Predicting Drying Curves in Algal Biorefineries using Gaussian Process Autoregressive Models

Abstract

In algal biofuel production, drying of the microalgal biomass is considered the most energy-intensive process. To save on operating costs, optimal control of the drying process should be guided by accurate mathematical models of the biomass parameters, particularly its moisture content. In this paper, we propose the use of Gaussian process autoregressive models (GPAR) for long-range moisture content prediction in the vacuum drying of algal biofuels. Our experiments involve the drying of Chlorococcum infusionum, wherein the measured variables are temperature, pressure, and moisture ratio. By computing the root mean squared error (RMSE) on test data, we demonstrate the superiority of GPAR to other models, namely Neural Networks, Support Vector Machines, Random Forest, Gradient Boosting, and Autoregressive Models for the same task. Through automatic relevance determination kernels, GPAR also found that the most significant predictors are the pressure readings. In the future, GPAR can potentially be used for the predictive control of the drying process, leading to more efficient biorefinery operations.
Graphical abstract

1. Download: Download high-res image (217KB)
2. Download: Download full-size image

• Previous article in issue
• Next article in issue

Keywords
Machine learning
Biorefinery
Microalgae drying
ARIMAX
Bayesian method
Feature relevance

Description