Examinando por Materia "UAV"

Mostrando 1 - 3 de 3

Estimation of height and aerial biomass in Eucalyptus globulus plantations using UAV-LiDAR
(Elsevier B.V., 2024-12-22) Enriquez Pinedo, Lucía; Ortega Quispe, Kevin; Ccopi Trucios, Dennis; Urquizo Barrera, Julio; Rios Chavarría, Claudia; Pizarro Carcausto, Samuel; Matos Calderon, Diana; Patricio Rosales, Solanch; Rodríguez Cerrón, Mauro; Ore Aquino, Zoila; Paz Monge, Michel; Castañeda Tinco, Italo
The lack of precise methods for estimating forest biomass results in both economic losses and incorrect decisions in the management of forest plantations. In response to this issue, this study evaluated the effectiveness of using the DJI Zenmuse L1 LiDAR, mounted on a DJI Matrice 300 RTK UAV, to provide three-dimensional measurements of canopy structure and estimate the aboveground biomass of Eucalyptus globulus. Various LiDAR metrics were employed alongside field measurements to calibrate predictive models using multiple regression and machine learning algorithms. The results at the individual tree level show that RF is the most accurate model, with a coefficient of determination (R²) of 0.76 in the training set and 0.66 in the test set, outperforming Elastic Net (R² of 0.58 and 0.57, respectively). At the plot level, a multiple regression model achieved an R² of 0.647, highlighting LiDAR-derived metrics as key predictors. The findings revealed that the combination of LiDAR with advanced statistical techniques, such as multiple regression and Random Forest, significantly improves the accuracy of biomass estimation, surpassing traditional methods based on allometric equations. Therefore, the use of LiDAR in conjunction with machine learning represents an effective alternative for biomasss estimation, with great potential in such plantations and contribute to more sustainable exploitation of timber resources.
Implementing cloud computing for the digital mapping of agricultural soil properties from high resolution UAV multispectral imagery
(MDPI, 2023-06-20) Pizarro Carcausto, Samuel Edwin; Pricope, Narcisa G.; Figueroa Venegas, Deyanira Antonella; Carbajal Llosa, Carlos Miguel; Quispe Huincho, Miriam Rocío; Vera Vilchez, Jesús Emilio; Alejandro Méndez, Lidiana Rene; Achallma Mendoza, Lino; González Tovar, Izamar Estrella; Salazar Coronel, Wilian; Loayza, Hildo; Cruz Luis, Juancarlos Alejandro; Arbizu Berrocal, Carlos Irvin
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.
Yield predictions of ‘Del Cerro’ cotton (Gossypium hirsutum L.) germplasm by multispectral monitoring in the north coast of Peru
(Instituto de Investigaciones Agropecuarias, INIA, 2025-02-01) Cruz Grimaldo, Camila Leandra; Nieves Rivera, Marite Yulisa; Vera Díaz, Elvis; Durán Gómez, Moisés Rodrigo; Morales Pizarro, Davies Arturo; Salazar Coronel, Willian; Arbizu Berrocal, Carlos Irvin
Peruvian cotton (Gossypium hirsutum L.) has great acceptance and demand in the national and international textile market due to the excellent quality of its extra-long fiber, durability and resistance. To evaluate cotton cultivar performance, we need to use tools such as drones + sensors. However, these tools have not been widely used in the Peruvian agricultural area. Here we evaluated seven agro-morphological characters of 21 accessions of Del Cerro cotton cultivar from the National Institute of Agrarian Innovation of Peru with highthroughput phenotyping methods. We employed a Matrice 300 RTK unmanned aerial vehicle (UAV) with the MicaSense Dual Red Edge Blue multispectral sensor to assess plant height, yield, and spectral signature during physiological maturity stage; other morphological characters were manually scored. Multispectral monitoring revealed the phytosanitary status of the crop, which begins to enter senescence after 130 d after sowing (DAS) due to the decrease of the vegetation indices (VI). Pearson correlations between yield and VI showed favorable values, exceeding 0.60 at 94 DAS for normalized difference vegetation index (NDVI), relative vigor index (RVI), and normalized difference red edge index (NDRE). Principal component analysis (PCA) was conducted on the same date, a significant correlation was found between NDVI and yield. Additionally, yield prediction equations were generated with the normalized difference water index (NDWI) showing an R value of 0.74 at 130 DAS. The findings of this study suggest that remote sensing evaluation is suitable for estimating ‘Del Cerro’ cotton yield in infrared (IR) bands, providing a tool for germplasm evaluation that can influence decision-making and better conservation strategies.