International Journal of Forecasting最新文献

英文中文

Interpretable water level forecaster with spatiotemporal causal attention mechanisms 基于时空因果注意机制的可解释水位预报

IF 6.9 2区经济学 Q1 ECONOMICS

International Journal of Forecasting

Pub Date : 2025-07-01 Epub Date: 2024-11-21 DOI: 10.1016/j.ijforecast.2024.10.003

Sungchul Hong , Yunjin Choi , Jong-June Jeon

Accurate forecasting of river water levels is vital for effectively managing traffic flow and mitigating the risks associated with natural disasters. This task presents challenges due to the intricate factors influencing the flow of a river. Recent advances in machine learning have introduced numerous effective forecasting methods. However, these methods lack interpretability due to their complex structure, resulting in limited reliability. Addressing this issue, this study proposes a deep learning model that quantifies interpretability, with an emphasis on water level forecasting. This model focuses on generating quantitative interpretability measurements, which align with the common knowledge embedded in the input data. This is facilitated by the utilization of a transformer architecture that is purposefully designed with masking, incorporating a multi-layer network that captures spatiotemporal causation. We perform a comparative analysis on the Han River dataset obtained from Seoul, South Korea, from 2016 to 2021. The results illustrate that our approach offers enhanced interpretability consistent with common knowledge, outperforming competing methods. The approach also enhances robustness against distribution shift.

准确预测河流水位对于有效管理交通流量和减轻与自然灾害有关的风险至关重要。由于影响河流流量的因素错综复杂，这项任务提出了挑战。机器学习的最新进展引入了许多有效的预测方法。但这些方法由于结构复杂，缺乏可解释性，可靠性有限。为了解决这个问题，本研究提出了一个深度学习模型，该模型量化了可解释性，重点是水位预测。该模型侧重于生成定量的可解释性度量，它与嵌入在输入数据中的公共知识相一致。这得益于变压器架构的利用，该架构有意设计了屏蔽，并结合了捕获时空因果关系的多层网络。我们对2016年至2021年从韩国首尔获得的汉江数据集进行了比较分析。结果表明，我们的方法提供了与常识一致的增强的可解释性，优于竞争方法。该方法还增强了对分布移位的鲁棒性。

{"title":"Interpretable water level forecaster with spatiotemporal causal attention mechanisms","authors":"Sungchul Hong , Yunjin Choi , Jong-June Jeon","doi":"10.1016/j.ijforecast.2024.10.003","DOIUrl":"10.1016/j.ijforecast.2024.10.003","url":null,"abstract":"<div><div>Accurate forecasting of river water levels is vital for effectively managing traffic flow and mitigating the risks associated with natural disasters. This task presents challenges due to the intricate factors influencing the flow of a river. Recent advances in machine learning have introduced numerous effective forecasting methods. However, these methods lack interpretability due to their complex structure, resulting in limited reliability. Addressing this issue, this study proposes a deep learning model that quantifies interpretability, with an emphasis on water level forecasting. This model focuses on generating quantitative interpretability measurements, which align with the common knowledge embedded in the input data. This is facilitated by the utilization of a transformer architecture that is purposefully designed with masking, incorporating a multi-layer network that captures spatiotemporal causation. We perform a comparative analysis on the Han River dataset obtained from Seoul, South Korea, from 2016 to 2021. The results illustrate that our approach offers enhanced interpretability consistent with common knowledge, outperforming competing methods. The approach also enhances robustness against distribution shift.</div></div>","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"41 3","pages":"Pages 1037-1054"},"PeriodicalIF":6.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144212021","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A projected nonlinear state-space model for forecasting time series signals 一种预测时间序列信号的非线性状态空间模型

IF 6.9 2区经济学 Q1 ECONOMICS

International Journal of Forecasting

Pub Date : 2025-07-01 Epub Date: 2025-02-07 DOI: 10.1016/j.ijforecast.2025.01.002

Christian Donner , Anuj Mishra , Hideaki Shimazaki

Learning and forecasting stochastic time series is essential in various scientific fields. However, despite the proposals of nonlinear filters and deep-learning methods, it remains challenging to capture nonlinear dynamics from a few noisy samples and predict future trajectories with uncertainty estimates while maintaining computational efficiency. Here, we propose a fast algorithm to learn and forecast nonlinear dynamics from noisy time series data. A key feature of the proposed model is kernel functions applied to projected lines, enabling the fast and efficient capture of nonlinearities in the latent dynamics. Through empirical case studies and benchmarking, the model demonstrates its effectiveness at learning and forecasting complex nonlinear dynamics, offering a valuable tool for researchers and practitioners in time series analysis.

