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.     

Application of artificial neural network in medical geochemistry

For the evaluation of various adverse health effects of chemical elements occurring in the environment on humans, the comparison and linking of geochemical data (chemical composition of groundwater, soils, and dusts) with data on health status of population (so-called health indicators) play a key role. Geochemical and health data are predominantly nonlinear, and the use of standard statistical methods can lead to wrong conclusions. For linking such data, we find appropriate the use method of artificial neural networks (ANNs) which enable to eliminate data inhomogeneity and also potential data errors. Through method of ANNs, we are able to determine the order of influence of chemical elements on health indicators as well as to define limit values for the influential elements at which the health status of population is the most favourable (i.e. the lowest mortality, the highest life expectancy). For determination of dependence between the groundwater contents of chemical elements and health indicators, we recommend to create 200 ANNs. In further calculations performed for identification of order of influence of chemical elements as well as definition of limit values, we propose to work with median or mean values from calculated 200 ANNs. The ANN represents an appropriate method to be used for environmental and health data analysis in medical geochemistry.     

Estimation of total sediment load concentration obtained by experimental study using artificial neural networks

Estimation of sediment concentration in rivers is very important for water resources projects planning and managements. The sediment concentration is generally determined from the direct measurement of sediment concentration of river or from sediment transport equations. Direct measurement is very expensive and cannot be conducted for all river gauge stations. However, sediment transport equations do not agree with each other and require many detailed data on the flow and sediment characteristics. The main purpose of the study is to establish an effective model which includes nonlinear relations between dependent (total sediment load concentration) and independent (bed slope, flow discharge, and sediment particle size) variables. In the present study, by performing 60 experiments for various independent data, dependent variables were obtained, because of the complexity of the phenomena, as a soft computing method artificial neural networks (ANNs) which is the powerful tool for input–output mapping is used. However, ANN model was compared with total sediment transport equations. The results show that ANN model is found to be significantly superior to total sediment transport equations.     

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.     

Applying artificial neural network methodology to ocean color remote sensing

Artificial neural networks (ANN) are widely used as continuous models to fit non-linear transfer functions. In this study we used ANN to retrieve chlorophyll pigments in the near-surface of oceans from Ocean Color measurements. This bio-optical inversion is established by analyzing concomitant sun-light spectral reflectances over the ocean surface and pigment concentration. The relationships are complex, non-linear, and their biological nature implies a significant variability. Moreover, the sun-light reflectances are usually measured by satellite radiometers flying at 800 km over the ocean surface, which affect the data by adding radiometric noise and atmospheric correction errors. By comparison with the polynomial fit usually employed to treat this problem, we show the advantages of neural function approximation like the association of non-linear complexity and noise filtering.     

神经网络模型森林生物量遥感估测方法的研究

森林生物量的估测是全球变化研究的基础,而遥感宏观、综合、动态、快速的特点决定了基于遥感的生物量模型为森林生物量估测的发展方向,目前的遥感生物量估测方法大多基于回归分析,需要预先假设、事后检验,仅为经验性的统计模型。神经网络的分布并行处理、非线性映射、自适应学习和容错等特性,使其具有独特的信息处理和计算能力,在机制尚不清楚的高维非线性系统体现出强大优势,可以用于遥感生物量估测。文章在野外调查的基础上,尝试应用BP网络和RBF网络技术,建立广州TM遥感影像数据与森林样方生物量实测数据之间的神经网络模型,通过训练和仿真,与生物量实测数据进行比较。结果表明,在独立样地估测中,人工神经网络估测的相对误差均小于15.18%,获得了满意的效果。而RBF网络与BP网络相比,在识别精度上、稳定性、速度上,均优于BP网络,其最大相对误差不超过10.12%,平均相对误差为4.76%。可见应用神经网络方法的“黑箱”操作虽然难以归纳出指导性规律,但可以获得很高的精度。尤其RBF网络,在训练完成后,可以应用该模型进行大区域生物量估算,对于森林的规划及管理具有深远意义。     

Modeling and inference of animal movement using artificial neural networks

Movement of animals in relation to objects in their environment is important in many areas of ecology and wildlife conservation. Tools for analysis of movement data, however, still remain rather limited. In previous work, we developed nonlinear regression models for movement in relation to a single landscape feature. Here we greatly expand these previous models by using artificial neural networks. The new models add substantial flexibility and capabilities, including the ability to incorporate multiple factors and covariates. We devise a likelihood-based model fitting procedure that utilizes genetic algorithms and demonstrate the approach with movement data for red diamond rattlesnakes. The proposed methodology can be useful for global positioning system tracking data that are becoming more common in studies of animal movement behavior.     

Estimation of the longitudinal dispersion coefficient using a two-zone model in a channel partially covered with artificial emergent vegetation

Environmental Fluid Mechanics - Understanding scalar transport in solvents is important in chemical engineering, pollution control, and water remediation, where the longitudinal dispersion...     

