Yesenia Saavedra-Navarro

Dr. Yesenia Saavedra-Navarro

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
15 December 2021 in Scientia Agropecuaria
Verified
Journal Article
Open access
PDF file
CYCristhian Nicolas Aldana Yarleque
Cristhian Nicolas Aldana Yarleque
YSYesenia Saavedra-Navarro
Yesenia Saavedra-Navarro
JGJhony Gonzales
Jhony Gonzales
DGDavid Gálvez
David Gálvez
CPClaudia Palacios
Claudia Palacios
WMWilmer Moncada
Wilmer Moncada
Agricultural production of Citrus x limon (lemon) and Mangifera indica (mango) in the Piura region is often affected by environmental-climatic factors, mainly by possible seasonal changes or extreme weather events, such as droughts or El Niño. The objective is to analyze the spatial-temporal agricultural production of lemon and mango, measuring with the FieldSpec4 spectroradiometer, the spectral signature (SF) and Sentinel 2 satellite images (ISS2) of the Chulucanas criollo mango in crops of Pampa Larga-Alvarados-Suyo-Ayabaca and INIA-Hualtaco-Tambogrande-Piura mango germplasm bank, respectively. The method consists of entering each EF in the ISS2 (2019) mosaic of tiles 17MMR-17MNR-17MPR-17MMQ-17MNQ-17MPQ-17MMP-17MMP-17MNP-17MPP, using SEN2COR280 in SNAP software. The time series of monthly/annual production of lemon and mango were analyzed using data from INEI and SIEA-MIDAGRI-PERU. The results obtained estimate a lemon cultivated area of 27 451.84 ha and mango cultivated area of 22000 ha; higher than the reported harvested area of 16113 ha and 20606 ha, respectively. Mango production 1970-2020, is higher in November-December-January-February, explained by the harvested area in 84.1%, showing seasonality, exponential growth behavior and positive (2003-2020) and negative (1970-2002) anomalies. Monthly lemon production 2007-2020 is seasonal, the annual trend increases by 2.8% despite the existence of negative anomalies in 2017, generated by the effects of the "Coastal El Niño" in its evolutionary flowering process, forecasting improvement in lemon production in Piura, between 2021 and 2022. La producción agrícola del Citrus x limon (limón) y Mangifera indica (mango) en la región Piura, muchas veces se ve afectada por factores ambientales-climáticos, principalmente por posibles cambios estacionales o eventos climáticos extremos, como las sequías o El Niño. El objetivo es analizar la producción agrícola espacial-temporal del limón y mango, midiendo con el espectroradiómetro FieldSpec4, la firma espectral (FE) e imágenes de satélite Sentinel 2 (ISS2) del mango criollo de Chulucanas en cultivos de Pampa Larga-Alvarados-Suyo-Ayabaca y banco de germoplasma de mango INIA-Hualtaco-Tambogrande-Piura, respectivamente. El método consiste en introducir cada FE en el mosaico de ISS2 (2019), de los tiles 17MMR-17MNR-17MPR-17MMQ-17MNQ-17MPQ-17MMP-17MNP-17MPP, utilizando SEN2COR280 en el software SNAP. Se analizó las series de tiempo de la producción mensual/anual del limón y del mango, con datos del INEI y SIEA-MIDAGRI-PERÚ. Los resultados obtenidos estiman un área cultivada de limón de 27451,84 ha y de mango de 22000 ha; mayores a la superficie cosechada de 16113 ha y 20606 ha reportadas, respectivamente. La producción de mango 1970-2020, es mayor en noviembre-diciembre-enero-febrero, explicada por el área de superficie cosechada en un 84,1%, presentando estacionalidad, comportamiento exponencial de crecimiento y anomalías positivas (2003-2020) y negativas (1970-2002). La producción mensual de limón 2007-2020 es estacional, la tendencia anual incrementa en 2,8% a pesar de existir anomalías negativas el 2017, generada por efectos del “Niño Costero” en su proceso evolutivo de floración; pronosticando mejoría en la producción de limón en Piura, entre el 2021 al 2022.

