共查询到20条相似文献，搜索用时 31 毫秒
1.
Neural network simulation of spring flow in karst environments 总被引：2，自引：2，他引：0
Evan K. Paleologos Irene Skitzi K. Katsifarakis Nektarios Darivianakis 《Stochastic Environmental Research and Risk Assessment (SERRA)》2013,27(8):1829-1837
Daily discharges of two springs lying in a karstic environment were simulated for a period of 2.5 years with the use of a multi-layer perceptron back-propagation neural network. Two models were developed for the springs, one relying on the original data and another where the missing discharge values were supplemented by assuming linear relationships during base flow conditions. For both springs the mean square error of the two models did not differ significantly, with an improvement exhibited at the extremes, during the network’s training phase, by the model that utilized the extended data set, the results of which are reported here. The time lag between precipitation and spring discharge differed significantly for the two springs indicating that in karstic environments hydraulic behavior is dominated, even within a few hundred meters, by local conditions. Optimum training results were attained with a Levenberg–Marquardt algorithm resulting in a network architecture consisting of two input layer neurons, four hidden layer neurons, and one output layer neuron, the spring’s discharge. The neural network’s predictions captured the behavior for both springs and followed very closely the discontinuities in the discharge time series. Under-/over-estimation of observed discharges for the two springs remained below 3 %, with the exception of a few local maxima where the predicted discharges diverged more strongly from observed values. Inclusion of temperature data did not add to the improvement of predictions. Finally, optimum predictions were attained when past discharge data were added to the input record and discharge differentials rather than direct discharges were calculated resulting in elimination of any local maximum discrepancy between observed and predicted discharge values. 相似文献
2.
Following many applications artificial neural networks (ANNs) have found in hydrology, a question has been rising for quantification of the output uncertainty. A pre‐optimized ANN simulated the hydraulic head change at two observation wells, having as input hydrological and meteorological parameters. In order to calculate confidence intervals (CI) for the ANN output two bootstrap methods were examined namely bootstrap percentile and BCa (Bias‐Corrected and accelerated). The actual coverage of the CI was compared to the theoretical coverage for different certainty levels as a means of examining the method's reliability. The results of this work support the idea that the bootstrap methods provide a simple tool for confidence interval computation of ANNs. Comparing the two methods, the percentile requires fewer calculations and yields narrower intervals with similar actual coverage to that of BCa. Overall, the actual coverage was proved lower than desired when not modeled points were present in the data subset. Copyright © 2011 John Wiley & Sons, Ltd. 相似文献
3.
Linear and nonlinear input/output models for karstic springflow and flood prediction at different time scales 总被引：1，自引：1，他引：0
D. Labat R. Ababou A. Mangin 《Stochastic Environmental Research and Risk Assessment (SERRA)》1999,13(5):337-364
Karstic formations function as three-dimensional (3D) hydrological basins, with both surface and subsurface flows through
fissures, natural conduits, underground streams and reservoirs. The main characteristic of karstic formations is their significant
3D physical heterogeneity at all scales, from fine fissuration to large holes and conduits. This leads to dynamic and temporal
variability, e.g. highly variable flow rates, due to several concurrent flow regimes with several distinct response times.
The temporal hydrologic response of karstic basins is studied here from an input/output, systems analysis viewpoint. The hydraulic
behaviour of the basins is approached via the relationship between hydrometeorological inputs and outputs. These processes
are represented and modeled as random, self-correlated and cross-correlated, stationary time processes. More precisely, for
each site-specific case presented here, the input process is the total rainfall on the basin and the output process is the
discharge rate at the outlet of the basin (karstic spring). In the absence of other data, these time processes embody all
the available information concerning a given karstic basin.
In this paper, we first present a brief discussion of the physical structure of karstic systems. Then, we formulate linear
and nonlinear models, i.e. functional relations between rainfall and runoff, and methods for identifying the kernel and coefficients
of the functionals (deterministic vs. statistical; error minimisation vs. polynomial projection). These are based mostly on Volterra first order (linear) or second order (nonlinear) convolution.
In addition, a new nonlinear threshold model is developed, based on the frequency distribution of interannual mean daily runoff.
