Using Andaptive Neuro Fuzzy Inference System to Build Models with Uncertain Data for Rainfed Maize - Study Case in the State of Puebla (Mexico)

Anais Vermonden Thibodeau, Carlos Gay Garcia

Abstract

Using the methodology of Adaptive Neuro Fuzzy Inference System (ANFIS) a model to determine the relationship suitability index with the yields per hectare and the percentage of production area lost of rainfed maize for the state of Puebla was built. The data used to build the model presented inconsistencies. The data of the INEGI’s land use map presented more municipalities without rainfed maize agriculture than the database of SAGARPA. Also the SAGARPA data, in terms of the percentage of production area lost, do not show any distinctions between the loss due to climate, pests, or simply that the farmer did not plant the total area that was declared, or had not harvested all the area declared. Even with data inconsistencies ANFIS produced a coherent output reviewed by experts. The model shows that higher the percentage of production area lost and high yields the higher the suitability index is. According to local studies this is due to the high degradation of the soils.

References

  1. Chiu, S. L. (1994). "Fuzzy Model Identification Based on Cluster Estimation." Journal of Intelligent & Fuzzy Systems 2(3): 267-278.
  2. Dubois, D. and H. Prade (1980). "Fuzzy Sets and Systems: Theory and Applications." New York Academic Press.
  3. Gaspar Angeles, E., E. Ortiz Torres, et al. (2010). "Caracterización y rendimiento de poblaciones de maíz nativas de Molcaxac, Puebla." Revista fitotecnica mexicana 33(4).
  4. INEGI (2005). Uso del Suelo y Vegetación Puebla, Instituto Nacional de Estadística y Geografía.
  5. Jang, J.-S. R. (1993). "ANFIS: adaptive-network-based fuzzy inference system." Systems, Man and Cybernetics, IEEE Transactions on 23(3): 665-685.
  6. MATLAB (2008). MATLAB. T. M. Inc. Natick, Massachusetts.
  7. Monterroso Rivas, A. I., C. Conde Álvarez, G. Rosales, J. D. Gómez, C. Gay (2011). "Assessing current and potential rainfed maize suitability under climate change scenarios in México " Atmósfera 24(1).
  8. SAGARPA, Secretaria de Agricultura, G., Desarrollo Rural, Pesca y Nutrición (2000-2008). Producción anual de maíz del estado de Puebla.
  9. Sugeno, M. (1977). "Fuzzy measures and fuzzy integrals: a survey." North-Holland, NY.
  10. Vermonden, A. (2012). Modelo Difuso para la Evaluación de la Aptitud Actual y Potencial del Maíz de Temporal en México con Cambio Climático. Posgrado de Ciencias de la Tierra. Mexico, Universidad Nacional Autónoma de México. Maestría: 110.
Download


Paper Citation


in Harvard Style

Vermonden Thibodeau A. and Gay Garcia C. (2013). Using Andaptive Neuro Fuzzy Inference System to Build Models with Uncertain Data for Rainfed Maize - Study Case in the State of Puebla (Mexico) . In Proceedings of the 3rd International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: MSCCEC, (SIMULTECH 2013) ISBN 978-989-8565-69-3, pages 512-516. DOI: 10.5220/0004622205120516


in Bibtex Style

@conference{msccec13,
author={Anais Vermonden Thibodeau and Carlos Gay Garcia},
title={Using Andaptive Neuro Fuzzy Inference System to Build Models with Uncertain Data for Rainfed Maize - Study Case in the State of Puebla (Mexico)},
booktitle={Proceedings of the 3rd International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: MSCCEC, (SIMULTECH 2013)},
year={2013},
pages={512-516},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004622205120516},
isbn={978-989-8565-69-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 3rd International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: MSCCEC, (SIMULTECH 2013)
TI - Using Andaptive Neuro Fuzzy Inference System to Build Models with Uncertain Data for Rainfed Maize - Study Case in the State of Puebla (Mexico)
SN - 978-989-8565-69-3
AU - Vermonden Thibodeau A.
AU - Gay Garcia C.
PY - 2013
SP - 512
EP - 516
DO - 10.5220/0004622205120516