School Asset Mapping Using Hyperspectral Analysis And Deep Learning: A Review For Stem Education

Abstract

A recent development in the field of Earth remote sensing is the successful extraction of data from hyperspectral images. Data generated by this technique is a crucial part of geographic databases. Detecting targets, classifying patterns, mapping and identifying materials, etc. are just a few examples of the many potential uses for this type of data. A material mapping technique is similar to a multi-stage target detector. In order to provide new perspectives on the natural, social, human, and built capital in the surrounding regions, asset mapping entails recognizing assets at the individual, group, and community levels. Students and educators can better engage with their environment through the use of remote sensing and asset mapping to enhance STEM (Science, Technology, Engineering, and Mathematics) education. This can be achieved by finding resources, solving engineering design challenges, or conducting different scientific investigations. In order to create a secure learning environment that prioritizes the needs of students, this article discusses various reviews on the topic of integrating hyperspectral image analysis with school asset mapping through the use of deep learning techniques.