Time Series Foundation Models (TSFMs) provide general-purpose forecasting capabilities, yet their forecasts can remain misaligned with the temporal characteristics of a target domain. This motivates lightweight forecast correction even when only black-box access to the TSFM is available. Our key observation is that two forms of historical information provide complementary correction signals: historical analogues reveal how similar contexts evolved, while past forecast errors reveal a TSFM's characteristic deviations in the target domain. Based on this observation, we propose ECHO, a black-box forecast correction framework that learns from both sources. ECHO uses AnalogE to assess retrieved historical analogues together with the current context and base forecast, learning transferable corrections through cross-domain pretraining. In parallel, RecentE learns target-specific residual corrections from past forecast errors and refines them as causally available feedback accumulates. ECHO dynamically combines the two corrections according to their observed forecasting performance. Across 5 representative TSFMs and 9 real-world datasets, ECHO reduces MSE in all 45 backbone--dataset settings, yielding an average relative reduction of 9.26\% in macro-average MSE. Its gains also extend to long-horizon forecasting.
Departments of Computer Science & Engineering and Data Science, New York University(纽约大学计算机科学与工程系和数据科学系);Department of Electrical Engineering and Computer Sciences, University of California, Berkeley(加州大学伯克利分校电气工程与计算机科学系)
Self-attentive Transformer for Fast and Accurate Postprocessing of Temperature and Wind Speed Forecasts
Faculty of Applied Engineering, University of Antwerp(应用工程学院,安特卫普大学);CEREA, École des Ponts and EDF R&D(CEREA,Ponts学院和EDF R&D);Royal Meteorological Institute of Belgium(比利时皇家气象研究所);Department of Physics and Astronomy, Ghent University(物理与天文学系,根特大学);United Nations University Institute for Water, Environment and Health(联合国大学水、环境与健康研究所)
Distributional Drift Adaptation with Temporal Conditional Variational Autoencoder for Multivariate Time Series Forecasting
School of Medical Technology, Beijing Institute of Technology(北京理工大学医学技术学院);School of Computer Science and Technology, Beijing Institute of Technology(北京理工大学计算机科学与技术学院);Department of Computer Science, Tongji University(同济大学计算机科学系);University of Technology Sydney(悉尼科技大学);DataX Research Centre, School of Computing, Macquarie University(麦考瑞大学计算学院DataX研究中心)
TimePre: Bridging Accuracy, Efficiency, and Stability in Probabilistic Time-Series Forecasting
Tohoku University(东京大学);WPI;Texas A&M University(德克萨斯大学);University of Wisconsin-Madison(威斯康星大学麦迪逊分校);UIUC(伊利诺伊大学香槟分校);Georgia Tech(佐治亚理工学院);MIT(麻省理工学院);University of Southern California(南加州大学);San Diego State University(圣地亚哥州立大学)
Pastprop-RNN: improved predictions of the future by correcting the past
Faculdade de Engenharia(工程学院);Universidade do Porto(波尔图大学);INESC TEC(葡萄牙系统与计算机工程研究所(技术与科学));Fraunhofer AICOS(弗劳恩霍夫辅助信息与通信系统研究所);LIACC(人工智能与计算机科学实验室);Inovretail(Inovretail公司)
Deep Echo State Networks for Short-Term Traffic Forecasting: Performance Comparison and Statistical Assessment
