Prediction of longitudinal dispersion coefficients in natural rivers using artificial neural network

An artificial neural network (ANN) model is developed for predicting the longitudinal dispersion coefficient in natural rivers. The model uses few rivers’ hydraulic and geometric characteristics, that are readily available, as the model input, and the target output is the longitudinal dispersion coefficient (K). For performance evaluation of the model, using published field data, predictions by the developed ANN model are compared with those of other reported important models. Based on various performance indices, it is concluded that the new model predicts the longitudinal dispersion coefficient more accurately. Sensitive analysis performed on input parameters indicates stream width, flow depth, stream sinuosity, flow velocity, and shear velocity to be the most influencing parameters for accurate prediction of the longitudinal dispersion coefficient.     

Artificial neural network modeling of the river water quality—A case study

The paper describes the training, validation and application of artificial neural network (ANN) models for computing the dissolved oxygen (DO) and biochemical oxygen demand (BOD) levels in the Gomti river (India). Two ANN models were identified, validated and tested for the computation of DO and BOD concentrations in the Gomti river water. Both the models employed eleven input water quality variables measured in river water over a period of 10 years each month at eight different sites. The performance of the ANN models was assessed through the coefficient of determination (R²) (square of the correlation coefficient), root mean square error (RMSE) and bias computed from the measured and model computed values of the dependent variables. Goodness of the model fit to the data was also evaluated through the relationship between the residuals and model computed values of DO and BOD. The model computed values of DO and BOD by both the ANN models were in close agreement with their respective measured values in the river water. Relative importance and contribution of the input variables to the model output was evaluated through the partitioning approach. The identified ANN models can be used as tools for the computation of water quality parameters.     

Artificial neural network modeling of caste odor discrimination based on cuticular hydrocarbons in termites

Summary. Individuals in an insect colony need to identify one another according to caste. Nothing is known about the sensory process allowing nestmates to discriminate minute variations in the cuticular hydrocarbon mixture. The purpose of this study was to attempt to model caste odors discrimination in four species of Reticulitermes termites for the first time by a non-linear mathematical approach using an "artificial neural network" (ANN). Several rounds of testing were carried out using 1 – the whole hydrocarbon mixtures 2 – mixtures containing the hydrocarbons selected by principal component analysis (PCA) as the most implicated in caste discrimination. Discrimination between worker and soldier castes was tested in all four species. For two species we tested discrimination of four castes (workers, soldiers, nymphs, neotenics). To test cuticular pattern similarity in two sibling species (R. santonensis and R. flavipes), we performed two experiments using one species for training and the other for query. Using whole hydrocarbons mixtures, worker/soldier discrimination was always successful in all species. Network performance decreased with the number of hydrocarbons used as inputs. Four-caste discrimination was less successful. In the experiment with the sibling species, the ANN was able to distinguish soldiers but not workers. The results of this study suggest that non-linear mathematical analysis is a good tool for classification of castes based on cuticular hydrocarbon mixture. In addition this study confirms that hydrocarbon mixtures observed are real chemical entities and constitute a true chemical signature or odor. Whole mixtures are not always necessary for discrimination. Received 23 July 1998; accepted 9 October 1998.     

Spatiotemporal calibration of atmospheric nitrogen dioxide concentration estimates from an air quality model for Connecticut

Environmental and Ecological Statistics - A spatiotemporal calibration and resolution refinement model was fitted to calibrate nitrogen dioxide ($$\hbox {NO}_2$$) concentration estimates from the...     

Case study on nitrogen and phosphorus emissions from paddy field in Taihu region

The agricultural non-point source pollution by nitrogen (N) and phosphorus (P) loss from typical paddy soil (whitish soil, Bai Tu in Chinese) in the Taihu Lake region was investigated through a case study. Results shown that the net load of nutrients from white soil is 34.1 kg ha(-1) for total nitrogen (TN), distributed as 19.4 kg ha(-1), in the rice season and 14.7 kg ha(-1) in the wheat season, and for total phosphorus (TP) 1.75 kg ha(-1), distributed as 1.16 kg ha(-1) in the rice season and 0.58 kg ha(-1) in the wheat season. The major chemical species of N loss is different in the two seasons. NH4-N is main the form in the rice season (53% of TN). NO3-N is the main form in wheat season (46% of TN). Particle-P is the main form in both seasons, (about 56% of TP). The nutrient loss varied with time of the year. The main loss of nutrients happened in the 10 days after planting, 64% of TN and 42% of TP loss, respectively. Rainfall and fertilizer application are the key factors which influence nitrogen and phosphorus loss from arable land, especially rainfall events shortly after fertilizer application. So it is very important to improve the field management of the nutrients and water during the early days of planting.     

