The present work describes the development and validation of Artificial Neural Networks (ANN) by comparison with classical and more advanced parametric and nonparametric statistical modeling methods such as Multiple Regression (MR), Generalized Additive Models (GAM), and Alternating Conditional Expe...
The present work describes the development and validation of Artificial Neural Networks (ANN) by comparison with classical and more advanced parametric and nonparametric statistical modeling methods such as Multiple Regression (MR), Generalized Additive Models (GAM), and Alternating Conditional Expectations (ACE) to esti‐mate spatial distribution of fish in a mesotrophic reservoir. The modeling approaches were developed and tested using 60 hydroacoustic transects covering the whole lake. Each transect was divided into 100‐m‐long sections, constituting a total of 732 sampling units. For each of them, the relationships between topology, chemical characteristics, and fish abundance were studied. The models had six independent topological (i.e., depth, distance from the bank, slope, and stratum) and chemical (i.e., temperature and dissolved oxygen) variables and one dependent output variable (fish density, FD). The data matrix was divided into two parts. The first contained units where FD was nonnil (i.e., 399 sampling units), and the second contained only cases without fish (i.e., 333 sampling units). Model training and testing procedures were run on the first submatrix after log(FD + 1) transformation. As linear MR results were not satisfactory (r2 = 0.42 in the training set, and r2 = 0.51 in the testing set) compared with ANN (r2 = 0.81 in the training set, and r2 = 0.77 in the testing set), we tried nonlinear transformations of the variables such as logarithmic, lowess (for the GAM), and an optimal nonlinear transformation using the SAS Transreg procedure (for the ACE model), but the determination coefficients remained clearly lower than those obtained using ANN (r2 = 0.60 in the training set for ACE, and r2 = 0.66 in the training set for GAM). The results of a second test on the nil submatrix stressed that, compared with other statistical techniques, ANN and, to a certain extent, GAM models were able to clearly define the potential FDs in samples where no fish were actually found. The model showed, on the basis of the topological and chemical variables taken into account, that the predicted potential FDs in the surface stratum are higher than in the underlying stratum. Finally, on the basis of the sensitivity analyses performed on the ANN and GAM results, we established relationships between FDs and the six environmental variables. Our results exhibit a clear summer habitat preferendum, the fish (predominantly roach) being located mainly in the surface stratum, in the warm shallow littoral areas. These observations led us to discuss the ecological significance of such a fish distribution, which may be due to a trade‐off between feeding, predation avoidance, and endogenous fish requirements.
The present work describes the development and validation of Artificial Neural Networks (ANN) by comparison with classical and more advanced parametric and nonparametric statistical modeling methods such as Multiple Regression (MR), Generalized Additive Models (GAM), and Alternating Conditional Expectations (ACE) to esti‐mate spatial distribution of fish in a mesotrophic reservoir. The modeling approaches were developed and tested using 60 hydroacoustic transects covering the whole lake. Each transect was divided into 100‐m‐long sections, constituting a total of 732 sampling units. For each of them, the relationships between topology, chemical characteristics, and fish abundance were studied. The models had six independent topological (i.e., depth, distance from the bank, slope, and stratum) and chemical (i.e., temperature and dissolved oxygen) variables and one dependent output variable (fish density, FD). The data matrix was divided into two parts. The first contained units where FD was nonnil (i.e., 399 sampling units), and the second contained only cases without fish (i.e., 333 sampling units). Model training and testing procedures were run on the first submatrix after log(FD + 1) transformation. As linear MR results were not satisfactory (r2 = 0.42 in the training set, and r2 = 0.51 in the testing set) compared with ANN (r2 = 0.81 in the training set, and r2 = 0.77 in the testing set), we tried nonlinear transformations of the variables such as logarithmic, lowess (for the GAM), and an optimal nonlinear transformation using the SAS Transreg procedure (for the ACE model), but the determination coefficients remained clearly lower than those obtained using ANN (r2 = 0.60 in the training set for ACE, and r2 = 0.66 in the training set for GAM). The results of a second test on the nil submatrix stressed that, compared with other statistical techniques, ANN and, to a certain extent, GAM models were able to clearly define the potential FDs in samples where no fish were actually found. The model showed, on the basis of the topological and chemical variables taken into account, that the predicted potential FDs in the surface stratum are higher than in the underlying stratum. Finally, on the basis of the sensitivity analyses performed on the ANN and GAM results, we established relationships between FDs and the six environmental variables. Our results exhibit a clear summer habitat preferendum, the fish (predominantly roach) being located mainly in the surface stratum, in the warm shallow littoral areas. These observations led us to discuss the ecological significance of such a fish distribution, which may be due to a trade‐off between feeding, predation avoidance, and endogenous fish requirements.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.