A 2.4 MB neural network surrogate reproduces EPA MOVES CO2 emissions with 6.013% MAPE on millions of test scenarios, enabling fast microscopic emission modeling.
MOVESTAR: An Open-Source Vehicle Fuel and Emission Model based on USEPA MOVES
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
In this paper, we introduce an open-source model "MOVESTAR" to calculate the fuel consumption and pollutant emissions of motor vehicles. This model is developed based on U.S. Environmental Protection Agency's (EPA) Motor Vehicle Emission Simulator (MOVES), which provides an accurate estimate of vehicle emissions under a wide range of user-defined conditions. Originally, MOVES requires users to specify many parameters through its software, including vehicle types, time periods, geographical areas, pollutants, vehicle operating characteristics, and road types. In this paper, MOVESTAR is developed as a simplified version, which only takes the second-by-second vehicle speed data and vehicle type as inputs. To enable easy integration of this model, its source code is provided in various languages, including Python, MATLAB and C++. A case study is introduced in this paper to illustrate the effectiveness of the model in the development of advanced vehicle technology.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
NeuralMOVES: A lightweight and microscopic vehicle emission estimation model based on reverse engineering and surrogate learning
A 2.4 MB neural network surrogate reproduces EPA MOVES CO2 emissions with 6.013% MAPE on millions of test scenarios, enabling fast microscopic emission modeling.