A Prediction Model Framework for Crop Yield Prediction  

Oleh:

Leon, Maria Rossana C. de ; Jalao, Eugene Rex L.

Jenis: Article from Proceeding
Dalam koleksi: The 14th Asia Pacific Industrial Engineering and Management Systems Conference (APIEMS), 3-6 December 2013 Cebu, Philippines, page 1-16.
Topik: Crop yield prediction; Prediction model; Data mining
Fulltext: 4024.pdf (697.6KB)

Isi artikel

Crop yield prediction has been a topic of interest for producers, consultants, and agricultural related organizations. Timely and accurate crop yield forecasts are essential for crop production, marketing, storage, and transportation decisions as well as managing the risk associated with these activities. Existing research used multiple linear regression for predicting crop yield, however, issues on multi-collinearity, along with linear and normality assumptions, plague this approach. Several other studies have been conducted using modern prediction algorithms nevertheless used only climatic variables and some agronomic-related variables. Against this background, this study investigates the development of a crop prediction model framework that can (1) pre-process and fuse input raw data from multiple sources, (2) provide an accurate prediction of crop yield, (3) identify significant variables that affect crop yield, and (4) identify useful prediction policies using four climate-related variables, 13 agronomic variables, and variables on weather disturbance. Climate-related data has been collected from the state’s weather bureau, while agronomic-related data has been gathered from the Office of Provincial Agriculturist (OPA) and Bureau of Agricultural Statistics (BAS). Comparison experiments are performed to determine which data mining technique is used for each framework component.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali