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 thegraph-learning-based model can improve prediction performance and optimize intricate low-carbon microalgal cultivation.

中文翻译：

---

基于图学习的机器学习改进了商业级海洋微藻 Porphyridium 的预测和培养


图学习 [二值化属性网络嵌入 （BANE）] 模型通过学习卟啉培养参数之间的复杂相互关系，增强了随机森林和极端梯度提升 （XGBoost） 的单目标和多目标预测性能。BANE-XGBoost 具有最好的预测性能（训练 R2 > 0.96 和测试 R2 > 0.87）。基于 Shapley 加法解释 （SHAP） 模型，光照强度、培养时间和 KH 2 PO 4 是卟啉生长的最关键因素。使用基于 SHAP 值的热图和组找到栽培参数的组合促进作用。为了同时达到高生物量和日生产率，单向和双向部分相关图模型找到最优条件。选择前 2 个关键参数 （照明强度和 KH 2 PO 4 ） 分别使用基于优化模型和实验室实验的图形用户界面网站进行验证。这项研究表明，基于图学习的模型可以提高预测性能并优化复杂的低碳微藻培养。