Biomass estimation of a high Andean plant community with multispectral images acquired using UAV remote sensing and Multiple Linear Regression, Support Vector Machine and Random Forests models
DOI:
https://doi.org/10.17268/sci.agropecu.2022.027Keywords:
Aerial biomass, machine learning, Unmanned Aerial Vehicle (UAV), Tolar, Support Vector Machine, Random ForestAbstract
Remote sensing with large-scale satellite images for precision studies in grasslands has spatial and spectral resolution limitations. Against this, using spectral signs and vegetation indices obtained with microsensors transported by unmanned aerial vehicles (UAV) constitutes a more accurate alternative for biomass estimation. In the fieldwork, images were acquired with microsensors, and fixed transects of 100 m were used where vegetation samples were collected. The photographs acquired with the UAV were processed in Pix 4D, Arc Gis, and algorithms elaborated in R programming language. The biomass estimation was carried out with Multiple Linear Regression, Vector Support Machine, and Random (Forest Random) models. The Random model showed a Kappa coefficient of 0.94 in the training set and 0.901 in the test set (R2 = 0.482). The Random Forest model predicted 3 g/pixel of MV for Puna grass in the rainy season and 2 g/pixel for the dry season; the predicted biomass for the Tola bush was 15 g/pixel of MV for both seasons of the year. The estimation of biomass/hectare for the tolar plant community with its tola shrub and Puna grass components was 6,535.88 kg/ha for the rainy season and 6,588.81 kg/ha for the dry season. The difference between the biomass estimated in the field and the biomass estimated with Random Forest was 5.48% for the rainy season and 9.63% for the dry season.
References
Acebedo, R. (2011). Sistemas de teledetección activos y pasivos embarcados en sistemas aéreos no tripulados para la monitorización de la tierra Barcelona España. 15pp.
Amat, J. 2016. Introducción a la Regresión Múltiple. https://www.cienciadedatos.net/documentos/25_regresion_lineal_multiple
Azcoiti, J. (2016). Evaluación de aplicaciones para el tratamiento de imágenes mediante correlación Automática. Tesis de Maestría Universidad Pública de Navarra.
Berrio, M., Mosquera, T., & Álzate, D. (2015). Uso de drones para el análisis de imágenes multiespectrales en agricultura de pre-utilización de imágenes multiespectrales obtenidas por vehículos aéreos no tripulados para la determinación de zonas intra-lote con mayor rendimiento y calidad en el trigo (Triticum aestivum), Universidad Nacional de Villamaría Argentina.
Bethany, M., Lucier, A., & Aryal, J. (2019). Classification of Lowland Native Grassland Communities Using Hyperspectral Unmanned Aircraft System (UAS) Imagery in the Tasmanian Midlands. Drones, 3(1), 5.
Botello, A., Reyes, F., Chavez, L., Galvis, A., & Hidalgo, R. (2019). Colegio de Postgraduados, Campus Montecillo. Posgrado en Hidro ciencias México- Estado de México, México.
Bivand, R., Keitt, T., & Rowlingson, B. (2017). rgdal: Bindings for the “Geospatial” Data Abstraction Library (1.2-16). https://r-forge.r-project.org/projects/rgdal/
Buitrón, C., & Callisaya, J. (2012). Estudio espacial multitemporal de variaciones en superficie observada a través de imágenes satelitales LANDSAT en una región del Parque Nacional Sajama Bolivia, DIACONIA. La Paz Bolivia.
Chávez, E., Paz, F., & Bolaños, M. (2017). Estimación de biomasa y cobertura aérea usando radiometría e imágenes digitales a nivel de campo en pastizales y matorrales. Terra Latinoamericana, 35(3), 247-257.
D’Oleira, S., Marzolff, I., Klaus, D., & Ries, J. (2012). Unmanned aerial Veicle (UAV) for Monitoring soil erosion in Moroco. Remote Sens, 4(11), 3390-3416.
Elshikha, D., Hunsake,D.,Waller, P., Thorp, K., Dierig, D., Wang, G., Cruz, M., Katterman, K., Bronson, G., Wall, W., & Thompson, A. (2022). Estimation of direct seeded guayule cover, crop coeffivient, and yield using UAS based multispectral and RGB data. Agricultural Water Management, 265, 107540.
Estrada, A., Cárdenas, J., Ñaupari, J., & Zapana, J. (2018). Capacidad de carga de pastos de puna húmeda en un contexto de cambio climático. Revista de investigaciones altoandinas, 20(3), 361-368.
Estrada, A., & Ñaupari, J. (2021). Detección e identificación de comunidades vegetales altoandinas, Bofedal y Tolar de Puna Seca mediante ortofotografías RGB y NDVI en drones “Sistemas Aéreos no Tripulados”. Scientia Agropecuaria, 12(3), 291-301.
Ezenne, G., Jupp, L., Mantel, S., & Tanner, J. L. (2019). Current and potential capabilities of UAS for crop water productivity in precision agriculture. Agricultural Water Management, 218, 158-164.
Pilho, F., Heldens, W., Kong, Z., & Lange, E. (2019). Drones: Innovate technology for use in precision pest management. Journal of Economic Entomology, 113(1), 1–25.
Flores, D., Gonzáles, H., Lozano, R., Vazquez, J., & Hernandez, J. (2021). Automated Agave detection and counting using a Convolutional Neural Network and Unmanned Aerial Systems. Drones, 5(1), 4.
Flores, E. R., Ñaupari, J. A., & Tacuna, R.E. (2014). La economía del cambio climático en el Perú: Ganadería altoandina en la economía del cambio climático en el Perú: Desarrollo, CEPAL.
Gregory, D., & Mira, J. (2016). Estudios de simulación estocástica con Random Forest frente a árboles individuales, Universidad Politécnica de Madrid España.
