Enhancing Crop Classification in Emilia-Romagna (Italy) Using Transformer-Based Multi-Source Data Fusion with Thermal Observations

This study explores the potential of integrating multi-source remote sensing data—including Sentinel-1 synthetic aperture radar (SAR) imagery, Sentinel-2 optical imagery, and Landsat 8 thermal data—for crop classification in Emilia-Romagna (Northern Italy). Using satellite imager...

Full description

Saved in:
Bibliographic Details
Main Authors: Y. Qi, E. Mandanici, M. Helmy, F. Trevisiol, G. Bitelli
Format: Article
Language:English
Published: Copernicus Publications 2025-07-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1237/2025/isprs-archives-XLVIII-G-2025-1237-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849246308209000448
author Y. Qi
E. Mandanici
M. Helmy
F. Trevisiol
G. Bitelli
author_facet Y. Qi
E. Mandanici
M. Helmy
F. Trevisiol
G. Bitelli
author_sort Y. Qi
collection DOAJ
description This study explores the potential of integrating multi-source remote sensing data—including Sentinel-1 synthetic aperture radar (SAR) imagery, Sentinel-2 optical imagery, and Landsat 8 thermal data—for crop classification in Emilia-Romagna (Northern Italy). Using satellite imagery and agricultural surveys, we constructed a temporal dataset covering 2020 with 27 biweekly time steps. After filtering out underrepresented crop types with insufficient samples for machine learning training, nine crop types remained. We implemented four deep learning models using TensorFlow: Dense Neural Network (DNN), Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), and Transformer. Our results indicate that removing underrepresented crops significantly improves classification performance, leading to an overall accuracy of approximately 91%. Incorporating Landsat 8 thermal data further enhanced accuracy, with the Transformer model achieving a peak accuracy of 92.08%. A crop-specific analysis revealed that temperature observations notably improved classification for crops with distinct thermal signatures (e.g., sugar beets, corn), whereas limited improvement was observed for spectrally similar cereals (e.g., wheat, barley). Overall, the Transformer model demonstrated exceptional ability in capturing spatial-temporal dependencies in multivariate time-series data. These findings underscore the advantages of integrating multi-source satellite data including thermal infrared and leveraging attention-based neural networks for large-scale agricultural monitoring and resource management.
format Article
id doaj-art-295a721a00c844c6b2b8da237d647f55
institution Kabale University
issn 1682-1750
2194-9034
language English
publishDate 2025-07-01
publisher Copernicus Publications
record_format Article
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-295a721a00c844c6b2b8da237d647f552025-08-20T03:58:32ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342025-07-01XLVIII-G-20251237124510.5194/isprs-archives-XLVIII-G-2025-1237-2025Enhancing Crop Classification in Emilia-Romagna (Italy) Using Transformer-Based Multi-Source Data Fusion with Thermal ObservationsY. Qi0E. Mandanici1M. Helmy2F. Trevisiol3G. Bitelli4Dept. of Civil, Chemical, Environmental and Materials Engineering (DICAM), Survey and Geomatics Laboratory (LARIG), University of Bologna, Bologna, ItalyDept. of Civil, Chemical, Environmental and Materials Engineering (DICAM), Survey and Geomatics Laboratory (LARIG), University of Bologna, Bologna, ItalyDept. of Civil, Chemical, Environmental and Materials Engineering (DICAM), Survey and Geomatics Laboratory (LARIG), University of Bologna, Bologna, ItalyCIMA Research Foundation, Via A. Magliotto 2, 17100 Savona, ItalyDept. of Civil, Chemical, Environmental and Materials Engineering (DICAM), Survey and Geomatics Laboratory (LARIG), University of Bologna, Bologna, ItalyThis study explores the potential of integrating multi-source remote sensing data—including Sentinel-1 synthetic aperture radar (SAR) imagery, Sentinel-2 optical imagery, and Landsat 8 thermal data—for crop classification in Emilia-Romagna (Northern Italy). Using satellite imagery and agricultural surveys, we constructed a temporal dataset covering 2020 with 27 biweekly time steps. After filtering out underrepresented crop types with insufficient samples for machine learning training, nine crop types remained. We implemented four deep learning models using TensorFlow: Dense Neural Network (DNN), Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), and Transformer. Our results indicate that removing underrepresented crops significantly improves classification performance, leading to an overall accuracy of approximately 91%. Incorporating Landsat 8 thermal data further enhanced accuracy, with the Transformer model achieving a peak accuracy of 92.08%. A crop-specific analysis revealed that temperature observations notably improved classification for crops with distinct thermal signatures (e.g., sugar beets, corn), whereas limited improvement was observed for spectrally similar cereals (e.g., wheat, barley). Overall, the Transformer model demonstrated exceptional ability in capturing spatial-temporal dependencies in multivariate time-series data. These findings underscore the advantages of integrating multi-source satellite data including thermal infrared and leveraging attention-based neural networks for large-scale agricultural monitoring and resource management.https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1237/2025/isprs-archives-XLVIII-G-2025-1237-2025.pdf
spellingShingle Y. Qi
E. Mandanici
M. Helmy
F. Trevisiol
G. Bitelli
Enhancing Crop Classification in Emilia-Romagna (Italy) Using Transformer-Based Multi-Source Data Fusion with Thermal Observations
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title Enhancing Crop Classification in Emilia-Romagna (Italy) Using Transformer-Based Multi-Source Data Fusion with Thermal Observations
title_full Enhancing Crop Classification in Emilia-Romagna (Italy) Using Transformer-Based Multi-Source Data Fusion with Thermal Observations
title_fullStr Enhancing Crop Classification in Emilia-Romagna (Italy) Using Transformer-Based Multi-Source Data Fusion with Thermal Observations
title_full_unstemmed Enhancing Crop Classification in Emilia-Romagna (Italy) Using Transformer-Based Multi-Source Data Fusion with Thermal Observations
title_short Enhancing Crop Classification in Emilia-Romagna (Italy) Using Transformer-Based Multi-Source Data Fusion with Thermal Observations
title_sort enhancing crop classification in emilia romagna italy using transformer based multi source data fusion with thermal observations
url https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1237/2025/isprs-archives-XLVIII-G-2025-1237-2025.pdf
work_keys_str_mv AT yqi enhancingcropclassificationinemiliaromagnaitalyusingtransformerbasedmultisourcedatafusionwiththermalobservations
AT emandanici enhancingcropclassificationinemiliaromagnaitalyusingtransformerbasedmultisourcedatafusionwiththermalobservations
AT mhelmy enhancingcropclassificationinemiliaromagnaitalyusingtransformerbasedmultisourcedatafusionwiththermalobservations
AT ftrevisiol enhancingcropclassificationinemiliaromagnaitalyusingtransformerbasedmultisourcedatafusionwiththermalobservations
AT gbitelli enhancingcropclassificationinemiliaromagnaitalyusingtransformerbasedmultisourcedatafusionwiththermalobservations