广州市园林绿化植物苗木对二氧化硫和二氧化氮吸收能力分析

采用人工模拟熏气法,研究了36种广州市园林绿化植物对SO2和NO2气体吸收净化能力,以系统聚类分析方法为依据,将参试植物的吸收净化能力划分为强性、较强、中等、较弱及弱5个等级。结果显示,在不同SO2质量浓度（0.259和0.448 mg.m-3）环境下,黄槐、鸡冠刺桐、红花银桦、木棉、红千层、大花紫薇、复羽叶栾树吸收SO2能力具有强或较强的能力,而罗汉松、竹柏、深山含笑、乐昌含笑、观光木、樟树、阴香、双翼豆、印度紫檀、大花五桠果、长芒杜英、五月茶、海南蒲桃、芒果、海南红豆、糖胶树和幌伞枫吸收SO2能力表现为较弱或弱;在NO2质量浓度（0.149和0.428 mg.m-3）环境下,黄槐、黄葛榕、红花银桦、红千层、麻楝、复羽叶栾树、大花紫薇和小叶榄仁吸收净化NO2能力为较强或强,而深山含笑、五月茶、芒果、海南红豆、糖胶树和桂花叶片对NO2吸收能力表现为较弱或弱。在不同SO2和NO2浓度环境下,黄槐、红花银桦、红千层、复羽叶栾树和大花紫薇叶片对SO2和NO2吸收净化能力表现为强或较强,而深山含笑、五月茶、芒果、海南红豆、糖胶树叶片对SO2和NO2吸收净化能力为较弱或弱。研究结果为珠三角城市功能型园林植物选择和广东生态景观林带建设提供科学依据。     

Integrated biogeochemical modelling of nitrogen load from anthropogenic and natural sources in Japan

This study proposed an integrated biogeochemical modelling of nitrogen loads from anthropogenic and natural sources in Japan. Firstly, the nitrogen load (NL) from different sources such as crop, livestock, industrial plant, urban and rural resident was calculated by using datasets of fertilizer utilization, population distribution, land use map, and social census. Then, the nitrate leaching from soil layers in farmland, grassland and natural conditions was calculated by using a terrestrial nitrogen cycle model (TNCM). The Total Runoff Integrating Pathways (TRIP) was used to transport nitrogen from natural and anthropogenic sources through river channels, as well as collect and route nitrogen to the river mouths. The forcing meteorological and hydrological data is a 30-year (1976–2005) dataset for Japan which were obtained by the land surface model, Minimal Advanced Treatments of Surface Interaction and Runoff (MATSIRO). For the model validation, we collected total nitrogen (TN) concentration data from 59 rivers in Japan. As a comparison result, calculated TN concentration values were in good agreement with the observed ones, which shows the reliability of the proposed model. Finally, the TN loads from point and nonpoint sources were summarized and evaluated for 59 river basins in Japan. The proposed modelling framework can be used as a tool for quantitative evaluation of nitrogen load in terrestrial ecosystems at a national scale. The connection to land use and climate data provides a possibility to use this model for analysis of climate change and land use change impacts on hydrology and water quality.     

Using artificial neural network for reservoir eutrophication prediction

Reservoirs provide approximately 70% of water supply for domestic and industrial use in Taiwan. The water quality of reservoirs is now one of the key factors in the operation and water quality management of reservoirs. Transient weather patterns result in highly variable magnitudes of precipitation and thereby sharp fluctuations in the surface elevation of the reservoirs. In addition, excessive watershed development in the past two decades has contributed to continuing increase in nutrient loads to the reservoirs. The difficulty in quantifying watershed nutrient loads and uncentainties in kinetic mechanism in the water column present a technical challenge to the mass balance based modeling of reservoir eutrophication. This study offers an alternative approach to quantifying the cause-and-effect relationship in reservoir eutrophication with a data-driven method, i.e., capturing non-linear relationships among the water quality variables in the reservoir. A commonly used back-propagation neural network was used to relate the key factors that influence a number of water quality indicators such as dissolved oxygen (DO), total phosphorus (TP), chlorophyll-a (Chl-a), and secchi disk depth (SD) in a reservoir in central Taiwan. Study results show that the neural network is able to predict these indicators with reasonable accuracy, suggesting that the neural network is a valuable tool for reservoir management in Taiwan.     

