Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
6.5
2.9
Journals
Information
Special Issues
Deep Learning Approach for Time Series Forecasting
share announcement

Deep Learning Approach for Time Series Forecasting

A special issue of Information (ISSN 2078-2489). This special issue belongs to the section "Information Applications".

Deadline for manuscript submissions: 31 October 2026 | Viewed by 13315

Special Issue Editors

Dr. Ruobin Gao

E-Mail Website
Guest Editor
School of Civil & Environmental Engineering, Nanyang Technological University, Singapore
Interests: forecasting; machine learning; deep learning; time series mining
Dr. Maohan Liang

E-Mail Website
Guest Editor
Department of Civil and Environmental Engineering, National University of Singapore, Singapore 119260, Singapore
Interests: intelligent shipping; machine learning; data mining
Special Issues, Collections and Topics in MDPI journals
Dr. Xiaocai Zhang

E-Mail Website
Guest Editor
Faculty of Engineering and Information Technology, University of Melbourne, Parkville, VIC 3010, Australia
Interests: time-series analysis; sequence modeling; machine learning; intelligent transportation systems

Special Issue Information

Dear Colleagues,

In recent years, deep learning (DL) methodologies have revolutionized the field of artificial intelligence (AI), particularly in the domain of time series forecasting. With their ability to capture complex nonlinear relationships in time-dependent data, these advanced models have shown remarkable success across various sectors, including finance, transportation, weather, energy, and healthcare.

Despite this tremendous success achieved by DL, data from different domains lead to various challenges to classical DL algorithms. Real-world time series data are usually irregular, high-dimensional, imperfect, non-Euclidean, or noisy, necessitating novel designs in DL architecture and training algorithms; therefore, it is of real value to delve into the principles of designing DL algorithms for various fields. The need for accuracy, transparency, and understandability in these models is not just academic; it has practical implications in real-world applications. This Special Issue encourages forecasting researchers to provide publicized datasets.

The objective of this Special Issue is to explore recent advances and techniques in the area of time series forecasting. Research topics of interest include (but are not limited to):

  • Innovative deep learning models for time series forecasting;
  • Techniques for improving the interpretability and transparency of deep learning models in time series analysis;
  • Hybrid deep learning models for forecasting;
  • Applications of advanced deep learning models for forecasting;
  • Deep learning models for imperfect time series forecasting;
  • Deep learning models for irregular time series forecasting;
  • Missing value imputation for forecasting;
  • Benchmark studies about deep learning models for forecasting.

Dr. Ruobin Gao
Dr. Maohan Liang
Dr. Xiaocai Zhang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Information is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • forecasting
  • deep learning
  • artificial intelligence
  • machine learning
  • neural networks

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (6 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Review

20 pages, 1137 KB  
Article
Diagonal Adaptive Graph: Revisiting Channel Dependency in Multivariate Time Series Forecasting
by Xiang Li, Yanping Zheng and Zhewei Wei
Information 2026, 17(4), 394; https://doi.org/10.3390/info17040394 - 21 Apr 2026
Viewed by 408
Abstract
Adaptive graph learning has become a widely adopted paradigm for multivariate time series forecasting when explicit physical topology is unavailable. In these approaches, node embeddings are typically used to construct dense adjacency matrices based on pairwise similarity, implicitly coupling representation learning with relational [...] Read more.
Adaptive graph learning has become a widely adopted paradigm for multivariate time series forecasting when explicit physical topology is unavailable. In these approaches, node embeddings are typically used to construct dense adjacency matrices based on pairwise similarity, implicitly coupling representation learning with relational modeling. However, we observe that under identical training settings but different random initializations, the learned adjacency matrices can vary substantially while predictive performance remains nearly unchanged, indicating that the relational structure is often underdetermined by the forecasting objective. This observation suggests a mismatch between similarity-based structural learning and the forecasting objective. In this work, we revisit node embeddings from a sequence approximation perspective and propose a Diagonal Adaptive Graph (DiAG) module that restricts adaptive learning to diagonal elements. The diagonal coefficients are derived from channel-independent predictions, while off-diagonal interactions are constructed from the similarity of input sequences. This design decouples representation learning from relational modeling, allowing variables to adaptively switch between channel-independent and channel-dependent regimes. Experiments on multiple datasets show that DiAG improves forecasting performance without modifying the channel-independent backbones. These results indicate that channel-dependent forecasting can be achieved as a prediction-driven refinement over channel-independent backbones, without requiring fully learned dense relational structures. Full article
(This article belongs to the Special Issue Deep Learning Approach for Time Series Forecasting)
►▼ Show Figures