Finally, the different models and identification methods are applied to two karstic watersheds in the french Pyrénées mountains,
using long sequences of rainfall and spring outflow data at two different sampling rates (daily and semi-hourly). The accuracy
of nonlinear and linear rainfall-runoff models is tested at three time scales: long interannual scale (20 years of daily data),
medium or seasonal scale (3 months of semi-hourly data), and short scale or “flood scale” (2 days of semi-hourly data). The
model predictions are analysed in terms of global statistical accuracy and in terms of accuracy with respect to high flow
events (floods). 相似文献
4.
Although artificial neural networks (ANNs) have been applied in rainfall runoff modelling for many years, there are still many important issues unsolved that have prevented this powerful non‐linear tool from wide applications in operational flood forecasting activities. This paper describes three ANN configurations and it is found that a dedicated ANN for each lead‐time step has the best performance and a multiple output form has the worst result. The most popular form with multiple inputs and single output has the average performance. In comparison with a linear transfer function (TF) model, it is found that ANN models are uncompetitive against the TF model in short‐range predictions and should not be used in operational flood forecasting owing to their complicated calibration process. For longer range predictions, ANN models have an improved chance to perform better than the TF model; however, this is highly dependent on the training data arrangement and there are undesirable uncertainties involved, as demonstrated by bootstrap analysis in the study. To tackle the uncertainty issue, two novel approaches are proposed: distance analysis and response analysis. Instead of discarding the training data after the model's calibration, the data should be retained as an integral part of the model during its prediction stage and the uncertainty for each prediction could be judged in real time by measuring the distances against the training data. The response analysis is based on an extension of the traditional unit hydrograph concept and has a very useful potential to reveal the hydrological characteristics of ANN models, hence improving user confidence in using them in real time. Copyright © 2006 John Wiley & Sons, Ltd. 相似文献
5.
Mohammad Hadi Moeini Amir Etemad-Shahidi Vahid Chegini Iraj Rahmani 《Ocean Dynamics》2012,62(5):785-797
The main goal of this study is to develop an efficient approach for the assimilation of the hindcasted wave parameters in
the Persian Gulf. Hence, the third generation SWAN model was employed for wave modeling forced by the 6-h ECMWF wind data
with a resolution of 0.5°. In situ wave measurements at two stations were utilized to evaluate the assimilation approaches.
It was found that since the model errors are not the same for wave height and period, adaptation of model parameter does not
result in simultaneous and comprehensive improvement of them. Therefore, an approach based on the error prediction and updating
of output variables was employed to modify wave height and period. In this approach, artificial neural networks (ANNs) were
used to estimate the deviations between the simulated and measured wave parameters. The results showed that updating of output
variables leads to significant improvement in a wide range of the predicted wave characteristics. It was revealed that the
best input parameters for error prediction networks are mean wind speed, mean wind direction, wind duration, and the wave
parameters. In addition, combination of the ANN estimated error with numerically modeled wave parameters leads to further
improvement in the predicted wave parameters in contrast to direct estimation of the parameters by ANN. 相似文献
6.
Feed forward neural network and interpolation function models to predict the soil and subsurface sediments distribution in Bam,Iran 总被引：1，自引：1，他引：0
Khalil Rezaei Bernard Guest Anke Friedrich Farajollah Fayazi Muhammad Nakhaei Ali Beitollahi Seyed Mahmoud Fatemi Aghda 《Acta Geophysica》2009,57(2):271-293
An application of the artificial neural network (ANN) approach for predicting mean grain size using electric resistivity data
from Bam city is presented. A feed forward back propagation network was developed employing 45 sets of input data. The input
variables in the ANN model are the electrical resistivity, water table as a Boolean value and depth; the output is the mean
grain size. To demonstrate the authenticity of this approach, the network predictions are compared with those from interpolation
methods and the same data. This comparison shows that the ANN approach performs better results. The predicted and observed
mean grain size values were compared and show high correlation coefficients. The ANN approach maps show a high degree of correlation
with well data based grain size maps and can therefore be used conservatively to better understand the influence of input
parameters on sedimentological predictions. 相似文献
7.
