High-Throughput Biomass Estimation in Rice Crops Using UAV Multispectral Imagery

This paper presents a high-throughput method for Above Ground Estimation of Biomass (AGBE) in rice using multispectral near-infrared (NIR) imagery captured at different scales of the crop. By developing an integrated aerial crop monitoring solution using an Unmanned Aerial Vehicle (UAV), our approac...

Full description

Bibliographic Details
Main Authors: Devia, Carlos Andres, Rojas, Juan P., Petro Páez, Eliel Enrique, Martínez, Carol, Mondragon, Iván Fernando, Patino, D., Rebolledo, María Camila, Colorado, J.
Format: Journal Article
Language:Inglés
Published: Springer 2019
Subjects:
Online Access:https://hdl.handle.net/10568/100348
_version_ 1855543298363490304
author Devia, Carlos Andres
Rojas, Juan P.
Petro Páez, Eliel Enrique
Martínez, Carol
Mondragon, Iván Fernando
Patino, D.
Rebolledo, María Camila
Colorado, J.
author_browse Colorado, J.
Devia, Carlos Andres
Martínez, Carol
Mondragon, Iván Fernando
Patino, D.
Petro Páez, Eliel Enrique
Rebolledo, María Camila
Rojas, Juan P.
author_facet Devia, Carlos Andres
Rojas, Juan P.
Petro Páez, Eliel Enrique
Martínez, Carol
Mondragon, Iván Fernando
Patino, D.
Rebolledo, María Camila
Colorado, J.
author_sort Devia, Carlos Andres
collection Repository of Agricultural Research Outputs (CGSpace)
description This paper presents a high-throughput method for Above Ground Estimation of Biomass (AGBE) in rice using multispectral near-infrared (NIR) imagery captured at different scales of the crop. By developing an integrated aerial crop monitoring solution using an Unmanned Aerial Vehicle (UAV), our approach calculates 7 vegetation indices that are combined in the form of multivariable regressions depending on the stage of rice growth: vegetative, reproductive or ripening. We model the relationship of these vegetation indices to estimate the biomass of a certain crop area. The methods are calibrated by using a minimum sampling area of 1 linear meter of the crop. Comprehensive experimental tests have been carried out over two different rice varieties under upland and lowland rice production systems. Results show that the proposed approach is able to estimate the biomass of large areas of the crop with an average correlation of 0.76 compared with the traditional manual destructive method. To our knowledge, this is the first work that uses a small sampling area of 1 linear meter to calibrate and validate NIR image-based estimations of biomass in rice crops.
format Journal Article
id CGSpace100348
institution CGIAR Consortium
language Inglés
publishDate 2019
publishDateRange 2019
publishDateSort 2019
publisher Springer
publisherStr Springer
record_format dspace
spelling CGSpace1003482025-11-12T06:00:23Z High-Throughput Biomass Estimation in Rice Crops Using UAV Multispectral Imagery Devia, Carlos Andres Rojas, Juan P. Petro Páez, Eliel Enrique Martínez, Carol Mondragon, Iván Fernando Patino, D. Rebolledo, María Camila Colorado, J. rice phaseolus vulgaris vegetation biomass This paper presents a high-throughput method for Above Ground Estimation of Biomass (AGBE) in rice using multispectral near-infrared (NIR) imagery captured at different scales of the crop. By developing an integrated aerial crop monitoring solution using an Unmanned Aerial Vehicle (UAV), our approach calculates 7 vegetation indices that are combined in the form of multivariable regressions depending on the stage of rice growth: vegetative, reproductive or ripening. We model the relationship of these vegetation indices to estimate the biomass of a certain crop area. The methods are calibrated by using a minimum sampling area of 1 linear meter of the crop. Comprehensive experimental tests have been carried out over two different rice varieties under upland and lowland rice production systems. Results show that the proposed approach is able to estimate the biomass of large areas of the crop with an average correlation of 0.76 compared with the traditional manual destructive method. To our knowledge, this is the first work that uses a small sampling area of 1 linear meter to calibrate and validate NIR image-based estimations of biomass in rice crops. 2019-12 2019-03-19T15:00:14Z 2019-03-19T15:00:14Z Journal Article https://hdl.handle.net/10568/100348 en Open Access application/pdf Springer Devia, Carlos A.; Rojas, Juan P.; Petro, Eliel; Martinez, Carol; Mondragon, Ivan F.; Patino, D.; Rebolledo, Maria Camila & Colorado, J. (2019). High-Throughput Biomass Estimation in Rice Crops Using UAV Multispectral Imagery, Journal of Intelligent & Robotic Systems. 1-17 p.
spellingShingle rice
phaseolus vulgaris
vegetation
biomass
Devia, Carlos Andres
Rojas, Juan P.
Petro Páez, Eliel Enrique
Martínez, Carol
Mondragon, Iván Fernando
Patino, D.
Rebolledo, María Camila
Colorado, J.
High-Throughput Biomass Estimation in Rice Crops Using UAV Multispectral Imagery
title High-Throughput Biomass Estimation in Rice Crops Using UAV Multispectral Imagery
title_full High-Throughput Biomass Estimation in Rice Crops Using UAV Multispectral Imagery
title_fullStr High-Throughput Biomass Estimation in Rice Crops Using UAV Multispectral Imagery
title_full_unstemmed High-Throughput Biomass Estimation in Rice Crops Using UAV Multispectral Imagery
title_short High-Throughput Biomass Estimation in Rice Crops Using UAV Multispectral Imagery
title_sort high throughput biomass estimation in rice crops using uav multispectral imagery
topic rice
phaseolus vulgaris
vegetation
biomass
url https://hdl.handle.net/10568/100348
work_keys_str_mv AT deviacarlosandres highthroughputbiomassestimationinricecropsusinguavmultispectralimagery
AT rojasjuanp highthroughputbiomassestimationinricecropsusinguavmultispectralimagery
AT petropaezelielenrique highthroughputbiomassestimationinricecropsusinguavmultispectralimagery
AT martinezcarol highthroughputbiomassestimationinricecropsusinguavmultispectralimagery
AT mondragonivanfernando highthroughputbiomassestimationinricecropsusinguavmultispectralimagery
AT patinod highthroughputbiomassestimationinricecropsusinguavmultispectralimagery
AT rebolledomariacamila highthroughputbiomassestimationinricecropsusinguavmultispectralimagery
AT coloradoj highthroughputbiomassestimationinricecropsusinguavmultispectralimagery