A Deep Learning-Based Model to Reduce Costs and Increase Productivity in the Case of Small Datasets: A Case Study in Cotton Cultivation

Mohammad Amin Amani,Francesco Marinello

doi:10.3390/agriculture12020267

Mohammad Amin Amani, Francesco Marinello

Open Access

https://doi.org/10.3390/agriculture12020267

Copy DOI

Journal: Agriculture	Publication Date: Feb 14, 2022
Citations: 17	License type: CC BY 4.0

Affiliation: University of Tehran, University of Padua

Abstract

In this paper, a deep-learning model is proposed as a viable approach to optimize the information on soil parameters and agricultural variables’ effect in cotton cultivation, even in the case of small datasets. In this study, soil is analyzed to reduce the planting costs by determining the various combinations of soil components and nutrients’ precise amounts. Such factors are essential for cotton cultivation, since their amounts are often not precisely defined, and especially traditional farming methods are characterized by excessive distribution volumes producing significant economic and environmental impact. Not only can artificial intelligence decrease the charges, but it also increases productivity and profits. For this purpose, a deep learning algorithm was selected among other machine learning algorithms by comparison based on the accuracy metric to build the predictive model. This model gets the combination of the factors amounts as input and predicts whether the cotton growth will be successful or not. The predictive model was built by this algorithm based on 13 physical and chemical factors has 98.8% accuracy.

Highlights

Machine learning (ML) is a technique widely implemented for finding patterns and linear and non-linear relationships between different variables
The best algorithm for building the predictive model among machine thisdeep section, the best algorithmisfor building the predictive model machine learningInand learning algorithms chosen by comparison based onamong the accuracy learning and deep learning algorithms is are chosen by comparison onTensorflow the accuracy metric
This research provided a deep neural neural networks networks (DNNs) algorithm, which is selected among other machine learning algorithms based on a comparison of the accuracy to build a classifier that can determine the proper amount of soil parameters in the cotton cultivation process

Summary

Introduction

Machine learning (ML) is a technique widely implemented for finding patterns and linear and non-linear relationships between different variables. From the statistic point of view, a model is counted as linear if the model’s parameters are linear [1]. ML has various subcategories such as Classification, Regression, or Clustering, which can be utilized in order to analyze and to help make decisions [2]. Machine learning is gaining an increasing interest in agriculture, where complex relationships often have to be investigated to solve complex agri-engineering problems [3]. Agricultural practices suffer from the availability of a reduced amount of data and information on the many relevant parameters. Soil organic matter (SOM) and pH are critical factors regarding the degradation that might occur due to unsuitable management practices [4]

Objectives

Methods

Results

Discussion

Conclusion