Figure 1

31 pages, 2042 KB  
Article
Moderating Roles of the Big Five in Valence–Arousal Dynamics: A TFace-Bi-GRU-SE and CTSEM Study
by Lingping Meng, Mingzheng Li and Xiao Sun
Information 2026, 17(4), 334; https://doi.org/10.3390/info17040334 - 1 Apr 2026
Viewed by 550
Abstract
Existing research confirms associations between Big Five personality traits and emotional states, yet investigations into how personality traits modulate emotional dynamics and their gender-specific patterns remain limited. The present study developed a TFace-Bi-GRU-SE deep learning model that achieved a weighted accuracy of 63.50 [...] Read more.
Existing research confirms associations between Big Five personality traits and emotional states, yet investigations into how personality traits modulate emotional dynamics and their gender-specific patterns remain limited. The present study developed a TFace-Bi-GRU-SE deep learning model that achieved a weighted accuracy of 63.50 ± 0.98% (peak single-run: 64.96%) and an F1 score of 65.21% in performance testing, with a single-inference time of 14.1 s, outperforming traditional methods. The model processed 10 min video recordings from 30 participants (19,262 observations), generating time-series data for valence (P) and arousal (A). Combined with Big Five personality assessments, continuous-time structural equation modeling (CTSEM) revealed distinct emotional dynamics: both P and A exhibited significant negative autoregression (−0.056 and −0.558, p < 0.001), with A reverting to baseline substantially faster (half-life: 1.2 s) than P (half-life: 12.3 s); cross-lagged effects were nonsignificant (P_A: 0.007; A_P: −0.026, p > 0.05). Arousal demonstrated greater instantaneous volatility (=0.339) than valence (=0.286, p < 0.001), with positive covariation between dimensions (0.218, p = 0.006). Exploratory analyses (N = 30) indicated that higher neuroticism and openness scores were associated with elevated arousal (Cohen’s d > 0.8), whereas higher agreeableness and conscientiousness scores were associated with elevated valence (d > 0.8). Gender moderated the neuroticism–arousal relationship, with more potent effects in females (r = 0.746, p = 0.008). Robustness analyses demonstrated high stability of core DRIFT parameters (P_P, A_A): bootstrap resampling (n = 50) yielded coefficients of variation < 0.35 with 100% directional consistency; subgroup validation confirmed cross-sample invariance. Sensitivity analyses revealed that an additional 8% measurement error induced less than 9% bias (8.3% for both P_P and A_A) in autoregressive parameters while preserving half-life ratios, confirming CTSEM’s capacity to extract reliable dynamics from moderately accurate AI outputs. Bootstrap and Bayesian analyses identified ten personality–DRIFT associations with directional consistency ≥ 70%; these constitute preliminary hypotheses for adequately powered future studies (N ≥ 61). This study provides methodological foundations for personalized affective intervention research. Data and code are publicly available (see Data Availability Statement). Full article
(This article belongs to the Special Issue Deep Learning Approach for Time Series Forecasting)
►▼ Show Figures

Figure 1

21 pages, 1394 KB  
Article
Optimization and Application of Generative AI Algorithm Based on Transformer Architecture in Adaptive Learning
by Xuan Liu and Zhi Li
Information 2026, 17(1), 86; https://doi.org/10.3390/info17010086 - 13 Jan 2026
Viewed by 672
Abstract
At present, generative AI has problems of insufficient content generation accuracy, weak personalized response, and low reasoning efficiency in adaptive learning scenarios, which limit its in-depth application in intelligent teaching. To solve this problem, this paper proposed a Transformer fine-tuning method based on [...] Read more.
At present, generative AI has problems of insufficient content generation accuracy, weak personalized response, and low reasoning efficiency in adaptive learning scenarios, which limit its in-depth application in intelligent teaching. To solve this problem, this paper proposed a Transformer fine-tuning method based on low-rank adaptation technology, which realized efficient parameter update of pre-trained models through low-rank matrix insertion, and combined the instruction fine-tuning strategy to perform domain adaptation training on the model for the constructed educational scenario dataset. At the same time, a dynamic prompt construction mechanism was introduced to enhance the model’s context perception ability of individual learners’ behaviors, thereby achieving precise alignment and personalized control of generated content. This paper embeds the “wrong question guidance” and “knowledge graph embedding” mechanisms in the model, provides intelligent feedback based on student errors, and promotes in-depth understanding of subject knowledge through knowledge graphs. Experimental results showed that this method scored higher than 0.9 in BLEU and ROUGE-L. The average response delay was low, which was significantly better than the traditional fine-tuning method. This method showed good adaptability and practicality in the fusion of generative AI and adaptive learning and provided a generalizable optimization path and application solution for intelligent education systems. Full article
(This article belongs to the Special Issue Deep Learning Approach for Time Series Forecasting)
►▼ Show Figures

