This study proposes a multi-sensor fusion framework to address the limitations of single-sensor Unmanned Aerial Vehicle (UAV) systems in rice leaf area index (LAI) estimation. Three UAV platforms equipped with multispectral, RGB, or LiDAR sensors were employed to collect data during three critical rice growth stages. Ordinary Least Squares (OLS) regression models were first constructed to estimate LAI by using the single feature that exhibited high correlation with rice LAI. Results revealed that models based on Laser Penetration Index (LPI; R2 = 0.649, RMSE = 0.876) and Height Percentile Area 0-50 (HPA0-50; R2 = 0.601, RMSE = 0.933) derived from LiDAR sensor exhibited the best performance among all single features. Three machine learning algorithms (Gradient Boosting Regression, Random Forest, and Stacking) were further employed to construct LAI estimation models by fusing vegetation indices, colour indices, texture features, and spatial structural features extracted from three sensors. The Random Forest model based on multi-sensor fusion data achieved optimal performance (R2 = 0.861, RMSE = 0.600), demonstrating a 32.66% accuracy improvement over the single-feature OLS model. Permutation importance analysis was conducted to quantify sensor contributions, revealing the LiDAR sensor as the dominant contributor (67.78% of total importance), followed by multispectral (27.46%) and RGB sensors (4.75%). It was also demonstrated that a single-LiDAR sensor achieved higher accuracy (R2 = 0.812) for LAI estimation, much higher than the single-multispectral or single-RGB sensor, which benefited from spectral-texture fusion. These results demonstrated that multi-sensor fusion was an efficient approach to achieve higher accuracy for rice LAI estimation, with LiDAR-driven spatial structural features serving as the key role for high-accuracy LAI estimation.

Electrochemical sensing provides an alternative approach for the trace detection of bioactive substances in fruits. However, the complex matrix in fruit tissues, the coexistence of multiple active components, and the varied pH environments limit the sensing performance and accurate quantitative detection of conventional electrochemical sensors. Herein, a dual-mode electrochemical sensor based on a Co3O4@N-MWCNTs modified glassy carbon electrode was developed for the sequential detection of quercetin, rutin, and glucose in fruits under acidic and alkaline conditions. The as-prepared electrode exhibited improved charge transfer efficiency and favorable electrocatalytic activity toward the three target analytes. Under optimal conditions, the sensor displayed wide linear ranges of 0.5 similar to 70 mu M for quercetin and 0.5 similar to 5 mu M for rutin in acidic environment, with low detection limits of 0.124 mu M and 0.045 mu M, respectively. In alkaline environment, the detection limit for glucose was determined to be 8.86 mu M. Moreover, four combined machine learning models with feature selection algorithms were established, among which the CARS-RFE+RFR model achieved the best prediction accuracy and robustness for multicomponent quantification. Furthermore, the proposed sensing system was applied to the rapid determination of quercetin, rutin, and glucose in real litchi samples, with recoveries ranging from 98.4% to 105.4%. This study provides a feasible electrochemical strategy for multicomponent detection in complex plant matrices, showing good applicability for rapid on-site analysis in agricultural and food-related applications.

Detection accuracy of internal component contents in fruits by hyperspectral imaging (HSI) suffered from the geometric structure and the nonlinear relation between the content and spectral features. These issues were respectively addressed by developing approaches based on spectral normalization and spectral features (SPF)-image features (SSF)-geometric structure features (GSF)-nonlinear features (NLF) fusing. For this purpose, VNIR-SWIR transmission HSI combined with partial least squares regression (PLSR) model was employed to detect the soluble solid content (SSC) and anthocyanin content (AC) in litchi fruits. It was revealed that spectral normalization combined with SPF-SSF-GSF-NLF fusing improved Rp2 of PLSR model for SSC and AC by 17.47 % and 11.85 %, and the values reached 0.9148 and 0.8455, respectively. Furthermore, litchi grading approaches based on the predicted SSC and AC were developed with a high classification accuracy of 95.17 %. These results demonstrated that the proposed approach was effective in improving the detection accuracy of litchi fruit quality.

