Search

Soil organic carbon (SOC) is important in the global carbon cycle. Accurate estimation of SOC content in cultivated land is a prerequisite for evaluating the carbon sequestration potential and quality of soils. However, existing SOC prediction studies based on hyperspectral remote sensing neglect the spectral response of the physical properties of surface soil, leading to inadequate model generalization. With the exponential growth of remote sensing data, the development of pixel-level soil spectral correction methods based on multi-source remote sensing data has become an interesting and challenging topic. This method aims to minimize the effect of soil physical properties on spectra, thus addressing the poor spatiotemporal transferability of SOC prediction models due to uncertain variations in surface soil physical properties. In this study, a soil spectral correction strategy is constructed using satellite hyperspectral image (HSI) and synthetic aperture radar (SAR) images through multi-order polynomial regression and convolutional neural networks. This strategy considers soil physical variables such as soil moisture (SM) content and root mean square height (RMSH) of soil surface roughness. The soil spectral correction model and SOC content prediction model were established using 80 soil samples collected from Site 1. Afterward, the performance and transferability of both models were verified using the remaining 25 samples from Site 1 and 50 samples from Site 2. The results showed that: 1) The effect of SM and RMSH on the soil pixel spectrum can be significantly reduced after correcting HSI using soil spectral correction strategy. The correlation coefficients between the corrected pixel spectrum and the ground-based spectrum increase by over 60 % compared with those between the original spectrum and the ground-based spectrum. 2) Soil spectral correction improves the prediction accuracy and mapping capability of HSI for SOC content, with the highest RP2 of 0.743 and RMSEP of 3.455 g/kg at Site 1. 3) Compared with the original HSI-based SOC prediction model, the soil spectral correction strategy based on multi-order polynomial and convolutional neural network reduced the RMSEP of SOC prediction results at Site 2 by 5.082 g/kg and 5.454 g/kg, and the RP2 increased by 0.390 and 0.409, respectively. 4) When predicting SOC content from raw HIS, SM and RMSH contribute to more than 60 % of the bias, with SM having a larger bias than RMSH. The findings of this study emphasize the influence of soil physical properties on SOC prediction and contribute to the existing research on SOC mapping using HSI and SAR data.

Although nitrogen deficiency and sucrose are linked to anthocyanin synthesis, the potential role of sucrose in regulating anthocyanin biosynthesis under low nitrogen conditions (LN) in purple lettuce (Lactuca sativa L.) remains unclear. We found that adding exogenous sucrose enhanced anthocyanin biosynthesis but significantly inhibited lettuce growth at high concentrations. Optimal results were obtained using 1 mmol/L sucrose in a low-nitrogen nutrient solution (LN + T1). Chlorophyll fluorescence imaging indicated that the addition of exogenous sucrose induced mild stress. Meanwhile, the activities of antioxidant enzymes (SOD, CAT, and POD) and antioxidant capacity were both enhanced. The mild stress activated the antioxidant system, thereby promoting the accumulation of anthocyanins induced by exogenous sucrose. LN + T1 (low nitrogen nutrient solution supplemented with 1 mmol/L sucrose) up-regulated enzyme genes in the biosynthetic pathway of anthocyanins, including phenylalanine ammonia-lyase (PAL), chalcone synthase (CHS), dihydroflavonol reductase (DFR), flavanone 3-hydroxylase (F3H), flavonoid 3′-hydroxylase (F3′H), flavone synthase II (FNSII), and anthocyanidin synthase (ANS). Additionally, various transcription factors such as AP2/ERF, MYB, bHLH, C2H2, NAC, C2C2, HB, MADS, bZIP, and WRKY were found to be up-regulated. This study elucidates the regulatory mechanism of anthocyanin metabolism in response to the addition of exogenous sucrose under low nitrogen conditions and provides a nutrient solution formula to enhance anthocyanin content in modern, high-quality agricultural cultivation.

