The paper introduces MuViS-C, a multi‑domain benchmark that evaluates the robustness of learning‑based virtual sensing models against ten common sensor failure modes, ranging from subtle drifts to catastrophic dropouts. It assesses models using average error, relative degradation, and worst‑case fragility across nine datasets from six domains, comparing six architectures (gradient‑boosted trees, convolution, recurrence, attention, and MLP‑mixing). The study finds that all models degrade under corruption, gradient‑boosted trees are most robust, and targeted robustification can improve attention models at the cost of nominal performance.
By Jens U. Brandt, Noah C. Puetz, Alexander Windmann, Marc Hilbert, Elena Raponi, Thomas B\"ack, Thomas Bartz-Beielstein
Virtual sensing, the estimation of hard-to-measure quantities from available sensor measurements, is a critical enabler for control and monitoring in cyber-physical systems. However, when sensors fail...
arXiv:2606. 18539v1 Announce Type: new Abstract: Time series forecasting (TSF) underpins consequential decisions in energy, transportation, finance, and healthcare, yet TSF models are almost universally ranked by a single number (e.
By Yuyang Zhao, Lian Xu, Hao Miao, Chenxi Liu, Hao Xue
The paper argues that current time‑series forecasting benchmarks are too narrow, rewarding low held‑out error while failing to capture real‑world failure modes such as structured input anomalies, regime shifts, and sensor faults. It proposes scenario‑grounded stress testing, where each test includes historical data, future targets, a semantic scenario, a failure operator, and a difficulty level, to make evaluation interpretable and deployment‑relevant.
By Yuyang Zhao, Lian Xu, Hao Xue
arXiv:2512.22428v3 Announce Type: replace
Abstract: Post-hoc residual correction can reduce forecasting error, but always-on updates often fail to generalize: when residual signals are weak or noisy,...
By Jianxiang Xie, Yuncheng Hua, Mingyue Cheng, Flora D. Salim, Hao Xue
arXiv:2611.06194v1 Announce Type: new
Abstract: Reliability management of industrial fleets depends on early fault warnings, yet lifecycle data across similar assets are highly imbalanced. A few asse...
By Zekai Wang, Yuxuan Li, Zhangyue Shi
arXiv:2607. 14871v1 Announce Type: cross Abstract: In many operational time-series forecasting applications, such as crowd demand forecasting, the risk related to under-prediction is substantially higher than that of over-prediction.
By Theivaprakasham Hari, Yanan Xin, Winnie Daamen, Serge Paul Hoogendoorn, Sascha Hoogendoorn-Lanser
The paper introduces a data‑onboarding pipeline that detects and repairs defects in building meter data before training machine‑learning demand‑forecasting models. Controlled experiments on hourly electricity data from twelve U.S. buildings show that the pipeline restores forecast accuracy to clean‑data levels, even when defects affect up to 1.6% of training rows, and works across multiple models and horizons. The study also documents a first‑version over‑cleaning issue, its cause, and a per‑building calibration that corrects it, with all results reproducible from publicly pinned inputs.
By Yixuan Liang
arXiv:2606. 24173v1 Announce Type: cross Abstract: On-device fault detection enables real-time diagnostics without cloud dependency, but deploying machine learning models on resource-constrained hardware demands careful tradeoffs between accuracy, latency, and model size.
By Disha Patel
arXiv:2609.39789v1 Announce Type: cross
Abstract: Real-world time series forecasting systems operate under non-stationary data streams, where forecasting performance may degrade over time. Although r...
By Yeryeong Kwak, Yoo-Min Jung, Jonghun Park
arXiv:2608. 20024v1 Announce Type: new Abstract: District heating energy hubs require reliable heat load forecasts for efficient operational scheduling.
By Ben Spoek, Karim K. Ben Hicham, Kai Derzsi, Philipp Althaus, Alexander Mitsos, Dirk M\"uller
EvoBench is a diagnostic benchmark framework designed to reveal where and when machine‑learning models for environmental variables fail, rather than relying on a single average accuracy score. It tracks model performance over time and across spatial extrapolation, highlighting issues such as non‑stationarity, poor performance at unmonitored sites, and under‑prediction of rare events like floods. In a case study on daily streamflow prediction across 9,000 U.S. basins, EvoBench shows that no model dominates all scenarios and that targeted fixes can mitigate identified weaknesses.
By Yiming Sun, Yuan Zhang, Qi Cheng, Yingda Fan, Runlong Yu, Yiqun Xie, Xiaowei Jia