市政排水泵站雨天出流污染画像分析

为从数据视角识别中心城区排水泵站雨天出流污染的分类特征,采用基于无监督机器学习的K-means聚类算法对上海市中心城200余座泵站的设施数据和行为数据进行指标提取和画像分析。结果表明：中心城泵站分为低频高质型泵站、高频低质型泵站、高频高污型泵站和中频中污型泵站4类画像,建议优先加强第3类高频高污型泵站和第4类中频中污型泵站的出流污染管控,并根据分群特点提出了各类画像对应的管控对策。该研究结果具有较好的解释性和应用价值,可为基于数据分析的分类管控、管网提质增效实施优先级策略制定提供参考。     

The importance of context for effective public engagement: learning from the governance of waste

This paper takes a new look at the importance of context – institutional and political – in effective public engagement processes. It does so through a rare comparative opportunity to examine the effectiveness of processes of public engagement in two UK waste authorities, where the same waste company was involved as both the primary contractor for the delivery of the waste management service (including new energy-from-waste facilities) and, furthermore, the same staff delivered the public engagement. Interrogating these cases affords the opportunity to place flesh on the bones of the sometimes ‘abstract’ skeleton of context. While engagement processes support effective local governance in an era of partnerships and deliberative democracy, the paper identifies that the methods adopted cannot be played out devoid of detailed understanding and response to local context, including the strength of partnership working between the public and private sector, the degree of political support for engagement, and the extent to which a traditional institutional paternalism still dominates.     

基于SA-ELM的爆破震动速度预测

针对爆破震动速度与其影响因素之间的复杂非线性,结合模拟退火算法(SA)的全局寻优性,提出了一种新的SA-ELM算法.以矿山周边建筑物爆破震动实测数据作为训练样本,选取总药量、最大段药量、测点与爆破点距离、地面震动特性、建筑物震动特性等8个影响因素作为输入变量,建立了爆破震动速度预测的SA-ELM模型.模型训练值和预测值与实测值的均方误差(MSE)分别为0.20和3.26,平均相对误差控制在5％以内,显示出该模型具有良好的训练精度和泛化能力.对比传统ELM模型,SA-ELM模型不但提高了精度和泛化能力,而且降低了隐层节点数变化对训练结果的影响,提高了模型的稳定性.     

基于GA-ELM浆体管道输送临界流速预测模型研究

针对浆体管道输送临界流速预测难度大、精确度低等技术难题,提出了基于极限学习机(ELM)的临界流速预测模型,用训练集对模型进行训练,以验证集预测值的均方误差作为适应度函数,利用遗传算法(GA)对ELM模型参数进行优化,应用优化得到的ELM模型对预测集进行预测。以某矿山为例,模型参数优化结果如下:隐含层节点数L为400,输入权值ai、偏置向量bi最优组合下预测结果适应度为0.0201。采用优化的ELM模型对预测集进行预测,预测结果的最大相对误差x=3.96%,平均相对误差y=1.58%,对比BP神经网络(x=12.95%)和SVM模型(x=3.19%),表明ELM模型更加精确、高效。     

Predicting the efficiency of arsenic immobilization in soils by biochar using machine learning

Arsenic(As)pollution in soils is a pervasive environmental issue.Biochar immobilization offers a promising solution for addressing soil As contamination.The efficiency of biochar in immobilizing As in soils primarily hinges on the characteristics of both the soil and the biochar.However,the influence of a specific property on As immobilization varies among different studies,and the development and application of arsenic passivation materials based on biochar often rely on empirical knowledge.To enhance immobilization efficiency and reduce labor and time costs,a machine learning(ML)model was employed to predict As immobilization efficiency before biochar application.In this study,we collected a dataset comprising 182 data points on As immobilization efficiency from 17 publications to con-struct three ML models.The results demonstrated that the random forest(RF)model out-performed gradient boost regression tree and support vector regression models in predictive performance.Relative importance analysis and partial dependence plots based on the RF model were conducted to identify the most crucial factors influencing As immobilization.These findings highlighted the significant roles of biochar application time and biochar pH in As immobilization efficiency in soils.Furthermore,the study revealed that Fe-modified biochar exhibited a substantial improvement in As immobilization.These insights can fa-cilitate targeted biochar property design and optimization of biochar application conditions to enhance As immobilization efficiency.