In-Field Forage Biomass and Quality Prediction Using Image and VIS-NIR Proximal Sensing with Machine Learning and Covariance-Based Strategies for Livestock Management in Silvopastoral Systems
Controlling forage quality and grazing are crucial for sustainable livestock production, health, productivity, and animal performance. However, the limited availability of reliable handheld sensors for timely pasture quality prediction hinders farmers’ ability to make informed decisions. This stud...
| Main Authors: | , , , , , , |
|---|---|
| Format: | article |
| Language: | Inglés |
| Published: |
Multidisciplinary Digital Publishing Institute (MDPI)
2025
|
| Subjects: | |
| Online Access: | https://www.mdpi.com/2624-7402/7/4/111 https://hdl.handle.net/20.500.12324/41271 https://doi.org/10.3390/agriengineering7040111 |
| _version_ | 1854960294369951744 |
|---|---|
| author | Serpa Imbett, Claudia M. Gómez Palencia, Erika L. Medina Herrera, Diego A. Mejía Luquez, Jorge A. Martínez, Remberto R. Burgos Paz, William O. Aguayo Ulloa, Lorena A. |
| author_browse | Aguayo Ulloa, Lorena A. Burgos Paz, William O. Gómez Palencia, Erika L. Martínez, Remberto R. Medina Herrera, Diego A. Mejía Luquez, Jorge A. Serpa Imbett, Claudia M. |
| author_facet | Serpa Imbett, Claudia M. Gómez Palencia, Erika L. Medina Herrera, Diego A. Mejía Luquez, Jorge A. Martínez, Remberto R. Burgos Paz, William O. Aguayo Ulloa, Lorena A. |
| author_sort | Serpa Imbett, Claudia M. |
| collection | Repositorio AGROSAVIA |
| description | Controlling forage quality and grazing are crucial for sustainable livestock production, health, productivity, and animal performance. However, the limited availability of
reliable handheld sensors for timely pasture quality prediction hinders farmers’ ability to
make informed decisions. This study investigates the in-field dynamics of Mombasa grass
(Megathyrsus maximus) forage biomass production and quality using optical techniques such
as visible imaging and near-infrared (VIS-NIR) hyperspectral proximal sensing combined
with machine learning models enhanced by covariance-based error reduction strategies.
Data collection was conducted using a cellphone camera and a handheld VIS-NIR spectrometer. Feature extraction to build the dataset involved image segmentation, performed using
the Mahalanobis distance algorithm, as well as spectral processing to calculate multiple
vegetation indices. Machine learning models, including linear regression, LASSO, Ridge,
ElasticNet, k-nearest neighbors, and decision tree algorithms, were employed for predictive
analysis, achieving high accuracy with R2 values ranging from 0.938 to 0.998 in predicting
biomass and quality traits. A strategy to achieve high performance was implemented by
using four spectral captures and computing the reflectance covariance at NIR wavelengths,
accounting for the three-dimensional characteristics of the forage. These findings are expected to advance the development of AI-based tools and handheld sensors particularly
suited for silvopastoral systems. |
| format | article |
| id | RepoAGROSAVIA41271 |
| institution | Corporación Colombiana de Investigación Agropecuaria |
| language | Inglés |
| publishDate | 2025 |
| publishDateRange | 2025 |
| publishDateSort | 2025 |
| publisher | Multidisciplinary Digital Publishing Institute (MDPI) |
| publisherStr | Multidisciplinary Digital Publishing Institute (MDPI) |
| record_format | dspace |
