modeling and the prediction of material flows (plant production, CO2/O-2 concentrations, H2O) is an important but challenging task in the design and control of closed ecological life support systems (CELSS). The aim o...
详细信息
modeling and the prediction of material flows (plant production, CO2/O-2 concentrations, H2O) is an important but challenging task in the design and control of closed ecological life support systems (CELSS). The aim of this study was to develop a novel knowledge-and-data-driven modeling (KDDM) approach for simultaneously simulating plant production and CO2/O-2 concentrations in a closed system of plants and humans by integrating mechanistic and empirical models. The KDDM approach consists of a 'knowledge-driven (KD)' sub-model and a 'data-driven (DD)' sub-model. The KD sub-model describes hourly and up to daily plant photosynthesis, respiration and assimilation partitioning using the components of GreenLab and TomSim models. The DD sub-model describes the dynamics of CO2 production and O-2 consumption by the crew member using a piecewise linear model. The two sub-models were integrated with a mass balance model for CO2/O-2 concentrations in a closed system. The KDDM was applied with a two-person, 30-day integrated CELSS test. This model provides accurate computation of both the dry weights of different plant compartments and CO2/O-2 concentrations. The model also quantifies the underlying material flows among the crew members, plants and environment. This approach provides a computational basis for lifetime optimization of cabin design and experimental setup of CELSS (e.g., environmental control, planting schedule). With extension, this methodology can be applied to a half-closed system such as a glasshouse.
This paper proposes a novel knowledge-and-data-driven modeling (KDDM) approach for simulating plant growth that consists of two submodels. One submodel is derived from all available domain knowledge, including all kno...
详细信息
This paper proposes a novel knowledge-and-data-driven modeling (KDDM) approach for simulating plant growth that consists of two submodels. One submodel is derived from all available domain knowledge, including all known relationships from physically based or mechanistic models;the other is constructed solely from data without using any domain knowledge. In this work, a GreenLab model was adopted as the knowledge-driven (KD) submodel and the radial basis function network (RBFN) as the data-driven (DD) submodel. A tomato crop was taken as a case study on plant growth modeling. Tomato growth data sets from twelve greenhouse experiments over five years were used to calibrate and test the model. In comparison with the existing knowledge-drivenmodel (KDM, BIC=1215.67) and data-drivenmodel (DDM, BIC=1150.86), the proposed KDDM approach (BIC=1144.36) presented several benefits in predicting tomato yields. In particular, the KDDM approach is able to provide strong predictions of yields from different types of organs, including leaves, stems, and fruits, even when observational data on the organs are unavailable. The case study confirms that the KDDM approach inherits advantages from both the KDM and DDM approaches. Two cases of superposition and composition coupling operators in the KDDM approach are also discussed. (C) 2015 Elsevier B.V. All rights reserved.
暂无评论