A Data Mining Approach to Examine the Effect of Climate Change on the Growth of Pinot Noir Grapes in Western Oregon Using Machine Learning Methods.

Abstract

The wine industry is one of the top industries in Oregon, with over 700 wineries in the state. This is why this study aims to find the effect of climate change on the wine industry in Western Oregon. To find this, I had to choose a specific grape to look at. The chosen grape was Pinot Noir because a large part of Oregon's wine revenue is from the sale of Pinot Noir wine. Also, I looked at Western Oregon specifically in this study because most of the wineries in Oregon are in Western Oregon. Using NASA's Giovanni website, the surface temperature data of Western Oregon was collected in the form of color-coded heat maps. Using these heat maps, the average surface temperatures during the growing seasons from 1979 to 2015 were found. The growing season for Pinot Noir is April to September. Then, using the average surface temperature data I found the average area of land that was in the ideal temperature range for ripening Pinot Noir for each specific growing season. Next, I got Oregon's average annual temperature data from NOAA's Climate at a Glance website. Using a machine learning regression method called LOESS I examined the two data sets and was able to derive insights from them. The data showed that, generally, as the average annual temperature rises, the average area of land that has a temperature suitable for ripening Pinot Noir decreases. Also, the data shows that the best average annual temperature for growing Pinot Noir is 47 degrees Fahrenheit. Lastly, the data from NOAA's Climate at a Glance website showed that Oregon's average annual temperature is increasing. This means that as time goes on, the area of land with a suitable temperature for growing Pinot Noir will gradually decrease.

Open preprint

You need to login in order to like/dislike

0 Comments
Inline Feedbacks
View all comments
Preprints for Agriculture and Allied Sciences
Advisory Board
  • Leisa Armstrong, Edith Cowan University, Australia
  • Arianna Becerril García, Autonomous University of the State of Mexico, Redalyc/AmeliCA, Mexico
  • Susmita Das, Bangladesh Agricultural Research Council
  • Abeer Elhalwagi, National Gene Bank, Egypt
  • Gopinath KA, Central Research Institute for Dryland Agriculture
  • Niklaus Grünwald, USDA Agricultural Research Service
  • Sridhar Gutam, ICAR IIHR/Open Access India
  • Vinodh Ilangovan, Max Planck Institute for Biophysical Chemistry
  • Jayalakshmi M, ANGRAU, India
  • Khelif Karima, Institut National de la Recherche Agronomique d'Algérie
  • Dinesh Kumar, Indian Agricultural Statistics Research Institute
.
  • Satendra Kumar Singh, Indian Council of Agricultural Research
  • Devika P. Madalli, DRTC/Indian Statistical Institute, India
  • Prateek Mahalwar, Cellulosic Technologies UG, Germany
  • Bernard Pochet, University of Liège - Gembloux Agro-Bio Tech
  • Vassilis Protonotarios, NEUROPUBLIC
  • Andy Robinson, CABI
  • Paraj Shukla, King Saud University
  • Chandni Singh, Indian Institute for Human Settlements
  • Kuldeep Singh Jadon, ICAR-Central Arid Zone Research Institute, India
  • Rajeev K Varshney, CGIAR/ICRISAT, India
  • Sumant Vyas, ICAR- National Research Centre on Camel, India
  • Oya Yildirim Rieger, Ithaka S+R/ITHAKA, USA
©2020 CABI is a registered EU trademark