学习和预测随机时间序列在许多科学领域都是必不可少的。然而，尽管提出了非线性滤波器和深度学习方法，但从少量噪声样本中捕获非线性动力学并在保持计算效率的同时使用不确定性估计预测未来轨迹仍然具有挑战性。在这里，我们提出了一种快速的算法来学习和预测非线性动态从噪声时间序列数据。该模型的一个关键特征是将核函数应用于投影线，从而能够快速有效地捕获潜在动力学中的非线性。通过实证案例研究和基准测试，该模型证明了其在学习和预测复杂非线性动力学方面的有效性，为时间序列分析的研究人员和实践者提供了有价值的工具。

引用次数: 0

Modeling and predicting failure in US credit unions 对美国信用合作社破产进行建模和预测

IF 6.9 2区经济学 Q1 ECONOMICS

International Journal of Forecasting

Pub Date : 2025-07-01 Epub Date: 2025-01-16 DOI: 10.1016/j.ijforecast.2024.12.004

Qiao Peng , Donal McKillop , Barry Quinn , Kailong Liu

This study presents a random forest (RF)-based machine learning model to predict the liquidation of US credit unions one year in advance. The model demonstrates impressive accuracy on the test set (97.9% accuracy, with 2.0% false negatives and 8.8% false positives) when utilizing all 44 factors. Simplifying the model to only the top five factors based on feature importance analysis results in a slightly lower, but still significant, accuracy on the test set (92.2% accuracy, with 7.8% false negatives and 17.6% false positives). Comparisons with seven other classification methods verify the superiority of the RF model. This study also uses the Cox proportional-hazards model and Shapley value-based approaches to interpret key feature significance and interactions. The model provides regulators and credit unions with a valuable early warning system for potential failures, enabling corrective measures or strategic mergers to ultimately protect the National Credit Union Share Insurance Fund.

本研究提出了一个基于随机森林（RF）的机器学习模型，以提前一年预测美国信用合作社的清算。当利用所有44个因素时，该模型在测试集上显示出令人印象深刻的准确性（97.9%的准确率，2.0%的假阴性和8.8%的假阳性）。将模型简化为基于特征重要性分析的前五个因素，测试集的准确率略低，但仍然显著（准确率为92.2%，假阴性为7.8%，假阳性为17.6%）。与其他7种分类方法的比较验证了射频模型的优越性。本研究还使用Cox比例风险模型和Shapley基于值的方法来解释关键特征的重要性和相互作用。该模型为监管机构和信用合作社提供了一个有价值的潜在失败预警系统，使纠正措施或战略合并能够最终保护国家信用合作社股份保险基金。

引用次数: 0

Stock return predictability in the frequency domain 股票收益在频域的可预测性

IF 6.9 2区经济学 Q1 ECONOMICS

International Journal of Forecasting

Pub Date : 2025-07-01 Epub Date: 2025-01-16 DOI: 10.1016/j.ijforecast.2024.11.007

Zhifeng Dai , Fuwei Jiang , Jie Kang , Bowen Xue

This paper investigates the role of time–frequency information in dimension reduction prediction of stock returns. Using the long-term wavelet component of monthly S&P500 excess returns as supervision, we employ a machine learning method to extract the common predictive factor from prevalent macroeconomic variables and construct a new macroeconomic index aligned with stock return prediction. The macroeconomic index exhibits significant predictive power, both in and out of sample, at the market and portfolio levels. It outperforms all individual macroeconomic predictors and the factors based on higher frequency information of realized returns. Our findings demonstrate substantial economic value of the new index in asset allocation. Moreover, we also observe a complementary relation between macroeconomic index and investor sentiment. The predictive power is most pronounced during high-economic-uncertainty periods when investors are likely to underreact to fundamental signals and stems from cash flow predictability channel.

