Detection of Multitemporal Changes with Artificial Neural Network-Based Change Detection Algorithm Using Hyperspectral Dataset

Monitoring the Earth’s surface and objects is important for many applications, such as managing natural resources, crop yield predictions, hazard analysis. Remote sensing one of most efficient cost-effective solutions analyzing land-use land-cover (LULC) changes over through advanced computer algorithms, classification change detection. In past literature, various developments were made to detection algorithms detect LULC multitemporal using optical or microwave imagery. The optical-based hyperspectral highlights critical information, but sometimes it difficult analyze dataset due presence atmospheric distortion, radiometric errors, misregistration. this work, an artificial neural network-based post-classification comparison (ANPC) has been utilized muti-temporal a part Uttar Pradesh, India, Hyperion EO-1 dataset. experimental outcomes confirmed effectiveness ANPC (92.6%) compared existing models, spectral angle mapper (SAM) based (SAMPC) (89.7%) k-nearest neighbor (KNN) (KNNPC) (91.2%). study will be beneficial in extracting information about surface, analysis diseases, diversity, agriculture, weather forecasting, forest monitoring.