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.     

Multilevel air quality evolution in Shenyang: Impact of elevated point emission reduction

Visibility observed at different altitudes is favorable to understand the causes of air pollution. We conducted 4-years of observations of visibility at 2.8 and 60 m and particulate matter(PM) concentrations from 2015 to 2018 in Shenyang, a provincial city in Northeast China. The results indicated that visibility increased with the increasing height in winter(especially at night), and decreased with height in summer(especially at the daytime). PM concentration exhibited opposite vertical variati...     

福州市PM2.5污染过程中大气边界层和区域传输研究

以福建省会福州市2013年1月空气质量变化为对象,分析大气边界层变化和周边区域污染物传输对福州市大气颗粒物PM2.5的影响.利用福州市2013年1月逐日地面和探空观测资料以及NCEP提供的2013年1月FNL分析资料,通过大气边界层要素与PM2.5浓度之间的相关性,对PM2.5污染过程的大气边界层特征进行分析;同时采用HYSPLIT后向轨迹模拟及区域风场相关矢分析对影响福州雾霾的污染物区域传输路径进行探讨.结果表明:地面气温与PM2.5浓度呈正相关,地面风速与PM2.5浓度呈负相关,近地面边界层条件有利于霾颗粒物的形成和累积.但不同于我国东部主要污染源区霾污染过程中存在大气边界层逆温,福州PM2.5污染过程中并未出现大气边界层逆温结构,这一边界层结构的垂直混合可有利于区域传输的污染物从上层大气到达近地面从而加重福州霾污染,福州是华东地区一个PM2.5污染物的主要接受区,PM2.5污染物主要以外源输送为主.2013年1月份福州市清洁日近地面风向为海洋吹向大陆的东南风,霾污染日则为大陆吹向海洋的偏北风,PM2.5污染物主要从长三角地区、苏北以及安徽河南一带通过东北和西北方向的传输路径影响福州的空气质量.     

跨湖桥独木舟遗址区地下水渗流场模拟研究

独木舟遗址位于浙江省萧山区,是浙江省迄今为止发现最早的新石器时代文化遗存。现场踏勘发现,破坏遗址原址保护主要环境地质病害是水的问题。通过对该遗址区水文地质条件的分析,建立了遗址区水文地质概念模型和数学模型;运用地下水数值模拟软件Modflow模拟遗址区原始地下水分布;将模拟区地形图与模型模拟结果进行比较,发现它们具极大的相似性,这说明模拟的结果是符合实际情况的。     

铁路噪声对沿线住宅小区的影响

主要考虑铁路噪声的直达声和一次反射声对住宅小区的影响,建立了铁路沿线城市住宅区列车噪声衰减的理论模型,计算分析了铁路噪声对建筑群纵深的影响,并与实测值进行比较,验证了模型的可靠性.     

沈阳地区霾的环境特征研究

利用沈阳市1961—2009年的气象资料,分析了霾天气出现的年季特征及其天气形势特征。利用边界层气象资料与污染物质量浓度资料对特定的霾过程从边界层到污染物质量浓度条件进行了分析。结果表明：沈阳地区霾的出现呈现逐年上升的趋势,近5 a平均每年为120 d左右,目前霾天数已经占到了全年的30%~40%。冬秋季节出现霾天气较多,秋冬两季霾日数占全年霾日总数的75%。凌晨到上午是霾出现的高发期,02—08时霾出现频率占总霾数的44.5%。霾的出现主要发生在冬秋季节冷空气势力不强,大气扩散能力较弱,边界层出现逆温时刻。接地逆温层厚度常常稳定在200~300 m高度左右,PM10质量浓度与能见度（霾）呈负相关,相关系数-0.402 7。风速与能见度（霾）呈正相关,相关系数为0.886 4。     

考虑非线性吸附时溶质在有限厚度粘土中的一维扩散解

在采用非线性分段式吸附等温模式的基础上,建立了溶质在粘土中的一维扩散模型,在考虑有限厚度边界及土中溶质背景浓度的条件下得到了相应的解.模型引入了移动边界以说明当溶质在粘土孔隙水中的浓度达到某一较高值后,阻滞因子将发生显著变化.算例分析表明,该模型和考虑经典非线性吸附等温线得到的结果相差不大,这进一步说明了该模型的合理性.考虑非线性吸附效应对溶质迁移有重要影响.在较高溶质浓度下采用线性吸附等温模式会得到偏不安全的结果.该解相对较简单,并可用于验证各种数值模型、拟合试验数据等.     