本文研究了时频信息在股票收益降维预测中的作用。以标普500指数月度超额收益的长期小波分量为监督，采用机器学习方法从主流宏观经济变量中提取共同预测因子，构建与股票收益预测相一致的新宏观经济指标。宏观经济指数在样本内外、市场和投资组合水平上均表现出显著的预测能力。它优于所有个体宏观经济预测指标和基于实现收益高频信息的因素。我们的研究结果表明，新指数在资产配置方面具有巨大的经济价值。此外，我们还观察到宏观经济指数与投资者情绪之间存在互补关系。这种预测能力在经济高度不确定性时期最为明显，此时投资者可能对基本面信号反应不足，并且源于现金流可预测渠道。

引用次数: 0

Credit scoring model for fintech lending: An integration of large language models and FocalPoly loss 金融科技贷款的信用评分模型：大型语言模型和FocalPoly损失的集成

IF 6.9 2区经济学 Q1 ECONOMICS

International Journal of Forecasting

Pub Date : 2025-07-01 Epub Date: 2024-12-05 DOI: 10.1016/j.ijforecast.2024.07.005

Yufei Xia , Zhiyin Han , Yawen Li , Lingyun He

Fintech lending experiences high credit risk and needs an efficient credit scoring model, but it also faces limited data sources and severe class imbalance. We develop a novel two-stage credit scoring model (called LLM-FP-CatBoost) by solving the two issues simultaneously. Large language models (LLMs) initially extract narrative data as a supplementary credit dataset. A new FocalPoly loss is then incorporated with CatBoost to handle the class imbalance problem. Extensive comparisons demonstrate that the proposed LLM-FP-CatBoost significantly outperforms the benchmarks in most circumstances. When making pairwise comparisons between LLMs on the fintech lending dataset, we found that the Chinese-specific LLM, i.e., ERNIE 4.0, achieves the best overall performance, followed by GPT-4 and BERT-based models. The performance decomposition reveals that the superiority is mainly attributed to the new data source extracted by the LLMs. The SHAP algorithm further ensures the interpretability of LLM-FP-CatBoost. The superiority of the proposed LLM-FP-CatBoost model remains robust to hyperparameters of the loss function, specific LLMs, and other extraction methods of narrative data. Finally, we discuss some managerial implications concerning credit scoring in fintech lending.

金融科技借贷信用风险高，需要高效的信用评分模型，但数据来源有限，阶层失衡严重。我们通过同时解决这两个问题，开发了一种新的两阶段信用评分模型（称为LLM-FP-CatBoost）。大型语言模型（llm）最初提取叙事数据作为补充信用数据集。然后将新的FocalPoly损失与CatBoost结合起来处理类不平衡问题。大量的比较表明，LLM-FP-CatBoost在大多数情况下都明显优于基准测试。在对金融科技借贷数据集上的法学模型进行两两比较时，我们发现中国特有的法学模型，即ERNIE 4.0，总体表现最佳，其次是GPT-4和基于bert的模型。性能分解表明，这种优势主要归功于llm提取的新数据源。SHAP算法进一步保证了LLM-FP-CatBoost的可解释性。所提出的LLM-FP-CatBoost模型对损失函数的超参数、特定llm和其他叙事数据提取方法仍然具有鲁棒性。最后，我们讨论了金融科技贷款中信用评分的一些管理含义。

{"title":"Credit scoring model for fintech lending: An integration of large language models and FocalPoly loss","authors":"Yufei Xia , Zhiyin Han , Yawen Li , Lingyun He","doi":"10.1016/j.ijforecast.2024.07.005","DOIUrl":"10.1016/j.ijforecast.2024.07.005","url":null,"abstract":"<div><div>Fintech lending experiences high credit risk and needs an efficient credit scoring model, but it also faces limited data sources and severe class imbalance. We develop a novel two-stage credit scoring model (called LLM-FP-CatBoost) by solving the two issues simultaneously. Large language models (LLMs) initially extract narrative data as a supplementary credit dataset. A new FocalPoly loss is then incorporated with CatBoost to handle the class imbalance problem. Extensive comparisons demonstrate that the proposed LLM-FP-CatBoost significantly outperforms the benchmarks in most circumstances. When making pairwise comparisons between LLMs on the fintech lending dataset, we found that the Chinese-specific LLM, i.e., ERNIE 4.0, achieves the best overall performance, followed by GPT-4 and BERT-based models. The performance decomposition reveals that the superiority is mainly attributed to the new data source extracted by the LLMs. The SHAP algorithm further ensures the interpretability of LLM-FP-CatBoost. The superiority of the proposed LLM-FP-CatBoost model remains robust to hyperparameters of the loss function, specific LLMs, and other extraction methods of narrative data. Finally, we discuss some managerial implications concerning credit scoring in fintech lending.</div></div>","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"41 3","pages":"Pages 894-919"},"PeriodicalIF":6.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144212028","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fundamental determinants of exchange rate expectations 汇率预期的基本决定因素