1 March 2025 in International Soil and Water Conservation Research
Verified
Journal Article
Open access
WMWilmer Moncada
Wilmer Moncada
PPPereda-Medina Pereda-Medina
Pereda-Medina Pereda-Medina
MMManuel Masías
Manuel Masías
MLManuel Lagos
Manuel Lagos
EQEdwin Portal Quicaña
Edwin Portal Quicaña
ENEdwin Arnulfo Saavedra Navarro
Edwin Arnulfo Saavedra Navarro

18 March 2025 in IEEE Sensors Journal
Verified
Journal Article
Closed access
Vinie Lee Silva-AlvaradoVinie Lee Silva-Alvarado
Vinie Lee Silva-Alvarado
FDFrancisco Javier Diaz
Francisco Javier Diaz
Lorena ParraLorena Parra
Lorena Parra
Jaime LloretJaime Lloret
Jaime Lloret
CYCristhian Nicolas Aldana Yarleque
Cristhian Nicolas Aldana Yarleque
YSYesenia Saavedra-Navarro
Yesenia Saavedra-Navarro
The quality of hydrobiological species for human consumption, such as fish and shellfish, is crucial to ensure their safety. This paper highlights the use of MQ sensor modules (MQ-2, MQ-3, MQ-4, MQ-5, MQ-6, MQ-7, MQ-8), along with temperature and humidity, to analyse these species. The prototype is based on the use of an Arduino Mega 2560 Rev3 to connect the sensors with data stored on a Raspberry Pi 4, which can be accessed via Wi-Fi for downloading. Machine learning models were applied to classify and estimate non-refrigeration time with different quantities of variables, using species such as Illex argentinus, Sardina pilchardus, Scomber colias, and Sepia pharaonis. In total, 33 classification models and 28 regression models were employed. The best results were obtained with Boosted Trees model, achieving an accuracy of 99.93% in the validation phase and 99.74% in the testing phase. In the regression models to estimate non-refrigeration time, with 38 variables, the best model was Bagged Trees, with an R-squared of 0.995 for the validation phase and 0.997 for the testing phase.

27 November 2020 in Revista de Teledetección
Verified
Journal Article
Open access
PDF file
CYCristhian Nicolas Aldana Yarleque
Cristhian Nicolas Aldana Yarleque
MRM. Revilla
M. Revilla
JGJ. Gonzales
J. Gonzales
YSYesenia Saavedra-Navarro
Yesenia Saavedra-Navarro
WMWilmer Moncada
Wilmer Moncada
JMJ. Maicelo
J. Maicelo
El Niño phenomenon, droughts and the warm climate directly influence the good ecological state of the forests in the Piura Region. The objective is to relate the spectral signatures evaluated in the Sentinel-2 satellite images with the spectral signatures measured with the FieldSpec4 spectroradiometer, for the identification of dry forest in the lower basin of the Chira River, Piura región. The Sentinel-2 images corresponding to the 17MNR, 17MPR, 17MMQ, 17MNQ and 17MPQ tiles are pre-processed, mosaicked, resampled and cut with the SNAP software. Stacking of bands 2, 3, 4, 5, 6, 7, 8, 9, 11 and 12 generates a raster whose pixel reflectance values are related to their wavelengths. The classification of dry forest areas is done with the spectral signature measured with the FieldSpec4 spectroradiometer. The validation of the results is carried out by applying the non-parametric ANOVA and Mann-Whitney-Wilcoxon tests at four sampling points. The surface area of dry forest in the lower basin of the Chira River is 129 113.06 ha, which represents 3.8% of the total area of dry forest in northern Peru.