This study presents a comprehensive solution for precise and timely pest monitoring in field environments through the development of an advanced rice pest detection system based on the YOLO-RMD model. Addressing critical challenges in real-time detection accuracy and environmental adaptability, the proposed system integrates three innovative components: (1) a novel Receptive Field Attention Convolution module enhancing feature extraction in complex backgrounds; (2) a Mixed Local Channel Attention module balances local and global features to improve detection precision for small targets in dense foliage; (3) an enhanced multi-scale detection architecture incorporating Dynamic Head with an additional detection head, enabling simultaneous improvement in multi-scale pest detection capability and coverage. The experimental results demonstrate a 3% accuracy improvement over YOLOv8n, achieving 98.2% mean Average Precision at 50% across seven common rice pests while maintaining real-time processing capabilities. This integrated solution addresses the dual requirements of precision and timeliness in field monitoring, representing a significant advancement for agricultural vision systems. The developed framework provides practical implementation pathways for precision pest management under real-world farming conditions.

To enhance the production efficiency of the litchi industry, this study proposes an improved litchi fruit detection method based on a series of hyperspectral reconstruction networks and YOLOv8. This study assessed the performance of five hyperspectral reconstruction models reconstructing litchi fruits images to enhancing the ability of YOLOv8 to detect, segment and recognize the maturity of litchi fruits. We built the agricultural hyperspectral datasets to fine-tune the hyperspectral reconstruction models trained by the public hyperspectral reconstruction datasets. We collected the litchi fruits images in RGB format for the tasks of detection, segmentation, and maturity recognition. The RGB images were reconstructed by the five trained hyperspectral reconstruction models, the generated hyperspectral data can provide YOLOv8 with image data that has a significantly rich spectral information, and in this process, we applied a hyperspectral feature extraction algorithm to extract characteristic spectral information for YOLOv8. And then, we compared the performance of different YOLO models with our methods in normal images and underexposed-overexposed images to valid the performance and robustness of our method when facing the harsh imaging environments. In detection and segmentation part, the YOLOv8n, YOLOv8n-HRNet, YOLOv8n-HiNet, YOLOv8n-MIRNet, YOLOv8n-MST, and YOLOv8n-MST++ models achieved precision values of 80.82 %, 81.21 %, 81.73 %, 82.21 %, 89.12 %, and 91.17 %, respectively; As for the maturity recognition part, our best model YOLOv8n-MST++ achieved 98.40 % of accuracy in all the three classes, while the original YOLOv8 only achieved 88.00 % of accuracy in all the three classes. Compared to the original YOLOv8n model, the richer spectral information provided by the hyperspectral reconstruction models can enhance the performance of original YOLOv8n when detect and segment litchi fruits. These results indicate the feasibility and effectiveness of utilizing hyperspectral reconstruction models, especially MST and MST++, to enhance the performance of YOLOv8n, providing potential method to optimize litchi picking or litchi fruit management.

In the cutting-edge field of quantum nanophotonics, embedding quantum emitters (QEs) into nanostructures goes beyond the conventional exploration of light-structure interactions. The ability to optimize the local density of states (LDOS) through the design of nanophotonic structures for quantum manipulation is a significant area of research. Traditional inverse design methods are inefficient when dealing with complex structures and multiparameter optimizations, and there are issues such as the design non-uniqueness of the designed structures. In this work, we established a mapping between QEs and nanophotonic structures by introducing the LDOS and developed an artificial tandem neural network (TNN) to design nanophotonic structures with desired LDOS and optimize the spontaneous emission characteristics of QEs. The TNN enables precise one-to-one inverse design of nanostructures, significantly enhancing the LDOS at specific, desired frequency positions. Additionally, we introduce a structural loss function to address multiparameter optimizations, including the material thickness and types. Although our approach is exemplified by the design of two-layer core-shell structures that enhance the LDOS, it can also be readily extended to multilayer core-shell designs through transfer learning technology. Our work shows that TNN is an efficient methodology and a powerful tool for tailoring the LDOS and manipulating quantum dynamics in various nanophotonic structures.

Organic Solar Cells (OSCs) are one of the most promising solar cells due to the possible for large-scale and lowcost printed production. Therefore, efficient manufacturing processes and optimization methods are crucial. Currently, the traditional trial-and-error method is mostly used to optimize device performance, which is complex and time-consuming. Previous machine learning (ML) methods can reduce the workload, but relay on multiple inputs. To accelerate the optimization process, a novel ML-based approach was proposed to predict the power conversion efficiency (PCE) of OSCs, utilizing the reflectance spectrum of the transparent electrode/ charge transport layer/active layer (TCA triplelayer). For this purpose, a dataset, containing PCEs of six types of OSCs with different active layer materials and reflectance spectra of TCA triplelayers, had been constructed by simulations via finite-difference time-Domain method. Based on the dataset, machine learning algorithms were employed to construct the regression models. Spectra pre-processing and feature extraction techniques were integrated to refine the predictive accuracy of these models. Consequently, the model based on Multilayer Perceptron Regression (MLPR) algorithm demonstrated the best performance, with coefficient of determination (R2) of 0.984 and root-mean-squared error of 0.408. These results underscore the potential to accurately predict the PCE of OSCs from the reflectance spectra of TCA triplelayer. Ultimately, a strategy was further proposed to utilize the developed regression model for real-time quality monitoring of TCA triplelayer during device fabrication. This offers a rapid way to evaluate the quality of TCA triplelayers and their influence on device performance.

