Search

The increasing demand for food and rapid population growth have made advanced crop monitoring essential for sustainable agriculture. Deep learning models leveraging multispectral satellite imagery, like Sentinel-2, provide valuable solutions. However, transferring these models to diverse regions is challenging due to phenological differences in crop growth stages between training and target areas. This study proposes the Adaptive Month Matching (AMM) method to align the phenological stages of crops between training and target areas for enhanced transfer learning in cropland segmentation. In the AMM method, an optimal Sentinel-2 monthly time series is identified in the training area based on deep learning model performance for major crops common to both areas. A month-matching process then selects the optimal Sentinel-2 time series for the target area by aligning the phenological stages between the training and target areas. In this study, the training area covered part of the Mississippi River Delta, while the target areas included diverse regions across the US and Canada. The evaluation focused on major crops, including corn, soybeans, rice, and double-cropped winter wheat/soybeans. The trained deep learning model was transferred to the target areas, and accuracy metrics were compared across different time series chosen by various phenological alignment methods. The AMM method consistently demonstrated strong performance, particularly in transferring to rice-growing regions, achieving an overall accuracy of 98%. It often matched or exceeded other phenological matching techniques in corn segmentation, with an average overall accuracy across all target areas exceeding 79% for cropland segmentation.

The study aimed to evaluate the cold tolerance of various peach cultivars under diverse low-temperature conditions (−5, −10, −15, −20, −25, −30, and −35 °C). A comprehensive assessment of their responses to cold was performed by integrating LT50 values with membership functions and evaluating local adaptability among the selected peach cultivars. The findings revealed that as temperatures dropped, electrical conductivity (REC), malondialdehyde (MDA), and hydrogen peroxide (H2O2) levels initially rose, then fell, and subsequently increased once more. Soluble sugar (SS) and soluble protein (SP) concentrations peaked at −25 °C and showed a significant negative correlation with semi-lethal temperature (LT50). The expression of free proline varied among different samples. Combining physiological analyses with field adaptation correlation assessments, it was found that ‘Ziyan Ruiyang’ exhibited a relatively low LT50 value of −29.67 °C and a membership function degree of 0.76, suggesting robust field adaptation abilities. At the same time, ‘Ganlu Shumi’ demonstrated stable trends in H2O2 and MDA levels, maintaining them at relatively low concentrations; it also had the lowest LT50 value, the highest membership function score, and the highest survival rate. Consequently, this cultivar could be a valuable resource for enhancing cold resistance under low-temperature stress. In summary, by correlating LT50 values with membership functions and observing local adaptability in these peach cultivars, we have established reliable data that can serve as a basis for identifying potential cross-breeding parents to develop new cold-resistant varieties.

The increasing demand for food and rapid population growth have made advanced crop monitoring essential for sustainable agriculture. Deep learning models leveraging multispectral satellite imagery, like Sentinel-2, provide valuable solutions. However, transferring these models to diverse regions is challenging due to phenological differences in crop growth stages between training and target areas. This study proposes the Adaptive Month Matching (AMM) method to align the phenological stages of crops between training and target areas for enhanced transfer learning in cropland segmentation. In the AMM method, an optimal Sentinel-2 monthly time series is identified in the training area based on deep learning model performance for major crops common to both areas. A month-matching process then selects the optimal Sentinel-2 time series for the target area by aligning the phenological stages between the training and target areas. In this study, the training area covered part of the Mississippi River Delta, while the target areas included diverse regions across the US and Canada. The evaluation focused on major crops, including corn, soybeans, rice, and double-cropped winter wheat/soybeans. The trained deep learning model was transferred to the target areas, and accuracy metrics were compared across different time series chosen by various phenological alignment methods. The AMM method consistently demonstrated strong performance, particularly in transferring to rice-growing regions, achieving an overall accuracy of 98%. It often matched or exceeded other phenological matching techniques in corn segmentation, with an average overall accuracy across all target areas exceeding 79% for cropland segmentation. [ABSTRACT FROM AUTHOR]

Detecting binary changes in co-registered bitemporal hyperspectral images (HSIs) using deep learning methods is challenging due to the high dimensionality of spectral data and significant variations between images. To address this challenge, previous approaches often used dimensionality reduction methods separately from the change detection network, leading to less accurate results. In this study, we propose an end-to-end fully connected adversarial network (EFC-AdvNet) for binary change detection, which efficiently reduces the dimensionality of bitemporal HSIs and simultaneously detects changes between them. This is accomplished by extracting critical spectral features at the pixel level through a self-spectral reconstruction (SSR) module working in conjunction with an adversarial change detection (Adv-CD) module to effectively delineate changes between bitemporal HSIs. The SSR module employs a fully connected autoencoder for hyperspectral dimensionality reduction and spectral feature extraction. By integrating the encoder segment of the SSR module with the change detection network of the Adv-CD module, we create a generator that directly produces highly accurate change maps. This joint learning approach enhances both feature extraction and change detection capabilities. The proposed network is trained using a comprehensive loss function derived from the concurrent learning of the SSR and Adv-CD modules, establishing EFC-AdvNet as a robust end-to-end network for hyperspectral binary change detection. Experimental evaluations of EFC-AdvNet on three public hyperspectral datasets demonstrate that joint learning between the SSR and Adv-CD modules improves the overall accuracy (OA) by 5.44%, 10.43%, and 7.52% for the Farmland, Hermiston, and River datasets, respectively, compared with the separate learning approach. [ABSTRACT FROM AUTHOR]

