Evolutionary Algorithms and Agricultural Systems

David G. Mayer

ISBN 10: 1461356938 / ISBN 13: 9781461356936

Editore: Springer US, 2012

Riguardo questo articolo

Druck auf Anfrage Neuware - Printed after ordering - Evolutionary Algorithms and Agricultural Systems deals with the practical application of evolutionary algorithms to the study and management of agricultural systems. The rationale of systems research methodology is introduced, and examples listed of real-world applications. It is the integration of these agricultural systems models with optimization techniques, primarily genetic algorithms, which forms the focus of this book. The advantages are outlined, with examples of agricultural models ranging from national and industry-wide studies down to the within-farm scale. The potential problems of this approach are also discussed, along with practical methods of resolving these problems. Agricultural applications using alternate optimization techniques (gradient and direct-search methods, simulated annealing and quenching, and the tabu search strategy) are also listed and discussed. The particular problems and methodologies of these algorithms, including advantageous features that may benefit a hybrid approach or be usefully incorporated into evolutionary algorithms, are outlined. From consideration of this and the published examples, it is concluded that evolutionary algorithms are the superior method for the practical optimization of models of agricultural and natural systems. General recommendations on robust options and parameter settings for evolutionary algorithms are given for use in future studies. Evolutionary Algorithms and Agricultural Systems will prove useful to practitioners and researchers applying these methods to the optimization of agricultural or natural systems, and would also be suited as a text for systems management, applied modeling, or operations research. Codice articolo 9781461356936

Dati bibliografici

Titolo: Evolutionary Algorithms and Agricultural ...

Casa editrice: Springer US

Data di pubblicazione: 2012

Legatura: Taschenbuch

Condizione: Neu

Descrizione articolo

Riassunto:

Evolutionary Algorithms and Agricultural Systems deals with the practical application of evolutionary algorithms to the study and management of agricultural systems. The rationale of systems research methodology is introduced, and examples listed of real-world applications. It is the integration of these agricultural systems models with optimization techniques, primarily genetic algorithms, which forms the focus of this book. The advantages are outlined, with examples of agricultural models ranging from national and industry-wide studies down to the within-farm scale. The potential problems of this approach are also discussed, along with practical methods of resolving these problems.
Agricultural applications using alternate optimization techniques (gradient and direct-search methods, simulated annealing and quenching, and the tabu search strategy) are also listed and discussed. The particular problems and methodologies of these algorithms, including advantageous features that may benefit a hybrid approach or be usefully incorporated into evolutionary algorithms, are outlined. From consideration of this and the published examples, it is concluded that evolutionary algorithms are the superior method for the practical optimization of models of agricultural and natural systems. General recommendations on robust options and parameter settings for evolutionary algorithms are given for use in future studies.
Evolutionary Algorithms and Agricultural Systems will prove useful to practitioners and researchers applying these methods to the optimization of agricultural or natural systems, and would also be suited as a text for systems management, applied modeling, or operations research.

Contenuti:

Preface. Acknowledgments. Rationale for Systems Modelling. Agricultural Systems Models. Application of Evolutionary Algorithms to Models. Applications of Alternate Optimisation Techniques. Comparisons of Optimisation Techniques. Robust Parameters for Evolutionary Algorithms. Future Developments. Appendix 1. References. Index.