Latest Time Series Research Papers
The newest Time Series papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Time Series so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.
Get the latest Time Series papers in your inbox — free →Recent papers
- Hybrid ARIMAX–LSTM Modeling with Elastic Net for Time Series Forecasting the Education Index of Jambi ProvinceMhd. Teguh Arrozik, Tri Candra Nur Muhaimin, Melkisedek Sampari Koibur · CAUCHY - Journal of Pure Ma... · Nov 30, 2026
Abstract This study proposes a Hybrid ARIMAX–LSTM framework integrated with Elastic Net regularization to improve the forecasting accuracy of the Education Index of Jambi Province. Annual data from 2010 to 2024 are utilized, with Elastic Ne…
- Methodological Evaluation and Time-Series Forecasting for Process-Control System Adoption in TanzaniaGrace Mushi, Josephine Mwita, Juma Kondo, Rajabu Mwinyimvua · Zenodo (CERN European Organ... · Nov 16, 2026
{ "background": "The adoption of advanced process-control systems in industrial sectors within developing economies is a critical driver of productivity and quality. However, there is a paucity of robust, quantitative frameworks for modelli…
- Methodological Evaluation and Time-Series Forecasting for Process-Control System Adoption in TanzaniaGrace Mushi, Josephine Mwita, Juma Kondo, Rajabu Mwinyimvua · Zenodo (CERN European Organ... · Nov 16, 2026
{ "background": "The adoption of advanced process-control systems in industrial sectors within developing economies is a critical driver of productivity and quality. However, there is a paucity of robust, quantitative frameworks for modelli…
- Time-Series Forecasting Model Evaluation for Municipal Water Systems in Tanzania: An Efficiency Gain AssessmentSally Harvey, Amani Mwalimu, Marilyn Kinyanjui · Zenodo (CERN European Organ... · Nov 6, 2026
Municipal water systems in Tanzania face challenges related to efficiency and reliability, necessitating a robust evaluation method. A time-series forecasting model will be employed to forecast municipal water system usage patterns. Robust …
- Time-Series Forecasting Model Evaluation for Municipal Water Systems in Tanzania: An Efficiency Gain AssessmentSally Harvey, Amani Mwalimu, Marilyn Kinyanjui · Zenodo (CERN European Organ... · Nov 6, 2026
Municipal water systems in Tanzania face challenges related to efficiency and reliability, necessitating a robust evaluation method. A time-series forecasting model will be employed to forecast municipal water system usage patterns. Robust …
- Methodological Evaluation and Reliability Forecasting for District Hospital Systems in Ethiopia: A Time-Series Meta-AnalysisMeklit Abebe, Tewodros Getachew · Zenodo (CERN European Organ... · Sep 26, 2026
District hospitals are critical nodes in healthcare delivery, yet systematic evaluations of their operational reliability in low-resource settings are scarce. Existing assessments often lack robust, predictive methodologies to inform proact…
- Methodological Evaluation and Reliability Forecasting for District Hospital Systems in Ethiopia: A Time-Series Meta-AnalysisMeklit Abebe, Tewodros Getachew · Zenodo (CERN European Organ... · Sep 26, 2026
District hospitals are critical nodes in healthcare delivery, yet systematic evaluations of their operational reliability in low-resource settings are scarce. Existing assessments often lack robust, predictive methodologies to inform proact…
- Evaluating Time-Series Foundation Models and Multimodal Dietary Context for CGM ForecastingBowen Zhang, Hsiu-Wen Cheng, Hongyu Yang, Evie L. Shen et al. · arXiv · Sep 10, 2026
Continuous glucose monitoring (CGM) provides high-frequency measurements of glucose dynamics and enables short-term glucose forecasting for diabetes management. Although time-series foundation models have shown strong general forecasting ab…
- Explainability Assistant: A Conversational XAI Interface for Interpreting Energy Consumption ModelsRodion Krjutškov, Eduard Barbu, Nikos Sakkas, Sofia Yfanti · arXiv · Sep 10, 2026
