Exportar Publicação

A publicação pode ser exportada nos seguintes formatos: referência da APA (American Psychological Association), referência do IEEE (Institute of Electrical and Electronics Engineers), BibTeX e RIS.

Exportar Referência (APA) 
Sternberg, Troy & Christopher McCarthy (2025). A new paradigm in desert research: using Artificial Intelligence in arid environments. Desert Technology XVI International Conference on Arid Lands.
Exportar Referência (IEEE) 
T. Sternberg and C. McCarthy,  "A new paradigm in desert research: using Artificial Intelligence in arid environments", in Desert Technology XVI Int. Conf. on Arid Lands, 2025
Exportar BibTeX 
@misc{sternberg2025_1788417488405,
	author = "Sternberg, Troy and Christopher McCarthy",
	title = "A new paradigm in desert research: using Artificial Intelligence in arid environments",
	year = "2025",
	url = "https://www.jaals.net/conferences/2025-conferences/"
}
Exportar RIS 
TY  - CPAPER
TI  - A new paradigm in desert research: using Artificial Intelligence in arid environments
T2  - Desert Technology XVI International Conference on Arid Lands
AU  - Sternberg, Troy
AU  - Christopher McCarthy
PY  - 2025
UR  - https://www.jaals.net/conferences/2025-conferences/
AB  - Covering 40% of the globe, deserts are critical research landscapes. Across arid regions rapid environmental and ecological change reconfigure environments. Increased water scarcity, land degradation, biodiversity loss and climate change impact drylands. Expanding populations, geopolitics, mining, infrastructure, and urbanisation affect human action. To address and understand our changing world conventional academic study can now take advantage of new technologies for cutting-edge dryland research. Today Artificial Intelligence (AI) provides an advanced method to investigate the world’s deserts.

Characterised by vast datasets and great spatial extent, desert research faces limitations to information analysis, numerical processing and pattern identification. Current AI tools can maximise researchers’ capacity and creativity. Examples include algorithms to analyze satellite imagery, quantifying desert expansion and vegetation changes and models predicting drought patterns and water availability. Techniques can detect geological features, including earthquake fault lines, and give insights into groundwater systems and natural hazards. Natural language processing synthesizes research literature and environmental reports. In combination these advances suggest AI applications can be part of a unified system for comprehensive desert landscape analysis. 

Drawing on our recent paper on species identification in deserts, we outline initial uses of AI architecture in dryland research. Examples include data integration and predictive modeling for earthquake fault identification and natural hazard tracking. Research provides an initial engagement with AI methods that expand academic capacity, expertise and contribution to science. Whilst AI presents challenges and caveats, data-rich arid and semi-arid investigations can benefit from the new AI research paradigm.

ER  -