The term "Land Cover" (LC) refers to the physical characteristics of the land, such as flora, water bodies, building areas, and forests. Identifying them using a remote sensing dataset is called land cover mapping. Land Use (LU) is a series of activities carried out on land by humans to obtain products. Land use classification examples include cropland, a built-up region used for business or industrial needs. Mapping and monitoring both land use and land cover (LULC) can be carried out using remote sensing datasets like Sentinal-2 Landsat-8 etc. Compared to algebra-based change detection techniques, the change vector analysis method offers a higher level of accuracy, according to the current study. This paper discussed the change detection analysis criteria and techniques which can be used for detecting the change and also compared the accuracy of different classifiers used for land use land cover in Agriculture.

Agriculture is the backbone of Punjab’s economy, and with much of India’s population dependent on agriculture, the requirement for accurate and timely monitoring of land has become even more crucial. Blending remote sensing with state-of-the-art machine learning algorithms enables the detailed classification of agricultural lands through thematic mapping, which is critical for crop monitoring, land management, and sustainable development. Here, a Hyper-tuned Deep Neural Network (Hy-DNN) model was created and used for land use and land cover (LULC) classification into four classes: agricultural land, vegetation, water bodies, and built-up areas. The technique made use of multispectral data from Sentinel-2 and Landsat-8, processed on the Google Earth Engine (GEE) platform. To measure classification performance, Hy-DNN was contrasted with traditional classifiers—Convolutional Neural Network (CNN), Random Forest (RF), Classification and Regression Tree (CART), Minimum Distance Classifier (MDC), and Naive Bayes (NB)—using performance metrics including producer’s and consumer’s accuracy, Kappa coefficient, and overall accuracy. Hy-DNN performed the best, with overall accuracy being 97.60% using Sentinel-2 and 91.10% using Landsat-8, outperforming all base models. These results further highlight the superiority of the optimised Hy-DNN in agricultural land mapping and its potential use in crop health monitoring, disease diagnosis, and strategic agricultural planning.

Accurate classification of agricultural land cover using satellite remote sensing is essential for monitoring crop health, predicting yields, and optimizing farming practices. This paper examines key datasets such as the Landsat series (Landsat 7–9), Sentinel-1, Sentinel-2, and MODIS, among others, assessing their suitability for these purposes. It compares critical features like sensor types, spectral bands, and spatial/temporal resolutions, swath width to highlight their advantages and limitations. The paper also discusses important pre-processing techniques, including radiometric and atmospheric corrections, stressing their role in preparing satellite images for analysis. Additionally, it reviews widely used processing software tools like ENVI, Google Earth Engine, and SNAP, detailing their functionalities. The goal is to provide researchers and practitioners with valuable insights into utilizing satellite imagery for agricultural land cover classification by comparing these datasets and tools.

Land cover (LC) refers to natural and man-made features on Earth’s surface, including forests, water bodies, urban areas, and vegetation. Remote sensing data is used to identify and categorize these features through land cover mapping. In contrast, land use (LU) describes human activities like agriculture and industry. LULC mapping relies on remote sensing datasets such as Landsat, Sentinel, Modis, and Radarsatl-2. LULC data is crucial for finding out changes in land features over time, with applications in urban planning, deforestation monitoring, agriculture, biodiversity conservation, and disaster management. Researchers explore machine ML and DL methods for agricultural land use classification using satellite imagery, aiming to improve accuracy and guide future research directions. Future research should focus on enhancing training data quality, feature selection, and model generalization. Developing robust, scalable models to handle diverse agricultural landscapes is essential. <!----> <!----> <!----> <!---->