Sudden high concentration of TSP affected by atmospheric boundary layer in Seoul metropolitan area during duststorm period

Hourly concentrations of TSP, PM(10), PM(2.5) near the surface at Seoul city were examined from March 20 to March 25, 2001 (duststorm event) in order to investigate the effect of a duststorm generated in China on the local aerosol concentration in Korea, The ratios of fine to coarse particles such as TSP to PM(10), TSP to PM(2.5) and PM(10)-PM(2.5) to PM(2.5) showed that a great amount of dust transported from the origin of the duststorm was remarkable with a maximum ratio of 9.77 between TSP and PM(2.5). Back trajectories every 6 h showed the movement of dust particles in the lower atmosphere near 500 m to 1500 m (atmospheric boundary layer), which implied transport from Baotou in inner Mongolia of northern China to the direction of Seoul city in Korea and then the back trajectories passed near the southern border of Mongolia and Baotou through Zengzhou in the midlevels (3000 m) and low levels (500 m) of China, finally reaching Seoul city. So, the TSP concentration at Seoul city was partially influenced by the duststorm, under the prevailing westerly wind and the transported aerosols could influence high concentrations of pollutants of TSP, PM(10) and PM(2.5) in Seoul. The sudden high concentrations of TSP and PM(10) were found for a few hours, especially at 1500 to 1800 LST, March 22. At 1200 LST, before the passage of a cold front through the Korean peninsula, the convective boundary layer (CBL) near Seoul was not shallow, but at 1500 LST, under the frontal passage, the CBL was remarkably thinner (less than 300 m), due to the compression of the boundary layer by the intrusion of cold air. This resulted in the increase of the TSP concentration, even though the mixed layer above maintained almost the same depth. At 1800 LST shortly after the frontal passage, that is, near sunset, the nocturnal cooling of the ground caused air parcels to cool, thereby enhancing the shallower nocturnal surface inversion layer and producing the maximum concentration of TSP of 1388 microg/m(3) near Seoul city.     

Analysis of behavioral changes of zebrafish (Danio rerio) in response to formaldehyde using Self-organizing map and a hidden Markov model

Two computational methods were applied to classification of movement patterns of zebrafish (Danio rerio) to elucidate Markov processes in behavioral changes before and after treatment of formaldehyde (0.1 mg/L) in semi-natural conditions. The complex data of the movement tracks were initially classified by the Self-organizing map (SOM) to present different behavioral states of test individuals. Transition probabilities between behavioral states were further evaluated to fit Markov processes by using the hidden Markov model (HMM). Emission transition probability was also obtained from the observed variables (i.e., speed) for training with the HMM. Experimental transition and emission probability matrices were successfully estimated with the HMM for recognizing sequences of behavioral states with accuracy rates in acceptable ranges at central and boundary zones before (77.3-81.2%) and after (70.1-76.5%) treatment. A heuristic algorithm and a Markov model were efficiently combined to analyze movement patterns and could be a means of in situ behavioral monitoring tool.     

From the outside in: The negative spillover effects of boundary spanners' relations with members of other organizations

Contrary to much boundary spanning research, we examined the negative consequences of boundary spanning contact in multi‐organizational contexts. Results from a sample of 833 Dutch peacekeepers show that employees' boundary spanning contact with members of other organizations was associated with reports of negative relationships with external parties (e.g., work‐specific problems, culture‐specific problems). These negative relationships also had a spillover effect such that they mediated the effect of boundary spanning contact on boundary spanners' negative attitudes toward their own jobs and organization (e.g., job attractiveness and confidence in the organization). Copyright © 2010 John Wiley & Sons, Ltd.