Figure 1

19 pages, 528 KB  
Article
On Cost-Effectiveness of Language Models for Time Series Anomaly Detection
by Ali Yassine, Luca Cagliero and Luca Vassio
Information 2026, 17(1), 72; https://doi.org/10.3390/info17010072 - 12 Jan 2026
Viewed by 1392
Abstract
Detecting anomalies in time series data is crucial across several domains, including healthcare, finance, and automotive. Large Language Models (LLMs) have recently shown promising results by leveraging robust model pretraining. However, fine-tuning LLMs with several billion parameters requires a large number of training [...] Read more.
Detecting anomalies in time series data is crucial across several domains, including healthcare, finance, and automotive. Large Language Models (LLMs) have recently shown promising results by leveraging robust model pretraining. However, fine-tuning LLMs with several billion parameters requires a large number of training samples and significant training costs. Conversely, LLMs under a zero-shot learning setting require lower overall computational costs, but can fall short in handling complex anomalies. In this paper, we explore the use of lightweight language models for Time Series Anomaly Detection, either zero-shot or via fine-tuning them. Specifically, we leverage lightweight models that were originally designed for time series forecasting, benchmarking them for anomaly detection against both open-source and proprietary LLMs across different datasets. Our experiments demonstrate that lightweight models (<1 Billion parameters) provide a cost-effective solution, as they achieve performance that is competitive and sometimes even superior to that of larger models (>70 Billions). Full article
(This article belongs to the Special Issue Deep Learning Approach for Time Series Forecasting)
►▼ Show Figures

Graphical abstract

20 pages, 2719 KB  
Article
BWO-Optimized CNN-BiGRU-Attention Model for Short-Term Load Forecasting
by Ruihan Wu and Xin Wen
Information 2026, 17(1), 6; https://doi.org/10.3390/info17010006 - 22 Dec 2025
Cited by 1 | Viewed by 804
Abstract
Short-term load forecasting is essential for optimizing power system operations and supporting renewable energy integration. However, accurately capturing the complex nonlinear features in load data remains challenging. To improve forecasting accuracy, this paper proposes a hybrid CNN-BiGRU-Attention model optimized by the Beluga Whale [...] Read more.
Short-term load forecasting is essential for optimizing power system operations and supporting renewable energy integration. However, accurately capturing the complex nonlinear features in load data remains challenging. To improve forecasting accuracy, this paper proposes a hybrid CNN-BiGRU-Attention model optimized by the Beluga Whale Optimization (BWO) algorithm. The proposed method integrates deep learning with metaheuristic optimization in four steps: First, a Convolutional Neural Network (CNN) is used to extract spatial features from input data, including historical load and weather variables. Second, a Bidirectional Gated Recurrent Unit (BiGRU) network is employed to learn temporal dependencies from both forward and backward directions. Third, an Attention mechanism is introduced to focus on key features and reduce the influence of redundant information. Finally, the BWO algorithm is applied to automatically optimize the model’s hyperparameters, avoiding the problem of falling into local optima. Comparative experiments against five baseline models (BP, GRU, BiGRU, BiGRU-Attention, and CNN-BiGRU-Attention) demonstrate the effectiveness of the proposed model. The experimental results indicate that the optimized model achieves superior predictive performance with significantly reduced error rates in terms of Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE), along with a higher Coefficient of Determination (R2) compared to the benchmarks, confirming its high accuracy and reliability for power load forecasting. Full article
(This article belongs to the Special Issue Deep Learning Approach for Time Series Forecasting)
►▼ Show Figures

Figure 1

Review

Jump to: Research

33 pages, 6672 KB  
Review
Advancements in Deep Learning Techniques for Time Series Forecasting in Maritime Applications: A Comprehensive Review
by Meng Wang, Xinyan Guo, Yanling She, Yang Zhou, Maohan Liang and Zhong Shuo Chen
Information 2024, 15(8), 507; https://doi.org/10.3390/info15080507 - 21 Aug 2024
Cited by 18 | Viewed by 7738
Abstract
The maritime industry is integral to global trade and heavily depends on precise forecasting to maintain efficiency, safety, and economic sustainability. Adopting deep learning for predictive analysis has markedly improved operational accuracy, cost efficiency, and decision-making. This technology facilitates advanced time series analysis, [...] Read more.
The maritime industry is integral to global trade and heavily depends on precise forecasting to maintain efficiency, safety, and economic sustainability. Adopting deep learning for predictive analysis has markedly improved operational accuracy, cost efficiency, and decision-making. This technology facilitates advanced time series analysis, vital for optimizing maritime operations. This paper reviews deep learning applications in time series analysis within the maritime industry, focusing on three areas: ship operation-related, port operation-related, and shipping market-related topics. It provides a detailed overview of the existing literature on applications such as ship trajectory prediction, ship fuel consumption prediction, port throughput prediction, and shipping market prediction. The paper comprehensively examines the primary deep learning architectures used for time series forecasting in the maritime industry, categorizing them into four principal types. It systematically analyzes the advantages of deep learning architectures across different application scenarios and explores methodologies for selecting models based on specific requirements. Additionally, it analyzes data sources from the existing literature and suggests future research directions. Full article
(This article belongs to the Special Issue Deep Learning Approach for Time Series Forecasting)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-6
Back to TopTop