基于Bootstrap法和极限学习机的月降水区间预测

针对降水预测中的不确定性、随机性和已有的降水预测模型无法反映其不确定性信息的问题,提出一种基于Bootstrap法和极限学习机的月降水区间预测模型,将模型应用于栾川县白土站,对其进行不确定性分析,建立月降水区间预测模型,并通过可靠性和清晰度对其预测结果进行评价。结果表明,构建的区间预测模型相比传统的确定性点预测模型,能同时兼顾可靠性和准确性,为区域水资源利用和水旱灾害管理提供更全面有效的降水信息。

基于SMA-LSSVM的径流中长期预测

径流中长期预测对防洪减灾和提高水资源利用效率极为重要。为解决预测模型参数对预测精度的影响,提出一种基于黏菌算法(SMA)优化LSSVM的径流中长期预测模型。首先,选取5个标准测试函数,对比在不同维度条件下SMA和PSO算法的仿真结果;其次,利用SMA优化LSSVM的惩罚参数和核参数,并构建LSSVM、PSO-LSSVM对比模型;最后,通过漫湾水电站水库入库月径流和莺落峡水文站月径流预测实例对各模型进行验证。结果表明,SMA-LSSVM模型相比LSSVM、POS-LSSVM模型,对漫湾站月径流预测的均方误差分别降低了29.26%、7.42%,对莺落峡站月径流预测的均方误差分别降低了32.61%、6.61%,预测精度更高。提出的SMA-LSSVM模型综合预测性能更好,也为中长期径流预测提供了一种新方法。

Zebrafish model for assessing induced organ toxicity by Strychnos nux-vomica

OBJECTIVE:To assess the acute organ toxicity of Strychnos nux-vomica with zebrafish model visually.METHODS:To assess acute toxicity,we initially determined the lethal concentration after Strychnos nux-vomica treatment for 24 h.Zebrafish was treated with five concentrations Strychnos nux-≦vo LC10 for 24 h,and the effects ofmica on morphology,function of heart,central nervous system,liver,kidney and organ-specific cell death were assessed.Next,we assessed the reversibility of toxic effect.RESULTS:Strychnos nux-vomica has an effect on the different organs of zebrafish,including heart,central nervous system,liver,and kidney,and cadiotoxicity induced by Strychnos nux-vomica was reversible to some extent.CONCLUSION:Zebrafish model is suitable for confirming the toxic target organs for Chinese traditional medicine.