Refine
Year of publication
- 2020 (68) (remove)
Document Type
- Article (25)
- Moving Images (18)
- Conference Proceeding (17)
- Book (2)
- Part of a Book (2)
- Working Paper (2)
- Bachelor Thesis (1)
- Report (1)
Keywords
- Nachhaltigkeit (3)
- Environment (2)
- Nutritional Policy (2)
- Nutritional footprint (2)
- Sustainable nutrition (2)
- agronomic biofortification (2)
- selenium (2)
- Agrarpolitik (1)
- Baustoff Holz (1)
- Biodiversity (1)
Institute
- Fakultät AuL (68) (remove)
In this paper, we evaluate the application of Bayesian Optimization (BO) to discrete event simulation (DES) models. In a first step, we create a simple model, for which we know the optimal set of parameter values in advance. We implement the model in SimPy, a framework for DES written in Python. We then interpret the simulation model as a black box function subject to optimization. We show that it is possible to find the optimal set of parameter values using the open source library GPyOpt. To enhance our evaluation, we create a second and more complex model. To better handle the complexity of the model, and to add a visual component, we build the second model in Simio, a commercial off-the-shelf simulation modeling tool. To apply BO to a model in Simio, we use the Simio API to write an extension for optimization plug-ins. This extension encapsulates the logic of the BO algorithm, which we deployed as a web service in the cloud.
The fact that simulation models are black box functions with regard to their behavior and the influence of their input parameters makes them an apparent candidate for Bayesian Optimization (BO). Simulation models are multivariable and stochastic, and their behavior is to a large extent unpredictable. In particular, we do not know for sure which input parameters to adjust to maximize (or minimize) the model’s outcome. In addition, the complex models can take a substantial amount of time to run.
Bayesian Optimization is a sequential and self-learning algorithm to optimize black box functions similar to as we find them in simulation models: they contain a set of parameters for which we want to identify the optimal set, they are expensive to evaluate, and they exhibit stochastic noise. BO has proven to efficiently optimize black box functions from varius disciplines. Among those, and most notably, it is successfully applied in machine learning algorithms to optimize hyperparameters.
Injection of slurry or digestate below maize seeds is a relatively new technique developed to improve nitrogen use efficiency. However, this practice has the major drawback of increasing nitrous oxide (N2O) emissions. The application of a nitrification inhibitor (NI) is an effective method to reduce these emissions. To evaluate the effect of the NI 3,4‐dimethypyrazole phosphate (DMPP) on N2O emissions and the stabilization of ammonium, a two‐factorial soil‐column experiment was conducted. PVC pipes (20 cm diameter and 30 cm length) were used as incubation vessels for the soil‐columns. The trial consisted of four treatments in a randomized block design with four replications: slurry injection, slurry injection + DMPP, digestate injection, and digestate injection + DMPP. During the 47‐day incubation period, N2O fluxes were measured twice a week and cumulated by linear interpolation of the gas‐fluxes of consecutive measurement dates. After completion of the gas flux measurement, concentration of ammonium and nitrate within the soil‐columns was determined. DMPP delayed the conversion of ammonium within the manure injection zone significantly. This effect was considerably more pronounced in treatment digestate + NI than in treatment slurry + NI. Regarding the cumulated N2O emissions, no difference between slurry and digestate treatments was determined. DMPP reduced the release of N2O significantly. Transferring the results into practice, the use of DMPP is a promising way to reduce greenhouse gas emissions and nitrate leaching, following the injection of slurry or digestate.