| spelling | RepoAGROSAVIA412712025-11-20T14:19:47Z In-Field Forage Biomass and Quality Prediction Using Image and VIS-NIR Proximal Sensing with Machine Learning and Covariance-Based Strategies for Livestock Management in Silvopastoral Systems In-Field Forage Biomass and Quality Prediction Using Image and VIS-NIR Proximal Sensing with Machine Learning and Covariance-Based Strategies for Livestock Management in Silvopastoral Systems Serpa Imbett, Claudia M. Gómez Palencia, Erika L. Medina Herrera, Diego A. Mejía Luquez, Jorge A. Martínez, Remberto R. Burgos Paz, William O. Aguayo Ulloa, Lorena A. Hyperspectral sensing Optical spectrum Handheld proximal sensors Image processing Mahalanobis distance Ganadería - L01 Biomasa Forraje Sistema silvopascícola Alimentación de los animales Ganadería y especies menores http://aims.fao.org/aos/agrovoc/c_926 http://aims.fao.org/aos/agrovoc/c_36108 http://aims.fao.org/aos/agrovoc/c_16097 http://aims.fao.org/aos/agrovoc/c_429 Controlling forage quality and grazing are crucial for sustainable livestock production, health, productivity, and animal performance. However, the limited availability of reliable handheld sensors for timely pasture quality prediction hinders farmers’ ability to make informed decisions. This study investigates the in-field dynamics of Mombasa grass (Megathyrsus maximus) forage biomass production and quality using optical techniques such as visible imaging and near-infrared (VIS-NIR) hyperspectral proximal sensing combined with machine learning models enhanced by covariance-based error reduction strategies. Data collection was conducted using a cellphone camera and a handheld VIS-NIR spectrometer. Feature extraction to build the dataset involved image segmentation, performed using the Mahalanobis distance algorithm, as well as spectral processing to calculate multiple vegetation indices. Machine learning models, including linear regression, LASSO, Ridge, ElasticNet, k-nearest neighbors, and decision tree algorithms, were employed for predictive analysis, achieving high accuracy with R2 values ranging from 0.938 to 0.998 in predicting biomass and quality traits. A strategy to achieve high performance was implemented by using four spectral captures and computing the reflectance covariance at NIR wavelengths, accounting for the three-dimensional characteristics of the forage. These findings are expected to advance the development of AI-based tools and handheld sensors particularly suited for silvopastoral systems. Ministerio de Ciencia, Tecnología e Innovación de Colombia - MINCIENCIAS Ganado de doble propósito-Ganaderia doble proposito 2025-10-03T20:05:45Z 2025-04-08 2025 article Artículo científico http://purl.org/coar/resource_type/c_2df8fbb1 info:eu-repo/semantics/article https://purl.org/redcol/resource_type/ART http://purl.org/coar/version/c_970fb48d4fbd8a85 https://www.mdpi.com/2624-7402/7/4/111 2624-7402 https://hdl.handle.net/20.500.12324/41271 https://doi.org/10.3390/agriengineering7040111 reponame:Biblioteca Digital Agropecuaria de Colombia instname:Corporación colombiana de investigación agropecuaria AGROSAVIA eng AgriEngineering 7 4 111 Beeri, O.; Phillips, R.; Hendrickson, J.; Frank, A.B.; Kronberg, S. Estimating Forage Quantity and Quality Using Aerial Hyperspec tral Imagery for Northern Mixed-Grass Prairie. Remote Sens. Environ. 2007, 110, 216–225. [CrossRef] Geipel, J.; Bakken, A.K.; Jørgensen, M.; Korsaeth, A. Forage Yield and Quality Estimation by Means of UAV and Hyperspectral Imaging. Precis. Agric. 2021, 22, 1437–1463. [CrossRef] Edvan, R.; Bezerra, L.; Marques, C.; Carneiro, M.S.; Oliveira, R.; Ferreira, R. Methods for Estimating Forage Mass in Pastures in a Tropical Climate. Rev. Ciências Agrárias 2016, 39, 36–45. [CrossRef] Jank, L.; Valle, C.B.; Resende, R. Brazilian Society of Plant Breeding. Printed in Brazil Breeding Tropical Forages; Brazilian Society of Plant Breeding: Londrina, Brazil, 2011; Volume 1. Mendes de Oliveira, D.; Pasquini, C.; Rita de Araújo Nogueira, A.; Dias Rabelo, M.; Lúcia Ferreira Simeone, M.; Batista de Souza, G. Comparative Analysis of Compact and Benchtop Near-Infrared Spectrometers for Forage Nutritional Trait Measurements. Microchem. J. 