ICESCO Chair in Machine Learning for Remote Sensing and Geographic

Remote Sensing and Geographical Information Systems plays an important role in gathering information about planet Earth. The development of satellites in the second half of the twentieth century allowed the field of Remote Sensing to advance on a global scale in addition to the development of space programs. ML techniques have had significant recent successes in the fields of satellite Remote Sensing, including signal and image processing, quality control mechanisms, pattern recognition, data fusion, forward and inverse problems, and prediction. Thus, ML in particular can be positively disruptive and a transformational change agent in the fields of satellite Remote Sensing by augmenting and, in some cases, replacing elements of traditional Remote Sensing, assimilation, and modeling tools. This change is needed to meet the increasing challenges of Big Data, advanced models and applications, and user demands. Future developments, for example, SmallSats and the Internet of Things, will continue the explosion of new environmental data. ML can help address the demands put on environmental products for higher accuracy, higher resolution (spatial, temporal, and vertical), enhanced conventional medium-range forecasts, outlooks and predictions on sub seasonal to seasonal time scales, and improvements in the process of issuing advisories and warnings. Hence, in order to keep up with the scientific requirements of the era, the proposed Chair is designed to cope with and add to the advancement of technology for applying Machine Learning in Remote Sensing via research breakthroughs that meet bespoke market research needs and that result in leadership in this field on the local and international levels.