用机器学习提升污水厂氮氧化物排放预测的可解释性
Enhancing the interpretability of spatially variable N2O model predictions with soft sensors during wastewater treatment
- 通过四种机器学习模型分析运行数据与排放关系
- 模型预测准确率达0.97±0.02，但特征重要性随场景变化
- 揭示了自养与异养路径交互对排放评估的影响
基于污水处理厂（WWTP）的运行数据和专门的N2O测量活动，本文研究了机器学习（ML）模型对运行扰动及空间异质性N2O排放的预测能力。利用真实数据验证了四个ML模型的预测性能（R² = 0.79 - 0.89）。通过全厂机理模型模拟16次扰动场景，引入额外传感器与站点级数据，评估了80组样本的预测表现。结果显示模型精度达0.97±0.02，但特征重要性受模型类型、情景及测量尺度（反应器级或全厂级）影响显著。研究指出，软传感器预测受限于测量位置与数据方法学不确定性，降低模型可解释性。进一步分析机理模型结构发现，自养与异养路径在亚硝酸盐生成上的交互可能高估好氧亚硝酸盐产量，进而偏差对N2O贡献路径的评估。
原文摘要 · Abstract (English)
Model-based solutions for nitrous oxide (N2O) emissions from wastewater treatment plants (WWTP) are informed by operational datasets designed to control nutrient levels in liquid waste, coupled with dedicated campaigns for N2O measurements. We analysed how machine learning (ML) models predict disturbances to WWT operation and spatially variable N2O emissions. A real dataset was investigated to validate the modelling framework from N2O emissions predicted by four ML models (R2 = 0.79 - 0.89). Monitoring campaigns for N2O were simulated with a plant-wide mechanistic model to include additional sensors, site-level N2O datasets, and wastewater disturbances (n = 16). ML models were highly accurate (0.97 +- 0.02, n = 80), but the feature importance depended on the model, the scenario and the N2O measurement scale (reactor vs. WWTP). We argue that N2O soft sensor model predictions are limited to the measuring location and the methodological uncertainty of the dataset, which affect the interpretability of the model. Lastly, the analysis of the mechanistic model structure exposed interactions between autotrophic and heterotrophic pathways over nitric oxide which can overestimate aerobic nitrite production and bias the N2O pathway contributions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。