What does this research mean for the field?

A Multilayer Perceptron Artificial Neural Network (MLP) integrating satellite imagery and field data provides the most accurate estimation of Kikuyu grass biomass in high-altitude tropical farms (R² = 0.7), with NDVI, forage age, and CIGreen being the strongest predictors. Novelty: ClaimNovelty.INCREMENTAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To evaluate and compare the accuracy of four regression models for estimating Kikuyu grass (Cenchrus clandestinus) biomass by integrating satellite imagery, agroclimatic variables, and field data.

August 27, 2026Chilean journal of agricultural researchOpen Access

Comparison of models estimating biomass in Cenchrus clandestinus (Hochst. ex Chiov.) Morrone pastures at high-altitude tropical farms

View Full Paper

Ask AI

Bookmark

Authors

MSMayerling Sanabria-Buitrago MVMartha Patricia Valbuena-Gaona JTJorge Fernando Triana-Valenzuela

Discussion

Member takes

Overview

Comparative modeling analysis demonstrates superior pasture biomass estimation using neural networks in high-altitude tropical grazing systems, suggesting improved precision in livestock management.

Key Points

To evaluate and compare the accuracy of four regression models for estimating Kikuyu grass (Cenchrus clandestinus) biomass by integrating satellite imagery, agroclimatic variables, and field data.
Combined PlanetScope satellite imagery with field-collected variables, including forage age, forage type, ambient temperature, relative humidity, precipitation, and vegetation spectral indices.
Evaluated four predictive modeling approaches: Generalized Linear Model with Poisson distribution, Multiple Linear Regression, Multilayer Perceptron (MLP) Artificial Neural Network, and Random Forest Regression.
The Multilayer Perceptron (MLP) artificial neural network achieved the highest predictive accuracy among all evaluated models (R² = 0.7).
Variable importance analysis identified the Green Normalized Difference Vegetation Index (NDVI), forage age, and the Green Chlorophyll Index (CIGreen) as the most influential predictors of forage biomass.

Cite This Study

Sanabria-Buitrago et al. (2026) studied this question.

synapsesocial.com/papers/6a8fe9ad10c91c1e926217e2 https://doi.org/10.4067/s0718-58392026000500668

View Full Paper

Ask AI

Bookmark

August 27, 2026Chilean journal of agricultural researchOpen Access

Comparison of models estimating biomass in Cenchrus clandestinus (Hochst. ex Chiov.) Morrone pastures at high-altitude tropical farms

View Full Paper

Ask AI

Bookmark

Authors

MSMayerling Sanabria-Buitrago MVMartha Patricia Valbuena-Gaona JTJorge Fernando Triana-Valenzuela

Discussion

Member takes

Overview

Comparative modeling analysis demonstrates superior pasture biomass estimation using neural networks in high-altitude tropical grazing systems, suggesting improved precision in livestock management.

Key Points

To evaluate and compare the accuracy of four regression models for estimating Kikuyu grass (Cenchrus clandestinus) biomass by integrating satellite imagery, agroclimatic variables, and field data.
Combined PlanetScope satellite imagery with field-collected variables, including forage age, forage type, ambient temperature, relative humidity, precipitation, and vegetation spectral indices.
Evaluated four predictive modeling approaches: Generalized Linear Model with Poisson distribution, Multiple Linear Regression, Multilayer Perceptron (MLP) Artificial Neural Network, and Random Forest Regression.
The Multilayer Perceptron (MLP) artificial neural network achieved the highest predictive accuracy among all evaluated models (R² = 0.7).
Variable importance analysis identified the Green Normalized Difference Vegetation Index (NDVI), forage age, and the Green Chlorophyll Index (CIGreen) as the most influential predictors of forage biomass.

Cite This Study

Sanabria-Buitrago et al. (2026) studied this question.

synapsesocial.com/papers/6a8fe9ad10c91c1e926217e2 https://doi.org/10.4067/s0718-58392026000500668

View Full Paper

Ask AI

Bookmark