Random wave-induced onshore scour characteristics around submerged breakwaters using a stochastic method

This paper provides a stochastic method by which the two-dimensional onshore scour characteristics along the base of submerged breakwaters exposed to normally incident random waves on both sloping and horizontal sandy seabed can be derived. Here the formulas for the regular wave-induced scour characteristics provided by Young and Testik (2009) are used. These formulas are combined with describing the waves as a stationary Gaussian narrow-band random process to derive the random wave-induced onshore scour characteristics; the maximum scour depth, the scour length, and the distance of the maximum scour depth location from the onshore breakwater face. An example of calculation is also provided.     

Prediction of undrained shear strength using extreme gradient boosting and random forest based on Bayesian optimization

Accurate assessment of undrained shear strength(USS)for soft sensitive clays is a great concern in geotechnical engineering practice.This study applies novel data-driven extreme gradient boosting(XGBoost)and random forest(RF)ensemble learning methods for capturing the relationships between the USS and various basic soil parameters.Based on the soil data sets from TC304 database,a general approach is developed to predict the USS of soft clays using the two machine learning methods above,where five feature variables including the preconsolidation stress(PS),vertical effective stress(VES),liquid limit(LL),plastic limit(PL)and natural water content(W)are adopted.To reduce the dependence on the rule of thumb and inefficient brute-force search,the Bayesian optimization method is applied to determine the appropriate model hyper-parameters of both XGBoost and RF.The developed models are comprehensively compared with three comparison machine learning methods and two transformation models with respect to predictive accuracy and robustness under 5-fold cross-validation(CV).It is shown that XGBoost-based and RF-based methods outperform these approaches.Besides,the XGBoostbased model provides feature importance ranks,which makes it a promising tool in the prediction of geotechnical parameters and enhances the interpretability of model.     

基于机器学习的两个代表城市上呼吸道感染与气象要素关系及其发病风险预测研究

选取华南地区深圳市、西南地区攀枝花市两个不同气候区的当地医院上呼吸道感染发病逐日就诊病例数据和同期气象数据，采用随机森林方法和RNN（Recurrent neural network）深度学习方法，通过对两地上呼吸道感染发病特征及其与气象条件关系进行细致研究，分别构建了两地上呼吸道感染发病风险预测模型。研究结果表明：(1)深圳市上呼吸道感染就诊人数峰值每年出现在6-8月期间，谷值出现在1-2月期间，呈现以热不舒适的效应为主；而攀枝花市上呼吸道感染就诊人数峰值则出现在每年11月到次年的1月期间，谷值出现在每年3-7月期间，呈现以冷不舒适效应为主。(2)逐日平均气温的变化对两地上呼吸道感染发病的影响最明显，当日平均气温高于25℃或者低于10℃时，两地上呼吸道感染发病风险明显上升。(3)日平均风速影响次之，它与日平均相对湿度和日平均气温一起，通过对气候舒适度产生影响，进而影响上人群上呼吸道感染发病情况。(4)在对上呼吸道感染与气象要素关联性分析及预测方法优选的基础上，基于RNN深度学习方法构建的两城市上呼吸道感染发病风险预测模型，可为当地相关疾病风险预测及防控提供重要科技支持。