Integration of data analytics with cloud services for safer process systems,application examples and implementation challenges

Emerging sensors, computers, network technologies, and connected platforms result potentially in an immeasurable collection of data within plant operations. This creates the possibility of solving problems innovatively. Because most of the data appear to be unstructured or semi-structured, organizations shall design and adopt new strategies. Further, workflow architectures with data analytics are needed including machine learning tools and artificial intelligence techniques before proto-type solutions can be developed. We shall discuss several prospects of using (big) data analytics integrated with cloud services to produce solutions for improving plant operations. The paper outlines the vision and a systematic framework highlighting the data analytics lifecycle in the area of plant operation, process safety, and environmental protection. Four rather diverse example case studies are demonstrated including (1) deep learning-based predictive maintenance monitoring modeling, (2) Natural Language Processing (NLP) for mining text, (3) barrier assessment for dynamic risk mapping (DRA), and (4) correlation development for sustainability indicators. It further discusses the challenges in both research and implementation of proposed solutions in the industry. It is concluded that a well-balanced integrated approach including machine supporting decisions integrated with expert knowledge and available information from various key resources is required to enable more informed policy, strategic, and operational risk decision-making leading to safer, reliable and more efficient operations.     

Predation risk assessment by green frog (<Emphasis Type="Italic">Rana clamitans</Emphasis>) tadpoles through chemical cues produced by multiple prey

Many prey assess predation risk through predator chemical cues. Numerous studies have shown that (1) prey sometimes respond to chemical cues produced by heterospecifics and (2) that many species are capable of associative learning. This study extends this research by focusing on predation risk assessment and antipredator behavior in environments containing chemical cues produced by multiple prey species. The results show that green frog (Rana clamitans) tadpoles (1) assess risk from the chemical cue produced during predation by a heterospecific (gray tree frog, Hyla versicolor, tadpoles) and (2) can exhibit similarly strong behavioral responses to a mix of conspecific and heterospecific cues compared to conspecific cue alone, depending on their conditioning environment. I then discuss how the prey choice of the predators and the relative abundances of the prey species should influence the informational value of heterospecific cues.     

流域水质管理优化决策模型研究

针对目前流域水污染难以有效控制的局面,依据已有的流域水文、水动力、水质、水生态相关机理模拟模型的研究,在考虑了流域社会经济发展条件的基础上,构建了流域水质管理优化决策模型框架体系.基于该框架体系,本文从简单流域系统优化模型、模拟与优化联合模型和时空尺度复杂优化模型3个方面对流域优化决策模型的研究发展历程进行综述,并指出其各自在发展过程中所出现的问题.最后,提出了优化决策模型面临的瓶颈问题,并从模型结构简化和适应性管理两个方面提出了相关的解决思路.     

基于机器学习方法的上海市暴雨内涝灾情预测模型研究

本文基于区域灾害系统理论,综合考虑致灾因子、暴露度和脆弱性,提出了一套暴雨内涝灾情预测指标体系;在此基础上利用上海市应急联动中心110接报暴雨内涝灾情数据,构建了暴雨内涝灾情预测BP模型(Back Propagation Model)和XGBoost模型(Extreme Gradient Boosting Model),并对比分析了预测模型效果,实现对上海市暴雨过程内涝灾情数量预测;最后对内涝灾情影响等级进行阈值划分,以期为暴雨内涝影响预报与风险预警业务、服务及灾害管理提供技术支撑。结果表明:1)综合考虑致灾因子、暴露度、脆弱性指标且不经主成分分析降维的指标组合作为暴雨内涝灾情预测指标体系时,BP模型和XGBoost模型的预测精度最优;2)全量样本XGBoost模型总体表现最优,暴雨内涝灾情的右偏分布和内涝灾情的异常高值均对XGBoost模型预测误差有不同程度的贡献;3)综合评价法在历史灾情百分位法和模拟灾情百分位法基础上,结合多年业务实践经验和用户对于110灾情的处置承受力对暴雨内涝灾情进行阈值划分,在实际应用中具有一定参考意义。     

DEHP暴露对小鼠神经行为学及脑脂质过氧化物的影响

为研究增塑剂邻苯二甲酸二乙基己酯(Di-2-ethylhexyl phthalate,DEHP)对脑组织造成氧化损伤以及对小鼠神经行为(主要包括学习、记忆能力与情绪)的影响.将24只雄性昆明小鼠随机分成4组,每组6只,分别为对照组(生理盐水),低浓度染毒组(5mg·kg-1DEHP,L组),中浓度染毒组(50mg·kg-1DEHP,M组),高浓度染毒组(500mg·kg-1DEHP,H组).利用Y型电迷宫检验小鼠的学习记忆能力变化,利用悬尾实验和强迫游泳实验检测小鼠抑郁行为的变化.然后取出脑组织,检验活性氧簇(ROS)及丙二醛(MDA)含量.数据显示,染毒组小鼠的学习记忆及行为学控制能力明显低于对照组(p<0.05),并且随DEHP浓度的增大小鼠的学习记忆及行为学控制能力降低.DEHP低、中、高剂量染毒组与对照组氧化应激反应均具有显著性(p<0.05),且呈剂量效应关系.因此,DEHP可导致小鼠学习记忆能力下降、抑郁情绪增加,其分子机制可能涉及DEHP对脑组织造成的氧化损伤.     

