Examinando por Autor "Goycochea Casas, Gianmarco"

Mostrando 1 - 5 de 5

Caracterización y diferencias anatómicas de maderas de Retrophyllum rospigliosii (Pilg.) C.N. Page y Prumnopitys harmsiana (Pilg.) de Laub. (Podocarpaceae) procedentes de la provincia de San Ignacio, Perú
(Instituto de Investigaciones de la Amazonía Peruana, 2021-12-31) Baselly Villanueva, Juan Rodrigo; Goycochea Casas, Gianmarco; Macedo Ledeira Carvalho, Ana Marcia; Roncal Briones, Wálter Ricardo; Chumbimune Vivanco, Sheyla Yanett; Chavesta Custodio, Manuel
Las especies Retrophyllum rospigliosii (Pilg.) C. N. Page (Romerillo hembra) y Prumnopitys harmsiana (Pilg.) de Laub. (Romerillo macho) son coníferas nativas del Perú y forman parte importante de los bosques nublados del Departamento de Cajamarca. Sus maderas son solicitadas en el mercado local para obras de carpintería, debido a las propiedades físico mecánicas y buen acabado; sin embargo, información sobre la estructura microscópica es escasa. El presente trabajo tuvo como objetivo caracterizar y determinar las diferencias anatómicas de la madera de las dos especies y así ampliar el conocimiento de sus estructuras. Se obtuvieron muestras por método no destructivo, preparadas y estudiadas mediante la microtomía y maceración; cuya descripción se realizó utilizando la norma del IAWA. La principal característica cualitativa que permite diferenciarlas es la presencia de parénquima difuso en Retrophyllum rospigliosii y ausente en Prumnopitys harmsiana.
Classifying the risk of forest loss in the Peruvian amazon rainforest: An alternative approach for sustainable forest management using artificial intelligence
(Elsevier, 2023-09-21) Goycochea Casas, Gianmarco; Baselly Villanueva, Juan Rodrigo; Coimbra Limeira, Mathaus Messias; Eleto Torres, Carlos Moreira Miquelino; Garcia Leite, Hélio
Peruvian Amazonian rainforests are constantly threatened by forest loss. Understanding changes in forest cover and assessing the level of risk is a permanent concern for numerous scientists and forest authorities. There are many conservation programs for Peruvian forests that involve collaborative efforts and employ diverse methodologies for forest monitoring. In this study, we propose an alternative approach to decision-making for forest preservation, aiming to classify the risk of forest loss in districts within the Peruvian Amazon rainforest. This classification enables sustainable forest management. To accomplish this, we utilized unsupervised learning artificial intelligence through Kohonen's neural network. The network was trained using a historical database spanning from 2001 to 2021, which includes variables such as forest cover and loss, climate, topography, hydrographic networks, and timber forest concessions. Through this approach, the network successfully established five clusters. Following preliminary analysis, we designated these clusters as: low, medium, high, very high, and extremely high risk of forest loss. Kohonen networks demonstrated their effectiveness in clustering forest loss and forest cover. The results indicate a shifting trend among the classes over time, with an increase in the categories exhibiting high and very high risk of forest cover loss. This study provides valuable information for decision-making in the prevention and conservation of Peruvian forests. We strongly recommend maintaining vigilance, particularly in districts classified as a very high or extremely high risk of losing forest cover.
Configuration of the deep neural network hyperparameters for the hypsometric modeling of the Guazuma crinita Mart. in the Peruvian Amazon
(MDPI, 2022-04-29) Goycochea Casas, Gianmarco; Elera Gonzáles, Duberlí Geomar; Baselly Villanueva, Juan Rodrigo; Pereira Fardin, Leonardo; Garcia Leite, Hélio
The Guazuma crinita Mart. is a dominant species of great economic importance for the inhabitants of the Peruvian Amazon, standing out for its rapid growth and being harvested at an early age. Understanding its vertical growth is a challenge that researchers have continued to study using different hypsometric modeling techniques. Currently, machine learning techniques, especially artificial neural networks, have revolutionized modeling for forest management, obtaining more accurate predictions; it is because we understand that it is of the utmost importance to adapt, evaluate and apply these methods in this species for large areas. The objective of this study was to build and evaluate the efficiency of the use of a deep neural network for the prediction of the total height of Guazuma crinita Mart. from a large-scale continuous forest inventory. To do this, we explore different configurations of the hidden layer hyperparameters and define the variables according to the function HT = f(x) where HT is the total height as the output variable and x is the input variable(s). Under this criterion, we established three HT relationships: based on the diameter at breast height (DBH), (i) HT = f(DBH); based on DBH and Age, (ii) HT = f(DBH, Age) and based on DBH, Age and Agroclimatic variables, (iii) HT = f(DBH, Age, Agroclimatology), respectively. In total, 24 different configuration models were established for each function, concluding that the deep artificial neural network technique presents a satisfactory performance for the predictions of the total height of Guazuma crinita Mart. for modeling large areas, being the function based on DBH, Age and agroclimatic variables, with a performance validation of RMSE = 0.70, MAE = 0.50, bias% = −0.09 and VAR = 0.49, showed better accuracy than the others.
