Samuel Pizarro

Mr. Samuel Pizarro

Instituto Nacional de Innovacion Agraria (INIA), Lima, Peru
orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
24 March 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Samuel PizarroSamuel Pizarro
Samuel Pizarro
NARCISA PRICOPENARCISA PRICOPE
NARCISA PRICOPE
DVDaniella Vargas-Machuca
Daniella Vargas-Machuca
OHOlwer Huanca
Olwer Huanca
JNJavier A Naupari
Javier A Naupari
Highland Andean ecosystems sustain high levels of floral and faunal biodiversity in areas with diverse topography and provide varied ecosystem services, including the supply of water to cities and downstream agricultural valleys. Google (™) has developed a product specifically designed for mapping purposes (Earth Engine), which enables users to harness the computing power of a cloud-based solution in near-real time for land cover change mapping and monitoring. We explore the feasibility of using this platform for mapping land cover types in topographically complex terrain with highly mixed vegetation types (Nor Yauyos Cochas Landscape Reserve located in the central Andes of Peru) using classification machine learning (ML) algorithms in combination with different sets of remote sensing data. The algorithms were trained using 3601 sampling pixels of (a) normalized spectral bands between the visible and near infrared spectrum of the Landsat 8 OLI sensor for the 2018 period, (b) spectral indices of vegetation, soil, water, snow, burned areas and bare ground and (c) topographic-derived indices (elevation, slope and aspect). Six ML algorithms were tested, including CART, random forest, gradient tree boosting, minimum distance, naïve Bayes and support vector machine. The results reveal that ML algorithms produce accurate classifications when spectral bands are used in conjunction with topographic indices, resulting in better discrimination among classes with similar spectral signatures such as pajonal (tussock grass-dominated cover) and short grasses or rocky groups, and moraines, agricultural and forested areas. The model with the highest explanatory power was obtained from the combination of spectral bands and topographic indices using the random forest algorithm (Kappa = 0.81). Our study presents a first approach of its kind in topographically complex Cordilleran terrain and we show that GEE is particularly useful in large-scale land cover mapping and monitoring in mountainous ecosystems subject to rapid changes and conversions, with replicability and scalability to other areas with similar characteristics.

20 June 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Samuel PizarroSamuel Pizarro
Samuel Pizarro
NARCISA PRICOPENARCISA PRICOPE
NARCISA PRICOPE
DFDeyanira Figueroa
Deyanira Figueroa
CCCarlos Carbajal
Carlos Carbajal
MHMiriam Rocio Quispe Huincho
Miriam Rocio Quispe Huincho
Carlos ArbizuCarlos Arbizu
Carlos Arbizu
The spatial heterogeneity of soil properties has a significant impact on crop growth, making it difficult to adopt site-specific crop management practices. Traditional laboratory-based analyses are costly, and data extrapolation for mapping soil properties using high-resolution imagery becomes a computationally expensive procedure, taking days or weeks to obtain accurate results using a desktop workstation. To overcome these challenges, cloud-based solutions such as Google Earth Engine (GEE) have been used to analyze complex data with machine learning algorithms. In this study, we explored the feasibility of designing and implementing a digital soil mapping approach in the GEE platform using high-resolution reflectance imagery derived from a thermal infrared and multispectral camera Altum (MicaSense, Seattle, WA, USA). We compared a suite of multispectral-derived soil and vegetation indices with in situ measurements of physical-chemical soil properties in agricultural lands in the Peruvian Mantaro Valley. The prediction ability of several machine learning algorithms (CART, XGBoost, and Random Forest) was evaluated using R2, to select the best predicted maps (R2 > 0.80), for ten soil properties, including Lime, Clay, Sand, N, P, K, OM, Al, EC, and pH, using multispectral imagery and derived products such as spectral indices and a digital surface model (DSM). Our results indicate that the predictions based on spectral indices, most notably, SRI, GNDWI, NDWI, and ExG, in combination with CART and RF algorithms are superior to those based on individual spectral bands. Additionally, the DSM improves the model prediction accuracy, especially for K and Al. We demonstrate that high-resolution multispectral imagery processed in the GEE platform has the potential to develop soil properties prediction models essential in establishing adaptive soil monitoring programs for agricultural regions.

