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.     

CDIO工程教育模式在高职创业教育中的应用研究——以中国环境管理干部学院为例

创业教育现在已成为我国高等职业教育中的重要一环。高职院校往往开设一门创业教育课程,试图通过该课程达到创业教育的目的,课程过分迷信＂说教、讲授＂的力量,而毕业生创业能力并没有得到预期的培养。通过借鉴CDIO工程教育模式,提出了创业教育应该以创业能力为培养目标,参照CDIO模式的12项标准进行模块化课程开发,通过CDIO循环提高学生的创业综合能力。     

The role of science-policy interface in sustainable urban water transitions: Lessons from Rotterdam

This paper investigates the role of the science-policy interface in leveraging transitions to sustainable urban water management. The paper presents a case study of the Dutch city of Rotterdam, which is increasingly regarded as a global leader in adaptive and resilient urban water management. The analysis reveals that Rotterdam’s transition has occurred incrementally over the past 15 years, driven by policy entrepreneurs: largely municipal policy makers and policy practitioners. Strategic use of the science-policy interface (SPI) has facilitated the development of innovative solutions to achieve policy goals and created the enabling conditions necessary for transformative change. The Rotterdam case suggests that an effective SPI requires: (1) compelling water narrative; (2) cross-sectoral collaboration; (3) co-production of knowledge; (4) experiential evidence-based learning; (5) strategic use of trusted scientists; (6) fostering networks; and (7) generating business from science-based innovation. Rotterdam’s strategic approach to knowledge and innovation coupled with a new narrative around water sets it apart from many other cities and adds a new dimension to debates regarding enabling factors for advancing sustainable practices. These findings will be of interest to those engaged in urban water management policy and practice, environmental governance, and debates over transitions more broadly.     

Adaptation or conflict? Responses to climate change in water management in Bangladesh

The potential of climate change to impact local conflict and cooperation over natural resources has received relatively little attention. Bangladesh floodplains are highly vulnerable to environmental stresses that are worsening with climate change, and community organisations have to respond to water insecurity − seasonally too little or too much. Two case studies based on action research in contrasting water and climate stressed floodplain environments in Bangladesh investigate local conflicts over water management that worsened when water regimes changed. By overcoming conflicts and improving adaptation for all local actors the cases reveal the importance of local knowledge, innovations in institutions, external facilitation, and incentives provided by disadvantaged groups who contribute towards costs in return for a share in decision making power and better adapted water management. The cases show how community organisations diversified their responsibilities and took up the challenge of water management to address local priorities and overcome conflicts. Without a more flexible and enabling approach, public investments in adaptation are likely to focus on strengthening existing water management infrastructure without understanding local social interactions and complexity. This may strengthen elite dominance and local conflicts if there is no comparable investment in developing robust and fair local institutions.     

基于EMD-MFOA-ELM的瓦斯涌出量时变序列预测研究

为准确分析工作面绝对瓦斯涌出量的非平稳特征,实现瓦斯涌出量的准确预测,基于经验模态分解(EMD)、修正的果蝇优化算法(MFOA)和极限学习机(ELM)基本原理,构建瓦斯涌出量的EMD-MFOA-ELM多尺度时变预测模型。通过EMD将瓦斯涌出量时变序列进行深层次分解,获得多尺度本征模态函数(IMF);采用MFOA-ELM对各IMF时变序列建立动态预测模型,等权叠加各预测值,得到模型最终预测结果。以晋煤某矿瓦斯涌出量监测时序样本为例进行研究分析,结果表明:EMD能充分挖掘出监测数据隐含信息,有效降低数据复杂度;该模型预测相对误差为0.024 3%~0.651 0%,平均值仅为0.252 6%,预测精度和泛化能力高于未经EMD分解模型,能很好地适用于非平稳时变序列预测。     

