AI and Sustainability: The Use of AI in Sustainability Initiatives
Permanent URI for this collection
Browse
Recent Submissions
1 - 3 of 3
-
ItemHow Artificial Intelligence Improves Agricultural Productivity and Sustainability: A Global Thematic Analysis( 2020-01-07)Amidst the rising issues of food security and climate change, the agricultural sector has started deploying artificial intelligence (AI) in business operations. While many potential AI benefits are anticipated, a comprehensive understanding of the objectives motivating AI adoption and its impacts is lacking. This research attempts to fill this gap by exploring the key themes related to the use of AI in agriculture through the lens of dynamic capabilities. Using centering resonance analysis, we conduct text mining of news articles from 2014-2019 in the regions of Asia, Africa, Europe, and North America to identify how AI is addressing significant farming challenges. Globally, the results suggest that AI is primarily being applied to increase productivity and efficiency and secondarily to address labor shortages and environmental sustainability concerns. At regional level, the results reflect active AI adoption in North America and Europe with increasing efforts in Asia and Africa.
-
ItemImproving Wildlife Monitoring using a Multi-criteria Cooperative Target Observation Approach( 2020-01-07)Wildlife Monitoring is very important for maintaining sustainability of environment. In this paper we pose Wildlife Monitoring as Cooperative Target Observation (CTO) problem and propose a Multi Criteria Decision Analysis (MCDA) based algorithm named MCDA-CTO, to maximize the observation of different animal species by Unmanned Aerial Vehicles (UAVs) and to effectively handle multiple target types and the multiple criteria that arise due to targets and environmental factors, during decision making. UAVs have uncertainty in observation of targets which makes it challenging to develop a high-quality monitoring strategy. We therefore develop monitoring techniques that explicitly take actions to improve belief about the true type of targets being observed. In wildlife monitoring, it is often reasonable to assume that the observers may themselves be a subject of observation by unknown adversaries (poachers). Randomizing the observer’s actions can therefore help to make the target observation strategy less predictable. We then provide experimental validation that shows that the techniques we develop provide a higher (true positive/true negative) ratio along with better randomization than state of the art approaches.
-
Item