Marc Semper Lloret

Academic record

Publications.

A cumulative archive of peer-reviewed journal articles on reliable model selection, graph learning and environmental forecasting.

9 journal articles3 years9 DOI records

Author identity: Marc Semper Lloret publishes scientific work as Marc Semper. Journal record reviewed 25 August 2026.

RSSGoogle ScholarORCID

2026

7 journal articles
01Journal article2026

Graph-based multivariable bias correction of meteorological variables under strict temporal validation in a western mediterranean region prone to atmospheric instability

Marc Semper, Manuel Curado, Jose F. Vicent

Journal of Computational Science, article 102988, 2026

Global atmospheric reanalyses like ERA5 exhibit persistent regional biases over complex terrain that can distort downstream hydrological, energy, and risk models. Combining local weather station networks (AVAMET) with spatial neighborhood graphs via GraphSAGE and Jumping Knowledge enables simultaneous correction across multiple meteorological variables. Rigorous chronological validation shows up to an 81% error reduction in pressure, humidity, temperature, and wind compared to classical baselines, while revealing clear operational boundaries for localized extreme precipitation.

Overview & abstractOriginal publication ↗
02Journal article2026

Out-of-sample statistical correctability limits under an uncertain operational reference: the case of IMERG sub-daily areal precipitation extremes

Marc Semper, Manuel Curado, Jose F. Vicent, Leandro Tortosa

Stochastic Environmental Research and Risk Assessment, vol. 40, no. 8, article 202, 2026

Correcting sub-daily satellite precipitation extremes (GPM IMERG V07) with machine learning becomes challenging when the ground observational reference itself carries spatial and density uncertainties. Benchmarking tabular models (LightGBM) and spatial deep learning (CNN) across strict temporal, spatial, and event-based holdouts demonstrates that continuous post-processing reliably reduces bulk error, but deterministic recovery of heavy rainfall tails hits fundamental limits. Direct probabilistic exceedance modeling provides the most dependable operational ranking for early warning and hazard screening.

Overview & abstractOriginal publication ↗
03Journal article2026

Performance limits of GPM IMERG for sub-daily precipitation extremes over the Comunitat Valenciana, eastern Spain: Representativeness, attenuation, and pixel-scale displacement

Marc Semper, Manuel Curado, Jose F. Vicent, Leandro Tortosa

Atmospheric Research, article 109244, 2026

Operational satellite precipitation products often struggle during Mediterranean flash floods due to rapid convective dynamics and steep orography. Auditing half-hourly GPM IMERG estimates against high-density rain-gauge networks quantifies pixel-scale spatial displacement, severe peak attenuation, and gauge co-availability limits, defining empirical boundaries for satellite-driven hydrological and flood modeling.

Overview & abstractOriginal publication ↗Code on GitHub ↗
04Journal article2026

A practical decision-support system for robust post-training model selection in spatiotemporal forecasting

Marc Semper, Manuel Curado, Jose F. Vicent, Leandro Tortosa

Knowledge-Based Systems, article 116673, 2026

Selecting the best forecasting model from a single clean validation set often leads to brittle deployment decisions when real-world evaluation data is missing, displaced, or degraded. Re-evaluating fixed predictions across declared reference perturbations, quantifying selection instability relative to training-seed variance, and balancing performance budgets transforms fragile model selection into an auditable decision-support system.

Overview & abstractOriginal publication ↗Code on GitHub ↗
05Journal article2026

Multi-Dataset Training for Improved Accuracy in Spatio-Temporal Problems: An Explainable Analysis

Javier García-Sigüenza, Alberto Real-Fernández, Faraón Llorens-Largo, Rafael Molina-Carmona, Marc Semper

Mathematics, vol. 14, no. 5, article 908, 2026

Graph forecasting architectures typically train individual node embeddings in isolation for every separate dataset. Extracting subgraphs across multiple related spatiotemporal networks and transferring the learned representations enables cross-domain knowledge reuse, improving prediction accuracy on target tasks while providing explainable insights into the shared node space.

Overview & abstractOriginal publication ↗
06Journal article2026

Global forecasting of aerosol optical depth through a deep learning spatiotemporal modeling

Marc Semper, Manuel Curado, Jose F. Vicent

International Journal of Environmental Science and Technology, vol. 23, no. 1, article 69, 2026

Forecasting global atmospheric aerosols requires capturing both worldwide spatial transport mechanisms and multi-scale temporal dynamics. Combining CAMS aerosol records with ERA5 meteorological forcing in a hybrid architecture (MultiscaleTCNGraphSAGE) outperforms state-of-the-art transformer and graph baselines, yielding superior representation of extreme aerosol episodes.

Overview & abstractOriginal publication ↗
07Journal article2026

Spatio-temporal graph neural network for inter-city air quality forecasting

Jose F. Vicent, Manuel Curado, Marc Semper

International Journal of Environmental Science and Technology, vol. 23, no. 1, article 63, 2026

Air pollutant concentrations at any given station depend simultaneously on local emissions, nearby sensor readings, and long-range atmospheric transport across distant urban centers. Coupling hierarchical message passing with spectral graph representations from adjacency singular value decomposition enables accurate multi-pollutant forecasting across extensive national monitoring networks.

Overview & abstractOriginal publication ↗

2025

1 journal articles
01Journal article2025

Noise Pollution Prediction in a Densely Populated City Using a Spatio-Temporal Deep Learning Approach

Marc Semper, Manuel Curado, Jose Luis Oliver, Jose F. Vicent

Applied Sciences, vol. 15, no. 10, article 5576, 2025

Urban acoustic pollution exhibits strong cyclic temporal patterns driven by human activity alongside spatial correlations governed by street topology and urban morphology. Integrating 1D temporal convolutions, recurrent LSTM memory, and graph transformer layers (CNN1D+LSTM+TransformerConv) delivers highly accurate predictive mapping across Madrid's urban sensor grid.

Overview & abstractOriginal publication ↗

2024

1 journal articles
01Journal article2024

Global forecasting of carbon concentration through a deep learning spatiotemporal modeling

Marc Semper, Manuel Curado, Jose F. Vicent

Journal of Environmental Management, vol. 371, article 122922, 2024

Projecting global carbon dioxide and methane concentrations up to six months ahead demands architectures capable of synthesizing satellite observations with dynamic and static environmental covariates. Formulating the planetary observation system as an explicit spatiotemporal graph neural network provides superior predictive accuracy over purely temporal methods, underscoring the importance of global spatial connectivity in greenhouse gas dynamics.

Overview & abstractOriginal publication ↗

Reproducible citation

Each publication has its own permanent overview.

Individual pages provide the full bibliographic record, author-written abstract where available, plain-language context, DOI links and exportable BibTeX.