AI-based runoff simulation based on remote sensing observations: A case study of two river basins in the United States and Canada

Data-driven techniques are used extensively for hydrologic time-series prediction. We created various data-driven models (DDMs) based on machine learning: long short-term memory (LSTM), support vector regression (SVR), extreme learning machines, and an artificial neural network with backpropagation, to define the optimal approach to predicting streamflow time series in the Carson River (California, USA) and Montmorency (Canada) catchments. The moderate resolution imaging spectroradiometer (MODIS) snow-coverage dataset was applied to improve the streamflow estimate. In addition to the DDMs, the conceptual snowmelt runoff model was applied to simulate and forecast daily streamflow. The four main predictor variables, namely snow-coverage (S-C), precipitation (P), maximum temperature (T_max), and minimum temperature (T_min), and their corresponding values for each river basin, were obtained from National Climatic Data Center and National Snow and Ice Data Center to develop the model. The most relevant predictor variable was chosen using the support vector machine-recursive feature elimination feature selection approach. The results show that incorporating the MODIS snow-coverage dataset improves the models' prediction accuracies in the snowmelt-dominated basin. SVR and LSTM exhibited the best performances (root mean square error = 8.63 and 9.80) using monthly and daily snowmelt time series, respectively. In summary, machine learning is a reliable method to forecast runoff as it can be employed in global climate forecasts that require high-volume data processing.     

A remote sensing tool for near real-time monitoring of harmful algal blooms and turbidity in reservoirs

Harmful algal blooms (HABs) diminish the utility of reservoirs for drinking water supply, irrigation, recreation, and ecosystem service provision. HABs decrease water quality and are a significant health concern in surface water bodies. Near real-time monitoring of HABs in reservoirs and small water bodies is essential to understand the dynamics of turbidity and HAB formation. This study uses satellite imagery to remotely sense chlorophyll-a concentrations (chl-a), phycocyanin concentrations, and turbidity in two reservoirs, the Grand Lake O′ the Cherokees and Hudson Reservoir, OK, USA, to develop a tool for near real-time monitoring of HABs. Landsat-8 and Sentinel-2 imagery from 2013 to 2017 and from 2015 to 2020 were used to train and test three different models that include multiple regression, support vector regression (SVR), and random forest regression (RFR). Performance was assessed by comparing the three models to estimate chl-a, phycocyanin, and turbidity. The results showed that RFR achieved the best performance, with R² values of 0.75, 0.82, and 0.79 for chl-a, turbidity, and phycocyanin, while multiple regression had R² values of 0.29, 0.51, and 0.46 and SVR had R² values of 0.58, 0.62, and 0.61 on the testing datasets, respectively. This paper examines the potential of the developed open-source satellite remote sensing tool for monitoring reservoirs in Oklahoma to assess spatial and temporal variations in surface water quality.     

工程机械不同工况下PM_(2.5)排放及其碳质组分特征

我国工程机械排放控制起步较晚.为研究实际工况下工程机械的PM2.5排放特性及其碳质组分构成,采用便携式颗粒物稀释采样系统,对3台工程机械(2台挖掘机和1台装载机)在不同典型工况(行驶、作业和怠速)下的PM2.5及其碳质组分〔OC(有机碳)和EC(元素碳)〕的现场排放特征进行了测试.结果表明:沃尔沃挖掘机、山河智能挖掘机的PM2.5排放因子(基于燃油)分别为1.85~3.26和1.56~2.62 g/kg,厦工装载机的PM2.5排放因子为0.98~1.48 g/kg.不同工况对PM2.5排放因子影响较大,怠速工况下PM2.5排放因子是行驶工况下的1.49~1.76倍.工程机械排放的PM2.5中,碳质组分是最主要的成分,其质量分数高达71.0%~84.5%.其中,w(OC)为44.6%~72.0%,在怠速工况下最高;w(EC)则为8.6%~30.9%,在行驶工况下较高.测试工程机械的PM2.5排放水平较高,因此应尽快加强工程机械排放的污染防治.     

有机化学品不同温度下(过冷)液体蒸气压预测模型的建立与评价

(过冷)液体蒸气压(PL)是评价化学品在环境中分配、迁移和归趋行为的重要参数。PL具有较强的温度依附性。发展一种能够精确预测不同环境温度下化学品PL的方法,有助于填补化学品生态风险评估的大量数据缺失。本研究收集整理了661种有机化合物在不同温度下(200~830 K)共计10 478个log PL值。在此基础上,采用偏最小二乘(PLS)回归和支持向量机(SVM)方法,构建了PL的线性和非线性预测模型。结果表明:2种模型均具有良好的拟合度、稳健性及预测能力,SVM模型的预测性能略高于PLS模型(PLS:R2adj.tra=0.912,RMSEtra=0.477,Q2ext=0.910;SVM:R2adj.tra=0.997,RMSEtra=0.092,Q2ext=0.967)。机理分析表明,温度是影响PL的主要因素,温度越高,蒸气压越大;其次,X1sol也影响PL大小,X1sol用来描述分子间的色散作用,分子间色散力越小,蒸气压越大;此外,化合物的氢键个数、极性和分子构型等因素也影响PL大小。采用Wiliams plot方法表征了PLS模型应用域。所建立的模型可用来预测烷烃、烯烃、醇、酮、羧酸、苯、酚、联苯、卤代芳香烃、含N化合物及含S化合物在不同温度下的PL数据。     

