Title of article :
Characterizing the presence of oilseed rape feral populations on field margins using machine learning
Author/Authors :
Pivard، نويسنده , , Sandrine and Dem?ar، نويسنده , , Damjan and Lecomte، نويسنده , , Jane and Debeljak، نويسنده , , Marko and D?eroski، نويسنده , , Sa?o، نويسنده ,
Pages :
8
From page :
147
To page :
154
Abstract :
Many cultivated species, such as oilseed rape, sunflower, wheat or sorghum can escape from crops, and colonize field margins as feral populations. The general processes leading to the escape and persistence of cultivated species on field margins are still poorly investigated. An exhaustive 4-year survey was conducted in the centre of France at a landscape level to study the origin of feral oilseed rape populations. We present here results obtained with machine learning methods, which are increasingly popular techniques for analysing large ecological datasets. As expected, the dynamics of feral populations relies on large seed immigration from fields and transport. However, the seed bank was shown to be the keystone of their persistence rather than local recruitment.
Keywords :
Oilseed rape , Feral population , risk assessment , DATA MINING , classification tree , Attribute ranking
Journal title :
Astroparticle Physics
Record number :
2084218
Link To Document :
بازگشت