The regional study of hydrodynamic characteristics of karstic aquifers is challenging because of the great variety of lithology and the structural complexity found in carbonate formations. In order to improve this situation, a combined approach of time series and stochastic analyses was adopted to assess the hydrodynamic behaviour of the karstic aquifers. To achieve this, daily flow rates of 20 springs were taken from the 11 most significant aquifer units of the Basque Country. The results demonstrate the presence of memory effects, which modulated the input rainfall for short‐, medium‐ and long‐term storage capacity, resulting in hydrodynamic properties such as system memory, response time and mean delay between input and output. They reflect the storage and the manner in which these are filled and emptied, thus indicating the karstification of the aquifer. Likewise, the hydrodynamic and hydraulic classification obtained from the stochastic analysis provides a complementary approach to characterize the hydraulic behaviour of the studied karstic aquifers. The discussed examples indicate that this approach provides an excellent method to research hydrological karst systems. It is also shown that the use of hydrologic time series, alone, does not lead to a satisfactory classification of the hydrodynamic characteristics. Therefore, the general approach to hydrological regionalization in karst areas should take into account the structural complexity, heterogeneity of the lithology and the degree of karstification. Only in this case will the regionalization be physically founded, leading to a regional understanding of the hydrodynamic characteristics and flow conditions in a karst aquifer. Copyright © 2009 John Wiley & Sons, Ltd. 相似文献
8.
A general method for estimating ground-water solute mass transfer rate parameters from field test data is presented. The method entails matching solute concentration and hydraulic head data collected during the recovery phase of a pumping test through application of a simulation-regression technique. Estimation of hydraulic conductivity and mass transfer rate parameter values is performed by fitting model simulations to the data. Parameter estimates are utilized to assess cleanup times for pump-and-treat aquifer remediation scenarios. Uncertainty in the cleanup time estimate is evaluated using statistical information obtained with the parameter estimation technique. Application of the method is demonstrated using a hypothetical ground-water flow and solute transport system. Simulations of field testing, parameter estimation, and remedial time frames are performed to evaluate the usefulness of the method. Sets of random noise that signify potential field and laboratory measurement errors are combined with the hypothetical data to provide rigorous testing of the method. Field tests are simulated using ranges of values for data noise, the mass transfer rate parameters, the test pumping rates, and the duration of recovery monitoring to evaluate their respective influence on parameter and cleanup time estimates. The demonstration indicates the method is capable of yielding accurate estimates of the solute mass transfer rate parameters. When the parameter values for the hypothetical system are well estimated, cleanup time predictions are shown to be more accurate than when calculated using the local equilibrium assumption. 相似文献
9.
Allogenic karst systems function in a particular way that is influenced by the type of water infiltrating through river water losses, by karstification processes, and by water quality. Management of this system requires a good knowledge of its structure and functioning, for which a new methodology based on an inverse modeling approach appears to be well suited. This approach requires both spring and river inflow discharge measurements and a continuous record of chemical parameters in the river and at the spring. The inverse model calculates unit hydrographs and the impulse responses of fluxes from rainfall hydraulic head at the spring or rainfall flux data, the purpose of which is hydrograph separation. Hydrograph reconstruction is done using rainfall and river inflow data as model input and enables definition at each time step of the ratio of each component. Using chemical data, representing event and pre-event water, as input, it is possible to determine the origin of spring water (either fast flow through the epikarstic zone or slow flow through the saturated zone). This study made it possible to improve a conceptual model of allogenic karst system functioning. The methodology is used to study the Bas-Agly and the Cent Font karst systems, two allogenic karst systems in Southern France. 相似文献
10.
Jun Guo Jianzhong Zhou Lixiang Song Qiang Zou Xiaofan Zeng 《Stochastic Environmental Research and Risk Assessment (SERRA)》2013,27(4):985-1004
Assessment of parameter and predictive uncertainty of hydrologic models is an essential part in the field of hydrology. However, during the past decades, research related to hydrologic model uncertainty is mostly done with conceptual models. As is accepted that uncertainty in model predictions arises from measurement errors associated with the system input and output, from model structural errors and from problems with parameter estimation. Unfortunately, non-conceptual models, such as black-box models, also suffer from these problems. In this paper, we take the artificial neural network (ANN) rainfall-runoff model as an example, and the Shuffled Complex Evolution Metropolis algorithm (SCEM-UA) is employed to analysis the parameter and predictive uncertainty of this model. Furthermore, based on the results of uncertainty assessment, we finally arrive at a simpler incomplete-connection artificial neural network (ICANN) model as well as with better performance compared to original ANN rainfall-runoff model. These results not only indicate that SCEM-UA can be a useful tool for uncertainty analysis of ANN model, but also prove that uncertainty does exist in ANN rainfall-runoff model. Additionally, in some way, it presents that the ICANN model is with smaller uncertainty than the original ANN model. 相似文献
11.
