Combining target sampling with route-optimization to optimise yield estimation in viticulture

Baptiste Oger (1, 2) , Philippe Vismara (3, 4) , Bruno Tisseyre (1)

1 UMR ITAP - Information – Technologies – Analyse Environnementale – Procédés Agricoles
2 MISTEA - Mathématiques, Informatique et STatistique pour l'Environnement et l'Agronomie
3 INRA - Institut National de la Recherche Agronomique
4 COCONUT - Agents, Apprentissage, Contraintes

This paper describes a new approach for yield sampling in viticulture. It combines approaches based on auxiliary information and path optimization to offer more consistent sampling strategies, integrating statistical approaches with computer methods. To achieve this, groups of potential sampling points, comparable according to their auxiliary data values are created. Then, an optimal path connecting several points, one from each group of potential sampling points and minimizing the route distance is created. This part is performed using constraint programming, a programming paradigm offering tools to deal efficiently with combinatorial problems. The paper presents the formalization of the problem, as well as the tests performed on real fields. Results show that combining target sampling and path optimization can reduce by 45% the average sampling circuit length compared to previous methods based on auxiliary data while being almost equivalent in yield prediction error.

Mots clés: CONSTRAINT PROGRAMMING; NORMALISED DIFFERENCE VEGETATION INDEX; SAMPLING OPTIMIZATION; YIELD ESTIMATION; CONSTRAINT THEORY; SALINITY MEASUREMENT; AUXILIARY INFORMATION; CONSISTENT SAMPLINGS; PROGRAMMING PARADIGMS; MODEL SAMPLING; COMBINATORIAL PROBLEM

Domaines: Sciences de l'environnement

Baptiste Oger, Philippe Vismara, Bruno Tisseyre. Combining target sampling with route-optimization to optimise yield estimation in viticulture. ECPA 2019 - 12th European Conference on Precision Agriculture, Jul 2019, Montpellier, France. pp.173-179, ⟨10.3920/978-90-8686-888-9_20⟩. ⟨hal-02609782⟩