Agroecological systems are difficult to model because of their high complexity and their nonlinear dynamic behavior. The evolution of such systems depends on a large number of ill-defined processes that vary in time, and whose relationships are often highly non-linear and very often unknown. According to Schultz et al. (2000), there are two major problems when dealing with modeling agroecological processes. On the one hand, there is an absence of equipment able to capture information in an accurate way, and on the other hand there is a lack of knowledge about such systems. Researchers are thus required to build-up models in rich and poor-data situations, by integrating different sources of data, even if this data is noisy, incomplete, and imprecise. © 2008 Springer-Verlag Berlin Heidelberg.
CITATION STYLE
Jiménez, D., Pérez-Uribe, A., Satizábal, H., Barreto, M., Van Damme, P., & Tomassini, M. (2008). A survey of artificial neural network-based modeling in agroecology. Studies in Fuzziness and Soft Computing, 226, 247–269. https://doi.org/10.1007/978-3-540-77465-5_13
Mendeley helps you to discover research relevant for your work.