Energy consumption forecasting relies on increasingly complex machine learning (ML) models, such as Genetic Programming-based symbolic regressors, whose predictions can be difficult for facility managers and building operators to interpret.…
- RDDMPI: Residual Denoising Diffusion Model for Probabilistic Multivariate Time Series ImputationRamiro Valdes Jara, David Chapman, Adam Meyers · arXiv · Sep 10, 2026
Multivariate time series imputation (MTSI) aims to recover missing values in temporal data composed of multiple interdependent variables. This problem is central to real-world applications such as healthcare monitoring, traffic networks, an…
- LoaDiff: Conditional Generation of Electricity Consumption Time Series for Energy AnalyticsMariia Baranova, Adrien Petralia, Etienne Le Naour, Nathan Etourneau et al. · arXiv · Sep 10, 2026
The energy transition is reshaping residential electricity consumption through the increasing adoption of distributed generation, electrified appliances, and demand-response programs. Understanding these evolving behaviors requires access t…
- A Dataset and Model for Imputing Water Surface Elevation on a Large and Extremely Sparse Spatiotemporal GraphRuben Cartuyvels, Karim Douch, Gabriele Bertoli, Mounia El Baz et al. · arXiv · Sep 10, 2026
Continuous monitoring of water surface elevation across river networks is critical for flood forecasting, water resource management, and understanding the global water cycle. Yet, the scarcity of in situ gauges across much of the globe cons…
- A Later Test Set Is Not a New Domain: Pretraining Familiarity Survives a Contamination-Free Hold-OutMahdi Naser Moghadasi, Faezeh Ghaderi · arXiv · Sep 9, 2026
Time-series foundation models are evaluated almost exclusively on public archives that predate them, so a strong score cannot be separated from having seen the test set during pretraining. The obvious remedy is a hold-out that postdates the…
- An intelligent optimization method for communication monitoring alarm threshold based on BeiDou satellite positioning dataAn Lu, Yue Long, Fan JiFeng, Liang FaLiang et al. · Discover Computing · Sep 9, 2026
This paper proposes an intelligent optimization method for BeiDou communication monitoring alarm thresholds based on Representation Learning and Adaptive Thresholding for Anomaly Detection (RLAT-AD), aiming to address the issue that under c…
- NOAH: Learning the Full Patient Journey. A Longitudinal Multimodal Time-Aware Model for Representation and ForecastingTobias Susetzky, Raphael Rehms, Dmitrii Seletkov, Özgün Turgut et al. · arXiv · Sep 8, 2026
The digitization of healthcare has generated vast, longitudinal, and multimodal patient records over a lifetime, yet fully exploiting these data to represent and predict patient state trajectories remains a critical challenge. Current AI mo…
- Multi-Task Learning for Sparsely-Labeled Time Series: A Case Study on Cold-Hardiness ModelingAseem Saxena, Paola Pesántez-Cabrera, Jonathan Magby, Markus Keller et al. · arXiv · Sep 8, 2026
We present a real-world case study of multi-task learning (MTL) for temporal process modeling from limited data with temporally sparse labels. Specifically, we investigate multi-task learning for the important agricultural problem of predic…
- Comparative Analysis of Models for Apple Stock Price PredictionQianle Cheng · Advances in Economics Manag... · Sep 8, 2026
Predicting stock prices remains a difficult task because financial markets are influenced by many uncertain and rapidly changing factors. Traditional statistical models often fail to capture dynamic market patterns, while machine learning a…
- A dual-branch time series forecasting approach based on frequency decompositionTao Bi, Weicheng Shao, Kai Di, Jiuchuan Jiang · Service Oriented Computing ... · Sep 6, 2026
- Imaging and modeling crater floor subsidence at Nyiragongo Volcano, DRCArthur Wan Ki Lo, C. Wauthier, Benoît Smets, Nicolas d’Oreye et al. · Bulletin of Volcanology · Sep 5, 2026
Abstract Localized crater deformation can shed insight into shallow magma processes and eruption hazards. To study localized crater deformation at Nyiragongo volcano (Democratic Republic of Congo), we processed Interferometric Synthetic Ape…