Soil organic matter (SOM) is important for the global carbon cycle, and hyperspectral remote sensing has proven to be a promising method for fast SOM content estimation. However, because of the neglect of the spectral response of soil physical properties, the accuracy and spatiotemporal transferability of the SOM prediction model are poor. This study aims to improve the spatiotemporal transferability of the SOM prediction model by alleviating the coupling effect of soil physical properties on spectra. Based on satellite hyperspectral images and soil physical variables, including soil moisture (SM), soil surface roughness (root-mean-square height, RMSH), and soil bulk weight (SBW), a soil spectral correction model was established based on the information unmixing method. Two important grain-producing areas in Northeast China were selected as study areas to verify the performance and transferability of the spectral correction model and SOM content prediction model. The results showed that soil spectral corrections based on fourth-order polynomials and the XG-Boost algorithm had excellent accuracy and generalization ability, with residual predictive deviations (RPDs) exceeding 1.4 in almost all the bands. In addition, when the soil spectral correction strategy was adopted, the accuracy of the SOM prediction model and the generalization ability after the model migration were significantly improved. The SOM prediction accuracy based on the XG-Boost-corrected spectrum was the highest, with a coefficient of determination (R2) of 0.76, a root-mean-square error (RMSE) of 5.74 g/kg, and an RPD of 1.68. The prediction accuracy, R2 value, RMSE, and RPD of the model after the migration were 0.72, 6.71 g/kg, and 1.53, respectively. Compared with the direct migration prediction of the model, adopting the soil spectral correction model based on fourth-order polynomials and XG-Boost reduced the RMSE of the SOM prediction results by 57.90% and 60.27%, respectively. This performance comparison highlighted the advantages for considering soil physical properties in regional-scale SOM predictions.

The degradation of water quality and decline in purification capacity of lakeshore zones due to anthropogenic activities and climate change is a growing concern in China. The identification of the critical width of the lakeshore zone remains a challenge due to natural geographic features and pollutant types, that is why a general identification approach has yet to be developed. To facilitate the planning of lakeshore restoration plans, it becomes necessary to conduct studies focusing on the development of relationships between water quality and landscape factors within the lakeshore zone in different regions. In this study, spatio-temporal patterns of water quality of 49 lakes in Western Jilin Province, China, were determined through field monitoring from 2015 to 2019. Multivariate statistical methods were applied to quantitatively identify the relationships between lakes water quality and landscape factors within lakeshore zones of different widths. The results indicated that nitrogen (N) contributed more to eutrophication, while fluoride concentrations were found to be abnormally high. Furthermore, the width of the lakeshore zone was found to have a significant impact on water quality, with a critical width of 150 m having the greatest effect. Cropland and saline land explained almost 50% of the water quality variability throughout different seasons. The results also revealed that dual control of N and phosphorus (P) will be required to prevent eutrophication in the study area. Agricultural activities and severe soil salinization were identified as the main causes of diffuse pollution. The establishment of a width threshold identification framework for lakeshore zones is not only of great significance for development of scientific and acceptable restoration plans for lakeshore vegetation filters in ecologically vulnerable areas of western Jilin, but should also provide an effective and user-friendly tool for implementing diffuse pollution control.

The activation function plays a key role in influencing the performance and training dynamics of neural networks. There are hundreds of activation functions widely used as rectified linear units (ReLUs), but most of them are applied to complex and large neural networks, which often have gradient explosion and vanishing gradient problems. By studying a variety of non-monotonic activation functions, we propose a method to construct a non-monotonic activation function, x·Φ(x), with Φ(x) [0, 1]. With the hardening treatment of Φ(x), we propose an adaptive non-monotonic segmented activation function, called the adaptive quadratic linear unit, abbreviated as AQuLU, which ensures the sparsity of the input data and improves training efficiency. In image classification based on different state-of-the-art neural network architectures, the performance of AQuLUs has significant advantages for more complex and deeper architectures with various activation functions. The ablation experimental study further validates the compatibility and stability of AQuLUs with different depths, complexities, optimizers, learning rates, and batch sizes. We thus demonstrate the high efficiency, robustness, and simplicity of AQuLUs.

