Stochastic Transfer Function Model and Neural Networks to Estimate Soil Moisture1

Abstract: A practical methodology is proposed to estimate the three‐dimensional variability of soil moisture based on a stochastic transfer function model, which is an approximation of the Richard’s equation. Satellite, radar and in situ observations are the major sources of information to develop a model that represents the dynamic water content in the soil. The soil‐moisture observations were collected from 17 stations located in Puerto Rico (PR), and a sequential quadratic programming algorithm was used to estimate the parameters of the transfer function (TF) at each station. Soil texture information, terrain elevation, vegetation index, surface temperature, and accumulated rainfall for every grid cell were input into a self‐organized artificial neural network to identify similarities on terrain spatial variability and to determine the TF that best resembles the properties of a particular grid point. Soil moisture observed at 20 cm depth, soil texture, and cumulative rainfall were also used to train a feedforward artificial neural network to estimate soil moisture at 5, 10, 50, and 100 cm depth. A validation procedure was implemented to measure the horizontal and vertical estimation accuracy of soil moisture. Validation results from spatial and temporal variation of volumetric water content (vwc) showed that the proposed algorithm estimated soil moisture with a root mean squared error (RMSE) of 2.31% vwc, and the vertical profile shows a RMSE of 2.50% vwc. The algorithm estimates soil moisture in an hourly basis at 1 km spatial resolution, and up to 1 m depth, and was successfully applied under PR climate conditions.     

Development and Operational Testing of a Super‐Ensemble Artificial Intelligence Flood‐Forecast Model for a Pacific Northwest River

Coastal catchments in British Columbia, Canada, experience a complex mixture of rainfall‐ and snowmelt‐driven contributions to flood events. Few operational flood‐forecast models are available in the region. Here, we integrated a number of proven technologies in a novel way to produce a super‐ensemble forecast system for the Englishman River, a flood‐prone stream on Vancouver Island. This three‐day‐ahead modeling system utilizes up to 42 numerical weather prediction model outputs from the North American Ensemble Forecast System, combined with six artificial neural network‐based streamflow models representing various slightly different system conceptualizations, all of which were trained exclusively on historical high‐flow data. As such, the system combines relatively low model development times and costs with the generation of fully probabilistic forecasts reflecting uncertainty in the simulation of both atmospheric and terrestrial hydrologic dynamics. Results from operational testing by British Columbia's flood forecasting agency during the 2013‐2014 storm season suggest that the prediction system is operationally useful and robust.     

基于神经网络分类器的城市污水处理厂水力冲击预警系统

提出了一套基于神经网络分类器的城市污水处理厂水力负荷冲击预警系统,以期对进水水量骤增现象进行提前1天的预报,使污水处理厂可根据预报结果提前采取水力冲击防护措施,从而保证各单元的平稳运行.根据进水水量的涨幅将某污水处理厂12年日进水水量监测数据分为"常规"和"冲击"两类,重点对"冲击"数据进行提前1天的预测,并采用冲击漏报率、冲击误报率和报准率对模型的预测精度进行评价;同时,基于同样的建模方法和不同的训练、验证样本建立了N(1)、N(2)和N(3)3个平行模型,以对模型的鲁棒性和建模方法的可重复性进行考察.结果显示,3个模型对2010年、2011年和2012年3年测试样本的预测效果良好,冲击漏报率和报准率两项指标数值均较为稳定,分别在0~0.167和0.981~0.995之间浮动,冲击误报率虽然在数值上的浮动较大,最低为0.143,最高为0.500,平均为0.310,但仍在工程上的可承受范围内.该结果表明,本研究基于神经网络分类器所建立的3个神经网络模型预测精度高、鲁棒性好,显示出良好的性能,有望为污水处理厂水力冲击防护工作提供有力参考.     

Sources of organisational resiliency during the Thailand floods of 2011: a test of the bonding and bridging hypotheses

Based on the Institutional Collective Action framework, this research tests the impact of two competing hypotheses—bonding and bridging—on enhancing organisational resiliency. The bonding hypothesis posits that organisational resiliency can be achieved if an organisation works closely with others, whereas the bridging hypothesis argues that such a structure places considerable stress on an organisation and advocates for an organisation to position itself as a central actor to gain access to novel resources from a diverse set of entities to achieve resiliency. The paper analyses data gathered from semi‐structured interviews with 44 public, private, and non‐profit organisations serving communities affected by the Great Floods of 2011 in the Thai capital, Bangkok (urban), and in Pathum Thani (suburban) and Ayutthaya (rural) provinces. The findings suggest that: organisational resiliency was associated with the bridging effect; organisations in the rural province were more resilient than those in the suburban and urban centres; and private and non‐governmental organisations generally were more resilient than public sector organisations. The findings highlight the importance of fostering multi‐sector partnerships to enhance organisational resiliency for disaster response.     

