@article{fdi:010044317,
  title = {{I}dentifying indicators of the spatial variation of agricultural practices by a tree partitioning method : the case of weed control practices in a vine growing catchment},
  author = {{B}iarn{\`e}s, {A}nne and {B}ailly, {J}. {S}. and {B}oissieux, {Y}annick},
  editor = {},
  language = {{ENG}},
  abstract = {{E}nvironmental impact assessments of agricultural practices on a regional scale may be computed by running spatially distributed biophysical models using mapped input data on agricultural practices. {I}n cases of hydrological impact assessments, {S}uch as herbicide pollution through runoff, methods for generating these data over the entire water resource catchment and at the plot resolution are needed. {I}n this study, we aimed to identify indicators for simulating the spatial distribution of weed control practices ({WCP}) in a {F}rench vine growing catchment. {O}n the basis of interviews of 63 winegrowers, a spatially explicit database was developed that included 1007 vine plots and information regarding practices and potential explanatory variables. {F}our practices were differentiated according to the methods used (chemical weed control, shallow tillage, grass cover or a combination) that determine the intensity of herbicide use and potential surface runoff. {T}hree groups of explanatory variables corresponding to three assumed levels of spatial organisation of {WCP} (the plot, the farm and the local government area ({LGA})) were tested and compared. {I}n the first step, selection of explanatory variables within each group was performed using a tree-partitioning method that combined the advantages of the {CART} algorithm (building an interpretable and controlled model) and the {R}andom {F}orest algorithm (limiting overfitting) algorithm. {I}n the second step, the performance of the selected variables for reproducing the observed repartition or practices was evaluated by a stochastic use of the tree, leading to a set of equiprobable spatial distributions of practices at the plot resolution. {T}he results indicate that plot characteristics related to alley width play an important role in the weed control choices; however, to take into account the total diversity of the {WCP}, it appears to be necessary to focus on the farm holding variables and, in particular, on the variable {LGA}. {H}owever, the interpretation of these results is still difficult. {S}pecifically, the great relevance of the variable {LGA} to discriminate the practices may be related to various factors, one of which is the distribution of soil properties within the {P}eyne catchment that still requires more precise characterization. {T}he results also indicate that the combination of the three groups of variables leads to the highest-performing simulations of the spatial distribution of {WCP}. {N}evertheless, the farm holding variables provided little additional spatial information, which supports the idea that they may be omitted without significantly impacting the final results.},
  keywords = {{V}iticulture ; {C}lassification tree ; {U}ncertainties ; {S}tochastic simulation ; {I}ndicators of practices},
  booktitle = {},
  journal = {{A}gricultural {S}ystems},
  volume = {99},
  numero = {2-3},
  pages = {105--116},
  ISSN = {0308-521{X}},
  year = {2009},
  DOI = {10.1016/j.agsy.2008.10.002},
  URL = {https://www.documentation.ird.fr/hor/fdi:010044317},
}