The human population is growing at an extremely rapid rate, the demand of food supplies for the survival and sustainability of life is a gleaming challenge. Each living being in the planet gets bestowed with the healthy food to remain active and healthy. Agriculture is a domain which is extremely important as it provides the fundamental resources for survival in terms of supplying food and thus the economy of the entire world is highly dependent on agricultural production. The agricultural production is often affected by various environmental and geographical factors which are difficult to avoid being part of nature. Thus, it requires proactive mitigation plans to reduce any detrimental effect caused by the imbalance of these factors. Precision agriculture is an approach that incorporates information technology in agriculture management, the needs of crops and farming fields are fulfilled to optimized crop health and resultant crop production. The proposed study involves an ambient intelligence-based implementation using machine learning to classify diseases in tomato plants based on the images of its leaf dataset. To analytically evaluate the performance of the framework, a publicly available plant-village dataset is used which is transformed to appropriate form using one-hot encoding technique to meet the needs of the machine learning algorithm. The transformed data is dimensionally reduced by Principal Component Analysis (PCA) technique and further the optimal parameters are selected using Spider Monkey Optimization (SMO) approach. The most relevant features as selected using the Hybrid PCA-SMO technique fed into a Deep Neural Networks (DNN) model to classify the tomato diseases. The optimal performance of the DNN model after implementing dimensionality reduction by Hybrid PCA-SMO technique reached at 99% accuracy was achieved in training and 94% accuracy was achieved after testing the model for 20 epochs. The proposed model is evaluated based on accuracy and loss rate metrics; it justifies the superiority of the approach.

The information acquisition about potassium, which affects the quality and yield of crops, is of great significance for crop nutrient management and intelligent decision making in smart agriculture. This article proposes a method for predicting the rice leaf potassium content (LKC) using spectral characteristics and random forests (RF). The method screens spectral characteristic variables based on the linear correlation analysis results of rice LKC and four transformed spectra (original reflectance (R), first derivative reflectance (FDR), continuum-removed reflectance (CRR), and normalized reflectance (NR)) of leaves and the PCA dimensionality reduction results of vegetation indices. Following a second screening of the correlated single band and vegetation index variables of the four transformed spectra, the RF is used to obtain the mixed variable (MV), and regression models are developed to achieve an accurate prediction of rice LKC. Additionally, the effect of potassium spectral sensitivity bands, indices, spectral transformation form, and different modeling methods on rice LKC prediction accuracy is assessed. The results showed that the mixed variable obtained with the second screening using the random forest feature selection method could effectively improve the prediction accuracy of rice LKC. The regression models based on the single band variables (BV) and the vegetation index variables (IV), FDR–RF and IV–RF, with R2 values of 0.62301 and 0.7387 and RMSE values of 0.24174 and 0.15045, respectively, are the best models. In comparison to the previous two models, the MV–RF validation had a higher R2 and a lower RMSE, reaching 0.77817 and 0.14913, respectively. It can be seen that the RF has a better processing ability for the MV that contains vegetation indices and IV than for the BV. Furthermore, the results of different variable screening and regression analyses also revealed that the single band’s range of 1402–1428 nm and 1871–1907 nm, as well as the vegetation indices constituted of reflectance 1799–1881 nm and 2276–2350 nm, are of great significance for predicting rice LKC. This conclusion can provide a reference for establishing a universal vegetation index related to potassium.

Regulating plant factories is crucial for optimal plant growth and yield. Although LEDs (light-emitting diode) are called cold light sources, more than 80% of the heat is still emitted into the surrounding environment. In high-density vertical agricultural facilities, the crop canopy is positioned close to the light source to maximize light absorption and promote plant growth. LED heat dissipation can cause disturbances in the microclimate of crop canopies, which can lead to tip burn disease in plant crops and result in economic losses for plant factories. CFD (computational fluid dynamics) is used as the main technical tool to simulate and optimize the environment of agricultural facilities. This study utilized Star-ccm+ to simulate the microclimate of plant factories under different light treatments. Uniformity coefficient UI and disturbance coefficient θ were proposed to quantitatively analyze LED heat dissipation’s impact on microclimate. In the T5 treatment group, which had a PPFD of 350 μmol/m2·s in the growth zone and 250 μmol/m2·s in the seedling zone, the relative humidity (RH), airflow, and temperature uniformity coefficients UI were 0.6111, 0.3259, and 0.5354, respectively, with corresponding disturbance coefficients θ of 0.0932, 0.1636, and 0.1533. This study clarifies the degree of perturbation caused by LED heat dissipation on microclimate, providing a theoretical basis for regulating plant factory light and promoting sustainability.