IF 6.9 2区经济学 Q1 ECONOMICS

International Journal of Forecasting

Pub Date : 2025-07-01 Epub Date: 2024-12-06 DOI: 10.1016/j.ijforecast.2024.09.004

Joscha Beckmann , Robert L. Czudaj

This paper provides a new perspective on the expectations-building mechanism in foreign exchange markets. We analyze the role of expectations regarding macroeconomic fundamentals for expected exchange rate changes. Real-time survey data is assessed for 29 economies from 2002 to 2023, and expectations regarding GDP growth, inflation, interest rates, and current accounts are considered. Our empirical findings show that fundamentals expectations are more important over longer than shorter horizons. We find that an expected increase in GDP growth relative to the US leads to an expected appreciation of the domestic currency. In contrast, higher relative inflation expectations lead to an expected depreciation, a finding consistent with purchasing power parity. Our results also indicate that the expectation-building process differs systematically across pessimistic and optimistic forecasts, with the former paying more attention to fundamentals expectations. Finally, we also observe that fundamentals expectations have some explanatory power for forecast errors, especially for longer horizons.

本文对外汇市场的预期构建机制提供了一个新的视角。我们分析了宏观经济基本面预期对预期汇率变化的作用。对29个经济体2002年至2023年的实时调查数据进行了评估，并考虑了对GDP增长、通货膨胀、利率和经常账户的预期。我们的实证研究结果表明，基本面预期在长期比短期更为重要。我们发现，相对于美国GDP增长的预期增加会导致预期的本币升值。相比之下，较高的相对通胀预期导致预期贬值，这一发现与购买力平价一致。我们的研究结果还表明，悲观和乐观预测的预期构建过程存在系统差异，前者更关注基本面预期。最后，我们还观察到，基本面预期对预测误差有一定的解释力，特别是对较长期的预测误差。

引用次数: 0

Multivariate dynamic mixed-frequency density pooling for financial forecasting 金融预测的多变量动态混频密度池

IF 6.9 2区经济学 Q1 ECONOMICS

International Journal of Forecasting

Pub Date : 2025-07-01 Epub Date: 2024-12-25 DOI: 10.1016/j.ijforecast.2024.11.011

Audronė Virbickaitė , Hedibert F. Lopes , Martina Danielova Zaharieva

This article investigates the benefits of combining information available from daily and intraday data in financial return forecasting. The two data sources are combined via a density pooling approach, wherein the individual densities are represented as a copula function, and the potentially time-varying pooling weights depend on the forecasting performance of each model. The dependence structure in the daily frequency case is extracted from a standard static and dynamic conditional covariance modeling, and the high-frequency counterpart is based on a realized covariance measure. We find that incorporating both high- and low-frequency information via density pooling provides significant gains in predictive model performance over any individual model and any model combination within the same data frequency. A portfolio allocation exercise quantifies the economic gains by producing investment portfolios with the smallest variance and highest Sharpe ratio.

本文研究了在财务回报预测中结合每日和当日数据信息的好处。这两个数据源通过密度池化方法组合在一起，其中单个密度被表示为一个联结函数，并且潜在的时变池化权重取决于每个模型的预测性能。从标准的静态和动态条件协方差模型中提取日频率情况下的依赖结构，并基于已实现的协方差度量提取高频情况下的依赖结构。我们发现，通过密度池结合高频和低频信息，在预测模型性能方面比任何单个模型和相同数据频率的任何模型组合都有显著的提高。投资组合分配通过产生具有最小方差和最高夏普比率的投资组合来量化经济收益。

引用次数: 0

SpotV2Net: Multivariate intraday spot volatility forecasting via vol-of-vol-informed graph attention networks SpotV2Net：通过volof - volinformed图形关注网络进行多变量日内现货波动预测

IF 6.9 2区经济学 Q1 ECONOMICS

International Journal of Forecasting

Pub Date : 2025-07-01 Epub Date: 2024-12-06 DOI: 10.1016/j.ijforecast.2024.11.004

Alessio Brini , Giacomo Toscano

This paper introduces SpotV2Net, a multivariate intraday spot volatility forecasting model based on a graph attention network architecture. SpotV2Net represents assets as nodes within a graph and includes non-parametric high-frequency Fourier estimates of the spot volatility and co-volatility as node features. Further, it incorporates Fourier estimates of the spot volatility of volatility and co-volatility of volatility as features for node edges, to capture spillover effects. We test the forecasting accuracy of SpotV2Net in an extensive empirical exercise, conducted with the components of the Dow Jones Industrial Average index. The results we obtain suggest that SpotV2Net yields statistically significant gains in forecasting accuracy, for both single-step and multi-step forecasts, compared to a panel heterogeneous autoregressive model and alternative machine-learning models. To interpret the forecasts produced by SpotV2Net, we employ GNNExplainer (Ying et al., 2019), a model-agnostic interpretability tool, and thereby uncover subgraphs that are critical to a node’s predictions.