14 October 2025 in Discover Food
Verified
Journal Article
Open access
PDF file
KCKarlo Castillo-Zapata
Karlo Castillo-Zapata
PVPriscila Estelita Luján Vera
Priscila Estelita Luján Vera
DLDiego Lachira-Estrada
Diego Lachira-Estrada
YSYesenia Saavedra-Navarro
Yesenia Saavedra-Navarro
VKVicente Amirpasha Tirado Kulieva
Vicente Amirpasha Tirado Kulieva
Native fruits, often adapted to local environments and rich in bioactive compounds, offer untapped potential to enhance food security, dietary diversity, and sustainable development, particularly in biodiversity-rich regions. However, scientific research on these species remains limited and fragmented. This study aimed to map global research trends on native fruits through a bibliometric and text mining analysis of 989 articles indexed in Scopus from 2001 to 2023. Results reveal a steady growth in scientific production, especially in the last decade, driven by the Sustainable Development Goals (SDGs), public health concerns, and the socioeconomic and environmental significance of native species. Brazil stands out as the leading contributor, with notable participation from countries such as Australia, Spain, the United States, and China, supported by international collaboration networks. Research hotspots include genetic studies, cultural valuation, chemical and sensory profiling, phytochemical composition, particularly phenolics and antioxidants, and other functional properties. Despite this progress, several barriers persist: limited species prioritization, knowledge gaps, insufficient processing technologies, lack of compositional data, and underutilization of by-products. The findings offer valuable insights for researchers, policymakers, entrepreneurs, and communities seeking to conserve, utilize, and promote native fruits within sustainable food systems. Graphical Abstract

21 April 2026 in Sensors
Verified
Journal Article
Open access
PDF file
AMABEL DE LA CRUZ MORAN
ABEL DE LA CRUZ MORAN
HLHemerson Lizarbe-Alarcón
Hemerson Lizarbe-Alarcón
WMWilmer Moncada
Wilmer Moncada
VAVICTOR BELLIDO AEDO
VICTOR BELLIDO AEDO
CCCarlos Emilio Carrasco-Badajoz
Carlos Emilio Carrasco-Badajoz
PPPereda-Medina Pereda-Medina
Pereda-Medina Pereda-Medina
Vulnerable road users in informal urban environments confront a distinct set of hazards that standard computer vision datasets are ill-equipped to represent: artisanal speed bumps constructed without regulatory compliance, deteriorated road markings, and the mototaxi—a three-wheeled motorized vehicle that constitutes the primary informal transport mode in intermediate Andean cities yet is absent from all major international repositories. This paper presents QHAWAY—from Quechua qhaway, a transitive verb meaning “to look; to observe”—an Advanced Driver Assistance System (ADAS) predicated on instance segmentation, monocular distance estimation via the pinhole camera model, and Time-to-Collision (TTC) computation, developed for the road environment of Ayacucho, Peru (2761 m a.s.l.), a city recognised by UNESCO as a Creative City of Crafts and Folk Art since 2019. A hybrid dataset comprising 25,602 images with 127,525 annotated instances across 12 classes was assembled by combining an original local collection of 4598 images (10,701 instances) captured through four complementary acquisition methods across the five urban districts of the Huamanga province with three established international datasets (BDD100K, BSTLD, RLMD; 21,004 images, 116,824 instances). A three-phase progressive training strategy with monotonically increasing resolution (640, 800, and 1024 pixels) was evaluated as an ablation study. A multi-architecture comparison spanning YOLOv8L-seg and the YOLO26 family (nano, small, large) identified YOLO26L-seg as the best-performing model, attaining mAP50 Box of 0.829 and mAP50 Mask of 0.788 at epoch 179. The integration of ByteTrack multi-object tracking with the pinhole equation D=(Hreal×f)/hpx delineates operational risk zones aligned with the NHTSA forward collision warning standard (danger: <3 m; caution: 3–7 m; TTC threshold ≤ 2.4 s). The system sustains processing rates of 19.2–25.4 FPS on an NVIDIA RTX 5080 GPU. A systematic field survey established that 96% of the audited speed bumps fail to comply with MTC Directive No. 01-2011-MTC/14, constituting the first quantitative record of informal road infrastructure non-compliance in the Andean region. Validation was conducted under naturalistic driving conditions without staged scenarios. Grad-CAM explainability analysis, encompassing three complementary visualisation algorithms (Grad-CAM, Grad-CAM++, and EigenCAM), confirmed that model attention concentrates consistently on safety-critical objects.