Approaching the upper boundary of driver-response relationships: identifying factors using a novel framework integrating quantile regression with interpretable machine learning

● A novel framework integrating quantile regression with machine learning is proposed. ● It aims to identify factors driving observations to upper boundary of relationship. ● Increasing N:P and TN concentration help fulfill the effect of TP on CHL. ● Wetter and warmer decrease potential and increase eutrophication control difficulty. ● The framework advances applications of quantile regression and machine learning. The identification of factors that may be forcing ecological observations to approach the upper boundary provides insight into potential mechanisms affecting driver-response relationships, and can help inform ecosystem management, but has rarely been explored. In this study, we propose a novel framework integrating quantile regression with interpretable machine learning. In the first stage of the framework, we estimate the upper boundary of a driver-response relationship using quantile regression. Next, we calculate “potentials” of the response variable depending on the driver, which are defined as vertical distances from the estimated upper boundary of the relationship to observations in the driver-response variable scatter plot. Finally, we identify key factors impacting the potential using a machine learning model. We illustrate the necessary steps to implement the framework using the total phosphorus (TP)-Chlorophyll a (CHL) relationship in lakes across the continental US. We found that the nitrogen to phosphorus ratio (N׃P), annual average precipitation, total nitrogen (TN), and summer average air temperature were key factors impacting the potential of CHL depending on TP. We further revealed important implications of our findings for lake eutrophication management. The important role of N׃P and TN on the potential highlights the co-limitation of phosphorus and nitrogen and indicates the need for dual nutrient criteria. Future wetter and/or warmer climate scenarios can decrease the potential which may reduce the efficacy of lake eutrophication management. The novel framework advances the application of quantile regression to identify factors driving observations to approach the upper boundary of driver-response relationships.     

沱江流域主要污染负荷预测及时空分布特征

耦合社会-经济因子探究工业点源和生活污染源污染负荷未来变化趋势,可为优化水环境规划和管理方案提供理论依据。选取沱江流域为研究区域,采用经济增长预测法、工业点源传统统计法、人口趋势灰色模型预测法和排污系数法分别计算了2020-2025年该区域28个县(市、区)的工业GDP值,工业点源废水排放量及主要污染负荷(COD、NH₃-N、TN、TP),农村与城镇人口及生活污染源的主要污染负荷,并利用ArcGIS技术探究了工业点源和生活污染源主要污染负荷空间分布特征。结果表明:2020-2025年,工业GDP值总体呈逐年增加趋势,而工业废水排放量总体呈逐年减少趋势,预计到2025年,流域工业GDP值将增加至2.52×10¹²元,而工业废水排放量将减少至0.64×10⁸ t。工业点源主要污染负荷表现为COD>NH₃-N>TN>TP。沱江流域总人口数与生活污染源污染负荷呈逐年增加趋势,其中城镇人口与生活污染源污染负荷呈逐年增加趋势,农村人口与生活污染源污染负荷呈逐年减少趋势,且城镇人口及生活污染源污染负荷增加量大于农村人口及生活污染源污染负荷减少量。城镇、农村生活污染源的主要污染负荷表现为COD>NH₃-N>TN>TP。工业点源和生活污染源主要污染负荷在空间上存在高度异质性。2025年,来自工业点源的主要污染负荷均呈上游较少,中、下游较多的特征;来自城市生活污染源的主要污染负荷均呈中、上游较多,下游较少的特征;来自农村生活污染源的主要污染负荷均呈中游较多,上、下游较少的特征。笔者提出耦合社会-经济因子预测流域污染负荷的方法可以推广到其他与社会经济指标相关联的流域工业点源、生活污染源污染负荷的预测研究中,以期为未来流域水环境管理与治理提供科学参考。     

