Next Article in Journal
A Dual-Branch Framework Integrating the Segment Anything Model and Semantic-Aware Network for High-Resolution Cropland Extraction
Previous Article in Journal
MSAFNet: Multi-Modal Marine Aquaculture Segmentation via Spatial–Frequency Adaptive Fusion
Previous Article in Special Issue
Land Cover Types Drive the Surface Temperature for Upscaling Surface Urban Heat Islands with Daylight Images
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Assessment of the Effectiveness of Spectral Indices Derived from EnMAP Hyperspectral Imageries Using Machine Learning and Deep Learning Models for Winter Wheat Yield Prediction

1
Department of Atmospheric and Geospatial Data Science, University of Szeged, Egyetem Str. 2, H-6722 Szeged, Hungary
2
Lajtamag Ltd., Bereki Str. 1, H-9246 Mosonmagyaróvár, Hungary
3
Nemzeti Ménesbirtok és Tangazdaság Zrt., Jung József Sq. 1, H-5820 Mezőhegyes, Hungary
4
Laboratory for Climatology and Remote Sensing, Department of Geography, Philipps-Universität Marburg, Deutschhausstr. 12, 35032 Marburg, Germany
5
Department of Geology, Faculty of Science, Cairo University, Giza P.O. Box 12613, Egypt
6
Doctoral School of Geosciences, University of Szeged, Egyetem Str. 2, H-6722 Szeged, Hungary
*
Author to whom correspondence should be addressed.
Remote Sens. 2025, 17(20), 3426; https://doi.org/10.3390/rs17203426 (registering DOI)
Submission received: 11 August 2025 / Revised: 21 September 2025 / Accepted: 8 October 2025 / Published: 13 October 2025

Abstract

Accurate and timely crop yield estimation is essential for effective agricultural management and global food security, particularly for winter wheat. This study aimed to assess the effectiveness of EnMAP hyperspectral imagery in combination with machine learning and deep learning models for winter wheat yield prediction in Hungary. Using EnMAP images from February and May 2023, along with ground truth yield data from four fields, we derived 10 distinct vegetation indices. Random Forest, Gradient Boosting, and Multilayer Perceptron algorithms were employed, and model performance was evaluated using Mean Absolute Error (MAE) and Coefficient of Determination (R2) values. The results consistently demonstrated that integrating multi-temporal data significantly enhanced predictive accuracy, with the MLP model achieving an R2 of 0.79 and an MAE of 0.27, notably outperforming single-date predictions. Shortwave infrared (SWIR) indices were particularly critical for early-season yield estimations. This research highlights the substantial potential of hyperspectral data and advanced machine learning techniques in precision agriculture, emphasizing the promising role of future missions such as CHIME in further refining and expanding yield estimation capabilities.
Keywords: spectral vegetation indices; machine learning regression; crop yield; multi-temporal analysis; spaceborne hyperspectral spectral vegetation indices; machine learning regression; crop yield; multi-temporal analysis; spaceborne hyperspectral

Share and Cite

MDPI and ACS Style

Mucsi, L.; Litkey-Kovács, D.; Bonus, K.; Farmonov, N.; Elgendy, A.; Aji, L.; Sóti, M. Assessment of the Effectiveness of Spectral Indices Derived from EnMAP Hyperspectral Imageries Using Machine Learning and Deep Learning Models for Winter Wheat Yield Prediction. Remote Sens. 2025, 17, 3426. https://doi.org/10.3390/rs17203426

AMA Style

Mucsi L, Litkey-Kovács D, Bonus K, Farmonov N, Elgendy A, Aji L, Sóti M. Assessment of the Effectiveness of Spectral Indices Derived from EnMAP Hyperspectral Imageries Using Machine Learning and Deep Learning Models for Winter Wheat Yield Prediction. Remote Sensing. 2025; 17(20):3426. https://doi.org/10.3390/rs17203426

Chicago/Turabian Style

Mucsi, László, Dorottya Litkey-Kovács, Krisztián Bonus, Nizom Farmonov, Ali Elgendy, Lutfi Aji, and Márkó Sóti. 2025. "Assessment of the Effectiveness of Spectral Indices Derived from EnMAP Hyperspectral Imageries Using Machine Learning and Deep Learning Models for Winter Wheat Yield Prediction" Remote Sensing 17, no. 20: 3426. https://doi.org/10.3390/rs17203426

APA Style

Mucsi, L., Litkey-Kovács, D., Bonus, K., Farmonov, N., Elgendy, A., Aji, L., & Sóti, M. (2025). Assessment of the Effectiveness of Spectral Indices Derived from EnMAP Hyperspectral Imageries Using Machine Learning and Deep Learning Models for Winter Wheat Yield Prediction. Remote Sensing, 17(20), 3426. https://doi.org/10.3390/rs17203426

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

Article Metrics

Back to TopTop