18 August 2021 in Water
Verified
Journal Article
Open access
PDF file
María CustodioMaría Custodio
María Custodio
Anthony FowAnthony Fow
Anthony Fow
FZFERNAN COSME CHANAME ZAPATA
FERNAN COSME CHANAME ZAPATA
EOEdith Orellana
Edith Orellana
Richard PeñalozaRichard Peñaloza
Richard Peñaloza
Samuel PizarroSamuel Pizarro
Samuel Pizarro
In this study, the quality of sediment and surface water in two natural wetlands, Paca and Tragadero, in the central region of Peru was evaluated using pollution indices, including the geoaccumulation index, pollutant load index, modified pollution degree, potential ecological risk index, and site rank index, for four heavy metals. Principal component analysis was used to identify potential metal contaminant sources. The determination of Fe, Zn, Pb, and As was performed by flame atomic absorption spectrophotometry. The average concentrations of metals in the sediments of both lagoons decreased in the order Fe > Zn > Pb > As. The analysis of the contamination indices determined that As and Pb are the elements that contribute the most to environmental degradation in both wetlands. There is a strong correlation between the values of potential ecological risk and the modified degree of contamination, revealing that the Paca wetland has a moderate degree of contamination and potential ecological risk, while Tragadero presents a high degree of contamination and considerable potential ecological risk. The application of the site rank index showed that more than 50% of the sampling sites have between high and severe contamination. The principal component analysis presented 79.2% of the total variance. Finally, the results of this study are essential in order to carry out preventive actions for environmental protection in these lake ecosystems of great importance for many activities, such as bird watching.

1 September 2018 in Egyptian Journal of Aquatic Research
Verified
Journal Article
Open access
María CustodioMaría Custodio
María Custodio
FZFERNAN COSME CHANAME ZAPATA
FERNAN COSME CHANAME ZAPATA
Samuel PizarroSamuel Pizarro
Samuel Pizarro
DFDANNY JULIO CRUZ FLORES
DANNY JULIO CRUZ FLORES

31 October 2023 in Sustainability
Verified
Journal Article
Open access
PDF file
Deyvis Jefferson CanoDeyvis Jefferson Cano
Deyvis Jefferson Cano
Samuel PizarroSamuel Pizarro
Samuel Pizarro
Carlos CacciuttoloCarlos Cacciuttolo
Carlos Cacciuttolo
Richard PeñalozaRichard Peñaloza
Richard Peñaloza
RAUL MARINO YARANGARAUL MARINO YARANGA
RAUL MARINO YARANGA
MGMarcelo Luciano Gandini
Marcelo Luciano Gandini
The high-Andean vegetation ecosystems of the Bombón Plateau in Peru face increasing degradation due to aggressive anthropogenic land use and the climate change scenario. The lack of historical degradation evolution information makes implementing adaptive monitoring plans in these vulnerable ecosystems difficult. Remote sensor technology emerges as a fundamental resource to fill this gap. The objective of this article was to analyze the degradation of vegetation in the Bombón Plateau over almost four decades (1985–2022), using high spatiotemporal resolution data from the Landsat 5, 7, and 8 sensors. The methodology considers: (i) the use of the atmosphere resistant vegetation index (ARVI), (ii) the implementation of non-parametric Mann–Kendall trend analysis per pixel, and (iii) the affected vegetation covers were determined by supervised classification. This article’s results show that approximately 13.4% of the total vegetation cover was degraded. According to vegetation cover types, bulrush was degraded by 21%, tall grass by 18%, cattails by 16%, wetlands by 14%, and puna grass by 13%. The Spearman correlation (p < 0.01) determined that degraded covers are replaced by puna grass and change factors linked with human activities. Finally, this article concludes that part of the vegetation degradation is related to anthropogenic activities such as agriculture, overgrazing, urbanization, and mining. However, the possibility that environmental factors have influenced these events is recognized.

16 September 2025 in Toxics
Verified
Journal Article
Open access
PDF file
María CustodioMaría Custodio
María Custodio
Samuel PizarroSamuel Pizarro
Samuel Pizarro
JJavier Alberto Huarcaya Quintana
Javier Alberto Huarcaya Quintana
Kevin Abner Ortega QuispeKevin Abner Ortega Quispe
Kevin Abner Ortega Quispe
Dennis Ccopi TruciosDennis Ccopi Trucios
Dennis Ccopi Trucios
Heavy metal contamination in rivers is a serious environmental and public health concern, especially in areas affected by mining. This study evaluated the levels of contamination and the associated ecological and carcinogenic risks in the sediments of the Cunas River, located in the central highlands of Peru. Sediment samples were collected from upstream and downstream sections. Several metals and metalloids were analyzed, including copper (Cu), chromium (Cr), iron (Fe), manganese (Mn), molybdenum (Mo), nickel (Ni), lead (Pb), vanadium (V), zinc (Zn), antimony (Sb), arsenic (As), and cadmium (Cd). The ecological risk assessment focused on ten of these elements, while carcinogenic and non-carcinogenic risks were assessed for seven metals selected based on their toxicological importance. The results showed that Cd and Pb concentrations were higher in the downstream section. Cd and As exceeded ecological risk thresholds. Regarding human health, As and Pb surpassed the acceptable limits for both the Hazard Index (HI) and the Potential Carcinogenic Risk (PCR). According to EPA guidelines, these values indicate a potentially significant lifetime cancer risk. The main exposure routes include direct contact with sediments and the consumption of aquatic organisms. Continuous monitoring, phytoremediation actions, and restrictions on the use of contaminated water are strongly recommended to reduce ecological and health risks.