Characterizing the presence of oilseed rape feral populations on field margins using machine learning

Pivard, Sandrine; Demšar, Damjan; Lecomte, Jane; Debeljak, Marko; Džeroski, Sašo

doi:10.1016/j.ecolmodel.2007.10.012

Cited by 37 publications

(28 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lek and Guégan, 1999;Debeljak et al, 2001;Recknagel, 2001;Dzeroski and Todorovski, 2003;Brewer et al, 2007;Dakou et al, 2007;deKock and Wolmarans, 2007a,b;Goethals et al, 2007;Lencioni et al, 2007;Pivard et al, 2008). This happened mainly because of the advantages they offer over traditional statistical analyses (Goethals and De Pauw, 2001;Dakou et al, 2007).…”

Section: Discussionmentioning

confidence: 95%

“…There are several well-known machine-learning techniques, including decision trees (Quinlan, 1986), artificial neural networks (Lek and Guégan, 1999), fuzzy logic (Barros et al, 2000) and Bayesian belief networks (Adriaenssens et al, 2004). These have been shown to be highly appropriate for habitat suitability modelling in mimicking aspects of biological information and so are being used in ecology more and more (Lek and Guégan, 1999;Debeljak et al, 2001;Goethals and De Pauw, 2001;Recknagel, 2001;Dzeroski and Todorovski, 2003;Dakou et al, 2007;Dakou et al, 2007;Goethals et al, 2007;Lencioni et al, 2007;Pivard et al, 2008). These modelling techniques have improved greatly over the last 10 years and have yielded highly reliability models.…”

Section: Introductionmentioning

confidence: 97%

See 1 more Smart Citation

Use of decision tree and artificial neural network approaches to model presence/absence of Telestes muticellus in piedmont (North‐Western Italy)

Tirelli

Pessani

2008

River Research & Apps

View full text Add to dashboard Cite

In Piedmont (Italy) the impact of human beings is causing some deep environmental changes in freshwaters and their inhabitants, so much so that we need to develop some practical tools for immediate use in providing accurate ecological assessments of the freshwater system and of the conditions of the species living there, one of which is Telestes muticellus, an endangered Cyprinidae found in the western Alps and the central Apennines in Italy. We aimed to help manage this species by assessing its presence using two types of data-mining approaches-decision-tree models and artificial neural networks. We built models using 10 environmental input variables to classify sites as positive or negative for the species. The unpruned decision tree models classified a high percentage of instances correctly and made accurate predictions, as did the post-pruned tree models. The post-pruned methods yielded simpler trees and therefore clearer models. Generally, the artificial neural networks (ANN) performed better than the decision tree models, except in the case of Cohen's k. We used the sensitivity analysis technique to understand which inputs are the most important ones for building the ANN model we obtained.

show abstract

Section: Discussionmentioning

confidence: 95%

Section: Introductionmentioning

confidence: 97%

Use of decision tree and artificial neural network approaches to model presence/absence of Telestes muticellus in piedmont (North‐Western Italy)

Tirelli

Pessani

2008

River Research & Apps

View full text Add to dashboard Cite

show abstract

“…Deployment of life-history modeling approaches has proved a popular and informative strategy to address this need, and has generally confirmed a tendency towards extinction and emphasized the importance of seedbank dynamics and fresh spillage (Aono et al, 2006;Garnier et al, 2006;Pivard et al, 2008aPivard et al, , 2008bSaji et al, 2005;Kowarik, 2007a, 2007b;Yoshimura et al, 2006). These data are useful because they provide a valuable baseline comparator for any transgenic crop.…”

Section: Effects Of Enhanced Fitnessmentioning

confidence: 99%

Fitness and beyond: Preparing for the arrival of GM crops with ecologically important novel characters

Wilkinson

Tepfer

2009

Environ. Biosafety Res.

View full text Add to dashboard Cite

The seemingly inexorable expansion of global human population size, significant increases in the use of biofuel crops and the growing pressures of multifunctional land-use have intensified the need to improve crop productivity. The widespread cultivation of high-yielding genetically modified (GM) crops could help to address these problems, although in doing so, steps must also be taken to ensure that any gene flow from these crops to wild or weedy recipients does not cause significant ecological harm. It is partly for this reason that new GM cultivars are invariably subjected to strict regulatory evaluation in order to assess the risks that each may pose to the environment. Regulatory bodies vary in their approach to decision-making, although all require access to large quantities of detailed information. Such an exhaustive case-by-case approach has been made tractable by the comparative simplicity of the portfolio of GM crops currently on the market, with four crops and two classes of traits accounting for almost all of the area under cultivation of GM crops. This simplified situation will change shortly, and will seriously complicate and potentially slow the evaluation process. Nowhere will the increased diversity of GM crops cause more difficulty to regulators than in those cases where there is a need to assess whether the transgene(s) will enhance fitness in a non-transgenic relative and thereafter cause ecological harm. Current practice to test this risk hypothesis focuses on attempting to detect increased fitness in the recipient. In this paper we explore the merits and shortcomings of this strategy, and investigate the scope for developing new approaches to streamline decision-making processes for transgenes that could cause unwanted ecological change.Keywords: environmental risk assessment / fitness / fitness parameters / GM crops / invasiveness / weediness THE CONTEXT OF ENVIRONMENTAL RISK ASSESSMENTThroughout the world, wherever transgenic crops are grown outside the confines of the laboratory, there is a regulatory system for governing and monitoring the conditions under which experimental field trials and/or commercial cultivation is sanctioned. There is considerable variation between individual countries in the legislative frameworks that dictate how decisions to permit, delay or halt the release of a particular transgenic event are made (Capalbo et al., 2003;Cardwell and Kerr, 2008;Guehlstorf and Hallstrom, 2005; Jepson et al., 2005;Kalaitzandonakes et al., 2007;Nasiruddin and Nasim, 2007;Ramjoue, 2007;Salleh, 2006;Zafar, 2007). Nevertheless, there appears to be a growing harmonization of the underlying process that governs decision-making, * Corresponding author: jjw@aber.ac.uk with all systems adopting a case-by-case approach in which large bodies of evidence are first presented and then evaluated in a reiterative fashion.The documents made in support of individual submissions are usually rather weighty and data-rich; they invariably include substantial information relating to the biology and agr...