A procedure combining the Soil Conservation Service‐Curve Number (SCS‐CN) method and the Green–Ampt (GA) infiltration equation was recently developed to overcome some of the drawbacks of the classic SCS‐CN approach when estimating the volume of surface runoff at a sub‐daily time resolution. The rationale of this mixed procedure, named Curve Number for Green–Ampt (CN4GA), is to use the GA infiltration model to distribute the total volume of the net hyetograph (rainfall excess) provided by the SCS‐CN method over time. The initial abstraction and the total volume of rainfall given by the SCS‐CN method are used to identify the ponding time and to quantify the hydraulic conductivity parameter of the GA equation. In this paper, a sensitivity analysis of the mixed CN4GA parameters is presented with the aim to identify conditions where the mixed procedure can be effectively used within the Prediction in Ungauged Basin perspective. The effects exerted by changes in selected input parameters on the outputs are evaluated using rectangular and triangular synthetic hyetographs as well as 100 maximum annual storms selected from synthetic rainfall time series. When applied to extreme precipitation events, which are characterized by predominant peaks of rainfall, the CN4GA appears to be rather insensitive to the input hydraulic parameters of the soil, which is an interesting feature of the CN4GA approach and makes it an ideal candidate for the rainfall excess estimation at sub‐daily temporal resolution at ungauged sites. Copyright © 2013 John Wiley & Sons, Ltd. 相似文献
12.
Spatial patterns of rainfall are known to cause differences in observed flow. In this paper, the effects of perturbations in rainfall patterns on changes in parameter sets as well as model output are explored using the hydrological model Dynamic TOPMODEL for the Brue catchment (135 km2) in southwest England. Overall rainfall amount remains the same at each time step so the perturbations act as effectively treated errors in the spatial pattern. The errors were analysed with particular emphasis on when they could be detected under an uncertainty framework. Higher rainfall perturbations (multipliers of × 4 and greater) in the low lying and high areas of the catchment resulted in changes to event peaks and accompanying compensation in the baseflow. More significantly, changes in the effective model parameter values required by the best models to take account of the more extreme patterns were able to be detected by noting when distributions of parameters change under uncertainty. Copyright © 2009 John Wiley & Sons, Ltd. 相似文献
13.
The hydraulic and transfer response of karst aquifers is complex and often highly nonlinear: due to their high transmissivity and connection with the surface, such systems are very sensitive to modifications of their boundary conditions. The aim of this study was to assess the variation of the response depending on both upstream and downstream parameters, and propose a methodology to simulate the response of the karst system depending on those parameters. The impact of the variations of multiple environmental parameters on the response of a karstic system submitted to tidal variations (Normandy, France) was investigated after a campaign of artificial tracer tests acquired in very different hydrologic conditions (rainfall events, low tide, high tide, low/high piezometric level, and low/high waters). Principal components analysis and hierarchical clustering were applied on both environmental variables and karstic system response variables (parameters of the residence time distribution [RTD] curves). Equations between the RTD parameters and the most relevant variables were established using a symbolic regression algorithm. It appeared that the variations of the RTD parameters depend mainly on the cumulated rainfall preceding the injection, the piezometric level of the aquifer, and on the tide parameters. The hydraulic conditions downstream of the aquifer have a strong influence on the hydraulic and transfer response of the aquifer. The response of the aquifer in various and extreme conditions has been simulated using the equations resulting from the symbolic regression algorithm. Such relationships can be useful for management of water resources in karst media, and support decision making. 相似文献
14.
ANN application for prediction of atmospheric nitrogen deposition to aquatic ecosystems 总被引：1，自引：0，他引：1
The occurrences of increased atmospheric nitrogen deposition (ADN) in Southeast Asia during smoke haze episodes have undesired consequences on receiving aquatic ecosystems. A successful prediction of episodic ADN will allow a quantitative understanding of its possible impacts. In this study, an artificial neural network (ANN) model is used to estimate atmospheric deposition of total nitrogen (TN) and organic nitrogen (ON) concentrations to coastal aquatic ecosystems. The selected model input variables were nitrogen species from atmospheric deposition, Total Suspended Particulates, Pollutant Standards Index and meteorological parameters. ANN models predictions were also compared with multiple linear regression model having the same inputs and output. ANN model performance was found relatively more accurate in its predictions and adequate even for high-concentration events with acceptable minimum error. The developed ANN model can be used as a forecasting tool to complement the current TN and ON analysis within the atmospheric deposition-monitoring program in the region. 相似文献
15.