2024, 196, 109682. [CrossRef] Gao, J.; Liang, T.; Liu, J.; Zhang, D.; Wu, C.; Feng, Q.; Xie, H. Hyperspectral remote sensing of forage stoichiometric ratios in the senescent stage of alpine grasslands. Field Crops Res. 2024, 313, 108027. [CrossRef] Hennessy, A.; Clarke, K.; Lewis, M. Hyperspectral Classification of Plants: A Review of Waveband Selection Generalisability. Remote Sens. 2020, 12, 113. [CrossRef] Tedesco, D.; Nieto, L.; Hernández, C.; Rybecky, J.; Min, D.; Sharda, A.; Hamilton, K.; Ciampitti, I. Remote Sensing on Alfalfa as an Approach to Optimize Production Outcomes: A Review of Evidence and Directions for Future Assessments. Remote Sens. 2022, 14, 4940. [CrossRef] Condran, S.; Bewong, M.; Islam, M.Z.; Maphosa, L.; Zheng, L. Machine Learning in Precision Agriculture: A Survey on Trends, Applications and Evaluations over Two Decades. IEEE Access 2022, 10, 73786–73803. [CrossRef] Liakos, K.; Busato, P.; Moshou, D.; Pearson, S.; Bochtis, D. Machine Learning in Agriculture: A Review. Sensors 2018, 18, 2674. [CrossRef] Zhou, Z.; Morel, J.; Parsons, D.; Kucheryavskiy, S.V.; Gustavsson, A.M. Estimation of Yield and Quality of Legume and Grass Mixtures Using Partial Least Squares and Support Vector Machine Analysis of Spectral Data. Comput. Electron. Agric. 2019, 162, 246–253. [CrossRef] Cevoli, C.; Di Cecilia, L.; Ferrari, L.; Fabbri, A.; Molari, G. Evaluation of Cut Alfalfa Moisture Content and Operative Conditions by Hyperspectral Imaging Combined with Chemometric Tools: In-Field Application. Biosyst. Eng. 2022, 222, 132–141. [CrossRef] Zhang, Y.; Zhao, D.; Liu, H.; Huang, X.; Deng, J.; Jia, R.; He, X.; Tahir, M.N.; Lan, Y. Research Hotspots and Frontiers in Agricultural Multispectral Technology: Bibliometrics and Scientometrics Analysis of the Web of Science. Front. Plant Sci. 2022, 13, 955340. [CrossRef] Liu, H.; Bruning, B.; Garnett, T.; Berger, B. Hyperspectral Imaging and 3D Technologies for Plant Phenotyping: From Satellite to Close-Range Sensing. Comput. Electron. Agric. 2020, 175, 105621. Gates, D.M.; Keegan, H.J.; Schleter, J.C.; Weidner, V.R. Spectral Properties of Plants. Appl. Opt. 1965, 4, 11–20. [CrossRef] Dymond, J.R.; Shepherd, J.D.; Qi, J. A Simple Physical Model of Vegetation Reflectance for Standardising Optical Satellite Imagery. Remote Sens. Environ. 2001, 75, 350–359. [CrossRef] Edward, B. Physical and Physiological Basis for the Reflectance of Visible and Near-Infrared Radiation from Vegetation. Remote Sens. Environ. 1970, 1, 155–159. Rao, N.R. Development of a Crop-Specific Spectral Library and Discrimination of Various Agricultural Crop Varieties Using Hyperspectral Imagery. Int. J. Remote Sens. 2008, 29, 131–144. [CrossRef] Singh, V.; Sharma, N.; Singh, S. A Review of Imaging Techniques for Plant Disease Detection. Artif. Intell. Agric. 2020, 4, 229–242. Zamft, B.M.; Conrado, R.J. Engineering Plants to Reflect Light: Strategies for Engineering Water-Efficient Plants to Adapt to a Changing Climate. Plant Biotechnol. J. 2015, 13, 867–874. [CrossRef] Mangold, K.; Shaw, J.A.; Vollmer, M. The Physics of Near-Infrared Photography. Eur. J. Phys. 2013, 34, S51. [CrossRef] Kothari, S.; Schweiger, A.K. Plant Spectra as Integrative Measures of Plant Phenotypes. J. Ecol. 2022, 110, 2536–2554. Tucker, C. Spectral Estimation of Grass Canopy Variables. Remote Sens. Environ. 