Solving Problems in Environmental Engineering and Geosciences with Artificial Neural NetworksArtificial Neural Networks (ANNs) offer an efficient method for finding optimal cleanup strategies for hazardous plumes contaminating groundwater by allowing hydrologists to rapidly search through millions of possible strategies to find the most inexpensive and effective containment of contaminants and aquifer restoration. ANNs also provide a faster method of developing systems that classify seismic events as earthquakes or underground explosions. Farid Dowla and Leah Rogers have developed a number of ANN applications for researchers and students in hydrology and seismology. This book, complete with exercises and ANN algorithms, illustrates how ANNs can be used in solving problems in environmental engineering and the geosciences, and provides the necessary tools to get started using these elegant and efficient new techniques. Following the development of four primary ANN algorithms (backpropagation, self-organizing, radial basis functions, and hopfield networks), and a discussion of important issues in ANN formulation (generalization properties, computer generation of training sets, causes of slow training, feature extraction and preprocessing, and performance evaluation), readers are guided through a series of straightforward yet complex illustrative problems. These include groundwater remediation management, seismic discrimination between earthquakes and underground explosions, automated monitoring for acoustic and seismic sensor data, estimation of seismic sources, geospatial estimation, lithologic classification from geophysical logging, earthquake forecasting, and climate change. Each chapter contains detailed exercises often drawn from field data that use one or more of the fourprimary ANN algorithms presented. |
From inside the book
Results 1-5 of 38
Page 10
Sorry, this page's content is restricted.
Sorry, this page's content is restricted.
Page 11
Sorry, this page's content is restricted.
Sorry, this page's content is restricted.
Page 12
Sorry, this page's content is restricted.
Sorry, this page's content is restricted.
Page 18
Sorry, this page's content is restricted.
Sorry, this page's content is restricted.
Page 19
Sorry, this page's content is restricted.
Sorry, this page's content is restricted.
Contents
Methods and Algorithms | 15 |
Training Set and Input Representation | 41 |
Summary | 76 |
6 | 104 |
7 | 123 |
Spatial Estimation for Geologic Characterization | 159 |
Other editions - View all
Solving Problems in Environmental Engineering and Geosciences with ... Farid U. Dowla,Leah L. Rogers No preview available - 2002 |
Common terms and phrases
analysis windows applications aquifer architecture Artificial Neural Networks backpropagation network cepstrum chapter cluster coefficient complex conjugate gradient contamination correlation CORRTEX data set defined described developed discrimination discuss distance distribution Dowla earthquake equation error example problem expert systems fclose(fp flow and transport fprintf(stderr fuzzy geologic geophysical geophysical logs geosciences geostatistical GFTC groundwater flow hidden layer Hopfield network input patterns input vector interpretation Kohonen Kohonen network kriging learning algorithm linear lithology magnitude matrix method minimize monitoring neural network neuron nodes nominal COE nonlinear number of examples number of weights nunits optimization parameters performance phase predict radial basis function regional remediation represents sample scaling factor seismic events seismogram self-organizing shown in figure solute solve spatial spectral spectrogram station supervised learning techniques tion training examples training set tree ring unknown event values variogram water table wireline logs yield estimation