基于机器学习和卫星遥感的PM2.5/10 空间连续分布反演方法研究

在过去的几十年里,快速的经济发展以及工业化、城镇化进程加速使得中国的资源环境承担的压力不断加大。作为影响空气质量的首要污染物,PM_2.5和PM₁₀（记为PM_2.5/10）直接影响着广大人民群众的身体健康。因此,针对PM_2.5/10浓度进行遥感反演研究,对环境监测和控制改善全国空气环境质量具有重要的意义。近些年来,随着对近地面PM_2.5/10浓度研究的不断深入,基于遥感影像数据进行PM_2.5/10浓度的反演方法也日益增多。本文利用Google Earth engine（GEE）平台获取了海量的Landsat 8 OLI遥感影像数据,并结合气象信息、空间特征等参数,采用机器学习中常用的多层映射反向传播神经网络构建了波段反射率与PM_2.5/10浓度之间的反演模型,以获得PM_2.5/10在研究区域的连续分布。为了提高基础PM_2.5/10反演模型的反演精度,还从影响因素和前溯时间两个维度出发,探寻了模型的最优化输入参数组合,并最终实现了对PM_2.5/10浓度的精准反演。以北京市地区为例,模型的PM_2.5和PM₁₀的反演精度R²分别达到0.814和0.796,均方根误差RMSE分别为19.21 μg?m^?3和28.31 μg?m^?3。鉴于该反演结果具有较高的准确性和可靠性,本文所建立的方法模型为研究PM_2.5/10在空间上的连续分布特征提供了新的思路和方法,具有较为重要的科研意义与广泛的应用价值。     

碳中和趋势下数学模拟在污水处理系统中的发展与综合应用

数学模拟技术在污水处理方面被广泛应用,为了系统总结相关技术,本文回顾了污水处理系统中数学模拟技术的发展历程;综述了活性污泥模型(ASM)与机器学习(ML)在水质预测及参数工况优化领域中的应用;重点探究了污水处理系统中温室气体排放模型,以及多目标优化模型在污水处理系统中温室气体排放(GHG)、出水质量(EQI)和运行成本(OCI)的权衡问题;归纳了数学模拟技术在实现污水厂能量自给与资源回收的应用发展.研究结果表明数学模拟技术能准确预测出水水质、快速优化工艺参数、权衡温室气体排放、出水水质与运行成本之间的关系、以及提高资源回收效率等.因此,数值模拟技术可有效指导污水处理工艺的运行优化以及管理,为污水处理行业减污降碳协同增效提供技术支撑.     

基于无人机影像的城市植被精细分类

针对传统植被资源调查方法工作量大、成本高、效率低的问题,利用高分辨率无人机遥感影像,联合地物光谱-纹理-空间信息,构建了一种适用于描述城市不同植被种类的多维特征空间,在此基础上对三种应用广泛的分类算法(基于像素的、面向对象的支持向量机及深度学习Mobile-Unet语义分割模型)开展了对比分析研究.结果表明:本文提出的联合地物光谱-纹理-空间信息的特征空间构建方法能够有效地描述城市不同类型植被的特征差异,提升影像分割、植被分类的精度;在分类精度上,基于像素和面向对象的支持向量机分类结果的总体精度均超过90%,深度学习方法的总体分类精度为84%;在算法效率上,传统机器学习方法也优于深度学习方法.因此,得出结论针对城市小区域、小样本的植被精细分类,传统机器学习分类方法比深度学习方法效果更好.     

机器学习在材料服役性能预测中的应用

针对材料服役性能预测存在误差大、计算复杂、适用性差等问题,提出了基于数据挖掘的机器学习预测方法。首先阐述了机器学习的应用流程,并总结了常用模型原理及其在材料性能预测中的应用。然后采用多种机器学习模型对RPV钢的辐照性能进行预测,并通过Stacking集成方法提高了模型的预测精度。结果表明,机器学习可用于材料服役性能预测,具有较高的预测精度和可靠性。根据材料服役数据的不同特征选择合适的学习模型,同时进行模型融合和参数优化,可有效提高模型的预测精度及运算速度。     

Learning for social-ecological change: a qualitative review of outcomes across empirical literature in natural resource management

Learning is considered as a promising mechanism to cope with rapid environmental change. The implications of learning for natural resource management (NRM) have not been explored in-depth and the evidence on the topic is scattered across multiple sources. We provide a qualitative review of types of learning outcomes and consider their manifestations in NRM across selected empirical literature. We conducted a systematic search of the peer-reviewed literature (N = 1,223) and a qualitative meta-synthesis of included articles, with an explicit focus on learning outcomes and NRM changes (N = 53). Besides social learning, we found several learning concepts used, including policy and transformative learning, and multiple links between learning and NRM reported. We observe that the development of skills, together with a system approach involving multi-level capacities, is decisive for implications of learning for NRM. Future reviews could systematically compare how primary research applies different learning concepts and discusses links between learning and NRM changes.