TECNALIA, Basque Research and Technology Alliance (BRTA)(TECNALIA,巴斯克研究与技术联盟(BRTA));University of the Basque Country (UPV/EHU)(巴斯克大学(UPV/EHU));National Technical University of Athens (NTUA)(雅典国立技术大学(NTUA))
在短期交通预测中,目标是准确地预测在查询预测之后不久发生的感兴趣的交通参数的未来值。在这一长期研究领域中报道的活动最近被不同的深度学习方法所主导,产生了过于复杂的预测模型,这些模型通常可以实现实际效用可疑的准确性增益。在这项工作中,我们详细介绍了深度回声状态网络在这一特定任务中的性能。这些替代建模方法的有效学习算法和更简单的参数配置使它们成为具有竞争力的交通预测方法,用于部署在具有严格有限的计算资源的设备和系统中的实际ITS应用。一个广泛的比较基准是利用在马德里(西班牙)捕获的真实交通数据设计的,共有130多个自动交通阅读器(ATR)和几个浅层学习,集成和深度学习模型。该比较基准的结果以及对报告的性能差距的统计显著性的分析具有决定性意义:Deep Echo State Networks比其他考虑的建模同行实现了更准确的流量预测。
Echo State Networks for Spatio-Temporal Area-Level Data
Department of Statistics, University of Missouri(统计学系,密苏里大学);Office of the Associate Director for Research and Methodology, U.S. Census Bureau(研究与方法副主任办公室,美国人口普查局)
GRAM: Correcting Frozen Time-Series Foundation Models via Graph-Retrieved Amplitude Memory
East China Normal University(华东师范大学);Peking University(北京大学);The Chinese University of Hong Kong(香港中文大学);Shanghai Innovation Institute(上海创新研究院);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);University of the Chinese Academy of Sciences(中国科学院大学)
Echo State Networks for Bitcoin Time Series Prediction
DFKI, Saarland Informatics Campus, Germany(德国达姆施塔特研究所,萨尔兰信息技术校园);Politecnico di Milano, Italy(意大利米兰理工学院);University of Stirling, UK(英国斯特林大学);National Institute of Informatics, Japan(日本信息学研究院)
STAS: Adaptive Selecting Spatio-Temporal Deep Features for Improving Bias Correction on Precipitation
Fudan University(复旦大学);Shanghai Central Meteorological Observation(上海中心气象台)
数值天气预报能够及时预报灾害性降水,减轻人类灾害。欧洲中期天气预报中心(European Centre for Medium Range Weather Forecasts,EC)是世界上最常用的数值天气预报中心。然而,由于人们对降水机制的认识还不充分,使得EC往往存在一定的偏差,因此有必要通过降水偏差修正(Bias Correcting on Precipitation,BCoP)来修正EC预测。现有的BCoPs受到有限的先验数据和固定的时空(ST)尺度。因此,我们提出了一个名为时空特征自动选择(STAS)模型的端到端深度学习BCoP模型,通过ST特征选择机制(SFM/TFM)从EC中选择最佳ST规则。根据不同的输入特征,这两种机制可以自动调整空间和时间尺度进行校正。在EC公共数据集上的实验表明,与8个已发表的BCoP方法相比,STAS在BCoP的几个标准上表现出最先进的性能,命名为威胁分数(TS)。烧蚀研究表明,SFM/TFM在提高BCoP的性能方面效果显著,尤其是在强降水天气中。
Introducing Randomized High Order Fuzzy Cognitive Maps as Reservoir Computing Models: A Case Study in Solar Energy and Load Forecasting
Federal University of Minas Gerais(米纳斯吉拉斯联邦大学);Federal Institute of Education Science and Technology of Northern Minas Gerais(北米纳斯吉拉斯联邦教育科技学院);Universidade Federal de Minas Gerais(米纳斯吉拉斯联邦大学)
Adaptive Nonlinear Vector Autoregression: Robust Forecasting for Noisy Chaotic Time Series
Department of Mathematics, Pusan National University, Republic of Korea(釜山国立大学数学系);Pusan National University, Republic of Korea(釜山国立大学);Industrial Mathematics Center, Pusan National University, Republic of Korea(釜山国立大学工业数学中心);Humanoid Olfactory Display Center, Pusan National University, Republic of Korea(釜山国立大学人形嗅觉显示中心);Department of Mathematics, Yonsei University, Republic of Korea(成均馆大学数学系);Innovation Center for MathScience Research&Education, Pusan National University, Republic of Korea(釜山国立大学数学科学研究与教育创新中心);Marine Natural Disaster Research Department, Korea Institute of Ocean Science and Technology, Republic of Korea(韩国海洋科学与技术研究院海洋自然灾害研究部);Institute for Future Earth, Pusan National University, Republic of Korea(未来地球研究所)