Detecting Soil Tillage in Portugal: Challenges and Insights from Rules-Based and Machine Learning Approaches Using Sentinel-1 and Sentinel-2 Data

Morais, Tiago G.; Domingos, Tiago; Falcão, João; Camacho, Manuel; Marques, Ana; Neves, Inês; Lopes, Hugo; Teixeira, Ricardo F. M.

doi:10.3390/su162310389

Open AccessArticle

Detecting Soil Tillage in Portugal: Challenges and Insights from Rules-Based and Machine Learning Approaches Using Sentinel-1 and Sentinel-2 Data

by

Tiago G. Morais

^1,2

,

Tiago Domingos

¹

,

João Falcão

³,

Manuel Camacho

³,

Ana Marques

³,

Inês Neves

³

,

Hugo Lopes

³ and

Ricardo F. M. Teixeira

^1,*

¹

MARETEC—Marine, Environment and Technology Centre, LARSyS, Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, 1, 1049-001 Lisbon, Portugal

²

VirtuaCrop, Lda., Rua Marquês de Fronteira, 102, 1070-300 Lisbon, Portugal

³

Instituto de Financiamento da Agricultura e Pescas (IFAP), 1649-034 Lisbon, Portugal

^*

Author to whom correspondence should be addressed.

Sustainability 2024, 16(23), 10389; https://doi.org/10.3390/su162310389

Submission received: 10 October 2024 / Revised: 14 November 2024 / Accepted: 22 November 2024 / Published: 27 November 2024

(This article belongs to the Special Issue Sustainable Soil Management: Conservation Strategies for Agricultural Resilience)

Download

Browse Figures

Versions Notes

Abstract

Monitoring soil tillage activities, such as plowing and cultivating, is essential for aligning agricultural practices with environmental standards for soil health. Detecting these activities presents significant challenges, especially when relying on remotely sensed data. This paper addresses these challenges within the framework of the Common Agricultural Policy (CAP), which requires EU countries to enhance their environmental monitoring and climate action efforts. We used remote sensing data from Sentinel-1 and Sentinel-2 missions to detect soil tillage practices in 73 test farms in Portugal. Three approaches were explored: a rule-based method and two machine learning techniques based on XGBoost (XGB). One machine learning approach utilized the original imbalanced dataset, while the other employed a SMOTE (Synthetic Minority Oversampling Technique) approach to balance underrepresented soil tillage operations within the training set. Our findings highlight the inherent difficulty in detecting soil tillage operations across all methods, though the XGB-SMOTE approach demonstrated the most promising results, achieving a recall of 67% and an AUC-ROC (area under the receiver operating characteristic curve) of 74%. These results underscore the need for further research to develop a fully automated detection model. This work has potential applications for monitoring compliance with CAP mandates and informing environmental policy to better support sustainable agricultural practices.

Keywords: Common Agricultural Policy; change detection; remote sensing; XGBoost; environmental monitoring

Share and Cite

MDPI and ACS Style

Morais, T.G.; Domingos, T.; Falcão, J.; Camacho, M.; Marques, A.; Neves, I.; Lopes, H.; Teixeira, R.F.M. Detecting Soil Tillage in Portugal: Challenges and Insights from Rules-Based and Machine Learning Approaches Using Sentinel-1 and Sentinel-2 Data. Sustainability 2024, 16, 10389. https://doi.org/10.3390/su162310389

AMA Style

Morais TG, Domingos T, Falcão J, Camacho M, Marques A, Neves I, Lopes H, Teixeira RFM. Detecting Soil Tillage in Portugal: Challenges and Insights from Rules-Based and Machine Learning Approaches Using Sentinel-1 and Sentinel-2 Data. Sustainability. 2024; 16(23):10389. https://doi.org/10.3390/su162310389

Chicago/Turabian Style

Morais, Tiago G., Tiago Domingos, João Falcão, Manuel Camacho, Ana Marques, Inês Neves, Hugo Lopes, and Ricardo F. M. Teixeira. 2024. "Detecting Soil Tillage in Portugal: Challenges and Insights from Rules-Based and Machine Learning Approaches Using Sentinel-1 and Sentinel-2 Data" Sustainability 16, no. 23: 10389. https://doi.org/10.3390/su162310389

APA Style

Morais, T. G., Domingos, T., Falcão, J., Camacho, M., Marques, A., Neves, I., Lopes, H., & Teixeira, R. F. M. (2024). Detecting Soil Tillage in Portugal: Challenges and Insights from Rules-Based and Machine Learning Approaches Using Sentinel-1 and Sentinel-2 Data. Sustainability, 16(23), 10389. https://doi.org/10.3390/su162310389

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Detecting Soil Tillage in Portugal: Challenges and Insights from Rules-Based and Machine Learning Approaches Using Sentinel-1 and Sentinel-2 Data

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI