Carlos Carbajal

Mr. Carlos Carbajal

Instituto Nacional de Innovación Agraria, Lima, Peru

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
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.

13 December 2024 in Agriculture
Verified
Journal Article
Open access
PDF file
KMKenyi Rolando Quispe Matos
Kenyi Rolando Quispe Matos
SMSharon Yahaira Mejia Maita
Sharon Yahaira Mejia Maita
CCCarlos Carbajal
Carlos Carbajal
LMLidiana Lidiana Alejandro Alejandro Méndez
Lidiana Lidiana Alejandro Alejandro Méndez
PMPatricia Verástegui Martínez
Patricia Verástegui Martínez
Richard Andi SolórzanoRichard Andi Solórzano
Richard Andi Solórzano
Soil acidity is a major limiting factor for potato production in Peru’s high Andean region. This study aims to predict the spatial variability of soil acidity as a fundamental tool for recommending site-specific liming treatments and to identify the physical–chemical characteristics most closely related to soil acidity. The soil samples were collected from five locations in the province of Pachitea, Huánuco. Descriptive statistics, principal component analysis (PCA), and Pearson correlation analysis were used to identify the soil properties contributing most to total variance and those most strongly correlated with soil acidity. The ordinary geostatistical kriging method evaluated the predictive accuracy for 23 soil properties and liming requirements over a 28,463 ha area, at a spatial resolution of 10 m. Results showed that the Plaza Punta and Buenos Aires locations had more degraded acidic soils, with frequencies between 55% and 100% above the general mean (30.94 ± 24.87%) and the critical threshold (25%) for potato cultivation. Variables such as exchangeable calcium percentage (ECP), Ca2+, Mg2+, sand content, and organic matter strongly correlated with soil acidity, while exchangeable H+ and ECP were the main contributors to the total variance. Geostatistical analysis revealed that Mg2+ and Ca2+ had the highest R2 values (0.87 and 0.76, respectively), indicating a strong fit between observed and predicted values in the spatial analysis of soil acidity. It is concluded that the agricultural dolomite requirements in the localities of Plaza Punta and Buenos Aires exhibit high spatial predictability. Additionally, the analysis of diverse soil physicochemical properties is emphasized as critical for determining precise application rates.

6 November 2025 in Frontiers in Soil Science
Verified
Journal Article
Open access
PDF file
CCCarlos Carbajal
Carlos Carbajal
ABAntony Barja
Antony Barja
SPSamuel Pizarro
Samuel Pizarro
In agricultural systems, soil pH and electrical conductivity (EC) are crucial chemical properties that directly affect nutrient availability and microbial activity, but the challenging environment of the Peruvian Andes has limited research on their estimation. This study aimed to develop an ensemble learning method to predict soil pH and EC in Andean agroecosystems using environmental predictors. By using simple and weighted averaging, we developed a heterogeneous ensemble learning approach that integrates machine learning (ML) algorithms, including Support Vector Machine (SVM), Artificial Neural Network (ANN), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). The weighted ensemble assigns weights to models based on their predictive accuracy, measured by R² from spatial cross-validation. Spatial patterns are noticeable, and pH displays greater spatial clustering than EC. Elevation was the most important predictor in ML models for both parameters. Ensemble models significantly outperformed individual models, with the weighted ensemble achieving R² >0.93 and reducing RMSE by approximately 72%. Among standalone models, RF and XGBoost performed best for pH, while SVM performed the best for EC. ANN models were the least effective. Uncertainty analysis indicated high confidence in pH predictions but moderate to high uncertainty in EC predictions, suggesting that EC is more challenging to predict. Ensemble models with optimized weighting provide robust and accurate mapping of spatially autocorrelated soil properties. The high-confidence pH maps are reliable for soil management decisions, while EC predictions, though more uncertain, effectively identify priority areas for future sampling and investigation.

17 January 2025 in Frontiers in Soil Science
Verified
Journal Article
Open access
PDF file
Richard Andi SolórzanoRichard Andi Solórzano
Richard Andi Solórzano
MCMirella Chanco
Mirella Chanco
MSMartín Seminario
Martín Seminario
RCRita Cabello-Torres
Rita Cabello-Torres
VCVladimir Camel
Vladimir Camel
CTCecilia Turín
Cecilia Turín
Introduction: Monoculture is a significant concern due to its negative impact on soil quality, resource productivity, and agricultural sustainability, particularly in vulnerable communities. This research aims to evaluate high Andean soil management for maca monoculture.Materials and methods: To this end, interviews were conducted with maca farmers adjacent to Lake Chinchaycocha. The effect on soil quality was evaluated based on principal component analysis (PCA), weighted soil quality index (SQIw), and physico-chemical characteristics.Results: The results indicated differences between farmers in agronomic management, monoculture period (from 5 to 9 years), and fallow time (up to 10 years in the best cases). Regarding soil quality, the PCA highlighted boron and total nitrogen locations in the same quadrant, with the highest contribution to the analysis. Finally, the SQIw showed that soils without maca cultivation presented better quality.Conclusion: This research’s results indicate a need to optimize soil management practices, especially for small farmers, who are the most vulnerable group. In addition, further studies on boron and nitrogen availability in soils cultivated with maca are required, emphasizing areas that exceed 10 years of continuous use.

3 May 2025 in Soil Security
Verified
Journal Article
Open access
CCCarlos Carbajal
Carlos Carbajal
FMFernanda Moya-Ambrosio
Fernanda Moya-Ambrosio
ABAntony Barja
Antony Barja
EOElvis Ottos-Diaz
Elvis Ottos-Diaz
CACinthya Aguilar-Tito
Cinthya Aguilar-Tito
RSRichard Solórzano-Acosta
Richard Solórzano-Acosta

21 October 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
KMKenyi Rolando Quispe Matos
Kenyi Rolando Quispe Matos
SMSharon Yahaira Mejia Maita
Sharon Yahaira Mejia Maita
CCCarlos Carbajal
Carlos Carbajal
LMLidiana Lidiana Alejandro Alejandro Méndez
Lidiana Lidiana Alejandro Alejandro Méndez
PMPatricia Verástegui Martínez
Patricia Verástegui Martínez
Richard Andi SolórzanoRichard Andi Solórzano
Richard Andi Solórzano
Soil acidity is a major limiting factor for potato production in Peru's high Andean region. Predicting the spatial variability of acidity is essential for recommending site-specific liming treatments. A total of 90 soil samples, taken from a depth of 0-30 cm, were collected from five locations in the province of Pachitea, Huánuco. Descriptive statistics, principal component analysis (PCA), and Pearson correlation analysis were used to identify the soil properties contributing most to total variance and those most strongly correlated with soil acidity. The ordinary geostatistical kriging method evaluated the predictive accuracy for 23 soil properties and liming requirements over a 28,463-ha area. Results showed that the Plaza Punta and Buenos Aires locations had more de-graded acidic soils, with frequencies between 55% and 100% above the general mean (30.94 ± 24.87%) and the critical threshold (25%) for potato cultivation. Variables such as exchangeable calcium percentage (ECP), Ca²⁺, Mg²⁺, sand content, and organic matter strongly correlated with soil acidity, while exchangeable H⁺ and ECP were the main contributors to the total variance. Ge-ostatistical analysis revealed that Mg²⁺ and Ca²⁺ had the highest R² values (0.87 and 0.76, respec-tively), indicating a strong fit between observed and predicted values in the spatial analysis of soil acidity. The spatial analysis predicted a liming requirement for a 28,463-ha area, ranging from 2 to 14 t∙ha⁻¹ of dolomite.