中国磷消费结构的变化特征及其对环境磷负荷的影响

本研究先建立物质流分析模型,分析1980～2008年期间我国磷消费结构的变化特征及其对环境磷负荷的影响,随后探讨若干社会经济因素同我国磷消费污染之间的关联性.结果表明,城市生活和农村生活的人均磷养分输入分别由0.83 kg.a-1和0.75 kg.a-1增加到1.20 kg.a-1和0.99 kg.a-1,而城市生活磷养分循环比例则由62.6%下降到15.6%;畜禽养殖和种植业的磷养分输入持续增加,但前者磷养分循环比例由67.5%下降到40.5%,后者大量磷养分蓄积在农业土壤;人口、城市化水平、种植业发展水平以及畜禽养殖业发展水平与我国磷消费污染总负荷的相关系数达到0.90以上,说明它们是我国磷消费污染的重要诱因;环境Kuznets曲线研究表明我国目前仍处于初级发展阶段,牺牲环境质量以换取经济发展.研究表明,我国磷消费体系正向线性开放的代谢结构演变,磷养分流失持续增加,环境磷负荷大大加重.     

A mathematical approach for retrofit and optimization of total site steam distribution networks

This paper presents a generic mathematical model for retrofitting the steam power plants in an industrial site. The industrial sector under review consists of one steel mill, one oil refinery, and several petrochemical plants, where only small-scale steam integration has been implemented before this study. The relevant unit models in a typical steam power plant are established, and the steam plant retrofit problem is formulated as a mixed-integer nonlinear program (MINLP). Feasible retrofit alternatives suggested by experienced field engineers are investigated in sequence to examine the revenue of those possible modifications. The first scenario examines operational optimization of existent plants; the second option allows installation of one new turbine and replacement of several boilers and turbines with lower efficiency; the third scenario considers using a steam ejector to upgrade the disqualified import steam in the oil refinery. The significant merits from these three retrofit alternatives show that the proposed MINLP formulation has been a great help to enhance the inter-plant steam integration in an industrial sector.     

数字滤波法在点源和非点源污染负荷分割中的应用

以分辨流域点源和非点源污染负荷为研究目标,在傅立叶分析的基础上,提出了从污染负荷时间序列中分辨点源和非点源污染负荷的新方法——数字滤波法,探讨了数字滤波方程的参数与滤波次数的关系,并将该方法应用到东江流域COD_Mn负荷的分割上. 应用实例表明,分割的点源和非点源负荷系列曲线符合点源和非点源负荷的产生特点,使用者能够在污染负荷分割过程中通过滤波参数的选取比较方便地加入自己的经验. 一般取较大滤波参数时,只需要3次滤波就能得出较满意的结果.      

Enhancing generic ecological model for short-term prediction of Southern North Sea algal dynamics with remote sensing images

Physically based numerical modelling follows from the basic understanding of the underlying mechanisms and is often represented by a set of (partial differential) equations. It is one of the main approaches in population dynamics modelling. The emphasis of the model introduced in this paper is on the simulation of short-term spatial and temporal dynamics of harmful algal bloom (HAB) events. Total suspended matter (TSM) concentration is one of the dominant factors for harmful algal bloom (HAB) prediction in North Sea. However, the modelling of suspended matter contains a high degree of uncertainty in this area. Therefore, this research aims to achieve a better estimation for the short-term prediction of harmful algal bloom development in both space and time by using spatially distributed TSM retrieved from remotely sensed images as physically based model inputs. In order to supply complete spatially covered datasets for the physically based model instrument: generic ecological model (GEM), this research retrieves TSM information from MERIS images by means of proper estimation techniques including biharmonic splines and self-learning cellular automata. A better estimation of HAB spatial pattern development is achieved by adding spatially distributed TSM data as inputs to original GEM model, and it proved that chlorophyll-a concentration in this area is very sensitive to TSM concentration.     

