Using sentinel-2 satellite images and machine learning algorithms to predict tropical pasture forage mass, crude protein, and fiber content
Abstract Grasslands cover approximately 24% of the Earth’s surface and are the main feed source for cattle and other ruminants. Sustainable and efficient grazing systems require regular monitoring of the quantity and nutritive value of pastures. This study demonstrates the potential of estimating pa...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2024-04-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-024-59160-x |
_version_ | 1797199565233848320 |
---|---|
author | Marcia Helena Machado da Rocha Fernandes Jalme de Souza FernandesJunior Jordan Melissa Adams Mingyung Lee Ricardo Andrade Reis Luis Orlindo Tedeschi |
author_facet | Marcia Helena Machado da Rocha Fernandes Jalme de Souza FernandesJunior Jordan Melissa Adams Mingyung Lee Ricardo Andrade Reis Luis Orlindo Tedeschi |
author_sort | Marcia Helena Machado da Rocha Fernandes |
collection | DOAJ |
description | Abstract Grasslands cover approximately 24% of the Earth’s surface and are the main feed source for cattle and other ruminants. Sustainable and efficient grazing systems require regular monitoring of the quantity and nutritive value of pastures. This study demonstrates the potential of estimating pasture leaf forage mass (FM), crude protein (CP) and fiber content of tropical pastures using Sentinel-2 satellite images and machine learning algorithms. Field datasets and satellite images were assessed from an experimental area of Marandu palisade grass (Urochloa brizantha sny. Brachiaria brizantha) pastures, with or without nitrogen fertilization, and managed under continuous stocking during the pasture growing season from 2016 to 2020. Models based on support vector regression (SVR) and random forest (RF) machine-learning algorithms were developed using meteorological data, spectral reflectance, and vegetation indices (VI) as input features. In general, SVR slightly outperformed the RF models. The best predictive models to estimate FM were those with VI combined with meteorological data. For CP and fiber content, the best predictions were achieved using a combination of spectral bands and meteorological data, resulting in R2 of 0.66 and 0.57, and RMSPE of 0.03 and 0.04 g/g dry matter. Our results have promising potential to improve precision feeding technologies and decision support tools for efficient grazing management. |
first_indexed | 2024-04-24T07:17:46Z |
format | Article |
id | doaj.art-c18bcf4ebc8b461594b34479edb81a52 |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-04-24T07:17:46Z |
publishDate | 2024-04-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-c18bcf4ebc8b461594b34479edb81a522024-04-21T11:14:41ZengNature PortfolioScientific Reports2045-23222024-04-0114111410.1038/s41598-024-59160-xUsing sentinel-2 satellite images and machine learning algorithms to predict tropical pasture forage mass, crude protein, and fiber contentMarcia Helena Machado da Rocha Fernandes0Jalme de Souza FernandesJunior1Jordan Melissa Adams2Mingyung Lee3Ricardo Andrade Reis4Luis Orlindo Tedeschi5Department of Animal Science, Sao Paulo State University (UNESP)Sigfarm Intelligence LLCDepartment of Animal Science, Texas A&M UniversityDepartment of Animal Science, Texas A&M UniversityDepartment of Animal Science, Sao Paulo State University (UNESP)Department of Animal Science, Texas A&M UniversityAbstract Grasslands cover approximately 24% of the Earth’s surface and are the main feed source for cattle and other ruminants. Sustainable and efficient grazing systems require regular monitoring of the quantity and nutritive value of pastures. This study demonstrates the potential of estimating pasture leaf forage mass (FM), crude protein (CP) and fiber content of tropical pastures using Sentinel-2 satellite images and machine learning algorithms. Field datasets and satellite images were assessed from an experimental area of Marandu palisade grass (Urochloa brizantha sny. Brachiaria brizantha) pastures, with or without nitrogen fertilization, and managed under continuous stocking during the pasture growing season from 2016 to 2020. Models based on support vector regression (SVR) and random forest (RF) machine-learning algorithms were developed using meteorological data, spectral reflectance, and vegetation indices (VI) as input features. In general, SVR slightly outperformed the RF models. The best predictive models to estimate FM were those with VI combined with meteorological data. For CP and fiber content, the best predictions were achieved using a combination of spectral bands and meteorological data, resulting in R2 of 0.66 and 0.57, and RMSPE of 0.03 and 0.04 g/g dry matter. Our results have promising potential to improve precision feeding technologies and decision support tools for efficient grazing management.https://doi.org/10.1038/s41598-024-59160-x |
spellingShingle | Marcia Helena Machado da Rocha Fernandes Jalme de Souza FernandesJunior Jordan Melissa Adams Mingyung Lee Ricardo Andrade Reis Luis Orlindo Tedeschi Using sentinel-2 satellite images and machine learning algorithms to predict tropical pasture forage mass, crude protein, and fiber content Scientific Reports |
title | Using sentinel-2 satellite images and machine learning algorithms to predict tropical pasture forage mass, crude protein, and fiber content |
title_full | Using sentinel-2 satellite images and machine learning algorithms to predict tropical pasture forage mass, crude protein, and fiber content |
title_fullStr | Using sentinel-2 satellite images and machine learning algorithms to predict tropical pasture forage mass, crude protein, and fiber content |
title_full_unstemmed | Using sentinel-2 satellite images and machine learning algorithms to predict tropical pasture forage mass, crude protein, and fiber content |
title_short | Using sentinel-2 satellite images and machine learning algorithms to predict tropical pasture forage mass, crude protein, and fiber content |
title_sort | using sentinel 2 satellite images and machine learning algorithms to predict tropical pasture forage mass crude protein and fiber content |
url | https://doi.org/10.1038/s41598-024-59160-x |
work_keys_str_mv | AT marciahelenamachadodarochafernandes usingsentinel2satelliteimagesandmachinelearningalgorithmstopredicttropicalpastureforagemasscrudeproteinandfibercontent AT jalmedesouzafernandesjunior usingsentinel2satelliteimagesandmachinelearningalgorithmstopredicttropicalpastureforagemasscrudeproteinandfibercontent AT jordanmelissaadams usingsentinel2satelliteimagesandmachinelearningalgorithmstopredicttropicalpastureforagemasscrudeproteinandfibercontent AT mingyunglee usingsentinel2satelliteimagesandmachinelearningalgorithmstopredicttropicalpastureforagemasscrudeproteinandfibercontent AT ricardoandradereis usingsentinel2satelliteimagesandmachinelearningalgorithmstopredicttropicalpastureforagemasscrudeproteinandfibercontent AT luisorlindotedeschi usingsentinel2satelliteimagesandmachinelearningalgorithmstopredicttropicalpastureforagemasscrudeproteinandfibercontent |