|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
The use of machine learning techniques in predicting crop yield has become increasingly important in recent years, as farmers face rapid changes in environmental conditions that make it difficult to make accurate predictions using traditional methods. Efficient feature selection methods are crucial to ensure that machine learning models work accurately, and the selection of appropriate features is key to achieving high levels of precision. Various machine learning techniques can be used to predict crop yield, and the results of these techniques can be compared based on their mean absolute error. By considering factors such as temperature, rainfall, and area, farmers can use the predictions made by these algorithms to decide which crop to grow to achieve the maximum yield. Different machine learning algorithms may have varying modulating factor values, depending on the specific features of the crop being analyzed. Artificial neural networks (ANNs) may be used when the quantity of input elements is reduced, and optimal features can be empirically selected to ensure accurate crop yield estimation. By using machine learning algorithms to analyze large soil datasets, farmers can obtain valuable insights that can help them increase crop production significantly. Ultimately, the use of machine learning in agriculture can support sustainable food production and help to meet the increasing demand for food worldwide.
Keyword
Machine Learning. Feature Selection, Agriculture, classification, crop prediction, Recommendation.
PDF Download (click here)
|
|
|
|
|