A fuzzy logic based soil chemical quality index for cacao

Mora-Herrera Denys Yohana, Guillaume Serge, Snoeck Didier, Zúñiga Escobar Orlando. 2020. A fuzzy logic based soil chemical quality index for cacao. Computers and Electronics in Agriculture, 177:105624, 9 p.

https://doi.org/10.1016/j.compag.2020.105624

Article de revue ; Article de recherche ; Article de revue à facteur d'impact

Version publiée - Anglais
Accès réservé aux personnels Cirad
Utilisation soumise à autorisation de l'auteur ou du Cirad.
Mora-Herera, A fuzzy logic based soil chemical quality index for cacao .pdf
Télécharger (1MB) | Demander une copie

Prévisualisation

Version post-print - Anglais
Sous licence

.
ID596448.pdf
Télécharger (1MB) | Prévisualisation

Url - jeu de données - Entrepôt autre : https://doi.org/10.17632/swtd9m4gsf.1

Quartile : Q1, Sujet : AGRICULTURE, MULTIDISCIPLINARY / Quartile : Q1, Sujet : COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Résumé : A soil chemical quality index is designed for cacao production systems. It is based on worldwide scientific knowledge and built using data from three municipalities of Tolima department in Colombia. Fuzzy logic is used in a multicriteria decision making framework in two different ways. First, fuzzy sets are used to model an expert preference relation for each of the individual information sources to turn raw data into satisfaction degrees. Second, fuzzy rules are used to model the interaction between sources to aggregate the individual degrees into a global score. The whole framework is implemented as an open source software called GeoFIS. A part of the data was used for calibration, then the remaining data served as a validation set. The results were easy to analyze and in agreement with field observations. The output inferred by the fuzzy inference system was used as a target to learn the weights of classical numerical aggregation operators. Only the Choquet Integral proved to have a similar modeling ability, but its optimal tuning would have been difficult without learning.

Mots-clés Agrovoc : Theobroma cacao, modélisation des cultures, système d'aide à la décision, chimie du sol, propriété physicochimique du sol, analyse de sol, qualité du sol

Mots-clés géographiques Agrovoc : Colombie

Mots-clés libres : Cacao, Fuzzy inference system, Soil

Classification Agris : P33 - Chimie et physique du sol
P32 - Classification des sols et pédogenèse

Champ stratégique Cirad : CTS 2 (2019-) - Transitions agroécologiques

Auteurs et affiliations