AbstractArtificial neural networks (ANNs) have recently been used to predict the hydraulic head in well locations. In the present work, the particle swarm optimization (PSO) algorithm was used to train a feed-forward multi-layer ANN for the simulation of hydraulic head change at an observation well in the region of Agia, Chania, Greece. Three variants of the PSO algorithm were considered, the classic one with inertia weight improvement, PSO with time varying acceleration coefficients (PSO-TVAC) and global best PSO (GLBest-PSO). The best performance was achieved by GLBest-PSO when implemented using field data from the region of interest, providing improved training results compared to the back-propagation training algorithm. The trained ANN was subsequently used for mid-term prediction of the hydraulic head, as well as for the study of three climate change scenarios. Data time series were created using a stochastic weather generator, and the scenarios were examined for the period 2010–2020.
Editor Z.W. Kundzewicz; Associate editor L. SeeCitation Tapoglou, E., Trichakis, I.C., Dokou, Z., Nikolos, I.K., and Karatzas, G.P., 2014. Groundwater-level forecasting under climate change scenarios using an artificial neural network trained with particle swarm optimization. Hydrological Sciences Journal, 59(6), 1225–1239. http://dx.doi.org/10.1080/02626667.2013.838005 相似文献
16.
Elaine M. FitzGerald Christopher J. Bean & Ronan Reilly 《Geophysical Prospecting》1999,47(6):1031-1044
Borehole-wall imaging is currently the most reliable means of mapping discontinuities within boreholes. As these imaging techniques are expensive and thus not always included in a logging run, a method of predicting fracture frequency directly from traditional logging tool responses would be very useful and cost effective. Artificial neural networks (ANNs) show great potential in this area. ANNs are computational systems that attempt to mimic natural biological neural networks. They have the ability to recognize patterns and develop their own generalizations about a given data set. Neural networks are trained on data sets for which the solution is known and tested on data not previously seen in order to validate the network result. We show that artificial neural networks, due to their pattern recognition capabilities, are able to assess the signal strength of fracture-related heterogeneity in a borehole log and thus fracture frequency within a borehole. A combination of wireline logs (neutron porosity, bulk density, P-sonic, S-sonic, deep resistivity and shallow resistivity) were used as input parameters to the ANN. Fracture frequency calculated from borehole televiewer data was used as the single output parameter. The ANN was trained using a back-propagation algorithm with a momentum learning function. In addition to fracture frequency within a single borehole, an ANN trained on a subset of boreholes in an area could be used for prediction over the entire set of boreholes, thus allowing the lateral correlation of fracture zones. 相似文献
17.
A rainfall‐runoff model based on an artificial neural network (ANN) is presented for the Blue Nile catchment. The best geometry of the ANN rainfall‐runoff model in terms of number of hidden layers and nodes is identified through a sensitivity analysis. The Blue Nile catchment (about 300 000 km2) in the Nile basin is selected here as a case study. The catchment is classified into seven subcatchments, and the mean areal precipitation over those subcatchments is computed as a main input to the ANN model. The available daily data (1992–99) are divided into two sets for model calibration (1992–96) and for validation (1997–99). The results of the ANN model are compared with one of physical distributed rainfall‐runoff models that apply hydraulic and hydrologic fundamental equations in a grid base. The results over the case study area and the comparative analysis with the physically based distributed model show that the ANN technique has great potential in simulating the rainfall‐runoff process adequately. Because the available record used in the calibration of the ANN model is too short, the ANN model is biased compared with the distributed model, especially for high flows. Copyright © 2005 John Wiley & Sons, Ltd. 相似文献
18.
