Graph-learning-based machine learning improves prediction and cultivation of commercial-grade marine microalgae Porphyridium

Huankai Li, Leijian Chen, Feng Zhang, Zongwei Cai*

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

Abstract

A graph learning [Binarized Attributed Network Embedding (BANE)] model enhances the single-target and multi-target prediction performances of random forest and eXtreme Gradient Boosting (XGBoost) by learning complex interrelationships between cultivation parameters of Porphyridium. The BANE-XGBoost has the best prediction performance (train R2 > 0.96 and test R2 > 0.87). Based on Shapley Additive Explanation (SHAP) model, illumination intensity, culture time, and KH2PO4 are the most critical factors for Porphyridium growth. The combined facilitating roles of cultivation parameters are found using the SHAP value-based heat map and group. To reach high biomass and daily production rate concurrently, one-way and two-way partial dependent plots models find the optimal conditions. The top 2 critical parameters (illumination intensity and KH2PO4) were selected to verify using the graphical user interface website based on the optimized model and lab experiments, respectively. This study shows the graph-learning-based model can improve prediction performance and optimize intricate low-carbon microalgal cultivation.

Original languageEnglish
Article number131728
Number of pages16
JournalBioresource Technology
Volume416
DOIs
Publication statusPublished - Jan 2025

Scopus Subject Areas

  • Bioengineering
  • Environmental Engineering
  • Renewable Energy, Sustainability and the Environment
  • Waste Management and Disposal

User-Defined Keywords

  • Artificial intelligence
  • Cultivation optimization
  • Illumination intensity
  • Porphyridium cultivation

Fingerprint

Dive into the research topics of 'Graph-learning-based machine learning improves prediction and cultivation of commercial-grade marine microalgae Porphyridium'. Together they form a unique fingerprint.

Cite this