1977, 6, 11–26. [CrossRef] Ahamed, T.; Tian, L.; Zhang, Y.; Ting, K.C. A Review of Remote Sensing Methods for Biomass Feedstock Production. Biomass Bioenergy 2011, 35, 2455–2469. Araus, J.L.; Kefauver, S.C.; Vergara-Díaz, O.; Gracia-Romero, A.; Rezzouk, F.Z.; Segarra, J.; Buchaillot, M.L.; Chang-Espino, M.; Vatter, T.; Sanchez-Bragado, R.; et al. Crop Phenotyping in a Context of Global Change: What to Measure and How to Do It. J. Integr. Plant Biol. 2022, 64, 592–618. Cook, C.W. Symposium on Nutrition of Forages and Pastures: Collecting Forage Samples Representative of Ingested Material of Grazing Animals for Nutritional Studies. J. Anim. Sci. 1964, 23, 265–270. [CrossRef] Weiss, W.P.; Hall, M.B. Laboratory Methods for Evaluating Forage Quality. In Forages; Wiley Online Library: Hoboken, NJ, USA, 2020; pp. 659–672. ISBN 9781119436669. Hernández Molina, D.D.; Gulfo Galaraga, J.M.; López López, A.M.; Serpa Imbett, C.M. Methods for estimating agricultural cropland yield based on the comparison of NDVI images analyzed by means of Image segmentation algorithms: A tool for spatial planning decisions. Ingeniare. Rev. Chil. Ing. 2023, 31, 224–235. Wang, Z.; Wang, E.; Zhu, Y. Image Segmentation Evaluation: A Survey of Methods. Artif. Intell. Rev. 2020, 53, 5637–5674. [CrossRef] Zhang, Y.; Huang, D.; Ji, M.; Xie, F. Image Segmentation Using PSO and PCM with Mahalanobis Distance. Expert Syst. Appl. 2011, 38, 9036–9040. [CrossRef] Zhou, Z.H. Machine Learning; Springer Nature: Berlin/Heidelberg, Germany, 2021; ISBN 9789811519673. Raheem, M.A.; Udoh, N.S.; Gbolahan, A.T. Choosing Appropriate Regression Model in the Presence of Multicolinearity. Open J. Stat. 2019, 09, 159–168. [CrossRef] Théau, J.; Lauzier-Hudon, É.; Aubé, L.; Devillers, N. Estimation of Forage Biomass and Vegetation Cover in Grasslands Using UAV Imagery. PLoS ONE 2021, 16, e0245784. [CrossRef] Nguyen, P.T.; Shi, F.; Wang, J.; Badenhorst, P.E.; Spangenberg, G.C.; Smith, K.F.; Daetwyler, H.D. Within and Combined Season Prediction Models for Perennial Ryegrass Biomass Yield Using Ground- and Air-Based Sensor Data. Front. Plant Sci. 2022, 13, 950720. [CrossRef] [PubMed] Gámez, A.L.; Vatter, T.; Santesteban, L.G.; Araus, J.L.; Aranjuelo, I. Onfield Estimation of Quality Parameters in Alfalfa through Hyperspectral Spectrometer Data. Comput. Electron. Agric. 2024, 216, 108463. [CrossRef] Wijesingha, J.; Astor, T.; Schulze-Brüninghoff, D.; Wengert, M.; Wachendorf, M. Predicting Forage Quality of Grasslands Using UAV-Borne Imaging Spectroscopy. Remote Sens. 2020, 12, 126. [CrossRef] Kawamura, K.; Tanaka, T.; Yasuda, T.; Okoshi, S.; Hanada, M.; Doi, K.; Saigusa, T.; Yagi, T.; Sudo, K.; Okumura, K.; et al. Legume Content Estimation from UAV Image in Grass-Legume Meadows: Comparison Methods Based on the UAV Coverage vs. Field Biomass. Sci. Rep. 2024, 14, 31705. [CrossRef] Villoslada Peciña, M.; Bergamo, T.F.; Ward, R.D.; Joyce, C.B.; Sepp, K. A Novel UAV-Based Approach for Biomass Prediction and Grassland Structure Assessment in Coastal Meadows. Ecol. Indic. 2021, 122, 107227. [CrossRef] McCann, J.A.; Keith, D.A.; Kingsford, R.T. Measuring Plant Biomass Remotely Using Drones in Arid Landscapes. Ecol. Evol. 2022, 12, e8891. [CrossRef] Bazzo, C.O.G.; Kamali, B.; Hütt, C.; Bareth, G.; Gaiser, T. A Review of Estimation Methods for Aboveground Biomass in Grasslands Using UAV. Remote Sens. 2023, 15, 639. [CrossRef] Zhu, X.; Liu, D. Improving Forest Aboveground Biomass Estimation Using Seasonal Landsat NDVI Time-Series. ISPRS J. Photogramm. Remote Sens. 2015, 102, 222–231. [CrossRef] Leenings, R.; Winter, N.R.; Plagwitz, L.; Holstein, V.; Ernsting, J.; Sarink, K.; Fisch, L.; Steenweg, J.; Kleine-Vennekate, L.; Gebker, J.; et al. PHOTONAI—A Python API for Rapid Machine Learning Model Development. PLoS ONE 2021, 16, e0254062. [CrossRef] Cherney, J.H.; Digman, M.F.; Cherney, D.J. Handheld NIRS for Forage Evaluation. Comput. Electron. Agric. 2021, 190, 106469. [CrossRef] Atribución-NoComercial-CompartirIgual 4.0 Internacional http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf application/pdf C.I Tibaitatá Multidisciplinary Digital Publishing Institute (MDPI) Basel, Switzerland AgriEngineering; Vol. 7, Núm. 4 (2025): AgriEngineering (Abril);p,111. |