The reliability of a procedure for investigation of flooding into an ungauged river reach close to an urban area is investigated. The approach is based on the application of a semi‐distributed rainfall–runoff model for a gauged basin, including the flood‐prone area, and that furnishes the inlet flow conditions for a two‐dimensional hydraulic model, whose computational domain is the urban area. The flood event, which occurred in October 1998 in the Upper Tiber river basin and caused significant damage in the town of Pieve S. Stefano, was used to test the approach. The built‐up area, often inundated, is included in the gauged basin of the Montedoglio dam (275 km2), for which the rainfall–runoff model was adapted and calibrated through three flood events without over‐bank flow. With the selected set of parameters, the hydrological model was found reasonably accurate in simulating the discharge hydrograph of the three events, whereas the flood event of October 1998 was simulated poorly, with an error in peak discharge and time to peak of −58% and 20%, respectively. This discrepancy was ascribed to the combined effect of the rainfall spatial variability and a partial obstruction of the bridge located in Pieve S. Stefano. In fact, taking account of the last hypothesis, the hydraulic model reproduced with a fair accuracy the observed flooded urban area. Moreover, incorporating into the hydrological model the flow resulting from a sudden cleaning of the obstruction, which was simulated by a ‘shock‐capturing’ one‐dimensional hydraulic model, the discharge hydrograph at the basin outlet was well represented if the rainfall was supposed to have occurred in the region near the main channel. This was simulated by reducing considerably the dynamic parameter, the lag time, of the instantaneous unit hydrograph for each homogeneous element into which the basin is divided. The error in peak discharge and time to peak decreased by a few percent. A sensitivity analysis of both the flooding volume involved in the shock wave and the lag time showed that this latter parameter requires a careful evaluation. Moreover, the analysis of the hydrograph peak prediction due to error in rainfall input showed that the error in peak discharge was lower than that of the same input error quantity. Therefore, the obtained results allowed us to support the hypothesis on the causes which triggered the complex event occurring in October 1998, and pointed out that the proposed procedure can be conveniently adopted for flood risk evaluation in ungauged river basins where a built‐up area is located. The need for a more detailed analysis regarding the processes of runoff generation and flood routing is also highlighted. Copyright © 2005 John Wiley & Sons, Ltd. 相似文献
19.
Flash floods represent one of the deadliest and costliest natural disasters worldwide. The hydrological analysis of a flash flood event contributes in the understanding of the runoff creation process. This study presents the analysis of some flash flood events that took place in a complex geomorphological Mediterranean River basin. The objective of the present work is to develop the thresholds for a real‐time flash flood forecasting model in a complex geomorphological watershed, based on high‐frequency data from strategically located hydrological and meteorological telemetric stations. These stations provide hourly real‐time data which were used to determine hydrological and meteorological parameters. The main characteristics of various hydrographs specified in this study were the runoff coefficients, lag time, time to peak, and the maximum potential retention. The estimation of these hydrometeorological parameters provides the necessary information in order to successfully manage flash floods events. Especially, the time to peak is the most significant hydrological parameter that affects the response time of an oncoming flash flood event. A study of the above parameters is essential for the specification of thresholds which are related to the geomorphological characteristics of the river basin, the rainfall accumulation of an event, the rainfall intensity, the threshold runoff through karstic area, the season during which the rainfall takes place and the time intervals between the rainstorms that affect the soil moisture conditions. All these factors are combined into a real‐time‐threshold flash flood prediction model. Historical flash flood events at the downstream are also used for the validation of the model. An application of the proposed model is presented for the Koiliaris River basin in Crete, Greece. Copyright © 2011 John Wiley & Sons, Ltd. 相似文献
20.
Artificial neural networks (ANNs) were developed to accurately predict highly time-variable specific conductance values in an unconfined coastal aquifer. Conductance values in the fresh water lens aquifer change in response to vertical displacements of the brackish zone and fresh water-salt water interface, which are caused by variable pumping and climate conditions. Unlike physical-based models, which require hydrologic parameter inputs, such as horizontal and vertical hydraulic conductivities, porosity, and fluid densities, ANNs can "learn" system behavior from easily measurable variables. In this study, the ANN input predictor variables were initial conductance, total precipitation, mean daily temperature, and total pumping extraction. The ANNs were used to predict salinity (specific conductance) at a single monitoring well located near a high-capacity municipal-supply well over time periods ranging from 30 d to several years. Model accuracy was compared against both measured/interpolated values and predictions were made with linear regression, and in general, excellent prediction accuracy was achieved. For example, although the average percent change of conductance over 90-d periods was 39%, the absolute mean prediction error achieved with the ANN was only 1.1%. The ANNs were also used to conduct a sensitivity analysis that quantified the importance of each of the four predictor variables on final conductance values, providing valuable insights into the dynamics of the system. The results demonstrate that the ANN technology can serve as a powerful and accurate prediction and management tool, minimizing degradation of ground water quality to the extent possible by identifying appropriate pumping policies under variable and/or changing climate conditions. 相似文献