Lunar base agent-based modeling - A benchmark for simulating crewed space missions

RESEARCH ARTICLE Lunar base agent-based modeling - A benchmark for simulating crewed space missions Raymond Vera *, Anamaria Berea‡, William G. Kennedy ‡ Department of Computational and Data Sciences, College of Science, George Mason University‌‌, Fairfax, Virginia, United States of America ‡ These authors are joint senior authors on this work. * Abstract OPEN ACCESS Citation: Vera R, Berea A, Kennedy WG (2026) Lunar base agent-based modeling - A benchmark for simulating crewed space missions. PLoS One 21(5): e0348882. https:// doi.org/10.1371/journal.pone.0348882 Editor: Babak Aslani, Memorial Sloan Kettering Cancer Center, UNITED STATES OF AMERICA Received: August 8, 2025 Accepted: April 22, 2026 Published: May 27, 2026 Peer Review History: PLOS recognizes the benefits of transparency in the peer review process; therefore, we enable the publication of all of the content of peer review and author responses alongside final, published articles. The editorial history of this article is available here: https://doi.org/10.1371/journal. pone.0348882 Copyright: This is an open access article, free of all copyright, and may be freely reproduced, distributed, transmitted, modified, built upon, or otherwise used by anyone for any lawful purpose. The work is made available under Space exploration has progressed significantly since the mid-20th century, and recent technological advancements, along with the emergence of commercial space travel, have led to substantial leaps in planning for future space missions. The largest planned upcoming mission is the Artemis program, supported by NASA and the international Artemis Accords, which aims to create the first permanent human presence on the Moon and in deep space (the Moon to Mars architecture). Although human psychology and team science have been crucial for the success of past space missions, from the Apollo program and Skylab to the Space Shuttle (STS) and the International Space Station (ISS), human factors and social behavior will become even more ubiquitous and essential for space missions in the new era of commercial space. By simulating upcoming permanent space missions in an agent-based model (ABM), we can draw insights into the long-term effects of human factors and interactions in space. Drawing from the literature on proxy environments (extreme environments on Earth (i.e., Antarctica), space analogs, and past space missions), and on theories of small group complex systems and team science, we created a highly probable representation or simulation of expected social interactions between astronauts, and astronauts with the lunar environment for the Artemis program (i.e., Artemis IV (Lunar Gateway) and Artemis V (Lunar South Pole Base)). Our Lunar Base ABM explores the exogenous and endogenous factors that are more likely to lead to sustainable versus catastrophic scenarios on the Moon in the next couple of decades. The model represents astronauts using a new Agent_Astronaut framework with cognitive skills, emotional states, and personality traits to capture how social and environmental factors interact to affect mission outcomes. Monte Carlo simulations consisting of tens of thousands of iterations show trade-offs in productivity and psychological well-being. This approach demonstrates how agent-based modeling can help mission planners evaluate operational resilience, team structures, and workload dynamics in support of future lunar exploration. PLOS One | https://doi.org/10.1371/journal.pone.0348882 May 27, 2026 1 / 27 the Creative Commons CC0 public domain dedication. Data availability statement: All relevant data are within the manuscript. The Lunar Base ABM code is available in the GitHub repository: https://github.com/rvera-gmu/ Lunar-Base-ABM. Funding: GMU ORIEI Award no. 102264. Competing interests: The authors have declared that no competing interests exist. Introduction From its early crewed spaceflights in the 1960s, beginning with the Mercury-Atlas 6 mission (1962) and culminating in the first crewed flight beyond Earth orbit during Apollo 8 (1968), NASA advanced the capabilities needed for human space travel, space exploration, and eventual lunar landings through the Apollo program that concluded in 1972 [1]. Humanity further expanded its footprint in space with the development of the International Space Station (ISS) initiated in the 1990s, which today represents collaboration among five partner agencies: NASA, the Canadian Space Agency, the European Space Agency, the Japan Aerospace Exploration Agency, and the State Space Corporation (“Roscosmos”) of Russia. The ISS has been serving as a long-term, crewed microgravity laboratory, enabling decades of scientific research and technology demonstrations with a planned deorbit transition in the 2030s [2]. The next phase in space settlement and exploration begins with NASA’s Artemis campaign, which involves a multinational effort to establish a long-term human presence on the Moon and prepares for future crewed missions to Mars. Grounded in the Artemis Accords established in 2020 [3] and in compliance with the Outer Space Treaty of 1967 [4], countries and corporations worldwide agree to a set of common principles for the governance of civil exploration and the use of outer space for the benefit of all humankind. The Artemis program includes a series of missions, which started with the uncrewed test flight of the Space Launch System (SLS) rocket and the Orion spacecraft around the Moon in 2022 (Artemis I). Artemis II is scheduled to launch in 2026 and will involve a four-person crewed test flight to 8,889 kilometers (km) beyond the Moon – the farthest humans have ever traveled in space. Afterward, Artemis III is expected to result in the first lunar landing by a human since Apollo 17 in 1972, and the first one at the lunar south pole [5]. While engineering and technology innovation is necessary for space missions, understanding human and operational dynamics is also crucial for mission success [6]. This is particularly important if the objective is to establish a long-term presence on the Moon. Human exploration and operations on the Moon can be viewed from a complex systems perspective. It entails heterogeneous agents making decisions and exhibiting behavior while interacting with one another and their environment [7]. The lunar environment also encompasses endogenous and exogenous factors that give rise to nonlinear interactions, reinforced by positive and negative feedback loops, and to unpredictable and emergent phenomena. As an effective tool for providing insight into complex systems, agent-based models (ABMs) [8] can enhance planning for future lunar exploration by simulating human factors and interactions in the Artemis mission. This paper aims to show a Lunar Base ABM framework grounded in NASA’s human factors and behavioral research [9–11], and how simulating the complexities of team dynamics can have an operational impact on space missions. (...truncated)