A Bayesian network approach to modelling land-use decisions under environmental policy incentives in the Brazilian Amazon

ABSTRACT

Deforestation driven by agricultural expansion is a major threat to the biodiversity of the Amazon Basin. Modelling how deforestation responds to environmental policy implementation has thus become a policy relevant scientific undertaking. However, empirical parameterization of land-use/cover change (LUCC) models is challenging due to the high complexity and uncertainty of land-use decisions. Bayesian Network (BN) modelling provides an effective framework to integrate various data sources including expert knowledge. In this study, we integrate remote sensing products with data from farm-household surveys and a decision game to model LUCC at the BR-163, in Brazil. Our ‘business as usual’ scenario indicates cumulative forest cover loss in the study region of 8,000 km² between 2014 and 2030, whereas ‘intensified law-enforcement’ would reduce cumulative deforestation to 1,600 km² over the same time interval. Our findings underline the importance of conservation law enforcement in modulating the impact of agricultural market incentives on land cover change.     

An integrated river basin-coast-sea modelling scenario for nitrogen management in coastal waters

Linked river basin and coastal water models were applied to analyse the effects of an optimal nitrogen management scenario in the Oder/Odra river basin on water quality in the Oder (Szczecin) Lagoon and the Pomeranian Bay (Baltic Sea). This scenario would reduce nitrogen loads into the coastal waters by about 35%, a level which is similar to the load of the late 1960’s. During summer the primary production and algae biomass in the Oder estuary is limited by nitrogen, which makes a nitrogen management reasonable. The comparison of the late 1960’s and the mid 1990’s shows that an optimal nitrogen management has positive effects on coastal water quality and algae biomass. However, this realistic nitrogen reduction scenario would not ensure a good coastal water quality according to the European Water Framework Directive. A good water quality in the river will not be sufficient to ensure a good water quality in the lagoon. Nitrogen load reductions bear the risk of increased potentially toxic, blue-green algae blooms, especially in the Baltic coastal sea. However, to reach water quality improvements in lagoons and inner coastal waters, nitrogen cuts are necessary. A mere focus on phosphorus is not sufficient.     

Verification of the plume rise/dispersion model USPR: plume rise for single stack emissions

Despite proliferation of the use of air pollution models for regulatory application, major discrepancies still occur between models and also between models and observations, especially when oversimplistic models are used. The problem of predicting plume rise (and subsequently ground level concentrations) from a single source is evaluated here in terms of an integral plume rise and dispersion model (USPR) which encompasses both bouyant rise and turbulent spreading; thus avoiding the problems of the concatenation of separate plume rise and dispersion models. The wide range of validity of the USPR model is demonstrated is terms of plume rise by comparison with the highly buoyant GCOS and Kincaid plumes as well as with dense effluents. It is also shown to be in agreement with Briggs' two-thirds law when the restrictions applicable to the latter model are imposed.     

应用于水文预报的优化BP神经网络研究

利用广东省滨江流域的水文观测资料，建立了以前期降水量为预报因子、以水位为输出的BP人工神经网络水文预报模型。首先采用了合理的方法进行样本组织，进而利用最优子集回归技术进行输入因子的确定，然后进行了不同隐层节点数、不同转移函数、不同训练算法的组合试验，确定了应用于水文预报中的优化BP神经网络：网络结构为8-9-1；转移函数的组合方式为tansig-线性函数；训练算法为采用evenberg-Marquardt(Lm)算法。为便于精度分析，还采用了最优子集回归模型作了研究。结果表明，优化BP网络模型无论在拟合精度还是在预测精度上都高于最优子集模型。总的来说BP网络是一种精度较高的水文预测模型。     

Unbiased sensitivity analysis and pruning techniques in neural networks for surface ozone modelling

This paper presents the use of artificial neural networks (ANNs) for surface ozone modelling. Due to the usual non-linear nature of problems in ecology, the use of ANNs has proven to be a common practice in this field. Nevertheless, few efforts have been made to acquire knowledge about the problems by analysing the useful, but often complex, input–output mapping performed by these models. In fact, researchers are not only interested in accurate methods but also in understandable models. In the present paper, we propose a methodology to extract the governing rules of trained ANN which, in turn, yields simplified models by using unbiased sensitivity and pruning techniques. Our proposal has been evaluated in thousands of trained ANNs under different conditions to establish a relationship between present contaminants (or several atmospheric variables) and surface ozone concentrations. The technique presented has demonstrated to be unbiased and stable with regard to the interpretability of the models and the good results obtained.     