Grüner, E, Astor, T., & Wachendorf, M. (2019). Biomass Prediction of Heterogeneous Temperate Grasslands Using an SfM Approach Based on UAV Imaging. Agronomy, 9(2), 54.
Hernández, L., Rudge, M., Bartolo, R., & Erskine, P. (2019). Identifying species and monitoring understory from UAS derived data, a literature review and future directions. Drones, 3(1), 9.
Hijmans, R. J., Etten, J. Van, Sumner, M., Cheng, J., Baston, D., Bevan, A., Bivand, R., Busetto, L., Canty, M., Fasoli, B., Forrest, D., Gray, J., Greenberg, J. A., Hiemstra, P., Karney, C., & Mattiuzzi, M. (2020). raster: Geographic Data Analysis and Modeling (Version 3.4-5, p. 249). CRAN. https://cran.r-project.org/package=raster
Holdrige, L. R. (1987). Ecología basada en zonas de vida, servicio editorial IICA, tercera edición, San José de Costa Rica. ISBN 92 9039 1316 pp. 2-26.
Ishida, T., Kurihara, J., Viray, F., & Takashi, J. (2017). A novel approach for vegetation classification using UAV-based hyperspectral imaging. Computers and Electronics in Agriculture, 144, 80-85.
Kharuf, S., Hernandez, L., Orosco, R., & Delgado, I. (2018). Análisis de imágenes multiespectrales adquiridas con vehículos aéreos no tripulados. Ingeniería electrónica, automática y comunicaciones, 39(2), 79-91.
Liaw, A., & Wiener, M. (2022). Breiman and Cutler’s Random Forests for Classification and Regression (Version 4.7-1.1, Issue 3, pp. 239–248).
Librán, F., Klaus, F., Tscharntke, T., & Grass, I. (2020). Unmanned aerial Vehicles for biodiversity friendly agricultural landscape a systematic review. Science of the total environment, 732, 139204
Max, K., Wing, J., Weston, S., Williams, A., Keefer, C., Engelhardt, A., Cooper, T., Mayer, Z., Ziem, A., Scrucca, L., & Hunt, T. (2021). caret: Classification and Regression Training. In R package version 6.0-86 (Version 6.0-90). https://cran.r-project.org/package=caret
Norasma, C., Fadzilah, M., Roslin, N., Zanariah, Z., Tarmidi, Z., & Candra, S. (2019). Unmanned aerial vehicle applications in agriculture, IOP Publishing South conference on engineering and technology. IOP Conf. Ser.: Mater. Sci. Eng., 506, 012063.
Paredes, M. (2018). Uso de índices de vegetación del sensor MODIS TERRA en la estimación de biomasa aérea en pajonales altoandinos, Universidad Nacional Agraria la Molina Lima Perú.
Pebesma, E., & Bivand, R. (2013). Classes and Methods for Spatial Data (Version 1.5-0). https://edzer.github.io/sp/
Peterson, B. G., Carl, P., Boudt, K., Bennett, R., Ulrich, J., Zivot, E., Cornilly, D., Hung, E., Lestel, M., Balkissoon, K., Wuertz, D., Christidis, A. A., Martin, R. D., Zhou, Z., & Shea, J. M. (2020). PerformanceAnalytics: Econometric Tools for Performance and Risk Analysis (Version 2.0.4., p. 240). https://github.com/braverock/PerformanceAnalytics
Pulgar, J. (1996). Geografía del Perú, las ocho regiones naturales, Promoción editorial Inca S.A. décima edición, Lima Perú, ISBN 9972 40 027 3pp 15 al 23.
Robb, C., Harday, A., Doonan, J., & Brook, J. (2020) Semi automated field plot segmentation from UAS imagery for experimental agriculture. Frontiers in plant Science, 11, 591886.
Santa, V., Rosa, M., Mónaco, N., & Heguiabehere, A. (2013). Determination of relationship between data obtained from biomass derived from filed and remote sensing NDVI along the Arroyo Chucul (PACIA Córdoba). Revista de la Facultad de Agronomía UNLPam, 22(S2), 157-162.
Sharma, P., Leigh, L., Chang, J., Maimaitijiang, M., Caffé, M. Above (2022). Ground Biomass Estimation in Oats Using UAV Remote Sensing and Machine Learning. Sensors, 22, 601.
Tapia, M., & Flores, J. (1984). Ecosistema de los andes del sur del Perú y su relación con los pastizales, Capítulo 2, in “Pastoreo y pastizales en los andes del sur del Perú”, Programa colaborativo de apoyo a la investigación en rumiantes menores.
Wei, T., & Simko, V. (2017). Corrplot: Visualización of a Correlation Matrix (Versión 0.84, p. 18). https://cran.r-project.org/web/packages/corrplot/corrplot.pdf.
Zhu, F., Jiewei, L., Honghui, X., & Goodman, E. (2018). Automatic Tobacco plant detection in UAV images via deep Neural Networks. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11(3), 876-887.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Scientia Agropecuaria
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The authors who publish in this journal accept the following conditions:
a. The authors retain the copyright and assign to the magazine the right of the first publication, with the work registered with the Creative Commons attribution license, which allows third parties to use the published information whenever they mention the authorship of the work and the First publication in this journal.
b. Authors may make other independent and additional contractual arrangements for non-exclusive distribution of the version of the article published in this journal (eg, include it in an institutional repository or publish it in a book) as long as it clearly indicates that the work Was first published in this journal.
c. Authors are encouraged to publish their work on the Internet (for example, on institutional or personal pages) before and during the review and publication process, as it can lead to productive exchanges and a greater and faster dissemination of work Published (see The Effect of Open Access).
