arXiv subjects

José Portela

Publications and source records attributed to José Portela.

6 recordsLinked to original sources

arXiv2026

Surrogate Modeling of Interconnector Flows: A Machine Learning Alternative to Full-Scale Power System Simulations with Application to Cross-Border Electricity Exchange

Cross-border electricity exchanges are crucial for operating and planning highly renewable power systems. Many studies reduce spatial granularity to keep models tractable and prescribe cross-border exchanges exogenously, often by reusing historical import/export time series. Such assumptions become inconsistent as renewable penetration changes the magnitude and timing of flows. The core contribution of this work is a machine-learning (ML) surrogate framework that maps nodal time-series data (e.g., hourly demand and renewable generation) to synthetic interconnector-level flow time series. The resulting flows serve as fixed boundary conditions in reduced power system optimization models (PSOMs). This addresses studies focused on a subset of an interconnected system, for which repeatedly solving the full model across multiple climate years or scenarios is computationally expensive. We demonstrate the framework on a pan-European single-node-per-country DC optimal power flow model. We benchmark k-nearest neighbors, ridge regression, random forests, Extra Trees, gradient boosting, XGBoost, and feedforward neural-network (SQU) surrogates. As an additional contribution, we introduce a novel custom neural-network loss that softly penalizes physically implausible flow patterns. This soft penalty is not a guarantee of full power-flow feasibility. Across benchmarks, the SQU variants provide the most consistent out-of-sample and downstream optimization performance while substantially outperforming scaled historical profiles. The ML-generated flows closely reproduce country-level results of the full European model while greatly reducing computation time. The proposed framework enables scenario-consistent reduced PSOM studies across climate years after a single full-model run, eliminating repeated pan-European simulations and supporting more robust climate-year analyses under fixed system assumptions.

eess.SY↗

arXiv2026

Attention Expansion: Enhancing Keyphrase Extraction from Long Documents with Attention-Augmented Contextualized Embeddings

Pre-trained language models (PLMs) have achieved strong performance in keyphrase extraction (KPE), largely due to their ability to generate rich contextualized representations. However, long-document KPE remains challenging because salient keyphrase evidence may be scattered across distant document sections that cannot be jointly captured within the limited context window of most PLMs. Although long-context large language models (LLMs) can process broader textual contexts, their computational cost limits their practicality for efficient and high-throughput KPE. To overcome this limitation, we propose an attention expansion mechanism that augments PLM token representations with information from surrounding out-of-context chunks using pre-trained word embeddings. The proposed mechanism expands the effective contextual scope of PLM-based KPE models without requiring full-document attention or expensive LLM-based inference. We evaluate our approach across five PLM backbones, including general-purpose, scientific, task-specific, and long-context encoders, using two training regimes and five benchmark corpora from scientific and news domains. Experimental results demonstrate that attention expansion consistently enhances KPE performance across all evaluation settings, outperforming state-of-the-art models and yielding notable improvements in F1 score. The improvements extend to domain-specific, task-specialized, and native long-context models, showing that the proposed mechanism provides complementary information rather than merely compensating for limited input length. These results establish attention expansion as an efficient and effective strategy for long-document KPE.

cs.CL↗

arXiv2025

Generating Building-Level Heat Demand Time Series by Combining Occupancy Simulations and Thermal Modeling

Despite various efforts, decarbonizing the heating sector remains a significant challenge. To tackle it by smart planning, the availability of highly resolved heating demand data is key. Several existing models provide heating demand only for specific applications. Typically, they either offer time series for a larger area or annual demand data on a building level, but not both simultaneously. Additionally, the diversity in heating demand across different buildings is often not considered. To address these limitations, this paper presents a novel method for generating temporally resolved heat demand time series at the building level using publicly available data. The approach integrates a thermal building model with stochastic occupancy simulations that account for variability in user behavior. As a result, the tool serves as a cost-effective resource for cross-sectoral energy system planning and policy development, particularly with a focus on the heating sector. The obtained data can be used to assess the impact of renovation and retrofitting strategies, or to analyze district heating expansion. To illustrate the potential applications of this approach, we conducted a case study in Puertollano (Spain), where we prepared a dataset of heating demand with hourly resolution for each of 9,298 residential buildings. This data was then used to compare two different pathways for the thermal renovation of these buildings. By relying on publicly available data, this method can be adapted and applied to various European regions, offering broad usability in energy system optimization and analysis of decarbonization strategies.

eess.SY↗

arXiv2023

ChatGPT vs State-of-the-Art Models: A Benchmarking Study in Keyphrase Generation Task

Transformer-based language models, including ChatGPT, have demonstrated exceptional performance in various natural language generation tasks. However, there has been limited research evaluating ChatGPT's keyphrase generation ability, which involves identifying informative phrases that accurately reflect a document's content. This study seeks to address this gap by comparing ChatGPT's keyphrase generation performance with state-of-the-art models, while also testing its potential as a solution for two significant challenges in the field: domain adaptation and keyphrase generation from long documents. We conducted experiments on six publicly available datasets from scientific articles and news domains, analyzing performance on both short and long documents. Our results show that ChatGPT outperforms current state-of-the-art models in all tested datasets and environments, generating high-quality keyphrases that adapt well to diverse domains and document lengths.

cs.CL↗

arXiv2023

Enhancing Keyphrase Extraction from Long Scientific Documents using Graph Embeddings

In this study, we investigate using graph neural network (GNN) representations to enhance contextualized representations of pre-trained language models (PLMs) for keyphrase extraction from lengthy documents. We show that augmenting a PLM with graph embeddings provides a more comprehensive semantic understanding of words in a document, particularly for long documents. We construct a co-occurrence graph of the text and embed it using a graph convolutional network (GCN) trained on the task of edge prediction. We propose a graph-enhanced sequence tagging architecture that augments contextualized PLM embeddings with graph representations. Evaluating on benchmark datasets, we demonstrate that enhancing PLMs with graph embeddings outperforms state-of-the-art models on long documents, showing significant improvements in F1 scores across all the datasets. Our study highlights the potential of GNN representations as a complementary approach to improve PLM performance for keyphrase extraction from long documents.

cs.CL↗

arXiv2023

Metric Tools for Sensitivity Analysis with Applications to Neural Networks

As Machine Learning models are considered for autonomous decisions with significant social impact, the need for understanding how these models work rises rapidly. Explainable Artificial Intelligence (XAI) aims to provide interpretations for predictions made by Machine Learning models, in order to make the model trustworthy and more transparent for the user. For example, selecting relevant input variables for the problem directly impacts the model's ability to learn and make accurate predictions, so obtaining information about input importance play a crucial role when training the model. One of the main XAI techniques to obtain input variable importance is the sensitivity analysis based on partial derivatives. However, existing literature of this method provide no justification of the aggregation metrics used to retrieved information from the partial derivatives. In this paper, a theoretical framework is proposed to study sensitivities of ML models using metric techniques. From this metric interpretation, a complete family of new quantitative metrics called $α$-curves is extracted. These $α$-curves provide information with greater depth on the importance of the input variables for a machine learning model than existing XAI methods in the literature. We demonstrate the effectiveness of the $α$-curves using synthetic and real datasets, comparing the results against other XAI methods for variable importance and validating the analysis results with the ground truth or literature information.

cs.LG↗