高效液相色谱-电感耦合等离子体质谱联用测定生物样品中的有机汞

建立了酸提取-高效液相色谱-电感耦合等离子体质谱联用技术(HPLC-ICP-MS)测定生物样品中甲基汞、乙基汞、苯基汞等3种有机汞的分析方法。鱼肉和贝类样品经盐酸消解,苯萃取,硫代硫酸钠溶液反萃取后,采用醋酸铵/L-半胱氨酸缓冲盐及甲醇体系组成的流动相按一定比例进行梯度洗脱,经前处理的生物样品在液相色谱中经C18柱分离后,进入电感耦合等离子体质谱检测其甲基汞、乙基汞和苯基汞的浓度。3种有机汞化合物均在0.50~50.0μg/L范围内呈现良好的线性关系,线性相关系数(r)均大于0.9998。方法检出限为0.010~0.038mg/kg;3种有机汞样品加标的RSD均小于12.2%;两个水平的加标回收率在50.8~129%。     

基于FTA-SVM的车辆发动机故障识别方法

发动机结构日益复杂,其故障具有多样性和频发性的特点,收集大量故障样本存在很多实施障碍。为了提高车辆发动机的故障识别的效率和准确性,提出了一种新的结合故障树(FTA)和支持向量机(SVM)各自特点,从故障模式分析到故障类型识别的FTA-SVM故障识别方法。首先利用故障树在复杂系统故障模式分析中的优势,找出系统的故障模式,建立故障树模型,通过对故障树模型中各故障事件的分析,采集与故障事件状态相关的数据,建立数据与故障树底事件的映射模型,最后利用支持向量机在小样本数据处理中的优势,进行故障类型的识别。以发动机的失火故障为例建立了发动机失火故障树模型及故障数据与故障模式映射模型,验证了FTA-SVM方法的有效性和适用性。     

岩溶塌陷倾向性等级的KPCA-SVM预测模型

为了快速、有效地预测岩溶塌陷倾向性等级,在统计分析大量观测实例的基础上,选取岩性系数、岩体结构系数、地下水系数、覆盖层系数、地形地貌系数和环境条件系数作为特征指标。利用核主成分分析(KPCA)方法在高维空间提取岩溶塌陷影响因子的主成分,将获取的主成分作为支持向量机(SVM)的特征向量,建立基于KPCA的岩溶塌陷倾向性等级的SVM预测模型。将12组观测数据作为学习样本对模型进行训练。采用回代估计法进行回检,误判率为0。利用训练好的模型对2组待判样本进行预测。结果表明:经KPCA后指标个数减少,相关性降低,SVM运算的复杂度降低。用该模型所得预测结果的准确率为100%。     

Using Sound to Reduce Visual Distraction from In-vehicle Human–Machine Interfaces

Objective: Driver distraction and inattention are the main causes of accidents. The fact that devices such as navigation displays and media players are part of the distraction problem has led to the formulation of guidelines advocating various means for minimizing the visual distraction from such interfaces. However, although design guidelines and recommendations are followed, certain interface interactions, such as menu browsing, still require off-road visual attention that increases crash risk. In this article, we investigate whether adding sound to an in-vehicle user interface can provide the support necessary to create a significant reduction in glances toward a visual display when browsing menus.

Methods: Two sound concepts were developed and studied; spearcons (time-compressed speech sounds) and earcons (musical sounds). A simulator study was conducted in which 14 participants between the ages of 36 and 59 took part. Participants performed 6 different interface tasks while driving along a highway route. A 3 × 6 within-group factorial design was employed with sound (no sound /earcons/spearcons) and task (6 different task types) as factors. Eye glances and corresponding measures were recorded using a head-mounted eye tracker. Participants’ self-assessed driving performance was also collected after each task with a 10-point scale ranging from 1 = very bad to 10 = very good. Separate analyses of variance (ANOVAs) were conducted for different eye glance measures and self-rated driving performance.

Results: It was found that the added spearcon sounds significantly reduced total glance time as well as number of glances while retaining task time as compared to the baseline (= no sound) condition (total glance time M = 4.15 for spearcons vs. M = 7.56 for baseline, p =.03). The earcon sounds did not result in such distraction-reducing effects. Furthermore, participants ratings of their driving performance were statistically significantly higher in the spearcon conditions compared to the baseline and earcon conditions (M = 7.08 vs. M = 6.05 and M = 5.99 respectively, p =.035 and p =.002).

Conclusions: The spearcon sounds seem to efficiently reduce visual distraction, whereas the earcon sounds did not reduce distraction measures or increase subjective driving performance. An aspect that must be further investigated is how well spearcons and other types of auditory displays are accepted by drivers in general and how they work in real traffic.     

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MDE和分形优化SVM的周期来压预测

为了解决周期来压的预测问题,首先对已知支架周期来压荷载曲线使用多重差异进化算法(MDE)进行拟合,将每重拟合形成的单一正弦曲线与上次差余曲线(Ei)再作差余曲线(Ei+1)。将这些Ei图通过分形几何的盒子法计算维度和相关系数(r)。将每条Ei的维度、r和支架相对距离(L)作为输入值,对应的Ei的周期Ti、缩放系数Si和纵移系数Di作为目标值,使用支持向量机(SVM)进行训练。通过对维度和r规律的研究得到拟设置支架处荷载各Ei的维度和r,带入训练后的SVM模拟得到Ei的Ti、Si和Di,进而得到Ei的表达式。将上述Ei求和即为所求拟设置支架处的周期来压荷载。实例分析说明,该种方法预测结果可以大体反映支架周期来压的基本形式和变化规律。