Abstract Travel to other planetary bodies represents a major challenge to resource management. Previous manned exploration missions of long duration have been resupplied with food, water, and air as required. Manned missions to other planetary bodies will have durations of years with little to no possibility of resupply. Consequently, monitoring and forecasting resource consumption are mission-critical capabilities. The Hawaii Space Exploration Analog and Simulation, a long-duration planetary analog simulation, has recently completed its fifth long-term isolation mission conducted to assess the energy, food, and water needs of a six-person long-term planetary mission. This study presents a novel method for forecasting energy consumption, which incorporates the emotional state of the habitat crew. Gathered data show inhabitants in small environments can be influenced considerably by the actions of a single member. This can result in dramatic changes in consumption that could cause forecasting models to deviate to the point of total failure. Previous work found that inclusion of the daily activities and the psychological states of the crew allows for higher accuracy in long-duration forecasts. Currently, psychological assessments in the form of a Positive and Negative Affect Schedule and a generalized artificial neural modulation method are used to incorporate emotional response into machine learning forecast methods. Using these techniques and developments, a large-scale smart habitat control and forecasting system is proposed that will monitor, control, and forecast HI-SEAS habitat resources for future HI-SEAS missions. This new system requires the incorporation of psychological and physiological data of the crew, together with information on their activities and schedules.
Highlights HI-SEAS Habitat energy forecasts linked to crew emotional state. Energy consumption in Mars Analog affected by crew emotions. Mars analog crew emotions cause failures in projected energy forecasts. HI-SEAS habitat energy consumption compared over five simulations. Mars analog simulation power analysis examined over five missions.
HI-SEAS habitat energy requirements and forecasting
Acta Astronautica ; 162 ; 50-55
2019-05-26
6 pages
Article (Journal)
Electronic Resource
English
Analog , Simulation , Manned missions , Machine learning , Mars habitat , Planetary habitat , HI-SEAS , Hawaii Space Exploration Analog and Simulation , PANAS , Positive and Negative Affect Schedule , NASA , National Aeronautical Space Agency , HFBP , Human Factors and Behavioral Performance , DSE , Disruptive Significant Event , ANN , Artificial Neural Network , M1 … M5 , Mission One … Mission Five , S2S , Sequence to Sequence , LSTM , Long Short Term Memory , RNN , Recurrent Neural Network
Forecasting Logistics Requirements
Wiley | 2003
|Forecasting Commercial Pilot Requirements
British Library Conference Proceedings | 1995
|Habitat Requirements for a Lunar Outpost
SAE Technical Papers | 1995
|