Review and comparison of methods to study the contribution of variables in artificial neural network models

Convinced by the predictive quality of artificial neural network (ANN) models in ecology, we have turned our interests to their explanatory capacities. Seven methods which can give the relative contribution and/or the contribution profile of the input factors were compared: (i) the ‘PaD’ (for Partial Derivatives) method consists in a calculation of the partial derivatives of the output according to the input variables; (ii) the ‘Weights’ method is a computation using the connection weights; (iii) the ‘Perturb’ method corresponds to a perturbation of the input variables; (iv) the ‘Profile’ method is a successive variation of one input variable while the others are kept constant at a fixed value; (v) the ‘classical stepwise’ method is an observation of the change in the error value when an adding (forward) or an elimination (backward) step of the input variables is operated; (vi) ‘Improved stepwise a’ uses the same principle as the classical stepwise, but the elimination of the input occurs when the network is trained, the connection weights corresponding to the input variable studied is also eliminated; (vii) ‘Improved stepwise b’ involves the network being trained and fixed step by step, one input variable at its mean value to note the consequences on the error. The data tested in this study concerns the prediction of the density of brown trout spawning redds using habitat characteristics. The PaD method was found to be the most useful as it gave the most complete results, followed by the Profile method that gave the contribution profile of the input variables. The Perturb method allowed a good classification of the input parameters as well as the Weights method that has been simplified but these two methods lack stability. Next came the two improved stepwise methods (a and b) that both gave exactly the same result but the contributions were not sufficiently expressed. Finally, the classical stepwise methods gave the poorest results.     

Prediction of sulphur removal with Acidithiobacillus sp. using artificial neural networks

Artificial neural network (ANN) model was used to predict the extent of sulphur removal from three types of coal using native cultures of Acidithiobacillus ferrooxidans. The type of coal, initial pH, pulp density, particle size, residence time, media composition and initial sulphur content of coal were fed as input to the network. The output of the model was sulphur removal. The resulting ANN showed satisfactory prediction of sulphur removal percentages with mean absolute deviations varying from 0.003 to 0.5. A three layer feed forward neural network model consisting of an input layer, one hidden layer and an output layer was found to give satisfactory results. Although the number of data sets were limited, the parity plot shows that the model estimations for the test set was good.     

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。     

Pesticide prediction in ground water in North Carolina domestic wells using artificial neural networks

This paper illustrates the application of artificial neural networks (ANN) for prediction of pesticide occurrence in rural domestic wells from the available limited information. Among the three ANN models (a feed-forward back propagation [BP], a radial basis function [RBF] and an adaptive neural network-based fuzzy inference system [ANFIS]) employed for this investigation, the BP neural network was found to be superior to RBF and ANFIS type networks for the detection of pesticide occurrences in wells. For improved model prediction efficiency, optimization of network structure (e.g., number of hidden layers and number of nodes in each hidden layer) and spread (the width of the radial basis function) are important for BP and RBF type of network, respectively. A four layer BP network with a 3:2 neurons ratio of the first hidden layer to the second hidden layer produced better prediction performance efficiencies in terms of the pesticide detection efficiency (E_f), the root mean square error (RMSE), and the correlation coefficient (R) and the overall E_f of the BP neural network was found greater than 85%. Sensitivity analysis was performed to measure the relative importance of one input parameter over the other in pesticide occurrence in wells. It was shown in terms of the prediction efficiencies (E_f, RMSE, and R) of a four-layer BP neural network that the time of sample collection (TSC; month of the year), the depths of wells, and pesticide travel times (PTT) were more important parameters in the prediction of the pesticide occurrences in rural domestic wells. This means that the wells having shallow ground water table are more vulnerable to pesticide occurrence.     

Modification of a stream temperature model with Beer's law and application to GaoShan Creek in Taiwan

A physics-based stream temperature model [Tung, C.P., Lee, T.Y., Yang, Y.C., 2006. Modelling climate-change impacts on stream temperature of Formosan Landlocked Salmon habitat. Hydrol. Process. 20, 1629–1649] was improved by incorporating shading effects caused by both cliff terrain and riverbank dense vegetation to simulate hourly stream temperature variations in 1 day. Daily maximal stream temperature is a critical factor to the habit distribution of the Formosan Landlocked Salmon, an important and endangered species. Currently, it only can be found in ChiChiaWan Creek and GaoShan Creek in Taiwan. The former stream temperature model only considers the shading effects of cliff terrain and works well for ChiChiaWan Creek, but overestimates stream temperatures of GaoShan Creek having dense riverbank vegetative covers. The model was modified with the Beer's law and a parameterization scheme to describe the diminishing of the incident solar radiation to take vegetative shading effects into account. Simulation results of GaoShan Creek show the success of this improvement. The shading effects induced by both terrain and vegetation can significantly affect stream temperature distributions. Simulation experiments were conducted to indicate shading effects are varied in different watersheds and seasons.     

