Next Article in Journal
Field Evaluation of the Effects of Planting Speed, Downforce, Seed-Plate Configuration, and High-Speed Seed Delivery Systems on Cotton Stand Establishment, Spacing Uniformity, and Lint Yield
Next Article in Special Issue
Enhanced Non-Invasive Estimation of Pig Body Weight in Growth Stage Based on Computer Vision
Previous Article in Journal
Modeling the Evaporative Cooling Potential in Dairy Farming: A Thermal Index-Based Approach Under Distinct Brazilian Climatic Conditions
Previous Article in Special Issue
Addressing Class Imbalance in Rice Disease Diagnosis with Contrastive Dissimilarity
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
AgriEngineering
Volume 8
Issue 4
10.3390/agriengineering8040125
agriengineering-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Semantic Segmentation of Coffee Crops with PlanetScope Images: A Comparative Analysis of Spectral Band Combinations for U-Net Architecture

by
Daniel Henrique Leite
1,*,
Domingos Sárvio Magalhães Valente
1,
Pedro Maya Ferreira Arruda
2,
Gabriel Dumbá Monteiro de Castro
1,
Daniel Marçal de Queiroz
1,
Diego Bedin Marin
3 and
Fábio Daniel Tancredi
4
1
Department of Agricultural Engineering, Federal University of Viçosa, Viçosa 36571-900, MG, Brazil
2
Department of Agricultural Engineering and Environment, Federal Fluminense University, Niterói 24210-240, RJ, Brazil
3
Institute of Science, Technology and Innovation (ICTIN), Federal University of Lavras, São Sebastião do Paraíso 37953-180, MG, Brazil
4
Minas Gerais Agricultural Research Agency (EPAMIG-Sudeste), Viçosa 36570-000, MG, Brazil
*
Author to whom correspondence should be addressed.
AgriEngineering 2026, 8(4), 125; https://doi.org/10.3390/agriengineering8040125
Submission received: 27 December 2025 / Revised: 12 March 2026 / Accepted: 24 March 2026 / Published: 1 April 2026
(This article belongs to the Collection Exploring the Application of Artificial Intelligence and Image Processing in Agriculture)
Browse Figures
Versions Notes

Abstract

Coffee is among the primary agricultural commodities in international trade; however, mapping coffee crops in mountainous regions faces limitations due to high spectral variability and complex canopy structures. This study hypothesized that optimized spectral band combinations focused on the visible spectrum may outperform configurations including near-infrared (NIR) for coffee crop segmentation. This work aimed to evaluate how different spectral band combinations affect the performance of the U-Net for segmenting coffee crops in mountainous regions. Seven PlanetScope images (4 m resolution) from Matas de Minas, Brazil, covering different phenological stages in 2023–2024, were divided into 316 training patches and 25 test patches of 256 × 256 pixels and used to train U-Net models across five spectral band combinations: (B, G, R), (B, G, NIR), (B, R, NIR), (G, R, NIR), and (B, G, R, NIR). The visible spectrum combination (B, G, R) demonstrated superior performance with an overall Accuracy of 0.8669 and, for the Coffee Crops class, an F1-score of 0.8682 and an IoU of 0.7671, outperforming all NIR-inclusive configurations. Visible bands’ sensitivity to pigmentation variations proved more effective in heterogeneous environments, while NIR increased spectral confusion near native vegetation and crop edges. The model overestimated cultivated area by 18.3% due to mixed pixels from 4 m resolution and mountainous terrain. These findings confirm that visible-spectrum bands offer a cost-effective alternative for coffee segmentation, though higher spatial resolution is needed for improved boundary delineation.
Keywords: coffee crop mapping; semantic segmentation; deep learning; remote sensing; precision agriculture coffee crop mapping; semantic segmentation; deep learning; remote sensing; precision agriculture

Share and Cite

MDPI and ACS Style

Leite, D.H.; Valente, D.S.M.; Arruda, P.M.F.; Castro, G.D.M.d.; Queiroz, D.M.d.; Marin, D.B.; Tancredi, F.D. Semantic Segmentation of Coffee Crops with PlanetScope Images: A Comparative Analysis of Spectral Band Combinations for U-Net Architecture. AgriEngineering 2026, 8, 125. https://doi.org/10.3390/agriengineering8040125

AMA Style

Leite DH, Valente DSM, Arruda PMF, Castro GDMd, Queiroz DMd, Marin DB, Tancredi FD. Semantic Segmentation of Coffee Crops with PlanetScope Images: A Comparative Analysis of Spectral Band Combinations for U-Net Architecture. AgriEngineering. 2026; 8(4):125. https://doi.org/10.3390/agriengineering8040125

Chicago/Turabian Style

Leite, Daniel Henrique, Domingos Sárvio Magalhães Valente, Pedro Maya Ferreira Arruda, Gabriel Dumbá Monteiro de Castro, Daniel Marçal de Queiroz, Diego Bedin Marin, and Fábio Daniel Tancredi. 2026. "Semantic Segmentation of Coffee Crops with PlanetScope Images: A Comparative Analysis of Spectral Band Combinations for U-Net Architecture" AgriEngineering 8, no. 4: 125. https://doi.org/10.3390/agriengineering8040125

APA Style

Leite, D. H., Valente, D. S. M., Arruda, P. M. F., Castro, G. D. M. d., Queiroz, D. M. d., Marin, D. B., & Tancredi, F. D. (2026). Semantic Segmentation of Coffee Crops with PlanetScope Images: A Comparative Analysis of Spectral Band Combinations for U-Net Architecture. AgriEngineering, 8(4), 125. https://doi.org/10.3390/agriengineering8040125

Article Metrics

Back to TopTop