Deep-Learning-Based Land Cover Mapping in Franciacorta Wine Growing Area
Land cover mapping is essential to understanding global land-use patterns and studying biodiversity composition and the functioning of eco-systems. The introduction of remote sensing technologies and artificial intelligence models made it possible to base land cover mapping on satellite imagery in o...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/2/871 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589210367819776 |
|---|---|
| author | Girma Tariku Isabella Ghiglieno Andres Sanchez Morchio Luca Facciano Celine Birolleau Anna Simonetto Ivan Serina Gianni Gilioli |
| author_facet | Girma Tariku Isabella Ghiglieno Andres Sanchez Morchio Luca Facciano Celine Birolleau Anna Simonetto Ivan Serina Gianni Gilioli |
| author_sort | Girma Tariku |
| collection | DOAJ |
| description | Land cover mapping is essential to understanding global land-use patterns and studying biodiversity composition and the functioning of eco-systems. The introduction of remote sensing technologies and artificial intelligence models made it possible to base land cover mapping on satellite imagery in order to monitor changes, assess ecosystem health, support conservation efforts, and reduce monitoring time. However, significant challenges remain in managing large, complex satellite imagery datasets, acquiring specialized datasets due to high costs and labor intensity, including a lack of comparative studies for the selection of optimal deep learning models. No less important is the scarcity of aerial datasets specifically tailored for agricultural areas. This study addresses these gaps by presenting a methodology for semantic segmentation of land covers in agricultural areas using satellite images and deep learning models with pre-trained backbones. We introduce an efficient methodology for preparing semantic segmentation datasets and contribute the “Land Cover Aerial Imagery” (LICAI) dataset for semantic segmentation. The study focuses on the Franciacorta area, Lombardy Region, leveraging the rich diversity of the dataset to effectively train and evaluate the models. We conducted a comparative study, using cutting-edge deep-learning-based segmentation models (U-Net, SegNet, DeepLabV3) with various pre-trained backbones (ResNet, Inception, DenseNet, EfficientNet) on our dataset acquired from Google Earth Pro. Through meticulous data acquisition, preprocessing, model selection, and evaluation, we demonstrate the effectiveness of these techniques in accurately identifying land cover classes. Integrating pre-trained feature extraction networks significantly improves performance across various metrics. Additionally, addressing challenges such as data availability, computational resources, and model interpretability is essential for advancing the field of remote sensing, in support of biodiversity conservation and the provision of ecosystem services and sustainable agriculture. |
| format | Article |
| id | doaj-art-ab8b457a608b4ad196a310c43b9e9e5a |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-ab8b457a608b4ad196a310c43b9e9e5a2025-01-24T13:21:10ZengMDPI AGApplied Sciences2076-34172025-01-0115287110.3390/app15020871Deep-Learning-Based Land Cover Mapping in Franciacorta Wine Growing AreaGirma Tariku0Isabella Ghiglieno1Andres Sanchez Morchio2Luca Facciano3Celine Birolleau4Anna Simonetto5Ivan Serina6Gianni Gilioli7Department of Information Engineering (DII), University of Brescia, 38 Via Branze, 25123 Brescia, ItalyAgrofood Research Hub, Department of Civil, Environmental, Architectural Engineering, and Mathematics, University of Brescia, 43 Via Branze, 25123 Brescia, ItalyAgrofood Research Hub, Department of Civil, Environmental, Architectural Engineering, and Mathematics, University of Brescia, 43 Via Branze, 25123 Brescia, ItalyAgrofood Research Hub, Department of Civil, Environmental, Architectural Engineering, and Mathematics, University of Brescia, 43 Via Branze, 25123 Brescia, ItalyAgrofood Research Hub, Department of Civil, Environmental, Architectural Engineering, and Mathematics, University of Brescia, 43 Via Branze, 25123 Brescia, ItalyAgrofood Research Hub, Department of Civil, Environmental, Architectural Engineering, and