Uncertainty Models for Estimates of Physical Characteristics of River Segments Over Large Areas

Spatially comprehensive estimates of the physical characteristics of river segments over large areas are required in many large‐scale analyses of river systems and for the management of multiple basins. Remote sensing and modeling are often used to estimate river characteristics over large areas, but the uncertainties associated with these estimates and their dependence on the physical characteristics of the segments and their catchments are seldom quantified. Using test data with varying degrees of independence, we derived analytical models of the uncertainty associated with estimates of upstream catchment area (CA), segment slope, and mean annual discharge for all river segments of a digital representation of the hydrographic network of France. Although there were strong relationships between our test data and estimates at the scale of France, there were also large relative local uncertainties, which varied with the physical characteristics of the segments and their catchments. Discharge and CA were relatively uncertain where discharge was low and catchments were small. Discharge uncertainty also increased in catchments with large rainfall events and low minimum temperature. The uncertainty of segment slope was strongly related to segment length. Our uncertainty models were consistent across large regions of France, suggesting some degree of generality. Their analytical formulation should facilitate their use in large‐scale ecological studies and simulation models.     

Radical,reformist, and garden-variety neoliberal: coming to terms with urban agriculture's contradictions

For many activists and scholars, urban agriculture in the Global North has become synonymous with sustainable food systems, standing in opposition to the dominant industrial agri-food system. At the same time, critical social scientists increasingly argue that urban agriculture programmes, by filling the void left by the “rolling back” of the social safety net, underwrite neoliberalisation. I argue that such contradictions are central to urban agriculture. Drawing on existing literature and fieldwork in Oakland, CA, I explain how urban agriculture arises from a protective counter-movement, while at the same time entrenching the neoliberal organisation of contemporary urban political economies through its entanglement with multiple processes of neoliberalisation. By focusing on one function or the other, however, rather than understanding such contradictions as internal and inherent, we risk undermining urban agriculture's transformative potential. Coming to terms with its internal contradictions can help activists, policy-makers and practitioners better position urban agriculture within coordinated efforts for structural change, one of many means to an end rather than an end unto itself.     

高速公路建设与区域城镇分布的相互影响初探--以山东省为例

本文在介绍山东省高速公路发展概况的基础上，对其发展速度、规模及布局做了初步评价，同时以现有的交通网络格局为基础，结合各城市2001年的GDP数量和所处的地理环境的差异，划分出城镇密集区与稀疏区，分析评价了高速公路路网结构与城镇分布的相互关系。并分析了高速公路的空间布局与山东省城镇分布和扩展方向的相互影响。     

条带开采下沉系数计算与优化设计的神经网络模型

在综合分析条带开采地表下沉系数影响因素的基础上,采用神经网络方法建立了条带开采地表下沉系数的计算模型。模型以国内外成功的条带开采实例为学习训练样本和测试样本,对模型的计算结果与实测值进行了对比分析,分析结果表明,该模型的计算值更接近于实测值。在上述研究的基础上,在给定条带开采采出率的条件下,以条带开采的地表下沉系数最小为原则,运用该模型实现了对条带开采尺寸的优化设计。该研究的成果,为条带开采地表下沉系数的理论计算及条带开采尺寸的优化设计探索出了一种新的方法。     

Emergent conservation outcomes of shared risk perception in human-wildlife systems

Human perception of risks related to economic damages caused by nearby wildlife can be transmitted through social networks. Understanding how sharing risk information within a human community alters the spatial dynamics of human-wildlife interactions has important implications for the design and implementation of effective conservation actions. We developed an agent-based model that simulates farmer livelihood decisions and activities in an agricultural landscape shared with a population of a generic wildlife species (wildlife-human interactions in shared landscapes [WHISL]). In the model, based on risk perception and economic information, farmers decide how much labor to allocate to farming and whether and where to exclude wildlife from their farms (e.g., through fencing, trenches, or vegetation thinning). In scenarios where the risk perception of farmers was strongly influenced by other farmers, exclusion of wildlife was widespread, resulting in decreased quality of wildlife habitat and frequency of wildlife damages across the landscape. When economic losses from encounters with wildlife were high, perception of risk increased and led to highly synchronous behaviors by farmers in space and time. Interactions between wildlife and farmers sometimes led to a spillover effect of wildlife damage displaced from socially and spatially connected communities to less connected neighboring farms. The WHISL model is a useful conservation-planning tool because it provides a test bed for theories and predictions about human-wildlife dynamics across a range of different agricultural landscapes.     

Teams as boundaries: How intra‐team and inter‐team brokerage influence network changes in knowledge‐seeking networks

What role does an ego's brokerage location—within a team (intra‐team) or outside the team (inter‐team)—play in the evolution of an instrumental knowledge‐seeking network in terms of both proximal (i.e., within the team) and distal (i.e., outside the team) tie formation and tie decay? We address this question by drawing on literature about social networks, brokerage, and teams. We use temporally separated data from 302 students embedded in 97 teams to test our hypotheses about the impacts of intra‐team and inter‐team brokerage on proximal and distal network evolution, specifically on four network changes in knowledge‐seeking networks: proximal tie formation, proximal tie decay, distal tie formation, and distal tie decay. We find that these four changes depend on individual network brokerage location even after controlling for personality and task characteristics. Specifically, inter‐team brokers change their networks both within and outside their teams, whereas intra‐team brokers curtail their network changes. We argue that these opposite effects occur because inter‐team brokers have greater autonomy than intra‐team brokers. This study adds to the ongoing dialog about network evolution in social network literature and to the conversations about brokerage and its location in the context of team‐based work.