期刊名：Forecasting

期刊主页：https://www.mdpi.com/journal/forecasting

Forecasting（ISSN 2571-9394） 是一个国际性、同行评审的开放获取期刊，致力于打造预测科学领域的国际化开放交流平台。本刊聚焦前沿预测方法与理论研究，重点关注AI、机器学习等在预测科学研究中的创新引用，鼓励多场景预测应用探索，如经济金融，能源电力，气候环境，灾害安全等。

本期文献清单我们为您精选2025年发表于Forecasting 期刊的10篇高引文章。希望能为相关领域学者提供新的思路和参考，欢迎各位学者阅读转发。

1.Navigating AI-Driven Financial Forecasting: A Systematic Review of Current Status and Critical Research Gaps

人工智能驱动的金融预测：发展现状与关键技术空白的未来展望

http://www.mdpi.com/2571-9394/7/3/36

Vancsura, L.; Tatay, T.; Bareith, T. Navigating AI-Driven Financial Forecasting: A Systematic Review of Current Status and Critical Research Gaps. Forecasting 2025, 7, 36.

2.Day-Ahead Energy Price Forecasting with Machine Learning: Role of Endogenous Predictors

基于机器学习的电力市场日前价格预测：内生预测变量的作用研究

http://www.mdpi.com/2571-9394/7/2/18

Ibebuchi, C.C. Day-Ahead Energy Price Forecasting with Machine Learning: Role of Endogenous Predictors. Forecasting 2025, 7, 18.

3.White Noise and Its Misapplications: Impacts on Time Series Model Adequacy and Forecasting

白噪声及其误用：对时间序列模型适用性与预测的影响

http://www.mdpi.com/2571-9394/7/1/8

Hassani, H.; Mashhad, L.M.; Royer-Carenzi, M.; Yeganegi, M.R.; Komendantova, N. White Noise and Its Misapplications: Impacts on Time Series Model Adequacy and Forecasting. Forecasting 2025, 7, 8.

4.Dynamic Bayesian Network Model for Overhead Power Lines Affected by Hurricanes

基于动态贝叶斯网络的飓风环境下架空输电线路建模

http://www.mdpi.com/2571-9394/7/1/11

Fatima, K.; Shareef, H. Dynamic Bayesian Network Model for Overhead Power Lines Affected by Hurricanes. Forecasting 2025, 7, 11.

5.Comparative Analysis of Physics-Guided Bayesian Neural Networks for Uncertainty Quantification in Dynamic Systems

融合物理信息的贝叶斯神经网络在动态系统不确定性评估中的比较分析

http://www.mdpi.com/2571-9394/7/1/9

Xu, X.; Wang, J. Comparative Analysis of Physics-Guided Bayesian Neural Networks for Uncertainty Quantification in Dynamic Systems. Forecasting 2025, 7, 9.

6.Evaluating the Potential of Copulas for Modeling Correlated Scenarios for Hydro, Wind, and Solar Energy

评估Copula方法在水能、风能与太阳能关联场景建模中的适用性研究

http://www.mdpi.com/2571-9394/7/1/7

Iung, A.M.; Cyrino Oliveira, F.L.; Marcato, A.L.M.; Pereira, G.A.A. Evaluating the Potential of Copulas for Modeling Correlated Scenarios for Hydro, Wind, and Solar Energy. Forecasting 2025, 7, 7.

7.Mode Decomposition Bi-Directional Long Short-Term Memory (BiLSTM) Attention Mechanism and Transformer (AMT) Model for Ozone (O3) Prediction in Johannesburg, South Africa

约翰内斯堡大气臭氧预测：一种结合模态分解、BiLSTM、注意力机制与Transformer的混合方法

http://www.mdpi.com/2571-9394/7/2/15

Agbehadji, I.E.; Obagbuwa, I.C. Mode Decomposition Bi-Directional Long Short-Term Memory (BiLSTM) Attention Mechanism and Transformer (AMT) Model for Ozone (O3) Prediction in Johannesburg, South Africa. Forecasting 2025, 7, 15.

8．A Wavelet–Attention–Convolution Hybrid Deep Learning Model for Accurate Short-Term Photovoltaic Power Forecasting

融合小波变换、注意力机制与CNN的混合深度学习模型及其在短期光伏功率高精度预测中的应用

http://www.mdpi.com/2571-9394/7/3/45

Ait Chaoui, K.; EL Fadil, H.; Choukai, O.; Ait Omar, O. A Wavelet–Attention–Convolution Hybrid Deep Learning Model for Accurate Short-Term Photovoltaic Power Forecasting. Forecasting 2025, 7, 45.

9.Identification of Investment-Ready SMEs: A Machine Learning Framework to Enhance Equity Access and Economic Growth

识别高投资潜力的中小企业：一个融合机器学习的融资赋能与经济增长框架

http://www.mdpi.com/2571-9394/7/3/51

Gogas, P.; Papadimitriou, T.; Goumenidis, P.; Kontos, A.; Giannakis, N. Identification of Investment-Ready SMEs: A Machine Learning Framework to Enhance Equity Access and Economic Growth. Forecasting 2025, 7, 51.

10.Parallel Multi-Model Energy Demand Forecasting with Cloud Redundancy: Leveraging Trend Correction, Feature Selection, and Machine Learning

基于云冗余的并行多模型能源需求预测：一个集成趋势校正、特征选择与机器学习的协同框架

http://www.mdpi.com/2571-9394/7/2/25

Hassanpouri Baesmat, K.; Farrokhi, Z.; Chmaj, G.; Regentova, E.E. Parallel Multi-Model Energy Demand Forecasting with Cloud Redundancy: Leveraging Trend Correction, Feature Selection, and Machine Learning. Forecasting 2025, 7, 25.

第一届国际预测线上会议（IOCFC 2026）开放征稿

为深入探讨预测科学前沿进展与未来方向，MDPI期刊 Forecasting（ISSN: 2571-9394, IF: 3.2, CITESCORE: 7.1）将举办第一届国际预测线上会议 (The 1st International Online Conference on Forecasting | IOCFC 2026) ，于2026年9月21日至22日在线上召开。

本次会议为推进预测科学与实践提供了重要平台，涵盖能源、气候、经济和人工智能等多个关键领域。旨在汇聚研究人员、学者和行业专业人士，促进跨学科合作、创新思想交流以及前沿研究成果展示。

会议主题：

S1. 能源预测与分析

S2. 人工智能预测与大语言模型

S3. 预测与计量经济模型

S4. 气候预测

会议信息：

会议时间：2026年9月21日至22日

会议形式：线上

会议网址：https://sciforum.net/event/IOCFC2026

Forecasting 期刊介绍

主编：Prof. Dr. Sonia Leva, Politecnico di Milano, Italy

Forecasting 是一个国际性、同行评审的开放获取期刊，致力于打造预测科学领域的国际化开放交流平台。本刊聚焦前沿预测方法与理论研究，重点关注AI、机器学习等在预测科学研究中的创新引用，鼓励多场景预测应用探索，如经济金融，能源电力，气候环境，灾害安全等。