| spellingShingle | Hyperspectral sensing Optical spectrum Handheld proximal sensors Image processing Mahalanobis distance Ganadería - L01 Biomasa Forraje Sistema silvopascícola Alimentación de los animales Ganadería y especies menores http://aims.fao.org/aos/agrovoc/c_926 http://aims.fao.org/aos/agrovoc/c_36108 http://aims.fao.org/aos/agrovoc/c_16097 http://aims.fao.org/aos/agrovoc/c_429 Serpa Imbett, Claudia M. Gómez Palencia, Erika L. Medina Herrera, Diego A. Mejía Luquez, Jorge A. Martínez, Remberto R. Burgos Paz, William O. Aguayo Ulloa, Lorena A. In-Field Forage Biomass and Quality Prediction Using Image and VIS-NIR Proximal Sensing with Machine Learning and Covariance-Based Strategies for Livestock Management in Silvopastoral Systems |
| title | In-Field Forage Biomass and Quality Prediction Using Image and VIS-NIR Proximal Sensing with Machine Learning and Covariance-Based Strategies for Livestock Management in Silvopastoral Systems |
| title_full | In-Field Forage Biomass and Quality Prediction Using Image and VIS-NIR Proximal Sensing with Machine Learning and Covariance-Based Strategies for Livestock Management in Silvopastoral Systems |
| title_fullStr | In-Field Forage Biomass and Quality Prediction Using Image and VIS-NIR Proximal Sensing with Machine Learning and Covariance-Based Strategies for Livestock Management in Silvopastoral Systems |
| title_full_unstemmed | In-Field Forage Biomass and Quality Prediction Using Image and VIS-NIR Proximal Sensing with Machine Learning and Covariance-Based Strategies for Livestock Management in Silvopastoral Systems |
| title_short | In-Field Forage Biomass and Quality Prediction Using Image and VIS-NIR Proximal Sensing with Machine Learning and Covariance-Based Strategies for Livestock Management in Silvopastoral Systems |
| title_sort | in field forage biomass and quality prediction using image and vis nir proximal sensing with machine learning and covariance based strategies for livestock management in silvopastoral systems |
| topic | Hyperspectral sensing Optical spectrum Handheld proximal sensors Image processing Mahalanobis distance Ganadería - L01 Biomasa Forraje Sistema silvopascícola Alimentación de los animales Ganadería y especies menores http://aims.fao.org/aos/agrovoc/c_926 http://aims.fao.org/aos/agrovoc/c_36108 http://aims.fao.org/aos/agrovoc/c_16097 http://aims.fao.org/aos/agrovoc/c_429 |
| url | https://www.mdpi.com/2624-7402/7/4/111 https://hdl.handle.net/20.500.12324/41271 https://doi.org/10.3390/agriengineering7040111 |
| work_keys_str_mv | AT serpaimbettclaudiam infieldforagebiomassandqualitypredictionusingimageandvisnirproximalsensingwithmachinelearningandcovariancebasedstrategiesforlivestockmanagementinsilvopastoralsystems AT gomezpalenciaerikal infieldforagebiomassandqualitypredictionusingimageandvisnirproximalsensingwithmachinelearningandcovariancebasedstrategiesforlivestockmanagementinsilvopastoralsystems AT medinaherreradiegoa infieldforagebiomassandqualitypredictionusingimageandvisnirproximalsensingwithmachinelearningandcovariancebasedstrategiesforlivestockmanagementinsilvopastoralsystems AT mejialuquezjorgea infieldforagebiomassandqualitypredictionusingimageandvisnirproximalsensingwithmachinelearningandcovariancebasedstrategiesforlivestockmanagementinsilvopastoralsystems AT martinezrembertor infieldforagebiomassandqualitypredictionusingimageandvisnirproximalsensingwithmachinelearningandcovariancebasedstrategiesforlivestockmanagementinsilvopastoralsystems AT burgospazwilliamo infieldforagebiomassandqualitypredictionusingimageandvisnirproximalsensingwithmachinelearningandcovariancebasedstrategiesforlivestockmanagementinsilvopastoralsystems AT aguayoulloalorenaa infieldforagebiomassandqualitypredictionusingimageandvisnirproximalsensingwithmachinelearningandcovariancebasedstrategiesforlivestockmanagementinsilvopastoralsystems |