Artificial Intelligence for Arid Land Agriculture (AIALA)

干旱地区农业人工智能（AIALA）

• 批准号: 2151254
• 负责人: Enrico Pontelli
• 金额: $ 200万
• 依托单位: New Mexico State University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-04-15 至 2027-03-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2151254&HistoricalAwards=false
• 关键词: Artificial; Intelligence; Arid; Land; Agriculture

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2).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.The NSF Research Traineeship (NRT) Program is designed to encourage the development and implementation of bold, new potentially transformative models for STEM graduate education training. The program is dedicated to effective training of STEM graduate students in high priority interdisciplinary or convergent research areas through comprehensive traineeship models that are innovative, evidence-based, and aligned with changing workforce and research needs.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

该奖项全部或部分由2021年美国救援计划法案（公法117-2）资助。由于世界人口增加，气候变化，自然资源减少和可用土地有限，全球粮食供应和粮食安全面临风险。在农业方面，主要的挑战是如何用更少的耕地，更少的水，更少的劳动力，更少的确定性来提高生产力。在干旱地区，这些挑战更为严峻。农业系统努力科普水资源供应和土地使用模式的快速变化、人口减少导致的劳动力短缺、与天气和气候变化相关的可变性和不确定性以及农村基础设施老化。覆盖美国西部大部分地区的干旱土地和旱地预计将随着气候变化而扩大。人工智能（AI）可以为如何解决干旱地区农业和牧场的双重经济和环境挑战带来范式转变。人工智能可以支持农民通过自主系统的帮助（例如，无人机、地面车辆和智能灌溉系统）以及支持智能软件系统以辅助决策（例如，检测和解决作物病害）。人工智能驱动的解决方案不仅能让农民事半功倍，还能提高质量，确保农作物和牲畜更快地进入市场。这个国家科学基金会研究培训（NRT）奖给新墨西哥州州立大学（NMSU）将能够创建一个协调的研究生培训计划，称为干旱土地农业人工智能（AIALA），通过教研究生如何弥合人工智能和干旱土地农业之间的鸿沟，为下一代学者和从业者做好准备。该项目预计将培训33名硕士和博士。学生，包括18名受资助的学员，来自计算相关学科和农业相关学科。AIALA学者的经验将与传统的研究生学科培训相结合，从而为人工智能或农业相关领域的研究人员提供深入的学科研究。此外，这些经验将使学者能够有效地在使用人工智能解决干旱土地挑战的研究团队中发挥催化剂的作用。AIALA学者及其研究导师进行的研究将推动人工智能和旱地农业的最新发展。该研究将促进新型多智能体系统框架的创建，推进机器学习和分布式数据分析的最新发展。此外，它还将提供方法和技术，以提高作物、牧场植物和牲畜的适应性，提高牲畜在广阔崎岖牧场的复原力，并最终建立有复原力和可持续的干旱土地农业系统。AIALA培训模式受益于许多创新。首先，它建立了一个跨学科的培训管道，将人工智能研究挑战嵌入干旱土地农业挑战中，实现情境化和情境化学习。第二，它将研究生和教师导师整合到相互支持的学习者团队中，反过来又得到广泛的指导基础设施的支持。第三，它在所有业务和学习活动中注入多样性和包容性，促进不同学者受众的参与，并使学者做好准备，成为包容性变革的推动者。最后，它强调专业技能的发展作为整体学科培训的一部分。NSF研究培训（NRT）计划旨在鼓励开发和实施大胆的，新的潜在变革性的STEM研究生教育培训模式。该计划致力于通过创新的、基于证据的、与不断变化的劳动力和研究需求相一致的综合培训模式，在高优先级的跨学科或融合研究领域对STEM研究生进行有效培训。该奖项反映了NSF的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Answer Set Planning: A Survey

• DOI: 10.1017/s1471068422000072
• 发表时间: 2022-02
• 期刊: Theory Pract. Log. Program.
• 作者: Tran Cao Son;Enrico Pontelli;M. Balduccini;Torsten Schaub

Potential of Accelerometers and GPS Tracking to Remotely Detect Perennial Ryegrass Staggers in Sheep

加速计和 GPS 跟踪远程检测绵羊多年生黑麦草摇晃的潜力

• DOI: 10.1016/j.atech.2022.100040
• 发表时间: 2022
• 期刊: Smart Agricultural Technology
• 作者: Trieu, Ly Ly;Bailey, Derek W.;Cao, Huiping;Son, Tran Cao;Scobie, David R.;Trotter, Mark G.;Hume, David E.;Sutherland, B. Lee;Tobin, Colin T.
• 通讯作者: Tobin, Colin T.