<link rel="stylesheet" href="styles.f3b1fba60ec7970c.css">

Leveraging Transfer Learning and Domain Adaptation for Crop Mapping and Classification in Precision Agriculture

dc.contributor.authorNAILI, NAda
dc.date.accessioned2026-06-21T07:53:41Z
dc.date.available2026-06-21T07:53:41Z
dc.date.issued2025
dc.descriptionSupervisor :Mr. Meziane Iftene / Supervisor :Mr. Mohamed Lamine Larabien_US
dc.description.abstractCrop classiĄcation is crucial for precision agriculture and food security but remains challenging in data-scarce regions like North Africa. This thesis reviews recent advances in crop classiĄcation using remote sensing, focusing on machine learning, transfer learning, and domain adaptation techniques. It compares methods including Random Forests, CNNs, Transformers, and unsupervised adaptation strategies. Special attention is given to approaches that work under limited annotations and regional variability. Results show that while Transformer and adaptation methods are effective, their use in Algeria requires tailored strategies due to domain shifts and environmental complexity**** La classiĄcation des cultures est essentielle pour lŠagriculture de précision, mais elle reste difficile dans les régions pauvres en données, comme lŠAfrique du Nord. Ce mémoire passe en revue les méthodes récentes basées sur la télédétection, incluant lŠapprentissage automatique, lŠapprentissage par transfert et lŠadaptation de domaine. Les approches comparées (Random Forest, CNN, Transformers, UDA) montrent que les méthodes récentes sont prometteuses. Toutefois, leur application en Algérie nécessite des adaptations spéciĄques à cause des différences régionales et du manque dŠannotations.en_US
dc.identifier.urihttps://repository.esi-sba.dz/jspui/handle/123456789/831
dc.language.isoenen_US
dc.subjectCrop Mappingen_US
dc.subjectTransfer Learningen_US
dc.subjectDomain Adaptationen_US
dc.subjectRemote Sensingen_US
dc.subjectAlgeriaen_US
dc.titleLeveraging Transfer Learning and Domain Adaptation for Crop Mapping and Classification in Precision Agricultureen_US
dc.typeThesisen_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Naili Nada Master Final Version .docx (1)-pages-1-1.pdf
Size:
177.03 KB
Format:
Adobe Portable Document Format
Description:

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:

Collections