No abstract

No abstract

No abstract

Disasters are an unpredictable way to change land use and land cover. Improving the accuracy of mapping a disaster area at different time is an essential step to analyze the relationship between human activity and environment. The goals of this study were to test the performance of different processing procedures and examine the effect of adding normalized difference vegetation index (NDVI) as an additional classification feature for mapping land cover changes due to a disaster. Using Landsat ETM+ and OLI images of the Bento Rodrigues mine tailing disaster area, we created two datasets, one with six bands, and the other one with six bands plus the NDVI. We used support vector machine (SVM) and decision tree (DT) algorithms to build classifier models and validated models performance using 10-fold cross-validation, resulting in accuracies higher than 90%. The processed results indicated that the accuracy could reach or exceed 80%, and the support vector machine had a better performance than the decision tree. We also calculated each land cover type’s sensitivity (true positive rate) and found that Agriculture, Forest and Mine sites had higher values but Bareland and Water had lower values. Then, we visualized land cover maps in 2000 and 2017 and found out the Mine sites areas have been expanded about twice of the size, but Forest decreased 12.43%. Our findings showed that it is feasible to create a training data pool and use machine learning algorithms to classify a different year’s Landsat products and NDVI can improve the vegetation covered land classification. Furthermore, this approach can provide a venue to analyze land pattern change in a disaster area over time.

Background: The aim of this study was to assess the geographic disparity in anemia and whether stunting was associated with anemia in different geographic groups among school-aged children in China. Methods: 71,129 Han children aged 7, 9, 12, and 14 years old were extracted from the 2014 cycle of Chinese National Surveys on Children Constitution and Health. Anemia, anemia severity, and stunting were defined according to WHO definitions. Binary logistic regression models were used to estimate the association between anemia and stunting in different geographic groups. Results: The prevalence of anemia was significantly higher in girls (10.8%) than boys (7.0%). The highest anemia prevalence was in Group VII (lower class/rural, 12.0%). A moderate/severe prevalence of anemia was concentrated in Group VII and Group VIII (western/lower class/rural) for both sexes. The prevalence of anemia was higher in stunting boys than non-stunting boys in Group IV (lower class/city, χ 2 = 12.78, P = 0.002) and Group VII (χ 2 = 6.21, P = 0.018), while for girls, it was higher in stunting girls than their non-stunting peers only in Group II (upper class/large city, χ 2 = 4.57, P = 0.046). Logistic regression showed that the stunting children have 30% higher risk of anemia than non-stunting children after adjustment for age, sex and school (OR = 1.30, 95% CI: 1.05-1.60). Conclusion: A significant geographic disparity and an association between anemia and stunting among specific groups of school-aged children in China was demonstrated. Consequently, eliminating the geographic disparity and ameliorating stunting might contribute to the improvement of Chinese children's anemia. Specific guidelines and interventions are needed, especially for adolescent girls and the groups with serious anemia burden.