To further reduce the error rate of rainfall prediction, we used a new machine learning model for rainfall prediction and new feature engineering methods, and combined the satellite system’s method of observing rainfall with the machine learning prediction. Based on multivariate correlations among meteorological information, this study proposes a rainfall forecast model based on the Attentive Interpretable Tabular Learning neural network (TabNet). This study used self-supervised learning to help the TabNet model speed up convergence and maintain stability. We also used feature engineering methods to alleviate the uncertainty caused by seasonal changes in rainfall forecasts. The experiment used 5 years of meteorological data from 26 stations in the Beijing–Tianjin–Hebei region of China to verify the proposed rainfall forecast model. The comparative experiment proved that our proposed method improves the performance of the model, and that the basic model used is also superior to other traditional models. This research provides a high-performance method for rainfall prediction and provides a reference for similar data-mining tasks.
BackgroundHemoconcentration has been proposed as surrogate for changes in volume status among patients hospitalized with acute heart failure (AHF) and is associated with a favorable outcome. However, there is a dearth of research assessing the clinical outcomes of hospitalized patients with hemoconcentration, hemodilution and unchanged volume status.MethodsWe enrolled 510 consecutive patients hospitalized for AHF from April 2011 to July 2015. Hematocrit (HCT) levels were measured at admission and either at discharge or on approximately the seventh day of admission. Patients were stratified by delta HCT tertitles into hemodilution (ΔHCT ≤ − 1.6%), no change (NC, −1.6% < ΔHCT ≤1.5%) and hemoconcentration (ΔHCT >1.5%) groups. The endpoint was all-cause death, with a median follow-up duration of 18.9 months.ResultsHemoconcentration was associated with lower left ventricle ejection fraction, as compared with NC and hemodilution groups, while renal function at entry, New York Heart Association class IV, and in-hospital worsening renal function (WRF) were not significantly different across the three groups. After multivariable adjustment, hemoconcentration had a lower risk of mortality as compared with hemodilution [hazard ratio (HR) 0.39, 95% confidence interval (CI) 0.24–0.63, P < 0.001], or NC (HR 0.54, 95% CI 0.33–0.88, P = 0.015], while hemodilution and NC did not have significantly differ in mortality (HR 0.72, 95% CI 0.48–1.10, P = 0.130).ConclusionsIn patients hospitalized with AHF, an increased HCT during hospitalization is associated with a lower risk of all-cause mortality than a decreased or unchanged HCT. Furthermore, all-cause mortality does not differ significantly between patients with unchanged and decreased HCT values.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.