Mariana Akemi Ikegawa Bernabé

Ms. Mariana Akemi Ikegawa Bernabé

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
5 March 2026 in Computers and Electronics in Agriculture
Verified
Journal Article
Open access
Mariana Akemi Ikegawa BernabéMariana Akemi Ikegawa Bernabé
Mariana Akemi Ikegawa Bernabé
RPRafael González Perea
Rafael González Perea
JDJuan Antonio Rodríguez Díaz
Juan Antonio Rodríguez Díaz
JMJorge García Morillo
Jorge García Morillo

Verified
Journal Article
Open access
PDF file
José Pérez-PadilloJosé Pérez-Padillo
José Pérez-Padillo
Mariana Akemi Ikegawa BernabéMariana Akemi Ikegawa Bernabé
Mariana Akemi Ikegawa Bernabé
JLJorge Pérez Lucena
Jorge Pérez Lucena
Pilar MontesinosPilar Montesinos
Pilar Montesinos
Jorge García MorilloJorge García Morillo
Jorge García Morillo
The monitoring of the discharge points of sewage networks is a complex task mainly due to dispersion and the difficulty of accessing this type of infrastructures. The aim of this work is to develop a device for monitoring discharges in the spillways of sewage networks. The proposed device represents a step forward in the digitization process of these networks, avoiding a high initial investment and ensuring sufficient robustness. The benefit for managers is twofold: it allows for monitoring discharge events and determining the maximum capacity of the network without spillage.

5 June 2025 in Technologies
Verified
Journal Article
Open access
PDF file
Mariana Akemi Ikegawa BernabéMariana Akemi Ikegawa Bernabé
Mariana Akemi Ikegawa Bernabé
MCMiguel Crespo Chacón
Miguel Crespo Chacón
Juan Antonio Rodríguez DíazJuan Antonio Rodríguez Díaz
Juan Antonio Rodríguez Díaz
Pilar MontesinosPilar Montesinos
Pilar Montesinos
Jorge García MorilloJorge García Morillo
Jorge García Morillo
The modernisation of irrigation networks has enhanced water use efficiency but increased energy demand and costs in agriculture. Energy recovery (ER) is possible by utilising excess pressure to generate electricity with pumps as turbines (PATs), offering a cost-effective alternative to traditional turbines. This study assesses the use of PATs in pressurised irrigation networks for recovering wasted hydraulic energy, employing the particle swarm optimisation (PSO) algorithm for PAT sizing based on two single-objective functions. The analysis focuses on minimising the payback period (MPP) and maximising energy recovery (MER) at specific excess pressure points (EPPs). A comparative analysis of values for each EPP and objective function is conducted independently in Sector II of the Canal del Zújar Irrigation District (CZID) in Extremadura, Spain. A sensitivity analysis on energy prices and installation costs is also performed to assess socioeconomic trends and volatility, examining their effects on both objective functions. The optimisation process predicts an annual ER for an average irrigation season using 2015 data ranging from 9554.86 kWh to 43,992.15 kWh per PATs from the MER function, and payback periods (PPs) from 12.92 years to 3.01 years for the MPP function. The sensitivity analysis replicated the optimisation for the years 2022 and 2023, showing potential annual ER of up to 54,963.21 kWh and PPs ranging from 0.88 to 5.96 years for the year 2022.

20 October 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
Mariana Akemi Ikegawa BernabéMariana Akemi Ikegawa Bernabé
Mariana Akemi Ikegawa Bernabé
RPRafael Gonzalez Perea
Rafael Gonzalez Perea
JDJuan Antonio Rodríguez Díaz
Juan Antonio Rodríguez Díaz
JMJorge García Morillo
Jorge García Morillo
Accurate energy demand (ED) forecasting is essential for energy management, renewable integration, and sustainable planning. However, most existing approaches are developed and validated within a single domain, providing limited evidence of their ability to generalize across heterogeneous consumers. This study proposes a Transformer-based framework for hourly medium-term ED forecasting (up to one week ahead) and evaluates it on four heterogeneous end-users: a fish-processing facility (Ireland), an irrigation district (Spain), a port (Spain), and a rural community (Portugal). The framework combines a Transformer encoder–decoder architecture with an adaptive feature selection procedure based on fuzzy curves and surfaces and statistical correlation analysis, which retained 7 input variables for the fish-processing facility and the port, 8 for the community, and 12 for the irrigation district, while the architecture, training strategy, and hyperparameters were kept identical across all cases. The model achieved coefficients of determination (R²) of 97.85–99.64% and normalized mean absolute errors (NMAE) of 2.92–8.25%, despite demand scales differing by over two orders of magnitude. An exploratory descriptor analysis indicated that accuracy differences were most closely aligned with distribution asymmetry and the strength of daily and weekly periodicity. Decoder cross-attention analysis revealed case-specific regimes: attention concentrated on short-term persistence for the port, on meteorological and calendar predictors for the community, on both for the irrigation district, and was nearly uniform for the fish-processing facility, the least accurate case. Overall, a single architecture combined with case-specific input selection sustained high and interpretable performance across structurally different energy consumers without domain-specific modifications.