应用自组织人工神经网络预报黄土高原生态破坏程度的初探

运用三维ＴＫｏｈｏｎｅｎ自组织人工神经网络，分析预测黄土高原生态经济破坏程度，预测成功率１００％。结果表明，神经网络方法性能良好，可望成为生态经济破坏程度预测的有效的辅助手段。     

基于人工神经网络方法的河北省近海沉积物重金属污染综合评价

利用误差反相传播神经（BP）网络对河北省近海沉积物中的铅、镉、锌、汞、砷5种重金属元素的污染水平进行分析,利用自组织特征映射（SOFM）网络对上述重金属元素分布特征进行分类,通过分类与污染水平量化值的结合,进行综合评价。SOFM把52个沉积物样品分别划分为3、4、6类和9类。对比各种分类,分为3类的物理意义较明确。每个类别分别对应高中低不同的污染物浓度水平,差异显著、分类方式比较合理。通过此种分类可以判断河北省近海的沉积物重金属污染在不同海域存在一定的差别,整体上是离海岸越远,沉积物的重金属污染水平越高,距海岸较近的海域内,沉积物的重金属污染水平较低,但渤海湾内的重金属污染水平高于其他海域。     

基于人工神经网络方法的河北省近海沉积物重金属污染综合评价

利用误差反相传播神经(BP)网络对河北省近海沉积物中的铅、镉、锌、汞、砷5种重金属元素的污染水平进行分析,利用自组织特征映射(SOFM)网络对上述重金属元素分布特征进行分类,通过分类与污染水平量化值的结合,进行综合评价。SOFM把52个沉积物样品分别划分为3、4、6类和9类。对比各种分类,分为3类的物理意义较明确,每个类别分别对应高中低不同的污染物浓度水平,差异显著、分类方式比较合理。通过此种分类可以判断河北省近海的沉积物重金属污染在不同海域存在一定的差别,整体上是离海岸越远,沉积物的重金属污染水平越高,距海岸较近的海域内,沉积物的重金属污染水平较低,但渤海湾内的重金属污染水平高于其他海域。     

Simulating wildfire patterns using a small-world network model

This paper presents the development and validation results of a weighted small-world network model designed to simulate fire patterns in real heterogeneous landscapes. Fire spread is simulated on a gridded landscape, a mosaic in which each cell represents an area of the land surface. In this model, the interaction between burning and non-burning cells (here, due to flame radiation) may extend well beyond nearest neighbors, and depends on local conditions of wind, topography, and vegetation. An approach based on the coupling of the solid flame model with the Monte Carlo method is used to predict the radiative heat flux from the flame generated by the burning of each combustible cell to its neighbors. The weighting procedure takes into account latency (a combustible cell will only ignite when it has accumulated enough energy along time) and flaming persistence of burning cells. The model is applied to very different fire scenarios: a historical Mediterranean fire that occurred in southeastern France in 2005 and experimental fires conducted in arid savanna fuels in South Africa in 1992. Model results are found to be in agreement with real fire patterns, in terms both of rate of spread, and of the area and shape of the burn. This work also shows that the fractal properties of fire patterns predicted by the model are similar to those observed from satellite images of three other Mediterranean fire scars.     

Implications of network particle tracking (NPT) for ecological model interpretation

Network particle tracking (NPT), building on the foundation of network environ analysis (NEA), is a new development in the definition of coherence relations within and between connected systems. This paper evaluates three ecosystem models in a comparison of throughflow- and storage-based NEA and NPT. Compartments in models with high indirect effects and Finn cycling showed low correlation of NEA storage and throughflow with particle repeat visits and numbers of particles in compartments at steady state. Conversely, the correlation between NEA and NPT results was high with two models having lower indirect effects and Finn cycling. Analysis of ecological orientors associated with NEA showed NPT to fully support conventional NEA results when the common conditions of donor control and steady state are satisfied. Particle trajectories are recorded in the new concept of a particle “passport”. Ability to track and record particle in-system histories enables views of multiple scales and opens the possibility of making pathway-dependent modeling decisions. NPT may also enable modeling of time, allowing integration of Newtonian, organismal and stochastic modeling perspectives in a single comprehensive analysis.     

Estimation of urban sensible heat flux using a dense wireless network of observations

The determination of the sensible heat flux over urban terrain is challenging due to irregular surface geometry and surface types. To address this, in 2006–07, a major field campaign (LUCE) took place at the école Polytechnique Fédérale de Lausanne campus, a moderately occupied urban site. A distributed network of 92 wireless weather stations was combined with routine atmospheric profiling, offering high temporal and spatial resolution meteorological measurements. The objective of this study is to estimate the sensible heat flux over the built environment under convective conditions. Calculations were based on Monin–Obukhov similarity for temperature in the surface layer. The results illustrate a good agreement between the sensible heat flux inferred from the thermal roughness length approach and independent calibrated measurements from a scintillometer located inside the urban canopy. It also shows that using only one well-selected station can provide a good estimate of the sensible heat flux over the campus for convective conditions. Overall, this study illustrates how an extensive network of meteorological measurements can be a useful tool to estimate the sensible heat flux in complex urban environments.