Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Monitoring digestate application on agricultural crops using Sentinel-2 Satellite imagery

Andreas Kalogeras, Dimitrios Bormpoudakis, Iason Tsardanidis, Dimitra A. Loka, Charalampos Kontoes

TL;DR

This study assesses the use of Sentinel-2 satellite imagery to monitor digestate (a form of Exogenous Organic Matter) application in agricultural fields by deriving EOM-focused spectral indices and applying multiple machine learning classifiers. It demonstrates that certain indices, notably EOMI_2, can reveal digestate-related spectral changes, while traditional vegetation indices may be less sensitive, particularly under partial vegetation cover. Random Forest and a Feed-forward Neural Network show complementary strengths in detecting treated fields, indicating potential for scalable, real-world monitoring across crop types in Thessaly, Greece. The work highlights practical pathways for landscape-level governance and precision agriculture, while outlining limitations tied to observability variability and the need for expanded data and methods refinement.

Abstract

The widespread use of Exogenous Organic Matter in agriculture necessitates monitoring to assess its effects on soil and crop health. This study evaluates optical Sentinel-2 satellite imagery for detecting digestate application, a practice that enhances soil fertility but poses environmental risks like microplastic contamination and nitrogen losses. In the first instance, Sentinel-2 satellite image time series (SITS) analysis of specific indices (EOMI, NDVI, EVI) was used to characterize EOM's spectral behavior after application on the soils of four different crop types in Thessaly, Greece. Furthermore, Machine Learning (ML) models (namely Random Forest, k-NN, Gradient Boosting and a Feed-Forward Neural Network), were used to investigate digestate presence detection, achieving F1-scores up to 0.85. The findings highlight the potential of combining remote sensing and ML for scalable and cost-effective monitoring of EOM applications, supporting precision agriculture and sustainability.

Monitoring digestate application on agricultural crops using Sentinel-2 Satellite imagery

TL;DR

This study assesses the use of Sentinel-2 satellite imagery to monitor digestate (a form of Exogenous Organic Matter) application in agricultural fields by deriving EOM-focused spectral indices and applying multiple machine learning classifiers. It demonstrates that certain indices, notably EOMI_2, can reveal digestate-related spectral changes, while traditional vegetation indices may be less sensitive, particularly under partial vegetation cover. Random Forest and a Feed-forward Neural Network show complementary strengths in detecting treated fields, indicating potential for scalable, real-world monitoring across crop types in Thessaly, Greece. The work highlights practical pathways for landscape-level governance and precision agriculture, while outlining limitations tied to observability variability and the need for expanded data and methods refinement.

Abstract

The widespread use of Exogenous Organic Matter in agriculture necessitates monitoring to assess its effects on soil and crop health. This study evaluates optical Sentinel-2 satellite imagery for detecting digestate application, a practice that enhances soil fertility but poses environmental risks like microplastic contamination and nitrogen losses. In the first instance, Sentinel-2 satellite image time series (SITS) analysis of specific indices (EOMI, NDVI, EVI) was used to characterize EOM's spectral behavior after application on the soils of four different crop types in Thessaly, Greece. Furthermore, Machine Learning (ML) models (namely Random Forest, k-NN, Gradient Boosting and a Feed-Forward Neural Network), were used to investigate digestate presence detection, achieving F1-scores up to 0.85. The findings highlight the potential of combining remote sensing and ML for scalable and cost-effective monitoring of EOM applications, supporting precision agriculture and sustainability.
Paper Structure (11 sections, 7 equations, 3 figures, 1 table)

This paper contains 11 sections, 7 equations, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Materials and Methods
  3. Study site and field description
  4. Spectral indices for EOM detection
  5. Model Implementation
  6. Results and Discussion
  7. Photo Interpretation
  8. Model Evaluation
  9. Discussion
  10. Conclusion
  11. Acknowledgements

Figures (3)

  • Figure 1: Pipeline of the process
  • Figure 2: Comparison of three monitoring approaches for assessing field conditions after digestate application: (a) standard RGB imagery, (b) vegetation health using the NDVI, and (c) exogenous organic matter using the EOMI2.
  • Figure 3: Comparison of barcharts showing the percentages of appearance or not of the change in the index: (a) per crop category, and (b) per season.