A new synergetic paradigm in environmental numerical modeling: Hybrid models combining deterministic and machine learning components

A new type of environmental numerical models, hybrid environmental numerical models (HEMs) based on combining deterministic modeling and machine learning components, is introduced and formulated. Conceptual and practical possibilities of developing HEM, as an optimal synergetic combination of the traditional deterministic/first principles modeling (like that used for solving PDEs on the sphere representing model dynamics of global climate models) and machine learning components (like accurate and fast neural network emulations of model physics or chemistry processes), are discussed. Examples of developed HEMs (hybrid climate models and a hybrid wind–wave ocean model) illustrate the feasibility and efficiency of the new approach for modeling extremely complex multidimensional systems.     

Simulation of long-term nutrient removal in a full-scale closed-loop bioreactor for sewage treatment: an example of Bayesian inference

In this study, the performance of nitrogen and phosphorus removal in a full-scale closed-loop bioreactor (oxidation ditch) system was simulated using the ASM2d model. Routine data describing the process for two years were compiled for calibration and validation. To overcome the identifiability problem, the classic Bayesian inference approach was utilized for parameter estimation. The calibrated model could describe the long-term trend of nutrient removal and short-term variations of the process performance, showing that the Bayesian method was a reliable and useful tool for the parameter estimation of the activated sludge models. The anoxic phosphate uptake by polyphosphate accumulating organisms (PAO) contributed 71.2% of the total Poly-P storage, which reveals the dominance of denitrifying phosphorus removal process under the oxygen limiting conditions. It was found that 58.7% of the anoxic Poly-P storage and denitrification by PAO in the reactor was achieved in the aerated compartment, implying that the PAO’s anoxic activity was significantly stimulated by the low dissolved oxygen (DO) level in this compartment due to the oxygen gradient caused by brush aerator.     

A Bayesian approach to multi-source forest area estimation

In efforts such as land use change monitoring, carbon budgeting, and forecasting ecological conditions and timber supply, there is increasing demand for regional and national data layers depicting forest cover. These data layers must permit small area estimates of forest area and, most importantly, provide associated error estimates. This paper presents a model-based approach for coupling mid-resolution satellite imagery with plot-based forest inventory data to produce estimates of probability of forest and associated error at the pixel-level. The proposed Bayesian hierarchical model provides access to each pixel’s posterior predictive distribution allowing for a highly flexible analysis of pixel and multi-pixel areas of interest. The paper presents a trial using multiple dates of Landsat imagery and USDA Forest Service Forest Inventory and Analysis plot data. The results describe the spatial dependence structure within the trial site, provide pixel and multi-pixel summaries of probability of forest land use, and explore discretization schemes of the posterior predictive distributions to forest and non-forest classes. Model prediction results of a holdout set analysis suggest the proposed model provides high classification accuracy, 88%, for the trial site.

Effectiveness of Panama as an intercontinental land bridge for large mammals

Habitat fragmentation is a primary driver of wildlife loss, and establishment of biological corridors is a common strategy to mitigate this problem. A flagship example is the Mesoamerican Biological Corridor (MBC), which aims to connect protected forest areas between Mexico and Panama to allow dispersal and gene flow of forest organisms. Because forests across Central America have continued to degrade, the functioning of the MBC has been questioned, but reliable estimates of species occurrence were unavailable. Large mammals are suitable indicators of forest functioning, so we assessed their conservation status across the Isthmus of Panama, the narrowest section of the MBC. We used large-scale camera-trap surveys and hierarchical multispecies occupancy models in a Bayesian framework to estimate the occupancy of 9 medium to large mammals and developed an occupancy-weighted connectivity metric to evaluate species-specific functional connectivity. White-lipped peccary (Tayassu pecari), jaguar (Panthera onca), giant anteater (Myrmecophaga tridactyla), white-tailed deer (Odocoileus virginianus), and tapir (Tapirus bairdii) had low expected occupancy along the MBC in Panama. Puma (Puma concolor), red brocket deer (Mazama temama), ocelot (Leopardus pardalis), and collared peccary (Pecari tajacu), which are more adaptable, had higher occupancy, even in areas with low forest cover near infrastructure. However, the majority of species were subject to ≥1 gap that was larger than their known dispersal distances, suggesting poor connectivity along the MBC in Panama. Based on our results, forests in Darien, Donoso–Santa Fe, and La Amistad International Park are critical for survival of large terrestrial mammals in Panama and 2 areas need restoration.     

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.     

Physiochemical properties influencing biomass abundance and primary production in Lake Hoare, Antarctica

The perennially ice-covered, closed basin lakes in the McMurdo Dry Valleys respond rapidly to environmental changes, especially climate. For the past 15 years, the McMurdo Dry Valleys Long-Term Ecological Research (MCM-LTER) program has monitored the physical, chemical and biological properties of the lakes in Taylor Valley. In order to better assess the physiochemical controls on the biological process within one of these lakes (Lake Hoare), we have used vertical profile data to estimate depth-dependent correlations between various lake properties. Our analyses reveal the following results. Primary production rates (PPR) are strongly correlated to light (PAR) at 12-15 m and to soluble reactive phosphorus (SRP) at 8-22 m. Chlorophyll-a (CHL) is also positively correlated to PAR at 14 m and greater depths, and SRP from 15 m and greater. This preliminary statistical analysis supports previous observations that both PAR and SRP play significant roles in driving plant growth in Lake Hoare. The lack of a strong relationship between bacterial production (BP) and dissolved organic carbon (DOC) is an intriguing result of the analysis.     

Eliciting expert knowledge in conservation science

Expert knowledge is used widely in the science and practice of conservation because of the complexity of problems, relative lack of data, and the imminent nature of many conservation decisions. Expert knowledge is substantive information on a particular topic that is not widely known by others. An expert is someone who holds this knowledge and who is often deferred to in its interpretation. We refer to predictions by experts of what may happen in a particular context as expert judgments. In general, an expert-elicitation approach consists of five steps: deciding how information will be used, determining what to elicit, designing the elicitation process, performing the elicitation, and translating the elicited information into quantitative statements that can be used in a model or directly to make decisions. This last step is known as encoding. Some of the considerations in eliciting expert knowledge include determining how to work with multiple experts and how to combine multiple judgments, minimizing bias in the elicited information, and verifying the accuracy of expert information. We highlight structured elicitation techniques that, if adopted, will improve the accuracy and information content of expert judgment and ensure uncertainty is captured accurately. We suggest four aspects of an expert elicitation exercise be examined to determine its comprehensiveness and effectiveness: study design and context, elicitation design, elicitation method, and elicitation output. Just as the reliability of empirical data depends on the rigor with which it was acquired so too does that of expert knowledge.     

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.     

某储罐区火灾多米诺效应场景推演

化工园区中危险源众多,一旦发生事故很容易在整个园区内蔓延和发展.针对化工园区内储罐密集,容易引发连锁反应导致事故扩大的特点,利用FDS软件对储罐火灾场景进行数值模拟,根据储罐所受热辐射确定化工园区内储罐火灾最可能的事故发生序列,并引入基于设备失效前时间的机械设备故障概率模型对罐区内单个储罐的火灾风险进行研究,得到储罐区...     

Dynamic Bayesian networks for reliability evaluation of subsea wellhead connector during service life based on Monte Carlo method

The subsea wellhead connector is a critical connection component between subsea Christmas tree and subsea wellhead for preventing the leakage of oil and gas in the subsea production system. Excited by cyclical loadings due to environmental forces and the other support forces, the subsea wellhead connector is prone to the failure, which could lead to the loss of subsea tree or wellhead integrity and even catastrophic accidents. With the Monte Carlo simulation method, this paper presents a reliability analysis approach based on dynamic Bayesian Networks, aiming to assess the failure probability of the subsea wellhead connector during service life. Take the driving ring component of the subsea wellhead connector as an example to demonstrate the reasonability of the proposed model. The generation data is processed by the transform between the numerical value and the state variable. Based on the stress-strength interference theory, the structure reliability of the driving ring with 96.26% is achieved by the proposed model with the consideration the aging of the material strength and the most influential factors are figured out. Meanwhile, the corresponding control measures are proposed effectively reduce the failure risk of the subsea wellhead connector during service life.