A Multiple-Input Neural Network Model for Predicting Cotton Production Quantity: A Case Study
Cotton constitutes a significant commercial crop and a widely traded commodity around the world. The accurate prediction of its yield quantity could lead to high economic benefits for farmers as well as for the rural national economy. In this research, we propose a multiple-input neural network mode...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-10-01
|
Series: | Algorithms |
Subjects: | |
Online Access: | https://www.mdpi.com/1999-4893/13/11/273 |
id |
doaj-c614233c10f44945a6d25f91124e79fb |
---|---|
record_format |
Article |
spelling |
doaj-c614233c10f44945a6d25f91124e79fb2020-11-25T02:42:08ZengMDPI AGAlgorithms1999-48932020-10-011327327310.3390/a13110273A Multiple-Input Neural Network Model for Predicting Cotton Production Quantity: A Case StudyIoannis E. Livieris0Spiros D. Dafnis1George K. Papadopoulos2Dionissios P. Kalivas3Department of Mathematics, University of Patras, GR 265-00 Patras, GreeceDepartment of Crop Science, Agricultural University of Athens, GR 118-55 Athens, GreeceDepartment of Crop Science, Agricultural University of Athens, GR 118-55 Athens, GreeceDepartment of Natural Resources Management & Agricultural Engineering, Agricultural University of Athens, GR 118-55 Athens, GreeceCotton constitutes a significant commercial crop and a widely traded commodity around the world. The accurate prediction of its yield quantity could lead to high economic benefits for farmers as well as for the rural national economy. In this research, we propose a multiple-input neural network model for the prediction of cotton’s production. The proposed model utilizes as inputs three different kinds of data (soil data, cultivation management data, and yield management data) which are treated and handled independently. The significant advantages of the selected architecture are that it is able to efficiently exploit mixed data, which usually requires being processed separately, reduces overfitting, and provides more flexibility and adaptivity for low computational cost compared to a classical fully-connected neural network. An empirical study was performed utilizing data from three consecutive years from cotton farms in Central Greece (Thessaly) in which the prediction performance of the proposed model was evaluated against that of traditional neural network-based and state-of-the-art models. The numerical experiments revealed the superiority of the proposed approach.https://www.mdpi.com/1999-4893/13/11/273multiple-input neural networkmachine learningexpert knowledgecotton production |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ioannis E. Livieris Spiros D. Dafnis George K. Papadopoulos Dionissios P. Kalivas |
spellingShingle |
Ioannis E. Livieris Spiros D. Dafnis George K. Papadopoulos Dionissios P. Kalivas A Multiple-Input Neural Network Model for Predicting Cotton Production Quantity: A Case Study Algorithms multiple-input neural network machine learning expert knowledge cotton production |
author_facet |
Ioannis E. Livieris Spiros D. Dafnis George K. Papadopoulos Dionissios P. Kalivas |
author_sort |
Ioannis E. Livieris |
title |
A Multiple-Input Neural Network Model for Predicting Cotton Production Quantity: A Case Study |
title_short |
A Multiple-Input Neural Network Model for Predicting Cotton Production Quantity: A Case Study |
title_full |
A Multiple-Input Neural Network Model for Predicting Cotton Production Quantity: A Case Study |
title_fullStr |
A Multiple-Input Neural Network Model for Predicting Cotton Production Quantity: A Case Study |
title_full_unstemmed |
A Multiple-Input Neural Network Model for Predicting Cotton Production Quantity: A Case Study |
title_sort |
multiple-input neural network model for predicting cotton production quantity: a case study |
publisher |
MDPI AG |
series |
Algorithms |
issn |
1999-4893 |
publishDate |
2020-10-01 |
description |
Cotton constitutes a significant commercial crop and a widely traded commodity around the world. The accurate prediction of its yield quantity could lead to high economic benefits for farmers as well as for the rural national economy. In this research, we propose a multiple-input neural network model for the prediction of cotton’s production. The proposed model utilizes as inputs three different kinds of data (soil data, cultivation management data, and yield management data) which are treated and handled independently. The significant advantages of the selected architecture are that it is able to efficiently exploit mixed data, which usually requires being processed separately, reduces overfitting, and provides more flexibility and adaptivity for low computational cost compared to a classical fully-connected neural network. An empirical study was performed utilizing data from three consecutive years from cotton farms in Central Greece (Thessaly) in which the prediction performance of the proposed model was evaluated against that of traditional neural network-based and state-of-the-art models. The numerical experiments revealed the superiority of the proposed approach. |
topic |
multiple-input neural network machine learning expert knowledge cotton production |
url |
https://www.mdpi.com/1999-4893/13/11/273 |
work_keys_str_mv |
AT ioanniselivieris amultipleinputneuralnetworkmodelforpredictingcottonproductionquantityacasestudy AT spirosddafnis amultipleinputneuralnetworkmodelforpredictingcottonproductionquantityacasestudy AT georgekpapadopoulos amultipleinputneuralnetworkmodelforpredictingcottonproductionquantityacasestudy AT dionissiospkalivas amultipleinputneuralnetworkmodelforpredictingcottonproductionquantityacasestudy AT ioanniselivieris multipleinputneuralnetworkmodelforpredictingcottonproductionquantityacasestudy AT spirosddafnis multipleinputneuralnetworkmodelforpredictingcottonproductionquantityacasestudy AT georgekpapadopoulos multipleinputneuralnetworkmodelforpredictingcottonproductionquantityacasestudy AT dionissiospkalivas multipleinputneuralnetworkmodelforpredictingcottonproductionquantityacasestudy |
_version_ |
1724775034142064640 |