This study investigates the application of 15 Quality Indicators (QIs) in clinical laboratories in Fujian Province, China, from 2018 to 2023. It identifies the main causes of laboratory errors and explores issues in the application of QIs, providing a reference for establishing provincial state-of-the-art and operational quality specifications (QSs). All clinical laboratories in Fujian Province were organized to submit general information and original QIs data through the online External Quality Assessment (EQA) system of the National Clinical Laboratory Center (NCCL) for a survey of 15 QIs. Data from 2018 to 2023 were downloaded for statistical analysis, and the current QSs for the 15 QIs in Fujian Province were compared and analyzed with those published by the International Federation of Clinical Chemistry and Laboratory Medicine (IFCC) Working Group on Laboratory Errors and Patient Safety (WG-LEPS). QIs data from 542 clinical laboratories were collected. The survey on data sources showed that the number of laboratories recording QIs data using Laboratory Information Systems (LIS) increased annually, but the growth was modest and the proportion was less than 50 %. Among the laboratories using LIS to record QIs data, 133 continuously participated in this survey for six years, reporting different QIs. Over the six years, all reported QIs showed significant improvement or at least remained stable. The best median Sigma (σ) metrics were for the percentage of critical values notification and timely critical values notification, reaching 6σ, followed by the percentage of incorrect laboratory reports, with σ metrics ranging from 4.9σ to 5.1σ. In contrast, the percentage of tests covered by internal quality control (IQC) (1.5σ–1.7σ) and inter-laboratory comparison (0.1σ) remained consistently low. Compared to the QSs published by IFCC WG-LEPS, the QSs for the 15 QIs in Fujian Province in 2023 were stricter or roughly equivalent, except for the percentage of incorrect laboratory reports (Fujian Province: 0–0.221, IFCC WG-LEPS: 0–0.03). 1. The application of QIs has significantly improved the quality of testing in clinical laboratories in Fujian Province, but the percentage of tests covered by IQC and inter-laboratory comparison remain low; 2. Effective application of QIs requires the establishment of comprehensive LIS, unified calculation standards, and other supporting measures. [ABSTRACT FROM AUTHOR]

The study aimed to evaluate the cold tolerance of various peach cultivars under diverse low-temperature conditions (−5, −10, −15, −20, −25, −30, and −35 °C). A comprehensive assessment of their responses to cold was performed by integrating LT50 values with membership functions and evaluating local adaptability among the selected peach cultivars. The findings revealed that as temperatures dropped, electrical conductivity (REC), malondialdehyde (MDA), and hydrogen peroxide (H2O2) levels initially rose, then fell, and subsequently increased once more. Soluble sugar (SS) and soluble protein (SP) concentrations peaked at −25 °C and showed a significant negative correlation with semi-lethal temperature (LT50). The expression of free proline varied among different samples. Combining physiological analyses with field adaptation correlation assessments, it was found that 'Ziyan Ruiyang' exhibited a relatively low LT50 value of −29.67 °C and a membership function degree of 0.76, suggesting robust field adaptation abilities. At the same time, 'Ganlu Shumi' demonstrated stable trends in H2O2 and MDA levels, maintaining them at relatively low concentrations; it also had the lowest LT50 value, the highest membership function score, and the highest survival rate. Consequently, this cultivar could be a valuable resource for enhancing cold resistance under low-temperature stress. In summary, by correlating LT50 values with membership functions and observing local adaptability in these peach cultivars, we have established reliable data that can serve as a basis for identifying potential cross-breeding parents to develop new cold-resistant varieties. [ABSTRACT FROM AUTHOR]

Objectives: Compliance is crucial for patients to control and manage their high blood pressure. This study assesses the compliance levels of hypertensive patients in China and explores the factors influencing compliance. Design: A descriptive, cross‐sectional design was conducted. Sample: A total of 371 hypertensive patients were recruited from six County hospitals and 12 township health centers in Zhejiang Province, China. Measure: Patient compliance was measured using the Hypertensive Patient Scale (CHPS). Independent‐sample T‐test or variance analysis was applied to analyze CHPS scores by sociodemographic factors, and linear regression was used to explore the significant correlates of the total CHPS score. Results: The total score of CHPS was 50.18 ± 6.12. Among the seven domains, drug treatment and lifestyle had the highest and lowest average scores, 3.59 ± 0.87 and 2.74 ± 0.73, respectively. The total score of CHPS positively associated with age (β = 0.075, p = 0.028), > 7 years of hypertension (β = 1.896, p = 0.022; Ref: < 3 years), and negatively associated with males (β = −2.224, p = 0.001; Ref: female) and rural area (β = −2.008, p = 0.007; Ref: urban area). Conclusion: These findings highlight the importance of related measurements of the local "health‐oriented" healthcare system. Primary health professionals should strengthen their health behavior intervention capacity and improve hypertension management among their patients. [ABSTRACT FROM AUTHOR]