Mario C. Cruz-Mercado

Dr. Mario C. Cruz-Mercado

orcid

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 September 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
DRDIEGO RESTREPO-LEAL
DIEGO RESTREPO-LEAL
MCMario C. Cruz-Mercado
Mario C. Cruz-Mercado
JAJairo Altamar
Jairo Altamar
HZHarley Zuñiga
Harley Zuñiga
MMMiguel Enrique Iglesias Martínez
Miguel Enrique Iglesias Martínez
Pedro Fernández de Córdoba CastelláPedro Fernández de Córdoba Castellá
Pedro Fernández de Córdoba Castellá
Monitoring landings in data-scarce fisheries is hampered by short, noisy series and multi-year reporting gaps. We benchmark Echo State Networks (ESNs) against SARIMA, LightGBM, and LSTM models and against naïve and seasonal-naïve persistence, for one-step-ahead forecasting of the monthly landings (1993–2023) of the shallow-water shrimp industrial trawl fishery of the Colombian Caribbean, using a gap-filled series, equal tuning budgets, and walk-forward validation (h=1, 72 origins) on an embedded NVIDIA Jetson Orin Nano. The ESN obtained the lowest errors (MAE = 1.33 tons, RMSE = 1.82 tons), 28% and 34% below the naïve forecast on the same window (1.85 and 2.77 tons), and Diebold–Mariano tests favored it over every other model; the advantage comes from the test years 2021–2023, and LightGBM is a close competitor. The ESN needed 337 ms per origin (fit plus predict) and 0.08 ms per sample at inference. A bidirectional ESN interpolated 108 unmonitored months; in blind-gap tests, it was no more accurate than linear or Kalman interpolation, and calibrated bands are wide. Because only landings, not fishing effort, are analyzed, the post-2013 decline cannot be separated from fleet contraction.

28 August 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
DRDIEGO RESTREPO-LEAL
DIEGO RESTREPO-LEAL
MCMario C. Cruz-Mercado
Mario C. Cruz-Mercado
JAJairo Altamar
Jairo Altamar
HZHarley Zuñiga
Harley Zuñiga
MMMiguel Enrique Iglesias Martínez
Miguel Enrique Iglesias Martínez
Pedro Fernández de Córdoba CastelláPedro Fernández de Córdoba Castellá
Pedro Fernández de Córdoba Castellá
Monitoring and forecasting environmental thresholds in data-scarce ecosystems poses a critical challenge for resource management. In this study, we evaluate four forecasting paradigms—Seasonal Autoregressive Integrated Moving Average (SARIMA), Light Gradient Boosting Machine (LightGBM), Long Short-Term Memory (LSTM) networks, and Echo State Networks (ESNs)—to model and reconstruct historical landing dynamics of a shallow-water shrimp fishery. The historical time series exhibits severe data gaps, including continuous unmonitored periods spanning up to six years. To assess real-time deployment feasibility, all models were benchmarked on an embedded NVIDIA Jetson Orin Nano edge platform using walk-forward validation (h=1). Empirical results demonstrate that the ESN architecture captures the non-linear temporal dynamics of the fishery, achieving the highest predictive accuracy (MAE=1.37t, RMSE=1.96t, and RMSSE=0.70). A bidirectional forecasting-backcasting reconstruction strategy filled the multi-year gaps and confirmed that the landing decline occurred abruptly after 2013. For edge computing applications, the ESN achieved low latency, executing sub-millisecond inference (0.27ms) and a fast training time per fold (424.44ms) while consuming less energy than LSTM. These findings indicate that projecting dynamics into a high-dimensional fixed reservoir provides a computationally efficient solution for continuous time-series reconstruction and landing trend detection under severe data and hardware constraints.