介绍了基于图关注网络结构的多变量日内现货波动率预测模型SpotV2Net。SpotV2Net将资产表示为图中的节点，并将现货波动率和协同波动率的非参数高频傅立叶估计作为节点特征。此外，它将波动率的现货波动率和波动率的协同波动率的傅立叶估计作为节点边缘的特征，以捕获溢出效应。我们用道琼斯工业平均指数的组成部分进行了广泛的实证练习，测试了SpotV2Net的预测准确性。我们获得的结果表明，与面板异构自回归模型和替代机器学习模型相比，SpotV2Net在单步和多步预测方面的预测准确性在统计上有显著提高。为了解释SpotV2Net产生的预测，我们使用了gnexplainer (Ying et al., 2019)，这是一种与模型无关的可解释性工具，从而揭示了对节点预测至关重要的子图。

{"title":"SpotV2Net: Multivariate intraday spot volatility forecasting via vol-of-vol-informed graph attention networks","authors":"Alessio Brini , Giacomo Toscano","doi":"10.1016/j.ijforecast.2024.11.004","DOIUrl":"10.1016/j.ijforecast.2024.11.004","url":null,"abstract":"<div><div>This paper introduces SpotV2Net, a multivariate intraday spot volatility forecasting model based on a graph attention network architecture. SpotV2Net represents assets as nodes within a graph and includes non-parametric high-frequency Fourier estimates of the spot volatility and co-volatility as node features. Further, it incorporates Fourier estimates of the spot volatility of volatility and co-volatility of volatility as features for node edges, to capture spillover effects. We test the forecasting accuracy of SpotV2Net in an extensive empirical exercise, conducted with the components of the Dow Jones Industrial Average index. The results we obtain suggest that SpotV2Net yields statistically significant gains in forecasting accuracy, for both single-step and multi-step forecasts, compared to a panel heterogeneous autoregressive model and alternative machine-learning models. To interpret the forecasts produced by SpotV2Net, we employ GNNExplainer (Ying et al., 2019), a model-agnostic interpretability tool, and thereby uncover subgraphs that are critical to a node’s predictions.</div></div>","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"41 3","pages":"Pages 1093-1111"},"PeriodicalIF":6.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144212024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Time-varying parameters as ridge regressions 时变参数作为脊回归

IF 6.9 2区经济学 Q1 ECONOMICS

International Journal of Forecasting

Pub Date : 2025-07-01 Epub Date: 2025-01-27 DOI: 10.1016/j.ijforecast.2024.08.006

Philippe Goulet Coulombe

Time-varying parameter (TVP) models are frequently used in economics to capture structural change. I highlight a rather underutilized fact—that these are actually ridge regressions. Instantly, this makes computations, tuning, and implementation much easier than in the state-space paradigm. Among other things, solving the equivalent dual ridge problem is computationally very fast even in high dimensions, and the crucial ‘amount of time variation’ is tuned by cross-validation. Evolving volatility is dealt with using a two-step ridge regression. I consider extensions that incorporate sparsity (the algorithm selects which parameters vary and which do not) and reduced-rank restrictions (variation is tied to a factor model). To demonstrate the usefulness of the approach, I use it to study the evolution of monetary policy in Canada using large time-varying local projections and TVP-VARs with demanding lag lengths. The applications require the estimation of up to 4600 TVPs, a task within the reach of the new method.

