Search

Soil salinization poses a critical challenge to global food security, impacting plant growth, development, and crop yield. This study investigates the efficacy of deep learning techniques alongside chlorophyll fluorescence (ChlF) imaging technology for discerning varying levels of salt stress in soybean seedlings. Traditional methods for stress identification in plants are often laborious and time-intensive, prompting the exploration of more efficient approaches. A total of six classic convolutional neural network (CNN) models—AlexNet, GoogLeNet, ResNet50, ShuffleNet, SqueezeNet, and MobileNetv2—are evaluated for salt stress recognition based on three types of ChlF images. Results indicate that ResNet50 outperforms other models in classifying salt stress levels across three types of ChlF images. Furthermore, feature fusion after extracting three types of ChlF image features in the average pooling layer of ResNet50 significantly enhanced classification accuracy, achieving the highest accuracy of 98.61% in particular when fusing features from three types of ChlF images. UMAP dimensionality reduction analysis confirms the discriminative power of fused features in distinguishing salt stress levels. These findings underscore the efficacy of deep learning and ChlF imaging technologies in elucidating plant responses to salt stress, offering insights for precision agriculture and crop management. Overall, this study demonstrates the potential of integrating deep learning with ChlF imaging for precise and efficient crop stress detection, offering a robust tool for advancing precision agriculture. The findings contribute to enhancing agricultural sustainability and addressing global food security challenges by enabling more effective crop stress management. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) technology has become an important means of flood monitoring because of its large coverage, repeated observation, and all-weather and all-time working capabilities. The commonly used thresholding and change detection methods in emergency monitoring can quickly and simply detect floods. However, these methods still have some problems: (1) thresholding methods are easily affected by low backscattering regions and speckle noise; (2) changes from multi-temporal information include urban renewal and seasonal variation, reducing the precision of flood monitoring. To solve these problems, this paper presents a new flood mapping framework that combines semi-automatic thresholding and change detection. First, multiple lines across land and water are drawn manually, and their local optimal thresholds are calculated automatically along these lines from two ends towards the middle. Using the average of these thresholds, the low backscattering regions are extracted to generate a preliminary inundation map. Then, the neighborhood-based change detection method combined with entropy thresholding is adopted to detect the changed areas. Finally, pixels in both the low backscattering regions and the changed regions are marked as inundated terrain. Two flood datasets, one from Sentinel-1 in the Wharfe and Ouse River basin and another from GF-3 in Chaohu are chosen to verify the effectiveness and practicality of the proposed method. [ABSTRACT FROM AUTHOR]

The challenge of analyzing microarray datasets is significantly compounded by the curse of dimensionality and the complexity of feature interactions. Addressing this, we propose a novel feature selection algorithm based on maximum conditional mutual information (MCMI) to identify a minimal feature subset that is maximally relevant and non-redundant. This algorithm leverages a greedy search strategy, prioritizing both feature quality and classification performance. Experimental results on high-dimensional microarray datasets demonstrate our algorithm's superior ability to reduce dimensionality, eliminate redundancy, and enhance classification accuracy. Compared to existing filter feature selection methods, our approach exhibits higher adaptability and intelligence. [ABSTRACT FROM AUTHOR]

Urban tailwater typically has a low carbon-to-nitrogen ratio and adding external carbon sources can effectively improve the denitrification performance of wastewater. However, it is difficult to determine the dosage of additional carbon sources, leading to insufficient or excessive addition. Therefore, it is necessary to prepare solid slow-release carbon source (SRC) materials to solve the difficulty in determining the dosage of carbon sources. This study selected two SRCs of slow-release carbon source 1 (SRC1) and slow-release carbon source 2 (SRC2), with good slow-release performance after static carbon release and batch experiments. The composition of SRC1 was: hydroxypropyl methylcellulose/disodium fumarate/polyhydroxy alkanoate (HPMC/DF/PHA) at a ratio of 3:2:4, with an Fe3O4 mass fraction of 3%. The composition of SRC2 was: HPMC/DF/PHA with a ratio of 1:1:1 and an Fe3O4 mass fraction of 3%. The fitted equations of carbon release curves of SRC1 and SRC2 were y = 61.91 + 7190.24e−0.37t and y = 47.92 + 8770.42e−0.43t, respectively. The surfaces of SRC1 and SRC2 had a loose and porous morphological structure, which could increase the specific surface area of materials and be more conducive to the adhesion and metabolism of microorganisms. The experimental nitrogen removal by denitrification with SRCs showed that when the initial total nitrogen concentration was 40.00 mg/L, the nitrate nitrogen (NO3−-N) concentrations of the SRC1 and SRC2 groups on the 10th day were 2.57 and 2.66 mg/L, respectively. On the 20th day, the NO3−-N concentrations of the SRC1 and SRC2 groups were 1.67 and 2.16 mg/L, respectively, corresponding to removal efficiencies of 95.83% and 94.60%, respectively. The experimental results indicated that SRCs had a good nitrogen removal effect. Developing these kinds of materials can provide a feasible way to overcome the difficulty in determining the dosage of carbon sources in the process of heterotrophic denitrification. [ABSTRACT FROM AUTHOR]

The present study was performed to investigate the effects of dietary supplementation with Lactobacillus plantarum (CGMCC1.557) on egg production and fecal microbiota composition in laying hens. Sixty Hy-Line Brown laying hens (18 weeks old) were randomly divided into two groups. The control group was fed a basal diet only, and the test group was fed basal diet supplemented with a final concentration of 1.0 × 109 CFU/mL during the 10-week experimental period. Egg production and fecal microbiota composition were both assessed in 28-week-old hens using high-throughput sequencing technology. The results showed that, compared with the control group, the test group exhibited increased laying and feed intake rates (p < 0.05). At the genus level, Lactobacillus was more abundant in the test group compared with the control group (p < 0.05). Conversely, Romboutsia was more abundant in the control group compared with the test group (p < 0.05). This study provides us with an insight into the potential use of L. plantarum as a food supplement in the laying hen industry. the study also provides us with a better understanding of the interplay between L. plantarum and the fecal microbiota of laying hens.

The control performance of the voltage source inverter will be reduced when it operates under complex microgrid (MG) conditions. Traditionally, problems such as high controller order and complex design may occur when robust control and secondary regulation are adopted for the inverters. Meanwhile, when the conventional adaptive control is adopted, the adaptive gain may be too high, resulting in increased sensitivity of the system to external disturbances. To address the above problems, a novel Narendra‐based adaptive anti‐disturbance control strategy for microgrid voltage source inverter is proposed in this paper. Firstly, a Narendra adaptive‐based controller is constructed, which enables the controller to adaptively adjust the system parameters to change the inverter output voltage quality. Secondly, the extended state observer (ESO) is introduced to observe and suppress the total disturbance of the system, which can make the system less sensitive and ensure the stability of the system operation. Thirdly, according to the Lyapunov stability theory, the Lyapunov function is chosen to prove the global asymptotic stability of the system, and an adaptive law is designed. Finally, the comparative experiment shows that the proposed control strategy based on Narendra adaptive anti‐disturbance can maintain excellent voltage control performance in complex working conditions, and then ensure that the inverter's output voltage always meets power quality standard in complex working conditions. [ABSTRACT FROM AUTHOR]