Statistical and Neural Methods for Site-Specific Yield Prediction Drummond, Scott Sudduth, Kenneth Birrell, Stuart Joshi, Anupam Birrell, Stuart Kitchen, Newell
dc.contributor.department Agricultural and Biosystems Engineering 2018-02-14T15:26:35.000 2020-06-29T22:40:46Z 2020-06-29T22:40:46Z 2014-09-17 2003-01-01
dc.description.abstract <p>Understanding the relationships between yield and soil properties and topographic characteristics is of critical importance in precision agriculture. A necessary first step is to identify techniques to reliably quantify the relationships between soil and topographic characteristics and crop yield. Stepwise multiple linear regression (SMLR), projection pursuit regression (PPR), and several types of supervised feed–forward neural networks were investigated in an attempt to identify methods able to relate soil properties and grain yields on a point–by–point basis within ten individual site–years. To avoid overfitting, evaluations were based on predictive ability using a 5–fold cross–validation technique. The neural techniques consistently outperformed both SMLR and PPR and provided minimal prediction errors in every site–year. However, in site–years with relatively fewer observations and in site–years where a single, overriding factor was not apparent, the improvements achieved by neural networks over both SMLR and PPR were small. A second phase of the experiment involved estimation of crop yield across multiple site–years by including climatological data. The ten site–years of data were appended with climatological variables, and prediction errors were computed. The results showed that significant overfitting had occurred and indicated that a much larger number of climatologically unique site–years would be required in this type of analysis.</p>
dc.description.comments <p>This article is from <em>Transactions of the ASAE</em> 46 (2003): 5–14, doi:<a href="" target="_blank">10.13031/2013.12541</a>.</p>
dc.format.mimetype application/pdf
dc.identifier archive/
dc.identifier.articleid 1840
dc.identifier.contextkey 6127237
dc.identifier.s3bucket isulib-bepress-aws-west
dc.identifier.submissionpath abe_eng_pubs/551
dc.language.iso en
dc.source.bitstream archive/|||Sat Jan 15 00:55:44 UTC 2022
dc.source.uri 10.13031/2013.12541
dc.subject.disciplines Agriculture
dc.subject.disciplines Bioresource and Agricultural Engineering
dc.subject.disciplines Soil Science
dc.subject.keywords Neural networks
dc.subject.keywords Precision agriculture
dc.subject.keywords Prediction
dc.subject.keywords Regression analysis
dc.title Statistical and Neural Methods for Site-Specific Yield Prediction
dc.type article
dc.type.genre article
dspace.entity.type Publication
relation.isAuthorOfPublication 1fd6ff71-dbea-4ada-9267-f9ff2ce1caba
relation.isOrgUnitOfPublication 8eb24241-0d92-4baf-ae75-08f716d30801
Original bundle
Now showing 1 - 1 of 1
263.89 KB
Adobe Portable Document Format