AI-Driven Ensemble Modelling for Agricultural Land Use Mapping and Change Detection Using Sentinel-2 Satellite Imagery
International Journal of Drug Delivery Technology · 02.05.2026 · 16 (32s)
DOI: 10.25258/ijddt.16.32s.124 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 02.05.2026. Verfasst von Namita Tyagi und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Global food security faces critical threats from urbanization, climate change, and declining arable land, necessitating advanced monitoring to boost production by 70% by 2050 in line with SDG 2: Zero Hunger. This research develops an automated, scalable framework leveraging Sentinel-2 satellite data for precise agricultural land use/land cover (LULC) mapping and spatiotemporal change detection, addressing key gaps in rural semantic interpretation, data scarcity, and model robustness. Key contributions include a systematic literature review of AI evolution from CNNs and U-Net to Vision Transformers; construction of a 30,000-sample high-resolution dataset with Sen2Cor atmospheric correction and DCGAN augmentation for cloud-free imagery; and a novel Soft Voting Ensemble Classifier integrating SVM, KNN, and Decision Trees, achieving 90-97% overall accuracy and F1-scores of 0.92-0.95—outperforming individual models by 2-5% through bias mitigation and preprocessing gains of 25-35%. Applied to multi-temporal datasets, the system quantifies shifts like agriculture-to-urban conversion (93% precision) and forest-to-cropland transitions, enabling policy insights for climate adaptation and biodiversity conservation. Future extensions involve few-shot learning, multi-sensor fusion, and XAI for broader scalability
Zitieren
APA
Tyagi, N., Tiwari, D. G., & Sharma, D. D. (2026). AI-Driven Ensemble Modelling for Agricultural Land Use Mapping and Change Detection Using Sentinel-2 Satellite Imagery. International Journal of Drug Delivery Technology, 16(32s). https://doi.org/10.25258/ijddt.16.32s.124
Vancouver
Tyagi N, Tiwari DG, Sharma DD. AI-Driven Ensemble Modelling for Agricultural Land Use Mapping and Change Detection Using Sentinel-2 Satellite Imagery. International Journal of Drug Delivery Technology. 2026;16(32s). doi:10.25258/ijddt.16.32s.124
BibTeX
@article{Tyagi2026,
author = {Tyagi, Namita and Tiwari, Dr. Gagan and Sharma, Dr. Deepika},
title = {AI-Driven Ensemble Modelling for Agricultural Land Use Mapping and Change Detection Using Sentinel-2 Satellite Imagery},
journal = {International Journal of Drug Delivery Technology},
year = {2026},
volume = {16},
number = {32s},
doi = {10.25258/ijddt.16.32s.124}
}
EUVIMED