- PRICE: A Systematic Study of LLM Adaptation Choices for Bitcoin Price ForecastingMaryam Fakhari, Mehran Safayani · arXiv · Sep 4, 2026
Cryptocurrency markets exhibit extreme volatility and non-stationary dynamics that challenge conventional forecasting methods. Although Large Language Models (LLMs) have shown promise for time series forecasting, the combined effects of ada…
- Trends (2014–2023), forecasting (2024–2026), and risk factors of drug-resistant tuberculosis in Iran: a negative binomial time-series generalized linear modelFatemeh Majdolashrafi, Mahshid Nasehi, Mahshid Namdari, Abolfazl Fateh et al. · Archives of Public Health · Sep 4, 2026
- A barycenter-based approach for the multi-model ensembling of subseasonal forecastsCamille Le Coz, Alexis Tantet, Rémi Flamary, Riwal Plougonven · Geoscientific model develop... · Sep 3, 2026
Abstract. Ensemble forecasts and their combination are examined from the perspective of probability spaces. By treating ensemble forecasts as discrete probability distributions, multi-model ensemble (MME) forecasts are reformulated as baryc…
- Dutch Books for Language ModelsIsaiah Andrews, Suproteem Sarkar · arXiv · Sep 2, 2026
People increasingly use language models to support life decisions. Many such decisions involve a probabilistic forecast: How likely is a major life event, a natural disaster, or an economic outcome? Users of language models may implicitly t…
- LoRA-TSD: Tangent-Space Spectral Descent for LoRA via Muon-Style UpdatesDmitrii Andriianov, Andrey Veprikov, Aleksandr Beznosikov · arXiv · Sep 2, 2026
Low-rank adaptation (LoRA) is the standard way to fine-tune large models, yet when its two factors are trained independently, the update ignores the geometry of the low-rank weight change it induces. We introduce LoRA-TSD, an optimizer that…
- TSPFN: A Temporal Tabular Foundation Model for Physiological Time Series ClassificationJérémie Stym-Popper, Clément Rambour, Federica Granese, Nicolas Thome et al. · arXiv · Aug 31, 2026
Designing models that generalize effectively in low- to medium-data regimes remains a primary challenge in medical machine learning, particularly for physiological time-series classification. While tabular foundation models such as TabPFN o…
- Forecasting oil spills in the Caribbean Sea. The Amuay refinery incident (2017)Claudia P. Urbano-Latorre, Leidy M. Castro-Rosero, Ángel G. Muñoz · Ocean Dynamics · Aug 29, 2026
- Insights into karst aquifer functioning from multi-method time series analysis of two adjacent tropical springs (Central Java, Indonesia)Tjahyo Adji, Andy Setyawan, Danang Riza Fauzi, romza agniy et al. · Sustainable Water Resources... · Aug 29, 2026
- How Proper Scoring Rules Shape LLM ForecastingBenjamin Turtel, Paul Wilczewski, Kris Skotheim, Ville A. Satopää et al. · arXiv · Aug 28, 2026
This paper evaluates how reward function choice shapes the performance and behavior of LLM forecasters. We compare five proper scoring rules as training objectives for binary forecasts of resolved real-world events. Although the rules share…
- Predictive-comparative framework for construction cost control using long short-term memory and digital twin technologiesYUXING WU, Samuel Frimpong · Automation in Construction · Aug 27, 2026
Fragmented project records and delayed validation hinder proactive cost control in construction. Yet current research offers limited guidance on converting inconsistent, lagged evidence into timely and auditable control signals, which can d…
- VMD-RDIC-DL: A Composite Relevance-Driven Hybrid Decomposition and Deep Learning Framework for Cryptocurrency ForecastingMaryam Maatallah, Mourad Fariss, Hakima Asaidi, Mohamed Bellouki · Journal of Computational an... · Aug 26, 2026
This study proposes a framework combining Variational Mode Decomposition (VMD) with a relevance-driven selection process to reduce noise and redundancy in financial time-series forecasting. The original time series is decomposed by VMD into…