production, allocation, and storage take place. Rice SUT and SWEET also play roles in both biotic and abiotic stress responses in addition to plant growth and development. At present, these sugar transporter gene regulation mechanisms are largely unclear. In this review, we compare the expressional profiles of these sugar transporter genes on the basis of chip data and elaborate their research advances. Some suggestions concerning future investigation are also proposed.

Evaluation of anti-cancer and anti-covid-19 properties of cationic pentapeptide Glu-Gln-Arg-Pro-Arg, from rice bran protein and its d-isomer analogs through molecular docking simulations.

Bioactive peptides derived from food proteins are becoming increasingly popular due to the growing awareness of their health-promoting properties. The structure and mechanism of anti-cancer action of pentapeptide Glu-Gln-Arg-Pro-Arg (EQRPR) derived from a rice bran protein are not known. Theoretical and experimental methods were employed to fill this gap. The conformation analysis of the EQRPR pentapeptide was performed first and the obtained lowest energy conformer was optimized. The experimental structural data obtained by FTIR and CD spectroscopies agree well with the theoretical results. d-isomer introduced one-by-one to each position and all D-isomers of the peptide were also examined for its possible anti-proteolytic and activity enhancement properties. The molecular docking revealed avid binding of the pentapeptide to the integrins α5ß1 and αIIbß3, with Kd values of 90 nM and 180 nM, respectively. Moreover, the EQRPR and its D-isomers showed strong binding affinities to apo- and holo-forms of Mpro, spike glycoprotein, ACE2, and dACE2. The predicted results indicate that the pentapeptide may significantly inhibit SARS-CoV-2 infection. Thus, the peptide has the potential to be the leading molecule in the drug discovery process as having multifunctional with diverse biological activities.

A novel aqueous extract from rice fermented with Aspergillus oryzae and Saccharomyces cerevisiae possesses an anti-influenza A virus activity.

Human influenza virus infections occur annually worldwide and are associated with high morbidity and mortality. Hence, development of novel anti-influenza drugs is urgently required. Rice Power® extract developed by the Yushin Brewer Co. Ltd. is a novel aqueous extract of rice obtained via saccharization and fermentation with various microorganisms, such as Aspergillus oryzae, yeast [such as Saccharomyces cerevisiae], and lactic acid bacteria, possessing various biological and pharmacological properties. In our previous experimental screening with thirty types of Rice Power® extracts, we observed that the 30th Rice Power® (Y30) extract promoted the survival of influenza A virus-infected Madin-Darby canine kidney (MDCK) cells. Therefore, to identify compounds for the development of novel anti-influenza drugs, we aimed to investigate whether the Y30 extract exhibits anti-influenza A virus activity. In the present study, we demonstrated that the Y30 extract strongly promoted the survival of influenza A H1N1 Puerto Rico 8/34 (A/PR/8/34), California 7/09, or H3N2 Aichi 2/68 (A/Aichi/2/68) viruses-infected MDCK cells and inhibited A/PR/8/34 or A/Aichi/2/68 viruses infection and growth in the co-treatment and pre-infection experiments. The pre-treatment of Y30 extract on MDCK cells did not induce anti-influenza activity in the cell. The Y30 extract did not significantly affect influenza A virus hemagglutination, and neuraminidase and RNA-dependent RNA polymerase activities. Interestingly, the electron microscopy experiment revealed that the Y30 extract disrupts the integrity of influenza A virus particles by permeabilizing the viral membrane envelope, suggesting that Y30 extract has a direct virucidal effect against influenza A virus. Furthermore, we observed that compared to the ethyl acetate (EtOAc) extract, the water extract of Y30 extract considerably promoted the survival of cells infected with A/PR/8/34 virus. These results indicated that more anti-influenza components were present in the water extract of Y30 extract than in the EtOAc extract. Our results highlight the potential of a rice extract fermented with A. oryzae and S. cerevisiae as an anti-influenza medicine and a drug source for the development of anti-influenza compounds.

The classical and potential novel healthy functions of rice bran protein and its hydrolysates.

Rice bran protein (RBP) is a plant protein obtained from rice bran, a byproduct produced during rice milling process. It has been proved to be a high quality protein due to containing all of the essential amino acids and the content closing to the FAO/WHO recommended ideal pattern. Recent studies indicated that RBP and rice bran protein hydrolysates (RBPH) served variety biological functions. In this review, we summarized the classical functions of RBP and RBPH mediating antioxidant activity, chronic diseases prevention (such as antihypertensive effect, anti-diabetic effect, cholesterol-lowering activity), and anti-cancer effect. We also proposed their potential novel functions on anti-obesity effect, attenuating sarcopenia, promoting wound healing. Furthermore, the potential benefit to coronavirus disease 2019 (COVID-19) patients was put forward, which might provide new strategy for development and utilization of RBP and RBPH.

Determination of Fatty Acid Content of Rice during Storage Based on Feature Fusion of Olfactory Visualization Sensor Data and Near-Infrared Spectra.

This study innovatively proposes a feature fusion technique to determine fatty acid content during rice storage. Firstly, a self-developed olfactory visualization sensor was used to capture the odor information of rice samples at different storage periods and a portable spectroscopy system was employed to collect the near-infrared (NIR) spectra during rice storage. Then, principal component analysis (PCA) was performed on the pre-processed olfactory visualization sensor data and the NIR spectra, and the number of the best principal components (PCs) based on the single technique model was optimized during the backpropagation neural network (BPNN) modeling. Finally, the optimal PCs were fused at the feature level, and a BPNN detection model based on the fusion feature was established to achieve rapid measurement of fatty acid content during rice storage. The experimental results showed that the best BPNN model based on the fusion feature had a good predictive performance where the correlation coefficient (RP) was 0.9265, and the root mean square error (RMSEP) was 1.1005 mg/100 g. The overall results demonstrate that the detection accuracy and generalization performance of the feature fusion model are an improvement on the single-technique data model; and the results of this study can provide a new technical method for high-precision monitoring of grain storage quality.