基于机器学习的浮标实时自动化赤潮预警研究

实现赤潮预警对于减轻海洋环境灾害、避免海洋产业特别是海洋渔业重大经济损失具有重要意义。针对当前水文监测数据海量却难以实现实时自动化监测与预警,特别是难以利用传统监测手段实现对危害更大的赤潮的精准实时预测这一显著问题,提出利用浮标数据作为依据,借助机器学习在大数据分析和智能决策方面的优势,建立一种新颖的双重递进式赤潮预警机制的方法。首先,通过相关算法分析历史数据,以确认赤潮初步预警阈值;其次,对叶绿素a、pH、溶解氧等重要监测指标的当前和阶段性变化进行初步分析,判断是否达到预警触发条件;然后,进一步联合分类、回归、聚类、神经网络等机器学习相关方法,对数据进行深度挖掘;最后,通过这种递进式的机制对短期内是否会发生赤潮作出判断,以实现赤潮自动化预警预报。在此基础上,利用宁波梅山湾实际监测数据,证实了该方法在赤潮实时自动化预警中的有效性。     

荧光传感器阵列检测农药污染物研究进展

农药的滥用已造成严重的环境污染,因此开发高效、简便和灵敏的农药检测技术是环境科学领域的研究焦点.荧光传感检测因其灵敏度高,检出限低,操作简单,成本低,目前已逐渐成为农药快速定量检测的一个发展方向.然而,在真实样品检测环境中,污染物不是单独存在的,常伴随结构或化学性质上与待检测分析物相似的污染物进行干扰.而基于阵列的荧光...     

Do organizations spend wisely on employees? Effects of training and development investments on learning and innovation in organizations

The present study examines the effects of training and development on organizational innovation. We specifically suggest that the training and development investments of an organization affect its innovative performance by promoting various learning practices. We empirically tested our hypothesis by using time‐lagged, multi‐source data collected from 260 Korean companies that represent diverse industries. Our analysis showed that corporate expenditure for internal training predicts interpersonal and organizational learning practices, which, in turn, increase innovative performance. The data also revealed that the positive relationship between interpersonal and organizational learning practices and innovative performance is stronger within organizations that have stronger innovative climates. By contrast, investment in employee development through financial support for education outside an organization poses a significant negative effect on its innovative performance and no significant effect on learning practices. The present study provides a plausible explanation for a mechanism through which the investment of an organization in employees enhances its innovative performance. Copyright © 2013 The Authors. Journal of Organizational Behavior published by John Wiley & Sons, Ltd.     

Teaching industrial ecology and environmental management in Second Life

Second Life is a virtual, open-access, and user-generated environment that has served as a platform for hosting everything from rock concerts to scientific conferences. Many institutions have also used Second Life as an educational tool, for example by, showcasing scientific exhibits or embedding video and images for learning purposes. Here we discuss the creation and use of an interactive, virtual industrial facility - the Elihu Paper Company - as a way to complement a traditional facility tours in a course in industrial environmental management. Virtual facilities offer a number of educational advantages over real-life ones: they are always open and available for tours, they can be accessed instantaneously from anywhere where there is an adequate internet connection, and most importantly, tours and embedded information can be tailored to specific educational objectives. Our experience in using Elihu Paper as a formal facility visit for the past several years shows that students had significantly more time than usual to ask questions, could and did explore the facility independently, and were still able to produce facility reports that fulfilled the educational objectives of the visits, including mapping material flows and explaining pollution prevention and sustainability opportunities.     

Modelling the relationship of driver license and offense history with fatal and serious injury (FSI) crash involvement

Introduction: Previous research has indicated that increases in traffic offenses are linked to increased crash involvement rates, making reductions in offending an appropriate measure for evaluating road safety interventions in the short-term. However, the extent to which traffic offending predicts fatal and serious injury (FSI) crash involvement risk is not well established, prompting this new Victorian (Australia) study. Method: A preliminary cluster analysis was performed to describe the offense data and assess FSI crash involvement risk for each cluster. While controlling demographic and licensing variables, the key traffic offenses that predict future FSI crash involvement were then identified. The large sample size allowed the use of machine learning methods such as random forests, gradient boosting, and Least Absolute Shrinkage and Selection Operator (LASSO) regression. This was done for the ‘all driver’ sample and five sometimes overlapping groups of drivers; the young, the elderly, and those with a motorcycle license, a heavy vehicle license endorsement and/or a history of license bans. Results: With the exception of the group of drivers who had a history of bans, offense history significantly improved the accuracy of models predicting future FSI crash involvement using demographic and licensing data, suggesting that traffic offenses may be an important factor to consider when analyzing FSI crash involvement risk and the effects of road safety countermeasures. Conclusions: The results are helpful for identifying driver groups to target with further road safety countermeasures, and for showing that machine learning methods have an important role to play in research of this nature. Practical Application: This research indicates with whom road safety interventions should particularly be applied. Changes to driver demerit policies to better target offenses related to FSI crash involvement and repeat traffic offenders, who are at greater risk of FSI crash involvement, are recommended.