Organic solar cells (OSCs) have gained significant attention due to their cost-effectiveness, lightweight, and flexibility. However, traditional optimization methods are time-consuming and labor-intensive. This study introduces a novel approach to rapidly predict the power conversion efficiency (PCE) of OSCs by leveraging their device reflectance spectra and machine learning techniques. A dataset comprising 606 reflectance spectra and corresponding PCE values for six types of OSCs was constructed using the Finite-Difference Time-Domain method. Various preprocessing techniques (STD, SG, D1, D2) and feature extraction methods (PCA, CARS, SPA) were applied, followed by training with traditional machine learning models (PLSR, KNNR, RFR, SVR, ELM). The STD-CARS-RFR model achieved a prediction accuracy (R2) of 0.987. Further improvements were made by integrating a multilayer perceptron regression (MLPR) model, raising the accuracy to 0.992. The introduction of an attention mechanism in the Attention-MLPR model further optimized the prediction, achieving an R2 of 0.998 and a root mean square error of 0.253. These results demonstrate that combining reflectance spectra with machine learning techniques can efficiently predict OSC efficiency, offering a non-contact alternative to traditional photoelectric measurement methods and holding significant potential for practical applications.

This paper presents a method to enhance the light absorption and power conversion efficiency of organic solar cells (OSCs) by embedding a plasmonic Ag nanocuboid array into the active layer. Numerical simulations based on the finite-difference time-domain method are conducted to compare the enhancement of short circuit current density (Jsc) caused by the Ag nanocuboid array with other types of plasmonic nanostructures such as nanocubes, nanospheres, nanorods, and nanocylinders. It is demonstrated that the nanocuboid array can lead to an enhancement of 25.5% in Jsc, much higher than that of other nanostructure arrays. Analyses of the photoelectric field and light absorption enhancement show that the enhancement in Jsc primarily results from the combined effects of localized surface plasmon resonance (LSPR) and optical interference within the devices. It is also revealed that the optical interference can improve or weaken the absorption-enhancing ability of the LSPR mode, which depends on the spectral position of the LSPR mode and the spatial position of the Ag nanocuboids in the optical electric field. Finally, we investigate the effects of light polarization and nanostructure size on Jsc enhancement of the OSC devices. The findings in the paper provide theoretical support for designing OSCs with thinner active layers and superior absorption performance.

The detection of endogenous hormones is of great significance for disease diagnosis, treatment guidance, and the development of personalized healthcare. By using biosensors, real-time monitoring and quantitative analysis of endogenous hormone levels can be achieved, providing scientific basis for clinical decision-making. The continuous innovation in this field will bring new breakthroughs in medical diagnosis and treatment, which are expected to accelerate the early detection of diseases and the implementation of personalized treatment plans. In this review, we mainly review the research progress of endogenous hormone biosensors based on different biological recognition elements, namely enzyme-based biosensors, immunobiosensors, aptamer-based biosensors, and molecularly imprinted polymer (MIP) based biosensors. Meanwhile, this paper also analyzes the detection efficiency and clinical application of these biosensors. Finally, we summarize the current challenges and future development directions of the different types of biosensors involved in the discussion.

