Algoritmos de aprendizaje de máquina para la predicción de propiedades fisicoquímicas del suelo mediante información espectral: una revisión sistemática
Resumen
En la literatura científica actual se discute ampliamente acerca de la predicción de propiedades edáficas mediante información espectral. El objetivo de esta revisión fue encontrar algoritmos con el mayor potencial predictivo para las propiedades fisicoquímicas del suelo, basados en información espectral capturada con diferentes instrumentos. Se realizó una revisión sistemática en la cual se encontraron 121 artículos de los cuales se eligieron 19, que cumplieran con un coeficiente de determinación mayor a 0,80 o una raíz del error cuadrado medio cercana a 0. Se determinó que el rango espectral más utilizado corresponde al rango desde 350 hasta 2500 nm; los algoritmos mínimos cuadrados parciales, máquina de soporte vectorial y máquina de soporte vectorial ajustado son adecuadas para predecir pH, materia orgánica y carbono orgánico. Además, la regresión lineal solo es efectiva para predecir el carbonato de calcio, materia orgánica, humedad y contenido de agua mediante bandas individuales.
Palabras clave
algoritmos de predicción, aprendizaje de máquina, análisis químico, espectroscopía
Biografía del autor/a
Mateo Vargas-Zapata
Zootecnista
Marisol Medina-Sierra
Ingeniera Agrónoma, Doctora en Ciencias
Luis Fernando Galeano-Vasco
Zootecnista, Doctor en Ciencias
Mario Fernando Cerón-Muñoz
Zootecnista, Doctor en Ciencias
Referencias
- Ahmadi, A., Emami, M., Daccache, A., & He, L. (2021). Soil properties prediction for precision agriculture using visible and near-infrared spectroscopy: A systematic review and meta-analysis. Agronomy, 11 (433), 1-14. https://doi.org/10.3390/agronomy11030433 DOI: https://doi.org/10.3390/agronomy11030433
- Aliyu, M. B. (2017). Efficiency of Boolean search strings for Information retrieval. American Journal of Engineering Research, 6 (11), 216-222.
- An, X., Li, M., Zheng, L., & Liu, Y. (2012). Effect of particle size on prediction of soil TN with remote sensing based on NIR spectroscopy. Multispectral, Hyperspectral, and Ultra spectral Remote Sensing Technology, Techniques and Applications IV. International Society for Optics and Photonics, 8527, 852710-1 - 852710-7. https://doi.org/10.1117/12.977349 DOI: https://doi.org/10.1117/12.977349
- Angelopoulou, T., Tziolas, N., Balafoutis, A., Zalidis, G., & Bochtis, D. (2019). Remote sensing techniques for soil organic carbon estimation: A review. Remote Sensing, 11 (6), 1-18. https://doi.org/10.3390/rs11060676 DOI: https://doi.org/10.3390/rs11060676
- Barra, I., Haefele, S. M., Sakrabani, R., & Kebede, F. (2021). Soil spectroscopy with the use of chemometrics, machine learning and pre-processing techniques in soil diagnosis: Recent advances–A review. Trends in Analytical Chemistry, 135, 1-13. https://doi.org/10.1016/j.trac.2020.116166 DOI: https://doi.org/10.1016/j.trac.2020.116166
- Benos, L., Tagarakis, A. C., Dolias, G., Berruto, R., Kateris, D., & Bochtis, D. (2021). Machine learning in agriculture: A comprehensive updated review. Sensors, 21 (11), 1-55. https://doi.org/10.3390/s21113758 DOI: https://doi.org/10.3390/s21113758
- Burton, L., Jayachandran, K., & Bhansali, S. (2020). The “Real-Time” revolution for in situ soil nutrient sensing. Journal of The Electrochemical Society, 167 (3), 1-9. https:doi.org/10.1149/1945-7111/ab6f5d DOI: https://doi.org/10.1149/1945-7111/ab6f5d
- Crucil, G., Castaldi, F., Aldana, E., van Wesemael, B., Macdonald, A., & Van Oost, K. (2019). Assessing the Performance of UAS-Compatible Multispectral and Hyperspectral Sensors for Soil Organic Carbon Prediction. Sustainability, 11 (7), 1-18. https://doi.org/10.3390/su11071889 DOI: https://doi.org/10.3390/su11071889
- Dangal, S. R., Sanderman, J., Wills, S., & Ramirez-Lopez, L. (2019). Accurate and precise prediction of soil properties from a large mid-infrared spectral library. Soil Systems, 3 (1), 11. https://doi.org/10.3390/soilsystems3010011 DOI: https://doi.org/10.3390/soilsystems3010011
