An Interannual Transfer Learning Approach for Crop Classification in the Hetao Irrigation District, China

Crop type classification is critical for crop production estimation and optimal water allocation. Crop type data are challenging to generate if crop reference data are lacking, especially for target years with reference data missed in collection. Is it possible to transfer a trained crop type classification model to retrace the historical spatial distribution of crop types? Taking the Hetao Irrigation District (HID) in China as the study area, this study first designed a 10 m crop type classification framework based on the Google Earth Engine (GEE) for crop type mapping in the current season. Then, its interannual transferability to accurately retrace historical crop distributions was tested. The framework used Sentinel-1/2 data as the satellite data source, combined percentile, and monthly composite approaches to generate classification metrics and employed a random forest classifier with 300 trees for crop classification. Based on the proposed framework, this study first developed a 10 m crop type map of the HID for 2020 with an overall accuracy (OA) of 0.89 and then obtained a 10 m crop type map of the HID for 2019 with an OA of 0.92 by transferring the trained model for 2020 without crop reference samples. The results indicated that the designed framework could effectively identify HID crop types and have good transferability to obtain historical crop type data with acceptable accuracy. Our results found that SWIR1, Green, and Red Edge2 were the top three reflectance bands for crop classification. The land surface water index (LSWI), normalized difference water index (NDWI), and enhanced vegetation index (EVI) were the top three vegetation indices for crop classification. April to August was the most suitable time window for crop type classification in the HID. Sentinel-1 information played a positive role in the interannual transfer of the trained model, increasing the OA from 90.73% with Sentinel 2 alone to 91.58% with Sentinel-1 and Sentinel-2 together.

The value of lymphocyte count in determining the severity of COVID-19 and estimating the time for nucleic acid test results to turn negative.

Peripheral blood lymphocyte count is shown to be decreased in patients with COVID-19 in the early stage of the disease. The degree of lymphocyte count reduction is related to COVID-19 severity and could be used as an indicator to reflect the disease severity. Our aim was to investigate the value of lymphocyte count in determining COVID-19 severity and estimating the time for SARS-CoV-2 nucleic acid test results to turn negative. We retrospectively analyzed clinical data of 201 patients with severe and critical COVID-19. The patients were admitted to the West Campus of Union Hospital of Tongji Medical College of Huazhong University of Science and Technology. The data included age, gender, chronic disease, lymphocyte count, and SARS-CoV-2 nucleic acid test results. The age of patients in critically ill group was higher than in severely ill group (p = 0.019). The lymphocyte count of critically ill patients was lower than of severely ill patients. The cutoff value of lymphocyte count to distinguish between the critically ill and the severely ill was 0.735 × 109/L (p = 0.001). The cutoff value of lymphocyte count for SARS-CoV-2 nucleic acid test results turning negative in severely and critically ill patients with chronic diseases (hypertension, diabetes, and coronary heart disease) was 0.835 × 109/L (p = 0.017). The cutoff value of lymphocyte count for SARS-CoV-2 nucleic acid test results turning negative in severely and critically ill male patients was 0.835 × 109/L (p < 0.0001). Lymphocyte count could be an effective indicator to predict COVID-19 severity. It may also be useful in determining the time for nucleic acid test results to turn negative in COVID-19 patients with underlying chronic diseases or male COVID-19 patients with severe and critical conditions.

Clinical characteristics of patients with COVID-19 presenting with gastrointestinal symptoms as initial symptoms: Retrospective case series.

BACKGROUND: A large number of pneumonia cases due to coronavirus disease 2019 (COVID-19) have been first reported in China. Meanwhile, the virus is sweeping all around the world and has infected millions of people. Fever and pulmonary symptoms have been noticed as major and early signs of infection, whereas gastrointestinal symptoms were also observed in a significant portion of patients. The clinical investigation of disease onset was underestimated, especially due to the neglection of cases presenting with gastrointestinal symptoms. AIM: To characterize the clinical features of coronavirus-infected patients with gastrointestinal symptoms as initial symptoms. METHODS: This is a retrospective, single-center case series of the general consecutive hospitalized patients with confirmed COVID-19 at Wuhan Union Hospital from February 2, 2020 to February 13, 2020. According to their initial symptoms, these patients were classified into two groups. Patients in group one presented with pulmonary symptoms (PS) as initial symptoms, and group two presented with gastrointestinal symptoms (GS). Epidemiological, demographic, clinical, laboratory, and treatment data were collected for analysis. RESULTS: Among the 50 patients recruited, no patient has been admitted to intensive care units, and no patient died during the study. The duration of hospitalization was longer in the GS group than in the PS group (12.13 ± 2.44 vs 10.00 ± 2.13, P < 0.01). All of the 50 patients exhibited decreased lymphocytes. However, lymphocytes in the GS group were significantly lower compared to those in the PS group (0.94 ± 0.06 vs 1.04 ± 0.15, P < 0.01). Procalcitonin and hs-CRP were both significantly higher in the GS group than in the PS group. Accordingly, the duration of viral shedding was significantly longer in the GS group compared to the PS group (10.22 ± 1.93 vs 8.15 ± 1.87, P < 0.01). CONCLUSION: COVID-19 patients presenting with gastrointestinal symptoms as initial symptoms need more days of viral shedding and hospitalization than the patients presenting with pulmonary symptoms.