Conventional chemical approaches could be limited in monitoring the concentration of pigments in plants in high volumes. To overcome these limitations, researchers often turn to non-invasive, high-throughput, and real-time monitoring techniques, such as spectroscopy and hyperspectral imaging, which allow for the assessment of pigment concentration in plants without the need for destructive sampling and offer the ability to monitor large volumes of plants efficiently. This research focused on the utilization of machine learning in conjunction with hyperspectral imaging to develop models for predicting the concentration of three pigments, namely chlorophylla, chlorophyll-b, and carotenoids, in tomato seedlings. The sample tomato seedlings were sourced from two distinct varieties: the wild type and the Long Hypocotyl-5-deficient (HY5) type. The spectral data were acquired using a near-infrared (NIR) camera with a spectral range spanning approximately 900-1700 nm. Machine learning algorithms such as partial least squares regression (PLSR) and extreme learning machine (ELM) were utilized to explore the latent relationship between hyperspectral information and chemical measurements. In addition, principal component analysis (PCA), independent component analysis (ICA), and competitive adaptive reweighted sampling (CARS) methods were used to extracted informative wavelengths from the reflectance spectrum. And a comprehensive analysis regarding to spectroscopy was conducted to investigate the validity and efficiency of the results of feature extraction. The ELM model demonstrated the highest effectiveness, achieving R2 values of 0.86, 0.83, and 0.83 for chlorophyll-a, chlorophyll-b, and carotenoids, respectively, on the test set. By integrating the predictive models with classifiers such as Logistic Regression, Support Vector Classifier (SVC), and K-nearest Neighbors (KNN), tomato seedlings were categorized into wild type and HY5 type. The findings showed that the proposed approach efficiently predicted the concentration of the pigments in tomato seedlings and explored the feasibility of using these results to identify tomato gene types.

Semitransparent organic solar cells (ST-OSCs) have garnered more interest and stand out as promising candidates for next-generation solar energy harvesters with their unique advantages. However, challenges remain for the advancement of colorful ST-OSCs, such as enhancing the light absorption and transmittance without considerable power conversion efficiency (PCE) losses. Herein, an optical analysis of silver (Ag) electrodes and one-dimensional photonic crystals (1DPCs) was conducted by simulations, revealing the presence of optical Tamm states (OTSs) at the interface of Ag/1DPCs. Furthermore, the spectral and electrical properties were fine-tuned by modulating the OTSs through theoretical simulations, utilizing PM6:Y6 as the active layer. The structural parameters of the ST-OSCs were optimized, including the Ag layer thickness, the central wavelength of 1DPCs, the first WO3 layer thickness, and the pair number of WO3/LiF. The optimization resulted in the successful development of blue, violet-blue, and red ST-OSC devices, which exhibited transmittance peak intensities ranging from 31.5% to 37.9% and PCE losses between 1.5% and 5.2%. Notably, the blue device exhibited a peak intensity of 37.0% and a PCE of 15.24%, with only a 1.5% loss in efficiency. This research presents an innovative approach to enhancing the performance of ST-OSCs, achieving a balance between high transparency and high efficiency.

We investigate the microscopic hyperspectral reconstruction from RGB images with a deep convolutional neural network (DCNN) in this paper. Based on the microscopic hyperspectral imaging system, a homemade dataset consisted of microscopic hyperspectral and RGB image pairs is constructed. For considering the importance of spectral correlation between neighbor spectral bands in microscopic hyperspectrum reconstruction, the 2D convolution is replaced by 3D convolution in the DCNN framework, and a metric (weight factor) used to evaluate the performance reconstructed hyperspectrum is also introduced into the loss function used in training. The effects of the dimension of convolution kernel and the weight factor in the loss function on the performance of the reconstruction model are studied. The overall results indicate that our model can show better performance than the traditional models applied to reconstruct the hyperspectral images based on DCNN for the public and the homemade microscopic datasets. In addition, we furthermore explore the microscopic hyperspectrum reconstruction from RGB images in infrared region, and the results show that the model proposed in this paper has great potential to expand the reconstructed hyperspectrum wavelength range from the visible to near infrared bands.

Excessive use of carbendazim (CBZ) for controlling fungal disease may result in pesticide residues in growth environments. There is an urgent requirement for real-time detection of CBZ content to enable rapid assessment of pesticide residues. Herein, a novel electrochemical sensor was created, which utilizes a laser-induced graphene (LIG) electrode modified with two-dimensional (2D) tungsten disulfide (WS2) nanosheets and a poly(L-lysine) (PLL) film to construct a 2D-on-2D layered structure. The PLL/WS2/LIG electrode exhibits strong charge transfer, excellent electrocatalytic performance, and high CBZ adsorption capacity, thus leading to enhanced sensitivity. As a result, the sensor exhibits a low detection limit of 1.2 ng/mL (6.2 nM), high sensitivity up to 135.1 μA(μg/mL)−1cm−2, and a wide response range of 0.01 to 1.5 μg/mL. Moreover, an intelligent analysis system, consisting of a portable device that connects to an online cloud platform equipped with a machine learning model and visualization software, has been developed for the real-time detection of CBZ residues on tea leaves in tea plantations. This study demonstrates that the PLL/WS2/LIG sensor and the intelligent analysis system have great potential to monitor pesticide residues to guarantee food safety.