Dynamic compartment approach for modelling regimes of carbon cycle functioning in bog ecosystems

Svirezhev's method of dynamic model design by a given “storage-flow” diagram [Svirezhev Y.M., 1997. On some general properties of trophic networks. Ecol. Model. 99, 7–17] is developed and used for investigating dynamic regimes of carbon cycle functioning in a typical boreal transitional bog ecosystem. Ecosystems are often represented by static “storage-flow” diagrams reflecting their structure and matter or energy transfer between components at fixed time moments. Using the data of such diagrams aggregated in ecological field studies one can construct a dynamic model of the ecosystem to predict its future behaviour and to estimate a response to external perturbations—natural and human. Stability of both current equilibrium and possible alternative steady states and more complicated attractors are studied under two types of parameter perturbation: CO₂ atmospheric concentration increase initiated by greenhouse effect, and change in the rate of carbon output from dead organic matter and litter which depends on the water table level and possible peat excavation. Calculation of bifurcation curves gives areas in the parameter space where stable functioning of carbon cycle is provided. Steady states can be interpreted as raised bog, meadow, forest and fen. CO₂ concentration increase leads the current state of transitional bog to loose stability with appearance of oscillatory dynamics and further evolution to the chaotic attractor. The model is rich by chaotic solutions serving as transition regimes between regular steady and periodic attractors. Another chaotic regime is formed from forest equilibrium and exists in the same area of phase space where current equilibrium is stable.     

An adapted companion modelling approach for enhancing multi-stakeholder cooperation in complex river basins

The sustainable development agenda 2030 calls for achievement of certain targets to ensure access to water and sanitation for all. Multi-stakeholder partnerships and the use of data and modelling tools are conditioning elements for their achievement. In this article, we demonstrate that participatory modelling supports informed and participatory decision making in complex river basins. An adapted companion modelling approach is presented to support collective action by reducing disputes and enhancing collaboration among stakeholders. The co-development and use of empirical models for understanding the complexity of the physical system is combined with the use of role-playing games to ensure the active involvement of stakeholders. The approach is implemented in a top-down water quality planning process in Turkey. Results show its suitability for managing water quality in complex river basins in an inclusive manner and its substantial benefits in developing stakeholders’ capacities and creating a cooperative environment.     

Fuzzy experts on recreational vessels, a risk modelling approach for marine invasions

Understanding risks from the human-mediated spread of non-indigenous species (NIS) is a critical component of marine biosecurity management programmes. Recreational boating is well-recognised as a NIS pathway, especially at a regional scale. Assessment of risks from this pathway is therefore desirable for coastal environments where recreational boating occurs. However, formal or quantitative risk assessment for the recreational vessel pathway is often hampered by lack of data, hence often relies on expert opinion. The use of expert opinion itself is sometimes limited by its inherent vagueness, which can be an important source of uncertainty that reduces the validity and applicability of the assessment. Fuzzy logic, specifically interval type-2 fuzzy logic, is able to model and propagate this type of uncertainty, and is a useful technique in risk assessment where expert opinion is relied upon. The present paper describes the implementation of a NIS fuzzy expert system (FES) for assessing the risk of invasion in marine environments via recreational vessels. The FES was based on expert opinion gathered through systematic elicitation exercises, designed to acknowledge important uncertainty sources (e.g., underspecificity and ambiguity). The FES, using interval type-2 fuzzy logic, calculated an invasion risk value (integrating NIS infection and detection probabilities) for a range of invasion scenarios. These scenarios were defined by all possible combinations of two vessel types (moored and trailered), five vessel components (hull, deck, internal spaces, anchor, fishing gear), two infection modes (fouling, water/sediment retention) and six frequently visited marine habitats (marina, mooring, farm, ramp, wharf, anchorage). Although invasion risk values determined using the FES approach was scenario-specific, general patterns were identified. Moored vessels consistently showed higher invasion risk values than trailered vessels. Invasion risk values were higher for anchorages, moorings and wharves. Similarly, hull-fouling was revealed as the highest infection risk mode after pooling results across all habitats. The NIS fuzzy expert system presented here appears as a valuable prioritising and decision-making tool for NIS research, prevention and control activities. Its easy implementation and wide applicability should encourage the development and application of this type of system as an integral part of biosecurity, and other environmental management plans.     

