Informations et ressources scientifiques
sur le développement des zones arides et semi-arides

Accueil du site → Projets de développement → Projets de recherche pour le Développement → 2022 → Artificial Intelligence for Arid Land Agriculture (AIALA)

National Science Foundation (NSF) 2022

Artificial Intelligence for Arid Land Agriculture (AIALA)

Arid Agriculture


Titre : Artificial Intelligence for Arid Land Agriculture (AIALA)

Organismes NSF : DGE Division Of Graduate Education

Durée : April 15, 2022 // March 31, 2027 (Estimated)

Global food supply and food security are at risk due to an increasing world population, climate change, diminishing natural resources, and limited available land. In agriculture, the primary challenge has been how to be more productive with less - less arable land, less water, less labor, less certainty. In arid lands, these challenges are amplified. Agricultural systems struggle to cope with rapid changes in water availability and land-use patterns, scarcity of labor due to declining population, variability and uncertainty related to changing weather and climate, and aging rural infrastructures. Arid lands and drylands, which cover much of the Western US, are expected to expand as the climate changes. Artificial intelligence (AI) can bring a paradigm shift in how the twin economic and environmental challenges of farming and ranching in arid lands can be addressed. AI can support farmers to operate with greater efficiency and precision through the assistance of autonomous systems (e.g., drones, ground vehicles, and intelligent irrigation systems) and the support of intelligent software systems to aid in decision making (e.g., detecting and resolving crop diseases). AI-driven solutions will not only enable farmers to do more with less ; they will also improve quality and ensure a faster path-to-market for crops and livestock. This National Science Foundation Research Traineeship (NRT) award to New Mexico State University (NMSU) will enable the creation of a coordinated graduate training program, called Artificial Intelligence for Arid Land Agriculture (AIALA), to prepare the next generation of scholars and practitioners by teaching graduate students how to bridge the divides between AI and Agriculture for Arid Lands. The project anticipates training 33 MS and Ph.D. students, including 18 funded trainees, from computing-related disciplines and agriculture-related disciplines .

The AIALA scholar experience will integrate with and complement the traditional graduate disciplinary training, thus contextualizing the in-depth disciplinary research for researchers in either AI or agriculture-related areas. Moreover, the experience will allow scholars to effectively serve as catalysts in research teams using AI to solve arid land challenges. The research conducted by the AIALA scholars and their research mentors will advance the state of the art in both AI and Arid Land Agriculture. The research will promote the creation of novel multi-agent systems frameworks, advancing the state of the art in machine learning and distributed data analytics. In addition, it will provide methodologies and technologies to enhance the adaptability of crops, rangeland plants and livestock, improve the resiliency of livestock in expansive rugged rangelands, and ultimately lead to resilient and sustainable arid land agricultural systems. The AIALA training model benefits from a number of innovations. First, it establishes a transdisciplinary training pipeline, embedding AI research challenges in Arid Land Agricultural challenges, enabling contextualized and situated learning. Second, it integrates graduate students and faculty mentors in mutually supportive teams of learners, supported, in turn, by an extensive mentoring infrastructure. Third, it infuses diversity and inclusion in all operations and learning activities, promoting engagement of a diverse audience of scholars and preparing the scholars to serve as agents of change for inclusion. Finally, it emphasizes the development of professional skills as part of holistic disciplinary training.

Bureau de recherche parrainé  : New Mexico State University

Financement : 2 000 000,00 US D

National Science Foundation

Page publiée le 9 novembre 2022