In this study, the feasibility of classifying soybean frogeye leaf spot (FLS) is investigated. Leaf images and hyperspectral reflectance data of healthy and FLS diseased soybean leaves were acquired. First, image processing was used to classify FLS to create a reference for subsequent analysis of hyperspectral data. Then, dimensionality reduction methods of hyperspectral data were used to obtain the relevant information pertaining to FLS. Three single methods, namely spectral index (SI), principal component analysis (PCA), and competitive adaptive reweighted sampling (CARS), along with a PCA and SI combined method, were included. PCA was used to select the effective principal components (PCs), and evaluate SIs. Characteristic wavelengths (CWs) were selected using CARS. Finally, the full wavelengths, CWs, effective PCs, SIs, and significant SIs were divided into 14 datasets (DS1-DS14) and used as inputs to build the classification models. Models' performances were evaluated based on the classification accuracy for both the overall and individual classes. Our results suggest that the FLS comprised of five classes based on the proportion of total leaf surface covered with FLS. In the PCA and SI combination model, 5 PCs and 20 SIs with higher weight coefficient of each PC were extracted. For hyperspectral data, 20 CWs and 26 effective PCs were also selected. Out of the 14 datasets, the model input variables provided by five datasets (DS2, DS3, DS4, DS10, and DS11) were more superior than those of full wavelengths (DS1) both in support vector machine (SVM) and least squares support vector machine (LS-SVM) classifiers. The models developed using these five datasets achieved overall accuracies ranging from 91.8% to 94.5% in SVM, and 94.5% to 97.3% in LS-SVM. In addition, they improved the classification accuracies by 0.9% to 3.6% (SVM) and 0.9% to 3.7% (LS-SVM).

Mergers and acquisitions are basic channels for modern companies’ growth. With globalization speeding up, multinational companies increasingly take on M_A activities to strengthen global market positions and raise competitiveness. In recent years, M_A activities have played an important role in Chinese companies. Financial risk is inherent to M_A processes in cross-border companies. Also, more than 50% of Chinese companies did not achieve their M_A goals. Therefore, recognizing and controlling financial risk is essential. This paper analyses the financial risk from different perspectives and then provides suggestions by analysing a typical M_A case: Bohai Leasing merger with Seaco Company. Complete due diligence and clear M_A strategies, combination of various financing instrument, strategic paying methods and finance integration are some ways for controlling and decreasing finance risk.

Micro-basin tillage is a soil and water conservation practice that requires building individual earth blocks along furrows. In this study, plot experiments were conducted to assess the efficiency of micro-basin tillage on sloping croplands between 2012 and 2013 (5°and 7°). The conceptual, optimal, block interval model was used to design micro-basins which are meant to capture the maximum amount of water per unit area. Results indicated that when compared to the up-down slope tillage, micro-basin tillage could increase soil water content and maize yield by about 45% and 17%, and reduce runoff, sediment and nutrients loads by about 63%, 96% and 86%, respectively. Meanwhile, micro-basin tillage could reduce the peak runoff rates and delay the initial runoff-yielding time. In addition, micro-basin tillage with the optimal block interval proved to be the best one among all treatments with different intervals. Compared with treatments of other block intervals, the optimal block interval treatments increased soil moisture by around 10% and reduced runoff rate by around 15%. In general, micro-basin tillage with optimal block interval represents an effective soil and water conservation practice for sloping farmland of the black soil region.