A Novel Machine Learning Approach: Soil Temperature Ordinal Classification (STOC)

Soil temperature prediction is an important task since soil temperature plays an important role in agriculture and land use. Although some progress has been made in this area, the existing methods provide a regression or nominal classification task. However, ordinal classification is yet to be explo...

Full description

Saved in:
Bibliographic Details
Main Authors: Derya Birant, Pelin Yıldırım Taşer, Cansel Küçük
Format: Article
Language:English
Published: Ankara University 2022-10-01
Series:Journal of Agricultural Sciences
Subjects:
Online Access:https://dergipark.org.tr/tr/download/article-file/1525389
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850236958914117632
author Derya Birant
Pelin Yıldırım Taşer
Cansel Küçük
author_facet Derya Birant
Pelin Yıldırım Taşer
Cansel Küçük
author_sort Derya Birant
collection DOAJ
description Soil temperature prediction is an important task since soil temperature plays an important role in agriculture and land use. Although some progress has been made in this area, the existing methods provide a regression or nominal classification task. However, ordinal classification is yet to be explored. To bridge the gap, this paper proposes a novel approach: Soil Temperature Ordinal Classification (STOC), which considers the relationships between the class labels during soil temperature level prediction. To demonstrate the effectiveness of the proposed approach, the STOC method using five different traditional machine learning methods (Decision Tree, Naive Bayes, K-Nearest Neighbors, Support Vector Machines, and Random Forest) was applied on daily values of meteorological and soil data obtained from 16 stations in three states (Utah, Alabama, and New Mexico) of United States at five soil depths (2, 4, 8, 20, and 40 inches) between the years of 2011 and 2020. The experiments show that the proposed STOC approach is an efficient method for soil temperature level (very low, low, medium, high, and very high) prediction. The applied STOC models (STOC.DT, STOC.NB, STOC.KNN, STOC.SVM, and STOC.RF) showed average accuracy rates of 90.95%, 77.09%, 90.84%, 89.94%, and 90.91% on the experimental datasets, respectively. It was observed from the experimental results that the STOC.DT method achieved the best soil temperature level prediction among the others.
format Article
id doaj-art-2be4641f7f084371a93dbbd06c79164c
institution OA Journals
issn 1300-7580
2148-9297
language English
publishDate 2022-10-01
publisher Ankara University
record_format Article
series Journal of Agricultural Sciences
spelling doaj-art-2be4641f7f084371a93dbbd06c79164c2025-08-20T02:01:51ZengAnkara UniversityJournal of Agricultural Sciences1300-75802148-92972022-10-0128463564910.15832/ankutbd.86604545A Novel Machine Learning Approach: Soil Temperature Ordinal Classification (STOC)Derya Birant0Pelin Yıldırım Taşer1Cansel Küçük2Dokuz Eylul University, Department of Computer EngineeringIzmir Bakircay University, Department of Computer EngineeringDokuz Eylul University, Graduate School of Natural and Applied SciencesSoil temperature prediction is an important task since soil temperature plays an important role in agriculture and land use. Although some progress has been made in this area, the existing methods provide a regression or nominal classification task. However, ordinal classification is yet to be explored. To bridge the gap, this paper proposes a novel approach: Soil Temperature Ordinal Classification (STOC), which considers the relationships between the class labels during soil temperature level prediction. To demonstrate the effectiveness of the proposed approach, the STOC method using five different traditional machine learning methods (Decision Tree, Naive Bayes, K-Nearest Neighbors, Support Vector Machines, and Random Forest) was applied on daily values of meteorological and soil data obtained from 16 stations in three states (Utah, Alabama, and New Mexico) of United States at five soil depths (2, 4, 8, 20, and 40 inches) between the years of 2011 and 2020. The experiments show that the proposed STOC approach is an efficient method for soil temperature level (very low, low, medium, high, and very high) prediction. The applied STOC models (STOC.DT, STOC.NB, STOC.KNN, STOC.SVM, and STOC.RF) showed average accuracy rates of 90.95%, 77.09%, 90.84%, 89.94%, and 90.91% on the experimental datasets, respectively. It was observed from the experimental results that the STOC.DT method achieved the best soil temperature level prediction among the others.https://dergipark.org.tr/tr/download/article-file/1525389agricultureclassificationdecision treemachine learningrandom forestsoil temperature level
spellingShingle Derya Birant
Pelin Yıldırım Taşer
Cansel Küçük
A Novel Machine Learning Approach: Soil Temperature Ordinal Classification (STOC)
Journal of Agricultural Sciences
agriculture
classification
decision tree
machine learning
random forest
soil temperature level
title A Novel Machine Learning Approach: Soil Temperature Ordinal Classification (STOC)
title_full A Novel Machine Learning Approach: Soil Temperature Ordinal Classification (STOC)
title_fullStr A Novel Machine Learning Approach: Soil Temperature Ordinal Classification (STOC)
title_full_unstemmed A Novel Machine Learning Approach: Soil Temperature Ordinal Classification (STOC)
title_short A Novel Machine Learning Approach: Soil Temperature Ordinal Classification (STOC)
title_sort novel machine learning approach soil temperature ordinal classification stoc
topic agriculture
classification
decision tree
machine learning
random forest
soil temperature level
url https://dergipark.org.tr/tr/download/article-file/1525389
work_keys_str_mv AT deryabirant anovelmachinelearningapproachsoiltemperatureordinalclassificationstoc
AT pelinyıldırımtaser anovelmachinelearningapproachsoiltemperatureordinalclassificationstoc
AT canselkucuk anovelmachinelearningapproachsoiltemperatureordinalclassificationstoc
AT deryabirant novelmachinelearningapproachsoiltemperatureordinalclassificationstoc
AT pelinyıldırımtaser novelmachinelearningapproachsoiltemperatureordinalclassificationstoc
AT canselkucuk novelmachinelearningapproachsoiltemperatureordinalclassificationstoc