show abstract

“…The dynamics of feral populations at one location not only depend on seed immigration from fresh seed spills, but also on soil seedbanks and local recruitment from seed produced by resident ferals (Pivard et al, 2008b). Demographic data on feral oilseed rape in different EU locations showed consistently that persistence in the soil seedbank allowed plants to recur after an absence of a year or more, while several populations persisted for two to four years (Squire et al, 2011).…”

Section: Recruitment From Seed Emerging From the Soil Seedbank Or Fromentioning

confidence: 99%

Feral genetically modified herbicide tolerant oilseed rape from seed import spills: are concerns scientifically justified?

Devos

Hails

Messéan³

et al. 2011

Transgenic Res

View full text Add to dashboard Cite

Contact CEH NORA team at noraceh@ceh.ac.ukThe NERC and CEH trademarks and logos ('the Trademarks') are registered trademarks of NERC in the UK and other countries, and may not be used without the prior written consent of the Trademark owner.1 | P a g e KEYWORDSGenetically modified oilseed rape, herbicide tolerance, seed spillage, ferality, persistence, invasiveness, coexistence, introgression 2 | P a g e ABSTRACTOne of the concerns surrounding the import (for food and feed uses or processing) of genetically modified herbicide tolerant (GMHT) oilseed rape is that, through seed spillage, the herbicide tolerance (HT) trait will escape into agricultural or semi-natural habitats, causing environmental or economic problems. Based on these concerns, three EU countries have invoked national safeguard clauses to ban the marketing of specific GMHT oilseed rape events on their territory. However, the scientific basis for the environmental and economic concerns posed by feral GMHT oilseed rape resulting from seed import spills is debatable.While oilseed rape has characteristics such as secondary dormancy and small seed size that enable it to persist and be redistributed in the landscape, the presence of ferals is not in itself an environmental or economic problem. Crucially, feral oilseed rape has not become invasive outside cultivated and ruderal habitats, and HT traits are not likely to result in increased invasiveness. Feral GMHT oilseed rape has the potential to introduce HT traits to volunteer weeds in agricultural fields, but would only be amplified if the herbicides to which HT volunteers are tolerant were used routinely in the field. However, this worst-case scenario is most unlikely, as seed import spills are mostly confined to port areas. Economic concerns revolve around the potential for feral GMHT oilseed rape to contribute to GM admixtures in non-GM crops. Since feral plants derived from cultivation (as distinct from import) occur at too low a frequency to affect the coexistence threshold of 0.9% in the EU, it can be concluded that feral GMHT plants resulting from seed import spills will have little relevance as a potential source of pollen or seed for GM admixture. This paper concludes that feral oilseed rape in Europe should not be routinely managed, and certainly not in semi-natural habitats, as the benefits of such action would not outweigh the negative effects of management.3 | P a g e INTRODUCTIONThe global area cropped with genetically modified (GM) crops has consistently increased each year since they were first commercially cultivated in 1996 (1.7 million hectares), reaching 148 million hectares in 2010 (James, 2010). The advent of GM crops and their rapid expansion in terms of cropping area evoked intense debate about their safety (Hails, 2000; Devos et al., 2008b;Waltz, 2009; Gaskell et al., 2011). Concerns have been raised that the commercial release of GM crops could result in adverse environmental and economic effects.Environmental concerns include the potential for altered fitness of the crop ...

show abstract

Characterizing the presence of oilseed rape feral populations on field margins using machine learning

Cited by 37 publications

References 22 publications

Use of decision tree and artificial neural network approaches to model presence/absence of Telestes muticellus in piedmont (North‐Western Italy)

Use of decision tree and artificial neural network approaches to model presence/absence of Telestes muticellus in piedmont (North‐Western Italy)

Fitness and beyond: Preparing for the arrival of GM crops with ecologically important novel characters

Feral genetically modified herbicide tolerant oilseed rape from seed import spills: are concerns scientifically justified?

Contact Info

Product

Resources

About