AN EXPLAINABLE DEEP LEARNING FRAMEWORK FOR LAND USE AND LAND COVER CLASSIFICATION USING REMOTE SENSING
DOI: 
SHARE THIS ARTICLE
DOWNLOAD ARTICLE
REVIEW REPORT
CITE THIS ARTICLE
Land use classification is an important job in remote sensing. It helps in many areas like planning for city growth, protecting the environment, managing disasters, and using resources wisely. This study presents a complete deep learning system designed to predict land use accurately and in a way that is easy to understand using images from satellites and drones. The process starts by improving the images using techniques like histogram equalization and Gaussian smoothing. These methods help make the contrast better and reduce noise, which in turn makes the important details easier to see. Next, the picture segmentation stage is used to separate important areas in image. This helps the model concentrate on important features likes groups of plants, bodies of water and constructed areas. The images are then send to a simple Convolutional neural network (CNN), which is a popular type of deep learning system. This network is built to quickly sort different land use types, such as urban areas, forests, water, agriculture and roads. The model is designed to work well and use computer resources efficiently, which makes it great for real time and large scale uses. To improve how clear the model is the framework uses Gradient weighted
Keywords
Article Information
Article Metrics
HOW TO CITE
Copy
B.Muthukkumaran, (2026). An Explainable Deep Learning Framework for Land use and Land Cover Classification using Remote Sensing. International Journal of Science, Strategic Management and Technology, 02(05). https://doi.org/10.55041/ijsmt.v2i5.212
B.Muthukkumaran, . "An Explainable Deep Learning Framework for Land use and Land Cover Classification using Remote Sensing." International Journal of Science, Strategic Management and Technology, vol. 02, no. 05, 2026, pp. . doi:https://doi.org/10.55041/ijsmt.v2i5.212.
B.Muthukkumaran, . "An Explainable Deep Learning Framework for Land use and Land Cover Classification using Remote Sensing." International Journal of Science, Strategic Management and Technology 02, no. 05 (2026). https://doi.org/https://doi.org/10.55041/ijsmt.v2i5.212.
References
2.Reem AlAli, “Artificial Intelligence for Land Cover and Land Use Classification in Remote Sensing: Review Study” – comparative review of ML & DL approaches.
3.Manuel Campos‑Taberner et al., “Understanding deep learning in land use classification based on Sentinel‑2 time series” – explores DL and interpretability challenges.
4.Firas F. et al., “AI in remote sensing and satellite image processing – a review” – covers AI improvements in land cover tasks.
5.Mengmeng Hao et al., “Land‑use classification based on high‑resolution remote sensing imagery and deep learning models” – compares FCN, SegNet, U‑Net and Swin‑UNet.
6.“Enhancing land use and land cover classification with deep learning‑based satellite imagery segmentation” – advanced segmentation using DeepLabV3+, Xception backbones.
7.Naushad et al., “Deep Transfer Learning for Land Use and Land Cover Classification: A Comparative Study” – demonstrates transfer learning strategies.
8.Chun Yang et al., “A hierarchical deep learning framework for consistent classification of land use objects” – hierarchical CNN approach for geospatial data.
9.Teymoor Seydi et al., “Multimodal and hybrid transformer architectures for land use classification” – transformer & multimodal strategies.
10.Kai Wang et al., “LC4‑DViT: Deformable Vision Transformer for land‑cover classification” – generative augmentation + transformer modeling.
Ethics and Compliance
Indexed In
Similar Articles
Previous Article
