2026-10-14T06:43:54Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34031180 2026-09-30T10:03:48Z category_146 category_7 category_272 category_39 category_45 category_734 portal_63 item_type_6 month_year_09_2026

Exformer: A Transformer-Based Forecasting Framework with Temporal Knowledge Assistance for Multistep Multivariate Influent Prediction in Wastewater Treatment Plants Ziqing Ye (5776304) Qilin Wang (385333) Yiqi Liu (1689634) Space Science Medicine Environmental Sciences not elsewhere classified Ecology Sociology Biological Sciences not elsewhere classified temporal knowledge assistance specific temporal characteristics range dependency modeling limitation usually frustrates increasingly pronounced advantages experimental results show complex multivariate nexus benchmark simulation model influent flow rates based forecasting framework wwtp influent proposed framework multistep forecasting framework employs forecasting horizons water quality variable interference study proposes representation strategy reduce cross preserve variable predictive performance practical utility optimal operations operational guidance often unsatisfactory longer horizons inherent disturbances great importance enhance long attention process additional robustness ablation analyses 48 steps Accurate forecasting of influent flow rates and water quality is of great importance to facilitate wastewater treatment plants (WWTPs) towards early fault warning and optimal operations. However, due to the seasonality, complex multivariate nexus and inherent disturbances, the predictive performance of WWTP influent is often unsatisfactory, particularly for multistep forecasting. This limitation usually frustrates the practical utility of such models for operational guidance and decision-making. To address these challenges, this study proposes a Transformer-based forecasting framework called Exformer. The framework employs a Channel-Independent (CI) representation strategy to preserve variable-specific temporal characteristics and reduce cross-variable interference. In addition, a Temporal Knowledge Guided Attention (TKGA) mechanism incorporates temporal prior knowledge into the attention process to enhance long-range dependency modeling. The proposed framework is evaluated on both the Benchmark Simulation Model No.2 (BSM2) dataset and a real-world WWTP dataset collected from Dongguan, China, under forecasting horizons of 6, 12, 24, and 48 steps. The experimental results show that Exformer delivers competitive performance across different forecasting horizons, with increasingly pronounced advantages at longer horizons, particularly at 24 and 48 steps. Additional robustness, interpretability, reliability and ablation analyses further demonstrate the effectiveness of Exformer for practical wastewater influent forecasting applications. 2026-09-30T00:00:00Z Text Journal contribution 10.1021/acsestwater.6c00503.s001 https://figshare.com/articles/journal_contribution/Exformer_A_Transformer-Based_Forecasting_Framework_with_Temporal_Knowledge_Assistance_for_Multistep_Multivariate_Influent_Prediction_in_Wastewater_Treatment_Plants/34031180 CC BY-NC 4.0