时变参数（TVP）模型在经济学中经常用于捕捉结构变化。我强调一个未被充分利用的事实，即这些实际上是脊回归。这立即使计算、调优和实现比状态空间范式容易得多。除此之外，即使在高维情况下，解决等效双脊问题的计算速度也非常快，关键的“时间变化量”是通过交叉验证来调整的。使用两步脊回归处理不断变化的波动率。我考虑了包含稀疏性（算法选择哪些参数变化，哪些参数不变化）和降阶限制（变化与因子模型相关联）的扩展。为了证明该方法的实用性，我用它来研究加拿大货币政策的演变，使用大型时变本地预测和要求滞后长度的tvp -var。应用程序需要估计多达4600个TVPs，这是新方法可以达到的任务。

引用次数: 0

SolNet: Open-source deep learning models for photovoltaic power forecasting across the globe SolNet：全球光伏发电预测的开源深度学习模型

IF 6.9 2区经济学 Q1 ECONOMICS

International Journal of Forecasting

Pub Date : 2025-07-01 Epub Date: 2025-02-03 DOI: 10.1016/j.ijforecast.2024.12.003

Joris Depoortere, Johan Driesen, Johan Suykens, Hussain Syed Kazmi

Deep learning models have gained increasing prominence in recent years in solar photovoltaic (PV) forecasting. One drawback of these models is that they require a lot of high-quality data to perform well. This is often infeasible in practice, due to poor measurement infrastructure in legacy systems and the rapid build-up of new solar systems across the world. This paper proposes SolNet: a novel, general-purpose, multivariate solar power forecaster, which addresses these challenges by using a two-step forecasting pipeline that incorporates transfer learning from abundant synthetic data generated from PVGIS, before fine-tuning on observational data.

Using actual production data from hundreds of sites in The Netherlands, Australia, and Belgium, we show that SolNet improves forecasting performance over data-scarce settings as well as baseline models. We find transfer learning benefits to be the strongest when only limited observational data are available. At the same time, we provide several guidelines and considerations for transfer learning practitioners, as our results show that weather data, seasonal patterns, and possible misspecification in source location can have a major impact on the results. The SolNet models created in this way are applicable for any land-based solar photovoltaic system across the planet to obtain improved forecasting capabilities.

近年来，深度学习模型在太阳能光伏（PV）预测领域得到了越来越多的关注。这些模型的一个缺点是，它们需要大量高质量的数据才能运行良好。这在实践中往往是不可行的，因为遗留系统的测量基础设施很差，而且世界各地正在迅速建立新的太阳能系统。本文提出了SolNet：一种新颖的、通用的、多元的太阳能预测器，它通过使用两步预测管道来解决这些挑战，该管道结合了从PVGIS生成的丰富合成数据的迁移学习，然后对观测数据进行微调。使用来自荷兰、澳大利亚和比利时数百个站点的实际生产数据，我们表明SolNet提高了数据稀缺设置和基线模型的预测性能。我们发现，只有有限的观测数据可用时，迁移学习的好处是最强的。同时，我们为迁移学习实践者提供了一些指导方针和注意事项，因为我们的结果表明，天气数据、季节模式和源位置可能的错误说明会对结果产生重大影响。以这种方式创建的SolNet模型适用于地球上任何陆基太阳能光伏系统，以获得改进的预测能力。

{"title":"SolNet: Open-source deep learning models for photovoltaic power forecasting across the globe","authors":"Joris Depoortere, Johan Driesen, Johan Suykens, Hussain Syed Kazmi","doi":"10.1016/j.ijforecast.2024.12.003","DOIUrl":"10.1016/j.ijforecast.2024.12.003","url":null,"abstract":"<div><div>Deep learning models have gained increasing prominence in recent years in solar photovoltaic (PV) forecasting. One drawback of these models is that they require a lot of high-quality data to perform well. This is often infeasible in practice, due to poor measurement infrastructure in legacy systems and the rapid build-up of new solar systems across the world. This paper proposes SolNet: a novel, general-purpose, multivariate solar power forecaster, which addresses these challenges by using a two-step forecasting pipeline that incorporates transfer learning from abundant synthetic data generated from PVGIS, before fine-tuning on observational data.</div><div>Using actual production data from hundreds of sites in The Netherlands, Australia, and Belgium, we show that SolNet improves forecasting performance over data-scarce settings as well as baseline models. We find transfer learning benefits to be the strongest when only limited observational data are available. At the same time, we provide several guidelines and considerations for transfer learning practitioners, as our results show that weather data, seasonal patterns, and possible misspecification in source location can have a major impact on the results. The SolNet models created in this way are applicable for any land-based solar photovoltaic system across the planet to obtain improved forecasting capabilities.</div></div>","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"41 3","pages":"Pages 1223-1236"},"PeriodicalIF":6.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144211941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

International Journal of Forecasting

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