Mathematics, University of Brescia, 43 Via Branze, 25123 Brescia, ItalyDepartment of Information Engineering (DII), University of Brescia, 38 Via Branze, 25123 Brescia, ItalyAgrofood Research Hub, Department of Civil, Environmental, Architectural Engineering, and Mathematics, University of Brescia, 43 Via Branze, 25123 Brescia, ItalyLand cover mapping is essential to understanding global land-use patterns and studying biodiversity composition and the functioning of eco-systems. The introduction of remote sensing technologies and artificial intelligence models made it possible to base land cover mapping on satellite imagery in order to monitor changes, assess ecosystem health, support conservation efforts, and reduce monitoring time. However, significant challenges remain in managing large, complex satellite imagery datasets, acquiring specialized datasets due to high costs and labor intensity, including a lack of comparative studies for the selection of optimal deep learning models. No less important is the scarcity of aerial datasets specifically tailored for agricultural areas. This study addresses these gaps by presenting a methodology for semantic segmentation of land covers in agricultural areas using satellite images and deep learning models with pre-trained backbones. We introduce an efficient methodology for preparing semantic segmentation datasets and contribute the “Land Cover Aerial Imagery” (LICAI) dataset for semantic segmentation. The study focuses on the Franciacorta area, Lombardy Region, leveraging the rich diversity of the dataset to effectively train and evaluate the models. We conducted a comparative study, using cutting-edge deep-learning-based segmentation models (U-Net, SegNet, DeepLabV3) with various pre-trained backbones (ResNet, Inception, DenseNet, EfficientNet) on our dataset acquired from Google Earth Pro. Through meticulous data acquisition, preprocessing, model selection, and evaluation, we demonstrate the effectiveness of these techniques in accurately identifying land cover classes. Integrating pre-trained feature extraction networks significantly improves performance across various metrics. Additionally, addressing challenges such as data availability, computational resources, and model interpretability is essential for advancing the field of remote sensing, in support of biodiversity conservation and the provision of ecosystem services and sustainable agriculture.https://www.mdpi.com/2076-3417/15/2/871land cover mappingsemantic segmentationdeep learningsatellite imagerypre-trained backbone |
| spellingShingle | Girma Tariku Isabella Ghiglieno Andres Sanchez Morchio Luca Facciano Celine Birolleau Anna Simonetto Ivan Serina Gianni Gilioli Deep-Learning-Based Land Cover Mapping in Franciacorta Wine Growing Area Applied Sciences land cover mapping semantic segmentation deep learning satellite imagery pre-trained backbone |
| title | Deep-Learning-Based Land Cover Mapping in Franciacorta Wine Growing Area |
| title_full | Deep-Learning-Based Land Cover Mapping in Franciacorta Wine Growing Area |
| title_fullStr | Deep-Learning-Based Land Cover Mapping in Franciacorta Wine Growing Area |
| title_full_unstemmed | Deep-Learning-Based Land Cover Mapping in Franciacorta Wine Growing Area |
| title_short | Deep-Learning-Based Land Cover Mapping in Franciacorta Wine Growing Area |
| title_sort | deep learning based land cover mapping in franciacorta wine growing area |
| topic | land cover mapping semantic segmentation deep learning satellite imagery pre-trained backbone |
| url | https://www.mdpi.com/2076-3417/15/2/871 |
| work_keys_str_mv | AT girmatariku deeplearningbasedlandcovermappinginfranciacortawinegrowingarea AT isabellaghiglieno deeplearningbasedlandcovermappinginfranciacortawinegrowingarea AT andressanchezmorchio deeplearningbasedlandcovermappinginfranciacortawinegrowingarea AT lucafacciano deeplearningbasedlandcovermappinginfranciacortawinegrowingarea AT celinebirolleau deeplearningbasedlandcovermappinginfranciacortawinegrowingarea AT annasimonetto deeplearningbasedlandcovermappinginfranciacortawinegrowingarea AT ivanserina deeplearningbasedlandcovermappinginfranciacortawinegrowingarea AT giannigilioli deeplearningbasedlandcovermappinginfranciacortawinegrowingarea |