Big multi-temporal geospatial data and the large-scale analysis of South Asia’s past landscapes

Today in the afternoon, Hèctor A. Orengo (ICREA research professor) is giving a talk in the conference 3rd International Conference on Geology: Emerging Methods & Applications (GEM-2023).

Title: ”Big multi-temporal geospatial data and the large-scale analysis of South Asia’s past landscapes
Session: Artificial Intelligence and Machine Learning in Earth Science

Abstract
The last few years have seen an unprecedented advance in the application of computational approaches for the geospatial analysis of past landscapes, settlements and features. This progress is mostly related to improvements in availability, quality and resolution of remote sensing (RS) data acquired from multiple platforms (ranging from satellite imagery to UAVs) and sensors (e.g. multispectral, radar, lidar, thermal) but also to increased access to high performance computing. This is partly related to the development of multi-petabyte catalogues of geospatial datasets linked to cloud computing environments, which have granted the geospatial community unparalleled access to RS data and computing power. These have allowed the development of large-scale, multi-temporal and multi-sensor analyses of the Earth’s surface but also the implementation of intensive computational processes such as machine learning-based data classification, multi-scale topographic analysis, long-term time series analysis, and so on.

This talk will showcase some of these current approaches to the analysis of past landscapes developed by the Landscape Archaeology Research Group (GIAP) at the Catalan Institute of Classical Archaeology (ICAC). Several South Asian large-scale case studies will be employed to illustrate how the use of multitemporal and multisource data can be analysed using machine learning and deep learning approaches within a probabilistic frame.

Tags: , , , ,