Hyperspectral imaging (HSI) provides opportunity for non-destructively detecting bioactive compounds contents of tea leaves and high detection accuracy require extracting effective features from the complex hyperspectral data. In this paper, we proposed a feature wavelength refinement method called interval band selecting-competitive adaptive reweighted sampling-fusing (IBS-CARS-Fusing) to extract feature wavelengths from visible-near-infrared (VNIR) and short-wave-near-infrared (SWIR) hyperspectral images. Combined with the proposed IBS-CARS-Fusing method, a kernel ridge regression (KRR) model was established to predict the contents of bioactive compounds including chlorophyll a, chlorophyll b, carotenoids, tea polyphenols, and amino acids in Dancong tea. It was revealed that the IBS-CARS-Fusing method can improve Rp2 of KRR model for these bioactive compounds by 4.77%, 4.60%, 6.74%, 15.52%, and 13.10%, respectively, and Rp2 of the model reached high values of 0.9500, 0.9481, 0.8946, 0.8882, and 0.8622. Additionally, a leaf compound mass per area thermal map was used to visualize the spatial distribution of the compounds.

Transverse radiation forces acting on the silicon nanoparticles illuminated by a tightly focused laser beam are investigated by using the Maxwell stress-tensor method combined with generalized Lorenz-Mie theory. It is found that the radiation force can be tuned flexibly by electric--magnetic multipolar resonances and the hybridization of the both kinds of resonances, and the nanoparticle receives a negative or positive transverse radiation force. We also analyze theoretically the far-field scattering patterns and the contributions of each typical electric--magnetic resonance and hybridization of electric and magnetic modes to the radiation forces on silicon nanoparticles with the multipolar expansion method. The simulation research results show that the negative (positive) transverse radiation forces mainly originate from the asymmetric far-field scattering when the particles are positioned at different positions in the focus plane. Our findings cannot only provide an effective strategy to enhance the efficiency of optical trapping of nanoparticles with the excitation of electric--magnetic resonances but also facilitate the optical sorting, selective trapping, and assembling of nanoparticles with a single tightly focused laser beam.

With the rapid development of hybrid rice breeding technology, hybrid rice varieties are becoming increasingly diverse, and their quality and price vary widely. The use of intelligent means for rapid classification, grading and quality detection of hybrid rice seeds has become a hot spot in hybrid rice research. In this paper, we first investigate the effect of different preprocessing methods on the accuracy of a 1D Convolutional Neural Network (1D-CNN) classification model constructed based on the near-infrared spectra of 10 hybrid rice seeds. The results show that the overall validation and prediction accuracy can be up to 95. 4% and 92. 9% respectively when the near-infrared spectra are preprocessed with the Savitzky-Golay convolution smoothing algorithm (SG). Secondly, the three most important feature wavelengths were selected by the random forest feature wavelength selection algorithm to build a single-wavelength grayscale image dataset and a 3 -wavelength reconstructed pseudo-color image dataset, and the hybrid rice seed classification model based on the convolutional neural network VGG and the residual network ResNet of the image dataset was constructed and studied. The results show that the VGG model based on the pseudo-color image dataset can obtain the optimal classification effect, and the classification accuracies of its validation set and test set are 92. 8% and 92. 8%, respectively. Compared with the ResNet classification model based on the pseudo-color image dataset, an improved value of 3. 6% is achievedin the validation set and 4. 9% in the test set. In order to further improve the classification accuracy, a hybrid rice seed classification method based on the fusion of image information and spectral information is proposed. This methodextracts spectral features using the 1D-CNN network branch and extracts dimensionalspatial features using the 2D-CNN network branch. 2Branches-CNN model is then constructed based on the fusion of image and spectral features, and the classification accuracy reaches high values of 98% and 96. 7% for the validation set and test set. The classification effect of the 2Branch-CNN model for each type of hybrid rice seeds is also evaluated by calculating the confusion matrix. The results of this paper show that the classification accuracy of the convolutional neural network model can be effectively improved by image-spectrum fusion, and the construction of a two-branch convolutional neural network model based on image-spectrum fusion will provide new ideas for rapid screening and classification of hybrid seed varieties.

