Wednesday, 31 January 2024: 5:30 PM
345/346 (The Baltimore Convention Center)
The increasing global human footprint has raised significant interest in understanding the extent of human impact on diverse geographical regions. This study presents a novel approach that utilizes Landsat satellite imagery and convolutional neural networks (CNNs) to analyze and quantify human impact on different parts of the world. The proposed method harnesses the power of deep learning to effectively label and classify regions based on the degree of human influence they exhibit. To enhance this methodology, we plan to incorporate the impact of climate hazards as supplementary information, enriching the index's comprehensiveness. By assimilating climate-related data, we aim to create an index that shows how human activity and environmental vulnerabilities combine to affect an area, which presents an opportunity to better understand the multiple dimensions of global change. This methodology shows potential for informing policy decisions and facilitating sustainable development strategies on a global scale.