MultiProduct Optimization of Cedrelinga cateniformis (Ducke) Ducke in Different Plantation Systems in the Peruvian Amazon
(MDPI, 2025-01-16) Baselly Villanueva, Juan Rodrigo; Fernández Sandoval, Andrés; Salazar Hinostroza, Evelin Judith; Cárdenas-Rengifo, Gloria Patricia; Puerta, Ronald; Chuquizuta Trigoso, Tony Steven; Rufasto Peralta, Yennifer Lisbeth; Vallejos Torres, Geomar; Goycochea Casas, Gianmarco; Araújo Junior, Carlos Alberto; Quiñónez Barraza, Gerónimo; Álvarez Álvarez, Pedro; Garcia Leite, Helio
This study addressed multi-product optimization in Cedrelinga cateniformis plantations in the Peruvian Amazon, aiming to maximize volumetric yields of logs and sawn lumber. Data from seven plantations of different ages and types, established on degraded land, were analyzed by using ten stem profile models to predict taper and optimize wood use. In addition, the structure of each plantation was evaluated using diameter distributions and height–diameter ratios; log and sawn timber production was optimized using SigmaE 2.0 software. The Garay model proved most effective, providing high predictive accuracy (adjusted R2 values up to 0.963) and biological realism. Marked differences in volumetric yield were observed between plantations: older and more widely spaced plantations produced higher timber volumes. Logs of optimal length (1.83–3.05 m) and larger dimension wood (e.g., 25.40 × 5.08 cm) were identified as key contributors to maximizing volumetric yields. The highest yields were observed in mature plantations, in which the total log volume reached 508.1 m3ha−1 and the sawn lumber volume 333.6 m3ha−1 . The findings demonstrate the power of data-driven decision-making in the timber industry. By combining precise modeling and optimization techniques, we developed a framework that enables sawmill operators to maximize log and lumber yields. The insights gained from this research can be used to improve operational efficiency and reduce waste, ultimately leading to increased profitability. These practices promote support for smallholders and the forestry industry while contributing to the long-term development of the Peruvian Amazon.
Relación de los factores ambientales con la productividad de Eucalyptus globulus en los Andes norperuanos
(Facultad de Ciencias Forestales Universidad Austral de Chile, 2024-06-03) Baselly Villanueva, Juan Rodrigo; Marcelo Bazán, Fátima Elizabeth; Goycochea Casas, Gianmarco; Lozano Lozano, Andrés Ibernón; Castedo Dorado, Fernando; Álvarez Álvarez, Pedro
Los Andes sudamericanos son un conjunto de montañas, generan una diversidad de climas. Eucalyptus globulus ha sido instalado en muchas laderas de los Andes norperuanos a elevadas altitudes (como por ejemplo en Cajamarca - Perú), desconociéndose su crecimiento y viabilidad productiva. En el presente estudio se establecieron los siguientes objetivos: i) elaborar curvas de Índice de Sitio para masas de Eucalyptus globulus situadas en los Andes peruanos sobre los 3.000 metros de altitud, ii) analizar la relación entre variables ambientales y el Índice de Sitio y iii) evaluar el efecto potencial del frío en el crecimiento de estas masas en comparación con las de otras regiones. El Índice de Sitio (IS) fue estimado usando tres modelos base de crecimiento (Bertalanffy-Richards, Hossfeld y Korf) y dos métodos de derivación (Diferencias Algebraicas – ADA y Diferencias Algebraicas Generalizadas – GADA). La relación entre los factores ambientales y el IS se determinó mediante el coeficiente de correlación de Spearman. El efecto potencial de la altitud se evaluó comparando las curvas de calidad de sitio obtenidas con las de otras regiones. La ecuación dinámica derivada del modelo de Bertalanffy-Richards mediante GADA explicó gran parte de la variabilidad del crecimiento en altura dominante. El IS presentó buena correlación con la distancia a cuerpos de agua y en menor grado con la radiación solar, profundidad efectiva y saturación de bases. Además, en comparación con otras regiones, se evidenció un lento crecimiento en la etapa inicial de la plantación, probablemente debido al efecto de aclimatación al frío (derivado de la elevada altitud).