Implementation of XGBoost Models for Predicting CO<sub>2</sub> Emission and Specific Tractor Fuel Consumption

Tillage is one of the most energy-intensive operations in crop production, leading to high fuel consumption and the emission of harmful gases such as CO<sub>2</sub> and NO<sub>x</sub>. This study was conducted under real field conditions to explore how soil parameters influen...

Full description

Saved in:
Bibliographic Details
Main Authors: Nebojša Balać, Zoran Mileusnić, Aleksandra Dragičević, Mihailo Milanović, Andrija Rajković, Rajko Miodragović, Olivera Ećim-Đurić
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Agriculture
Subjects:
Online Access:https://www.mdpi.com/2077-0472/15/11/1209
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849330769105780736
author Nebojša Balać
Zoran Mileusnić
Aleksandra Dragičević
Mihailo Milanović
Andrija Rajković
Rajko Miodragović
Olivera Ećim-Đurić
author_facet Nebojša Balać
Zoran Mileusnić
Aleksandra Dragičević
Mihailo Milanović
Andrija Rajković
Rajko Miodragović
Olivera Ećim-Đurić
author_sort Nebojša Balać
collection DOAJ
description Tillage is one of the most energy-intensive operations in crop production, leading to high fuel consumption and the emission of harmful gases such as CO<sub>2</sub> and NO<sub>x</sub>. This study was conducted under real field conditions to explore how soil parameters influence variations in fuel use and exhaust emissions. A machine learning approach based on the XGBoost algorithm was applied to develop predictive models for CO<sub>2</sub> concentrations in exhaust gases and specific fuel consumption. The CO<sub>2</sub> prediction model achieved an accuracy exceeding 80%, while the model for fuel consumption reached over 65%. Although not optimized for high precision, these models offer a valuable basis for preliminary assessments and highlight the potential of data-driven approaches for improving energy efficiency and environmental sustainability in agricultural mechanization.
format Article
id doaj-art-eafabbcb41c34878bcf8648cf914e294
institution Kabale University
issn 2077-0472
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Agriculture
spelling doaj-art-eafabbcb41c34878bcf8648cf914e2942025-08-20T03:46:49ZengMDPI AGAgriculture2077-04722025-05-011511120910.3390/agriculture15111209Implementation of XGBoost Models for Predicting CO<sub>2</sub> Emission and Specific Tractor Fuel ConsumptionNebojša Balać0Zoran Mileusnić1Aleksandra Dragičević2Mihailo Milanović3Andrija Rajković4Rajko Miodragović5Olivera Ećim-Đurić6Kite d.o.o., 21333 Čenej, SerbiaDepartment of Agricultural Engineering, Faculty of Agriculture, University of Belgrade, Nemanjina 6, 11080 Belgrade, SerbiaDepartment of Agricultural Engineering, Faculty of Agriculture, University of Belgrade, Nemanjina 6, 11080 Belgrade, SerbiaDepartment of Agricultural Engineering, Faculty of Agriculture, University of Belgrade, Nemanjina 6, 11080 Belgrade, SerbiaDepartment of Agricultural Engineering, Faculty of Agriculture, University of Belgrade, Nemanjina 6, 11080 Belgrade, SerbiaDepartment of Agricultural Engineering, Faculty of Agriculture, University of Belgrade, Nemanjina 6, 11080 Belgrade, SerbiaDepartment of Agricultural Engineering, Faculty of Agriculture, University of Belgrade, Nemanjina 6, 11080 Belgrade, SerbiaTillage is one of the most energy-intensive operations in crop production, leading to high fuel consumption and the emission of harmful gases such as CO<sub>2</sub> and NO<sub>x</sub>. This study was conducted under real field conditions to explore how soil parameters influence variations in fuel use and exhaust emissions. A machine learning approach based on the XGBoost algorithm was applied to develop predictive models for CO<sub>2</sub> concentrations in exhaust gases and specific fuel consumption. The CO<sub>2</sub> prediction model achieved an accuracy exceeding 80%, while the model for fuel consumption reached over 65%. Although not optimized for high precision, these models offer a valuable basis for preliminary assessments and highlight the potential of data-driven approaches for improving energy efficiency and environmental sustainability in agricultural mechanization.https://www.mdpi.com/2077-0472/15/11/1209tractor exhausts emissionpredictive soil tillageVRA soil tillageprecision agriculturemachine learningXGBoost model
spellingShingle Nebojša Balać
Zoran Mileusnić
Aleksandra Dragičević
Mihailo Milanović
Andrija Rajković
Rajko Miodragović
Olivera Ećim-Đurić
Implementation of XGBoost Models for Predicting CO<sub>2</sub> Emission and Specific Tractor Fuel Consumption
Agriculture
tractor exhausts emission
predictive soil tillage
VRA soil tillage
precision agriculture
machine learning
XGBoost model
title Implementation of XGBoost Models for Predicting CO<sub>2</sub> Emission and Specific Tractor Fuel Consumption
title_full Implementation of XGBoost Models for Predicting CO<sub>2</sub> Emission and Specific Tractor Fuel Consumption
title_fullStr Implementation of XGBoost Models for Predicting CO<sub>2</sub> Emission and Specific Tractor Fuel Consumption
title_full_unstemmed Implementation of XGBoost Models for Predicting CO<sub>2</sub> Emission and Specific Tractor Fuel Consumption
title_short Implementation of XGBoost Models for Predicting CO<sub>2</sub> Emission and Specific Tractor Fuel Consumption
title_sort implementation of xgboost models for predicting co sub 2 sub emission and specific tractor fuel consumption
topic tractor exhausts emission
predictive soil tillage
VRA soil tillage
precision agriculture
machine learning
XGBoost model
url https://www.mdpi.com/2077-0472/15/11/1209
work_keys_str_mv AT nebojsabalac implementationofxgboostmodelsforpredictingcosub2subemissionandspecifictractorfuelconsumption
AT zoranmileusnic implementationofxgboostmodelsforpredictingcosub2subemissionandspecifictractorfuelconsumption
AT aleksandradragicevic implementationofxgboostmodelsforpredictingcosub2subemissionandspecifictractorfuelconsumption
AT mihailomilanovic implementationofxgboostmodelsforpredictingcosub2subemissionandspecifictractorfuelconsumption
AT andrijarajkovic implementationofxgboostmodelsforpredictingcosub2subemissionandspecifictractorfuelconsumption
AT rajkomiodragovic implementationofxgboostmodelsforpredictingcosub2subemissionandspecifictractorfuelconsumption
AT oliveraecimđuric implementationofxgboostmodelsforpredictingcosub2subemissionandspecifictractorfuelconsumption