New parameterization scheme for effective indices for emissions from road transport

The local to regional processes of chemical transformations, washout and dry deposition cannot be directly resolved in global scale models, they rather need to be parameterized. A suitable way to account for the non-linearity, e.g., in chemical transformation processes, is the use of effective emission indices (EEIs). EEI translate the actual (small scale) emissions into input for global scale models, partially accounting for unresolved processes occurring shortly after the release of the emissions.The emissions from the road traffic have some specifics, because of which the concept of deriving EEI from the interaction of an instantaneous plume with the ambient air is perhaps not so convenient. A new parameterization scheme for the EEI from the road transport is suggested in the present paper, based on few simplifying assumptions and introducing the adjoin equations approach, which makes it possible to achieve unified, not depending on the specific emission pattern, procedure for calculating the EEI from road traffic.     

A network approach to prioritize conservation efforts for migratory birds

Habitat loss can trigger migration network collapse by isolating migratory bird breeding grounds from nonbreeding grounds. Theoretically, habitat loss can have vastly different impacts depending on the site's importance within the migratory corridor. However, migration-network connectivity and the impacts of site loss are not completely understood. We used GPS tracking data on 4 bird species in the Asian flyways to construct migration networks and proposed a framework for assessing network connectivity for migratory species. We used a node-removal process to identify stopover sites with the highest impact on connectivity. In general, migration networks with fewer stopover sites were more vulnerable to habitat loss. Node removal in order from the highest to lowest degree of habitat loss yielded an increase of network resistance similar to random removal. In contrast, resistance increased more rapidly when removing nodes in order from the highest to lowest betweenness value (quantified by the number of shortest paths passing through the specific node). We quantified the risk of migration network collapse and identified crucial sites by first selecting sites with large contributions to network connectivity and then identifying which of those sites were likely to be removed from the network (i.e., sites with habitat loss). Among these crucial sites, 42% were not designated as protected areas. Setting priorities for site protection should account for a site's position in the migration network, rather than only site-specific characteristics. Our framework for assessing migration-network connectivity enables site prioritization for conservation of migratory species.     

Optimal within-patch movement strategies for optimising patch residence time: an agent-based modelling approach

Several optimisation models, like the marginal value theorem (MVT), have been proposed to predict the optimal time foraging animals should remain on patches of resources. These models do not clearly indicate, however, how animals can follow the corresponding predictions. Hence, several proximate patch-leaving decision rules have been proposed. Most if not all of these are based on the animals’ motivation to remain on the patches, but the real behaviours involved in such motivation actually still remain to be identified. Since animals are usually exploiting patches of resources by walking, we developed a model simulating the intra-patch movement decisions of time-limited animals exploiting resources distributed in delimited patches in environments with different resource abundances and distributions. The values of the model parameters were optimised in the different environments by means of a genetic algorithm. Results indicate that simple modifications of the walking pattern of the foraging animals when resources are discovered can lead to patch residence times that appear consistent with the predictions of the MVT. These results provide a more concrete understanding of the optimal patch-leaving decision rules animals should adopt in different environments.     

基于概率神经网络的污泥堆肥腐熟度的综合判别

由于污泥堆肥过程中各组分间相互影响和制约,污泥腐熟程度的判别系统呈现模糊性,使得传统评价方法对该判别系统很难正确认识。文章根据污泥堆肥的具体情况,提出了以含水率、挥发固体、粪大肠菌值、发芽指数作为腐熟程度的判别指标体系,并基于概率神经网络建立污泥堆肥腐熟程度的综合判别模型,然后用该模型判别上海市某污水厂污泥快速好氧堆肥工艺污泥堆肥样品的腐熟程度。结果表明:①将污泥堆肥的含水率、有机质、粪大肠菌值和种子发芽指数作为判别指标,可以判别污泥堆肥腐熟程度;②概率神经网络可以建立判别指标与稳定化程度等级之间复杂的非线性关系,为腐熟度的判别提供一种通用的模式,且判别结果比较合理。