# Predictive Modelling of H2S Removal from Biogas Generated from Palm Oil Mill Effluent (POME) Using a Biological Scrubber in an Industrial Biogas Plant: Integration of Artificial Neural Network (ANN) and Process Simulation§

## TL;DR

This study uses machine learning and simulation to predict hydrogen sulfide removal in biogas from palm oil waste, improving gas quality and sustainability.

## Contribution

A novel integration of ANN and process simulation models to predict bioscrubber performance for H2S removal in biogas from POME.

## Key findings

- The bioscrubber achieved 96% H2S removal efficiency with ANN predictions showing high accuracy (R2 = 0.9).
- Biogas yield was 26.12 Nm3 per m3 POME, aligning with industry standards with less than 1% deviation.
- The process was economically feasible with a net present value of $131,000 and a 7-year payback period.

## Abstract

Biogas production from palm oil mill effluent (POME) is inherently unstable due to variations in feedstock composition and operating conditions. These fluctuations can lead to inconsistent biogas quality, variable methane content and fluctuating hydrogen sulphide (H2S) concentration. This poses significant challenges for bioscrubbers in removing H2S to meet quality standards for gas engines used for electricity generation. This research aims to address these challenges by integrating simulation models with a computer programme and artificial neural network (ANN) to predict the performance of a bioscrubber at a POME treatment plant in Johor, Malaysia.

First, the process flowsheet model was simulated using a computer programme. The H2S removal was then predicted using a machine learning algorithm, specifically ANN, based on two years of historical data obtained from the biogas plant. A detailed techno-economic analysis was also carried out to determine the economic feasibility of the process.

The simulation results showed a biogas yield of 26.12 Nm3 per m3 POME, which is in line with industry data with less than 1 % deviation. The ANN model achieved a high coefficient of determination (R2) of 0.9 and a low mean squared error (MSE), with the bioscrubber reaching an H2S removal efficiency of approx. 96 %. The techno-economic analysis showed that the process is feasible with a net present value (NPV) of $131 000 and a payback period of 7 years.

The integration of ANN and the computer programme provides a robust framework for predicting bioscrubber performance and ensuring stable bioscrubber operation due to their complementary strengths. ANN accurately predicts H2S removal based on daily recorded data, while the computer programme estimates parameters that are not monitored daily, such as chemical oxygen demand (COD), biological oxygen demand (BOD) and total suspended solids (TSS). This research provides valuable insights into sustainable biogas production practices and offers opportunities to improve energy efficiency and environmental sustainability in the palm oil industry.