Monitoring (including prediction and visualization) the gene modulated cadmium (Cd) accumulation in rice grains is one of the most important steps for identification of key transporter genes responsible for grain Cd accumulation and breeding low grain-Cd-accumulating rice cultivars. A method to predict and visualize the gene modulated ultralow Cd accumulation in brown rice grains based on the hyperspectral image (HSI) technology is proposed in this study. Firstly, the Vis-NIR HSIs of brown rice grain samples with 48Cd content levels induced by gene modulation (ranging from 0.0637 to 0.1845 mg/kg) are collected using HSI system. Then, Kernel-ridge (KRR) and random forest (RFR) regression models based on full spectral data and the data after feature dimension reduction (FDR) with kernel principal component analysis (KPCA) and truncated singular value decomposition (TSVD) algorithms are established to predict the Cd contents. RFR model shows poor performance due to the over-fitting based on the full spectral data, while the KRR model can obtain a good predict accuracy with R2p of 0.9035, RMSEP of 0.0037 and RPD of 3.278. After the FDR of the full spectral data, the RFR model combined with TSVD reaches the optimum prediction accuracy with R2p of 0.9056, RMSEP of 0.0074 and RPD of 3.318, and the best prediction precision of KRR model can also be further enhanced by TSVD with R2p of 0.9224, RMSEP of 0.0067 and RPD of 3.512. Finally, the visualization of the predicted Cd accumulation in brown rice grains are realized based on the best regression model (KRR + TSVD). The results of this work indicate that Vis-NIR HSI has great potential for detection and visualization gene modulation induced ultralow Cd accumulation and transport in rice crops.

Microcavity-based semitransparent organic solar cells (ST-OSCs) have become a hot issue in the research field of green energy harvesting due to their wider potential applications in colored photovoltaic glass, buildingintegrated photovoltaics, and so on. However, for this kind of ST-OSCs, high photoelectric conversion efficiency (PCE) and high peak transmittance cannot usually be achieved simultaneously. To circumvent the problem, this paper proposes MgF2 microcavity with a structure of Au/Ag/MgF2/Ag for ST-OSCs so that high peak transmittance can be achieved at low cost of PCE. The device structure of ST-OSCs is Glass/ITO/ZnO/PTB7Th: IEICO-4F/MoO3/Au/Ag/MgF2/Ag. By combining the high transmittance of MgF2 microcavities with the low absorption of IEICO-4F in the blue light, a colorful ST-OSCs with high blue light transmittance can be obtained. The IEICO-4F in the active layer shows strong optical absorption in the near-infrared wavelength region, but weak absorption in the visible region. The results demonstrate that the peak transmittance of ST-OSCs reached a high value of 48% at 440 nm and the PCE reached 10.4%. Such a high peak transmittance is achieved while the PCE reduction compared to the control opaque device is about 5%. The PCE loss rate at each peak transmittance is the lowest among the reported values for the similar ST-OSCs devices. By adjusting the thickness of MgF2, STOSCs with different colors can be obtained, the peak transmittance of which is over 32% and the PCE loss rate is less than 7.25%. This report provides a new approach to solve the trade-off between efficiency and transmittance of ST-OSCs.

A microelectrode glucose biosensor based on a three-dimensional hybrid nanoporous platinum/graphene oxide nanostructure was developed for rapid glucose detection of tomato and cucumber fruits. The nanostructure was fabricated by a two-step modification method on a microelectrode for loading a larger amount of glucose oxidase. The nanoporous structure was prepared on the surface of the platinum microelectrode by electrochemical etching, and then graphene oxide was deposited on the prepared nanoporous electrode by electrochemical deposition. The nanoporous platinum/graphene oxide nanostructure had the advantage of improving the effective surface area of the electrode and the loading quantity of glucose oxidase. As a result, the biosensor achieved a wide range of 0.1-20.0 mmol/L in glucose detection, which had the ability to accurately detect the glucose content. It was found that the three-dimensional hybrid nanostructure on the electrode surface realized the rapid direct electrochemistry of glucose oxidase. Therefore, the biosensor achieved high glucose detection sensitivity (11.64 mu A center dot L/(mmol center dot cm2), low detection limit (13 mu mol/L) and rapid response time (reaching 95% steady-state response within 3 s), when calibrating in glucose standard solution. In agricultural application, the as-prepared biosensor was employed to detect the glucose concentration of tomato and cucumber samples. The results showed that the relative deviation of this method was less than 5% when compared with that of high-performance liquid chromatography, implying high accuracy of the presented biosensor in glucose detection in plants.