Tradeoffs between forestry resource and conservation values under alternate policy regimes: A spatial analysis of the western Canadian boreal plains

An important element of resource management and conservation is an understanding of the tradeoffs between marketed products, such as timber, and measures of environmental quality, such as biodiversity. In this paper, we develop an integrated economic-ecological spatial optimization model that we then apply to evaluate alternate forest policies on a 560,000 km² study region of managed boreal forest in Alberta and British Columbia, Canada. The integrated model incorporates dynamic forest sector harvesting, current levels of oil and gas sector development, coarse-filter or habitat-based old forest indicators, a set of empirical forest bird abundance models, and statistical models of the natural and current fire regimes. Using our integrated model, economic tradeoff curves, or production possibility frontiers, are developed to illustrate the cost of achieving coarse-filter targets by a set time (50 years) within a 100-year time horizon. We found levels of ecological indicators and economic returns from the timber industry could both be increased if spatial constraints imposed by the current policy environment were relaxed; other factors being equal, this implies current policy should be revised. We explore the production possibility frontier's relationship to the range of natural variation of old forest habitat, and show how this range can be used to guide choices of preferred locations along the frontier. We also show that coarse-filter constraints on the abundance of certain habitat elements are sufficient to satisfy some fine-filter objectives, expressed as the predicted abundances of various species of songbirds.     

密云水库流域植被覆盖度变化对输沙量的影响

封闭流域中,泥沙的产生是多种因素相互作用,相互制约的结果,而在这些众多的环境影响因素中,植被是土壤侵蚀中最重要的环境控制因子,目前,植被覆盖度变化对输沙量的影响一直是区域生态环境研究中比较热门的话题。文章使用遥感（Remote Sensing（RS））、地理信息系统（Geographic In formmionSystem（GIS））与统计分析相结合的方法评价了密云水库流域内2个子流域出口处2002年至2005年植被覆盖度变化对输沙量的影响。密云水库流域多为山地,其降雨具有明显的季节性。本文的主要目的在于分析2002年至2005年植被覆盖度变化对流域输沙量的影响,并分析了植被覆盖度变化对气候改变及人类活动的综合影响,结果表明：在密云水库流域内,输沙量是降雨情况和人为因素引起的地表植被覆盖度变化情况的综合反映,人口增长、经济发展和城市化是密云水库流域内引起土地利用变化和地表植被覆盖度变化的主要驱动力。并且,输沙量可以被看作是一个很好的指标来定量分离出生物生理和人为的影响,并从中能够找出在流域生态系统中获得显著结果关键的临界点。研究结果对制定流域的合理开发和管理计划将有所帮助。     

总磷排放标准的讨论

总磷是评价水质的重要指标,磷以多种形式存在,随着污水排放标准的不断更新．总磷标准的尺度不相一致。根据国家相关标准和规范,给出了能让已有标准内在联系更加完整和协调的建议．期待环境行政管理部门对废水中总磷排放标准作出更加明确合理的相关规定．     

Nutrient Loadings to Streams of the Continental United States from Municipal and Industrial Effluent1

Maupin, Molly A. and Tamara Ivahnenko, 2011. Nutrient Loadings to Streams of the Continental United States From Municipal and Industrial Effluent. Journal of the American Water Resources Association (JAWRA) 47(5):950‐964. DOI: 10.1111/j.1752‐1688.2011.00576.x Abstract: Data from the United States Environmental Protection Agency Permit Compliance System national database were used to calculate annual total nitrogen (TN) and total phosphorus (TP) loads to surface waters from municipal and industrial facilities in six major regions of the United States for 1992, 1997, and 2002. Concentration and effluent flow data were examined for approximately 118,250 facilities in 45 states and the District of Columbia. Inconsistent and incomplete discharge locations, effluent flows, and effluent nutrient concentrations limited the use of these data for calculating nutrient loads. More concentrations were reported for major facilities, those discharging more than 1 million gallons per day, than for minor facilities, and more concentrations were reported for TP than for TN. Analytical methods to check and improve the quality of the Permit Compliance System data were used. Annual loads were calculated using “typical pollutant concentrations” to supplement missing concentrations based on the type and size of facilities. Annual nutrient loads for over 26,600 facilities were calculated for at least one of the three years. Sewage systems represented 74% of all TN loads and 58% of all TP loads. This work represents an initial set of data to develop a comprehensive and consistent national database of point‐source nutrient loads. These loads can be used to inform a wide range of water‐quality management, watershed modeling, and research efforts at multiple scales.