- Deiss, L., Margenot, A. J., Culman, S. W., & Demyan, M. S. (2020). Tuning support vector machines regression models improves prediction accuracy of soil properties in MIR spectroscopy. Geoderma, 365, 1-12. https://doi.org/10.1016/j.geoderma.2020.114227 DOI: https://doi.org/10.1016/j.geoderma.2020.114227
- Demattê, J. A., Alves, M. R., Gallo, B. C., Fongaro, C. T., Romero, D. J., & Sato, M. V. (2015). Hyperspectral remote sensing as an alternative to estimate soil attributes. Revista Ciência Agronômica, 46, 223-232. https://doi.org/10.5935/1806-6690.20150001 DOI: https://doi.org/10.5935/1806-6690.20150001
- Demattê, J. A., Dotto, A. C., Paiva, A. F., Sato, M. V., Dalmolin, R. S., Maria do Socorro, B., & do Couto, H. T. Z. (2019). The Brazilian Soil Spectral Library (BSSL): A general view, application and challenges. Geoderma, 354, 1-21. https://doi.org/10.1016/j.geoderma.2019.05.043 DOI: https://doi.org/10.1016/j.geoderma.2019.05.043
- Dhawale, N. M., Adamchuk, V. I., Prasher, S. O., & Viscarra Rossel, R. A. (2021). Evaluating the Precision and Accuracy of Proximal Soil vis–NIR Sensors for Estimating Soil Organic Matter and Texture. Soil Systems, 5(3), 1-19. DOI: https://doi.org/10.3390/soilsystems5030048
- Diaz-Gonzalez, F. A., Vuelvas, J., Correa, C. A., Vallejo, V. E., & Patino, D. (2022). Machine learning and remote sensing techniques applied to estimate soil indicators–Review. Ecological Indicators, 135, 1-12. https://doi.org/10.1016/j.ecolind.2021.108517 DOI: https://doi.org/10.1016/j.ecolind.2021.108517
- Divya, Y., & Gopinathan, P. (2019). Soil water content measurement using hyper-spectral remote sensing techniques - A case study from north-western part of Tamil Nadu, India. Remote Sensing Applications: Society and Environment, 14, 1-7. https://doi.org/10.1016/j.rsase.2019.01.005.45739 DOI: https://doi.org/10.1016/j.rsase.2019.01.005
- Fang, Q., Hong, H., Zhao, L., Kukolich, S., Yin, K., & Wang, C. (2018). Visible and near-infrared reflectance spectroscopy for investigating soil mineralogy: A review. Journal of Spectroscopy, 2018, 1-14. https://doi.org/10.1155/2018/3168974 DOI: https://doi.org/10.1155/2018/3168974
- Gaikwad, C. M., Kakarwal, S. N., Sapkal, S., & Uke, N. (2020). Estimation of Soil Attributes using Spectroscopy. CSI Journal of Computing, 3 (2), 12-15.
- Gourlay, S., Aynekulu, E., Carletto, C., & Shepherd, K. (2017). Spectral Soil Analysis & Household Surveys: Guidebook for Integration. https://cgspace.cgiar.org/handle/10568/99331
- Guerrero, A., De Neve, S., & Mouazen, A. M. (2021). Current sensor technologies for in situ and on-line measurement of soil nitrogen for variable rate fertilization: A review. Advances in Agronomy, 168, 1-38. https://doi.org/10.1016/bs.agron.2021.02.001 DOI: https://doi.org/10.1016/bs.agron.2021.02.001
- Guo, L., Shi, T., Linderman, M., Chen, Y., Zhang, H., & Fu, P. (2019). Exploring the influence of spatial resolution on the digital mapping of soil organic carbon by airborne hyperspectral VNIR imaging. Remote Sensing, 11 (9), 1-16. https://doi.org/10.3390/rs11091032 DOI: https://doi.org/10.3390/rs11091032
- He, T., Wang, J., Guo, X., & Chen, Y. (2004). Study on applying hyperspectral remote sensing technology in land quality monitoring. Remote Sensing for Environmental Monitoring, GIS Applications and Geology IV. International Society for Optics and Photonics, 5574, 410-419. https://doi.org/10.1117/12.565987 DOI: https://doi.org/10.1117/12.565987
- Hong, Y., Chen, S., Zhang, Y., Chen, Y., Yu, L., Liu, Y., ... & Liu, Y. (2018). Rapid identification of soil organic matter level via visible and near-infrared spectroscopy: Effects of two-dimensional correlation coefficient and extreme learning machine. Science of the Total Environment, 644, 1232-1243. https://doi.org/10.1016/j.scitotenv.2018.06.319 DOI: https://doi.org/10.1016/j.scitotenv.2018.06.319
- Hong, Y., Guo, L., Chen, S., Linderman, M., Mouazen, A. M., Yu, L., Chen, Y., Liu, Y., Liu, Y., Cheng, H., & amp; Liu, Y. (2020). Exploring the potential of airborne hyperspectral image for estimating topsoil organic carbon: Effects of fractional-order derivative and optimal band combination algorithm. Geoderma, 365, 1-12. https://doi.org/10.1016/j.geoderma.2020.114228 DOI: https://doi.org/10.1016/j.geoderma.2020.114228
- Inoue, Y. (2020). Satellite-and drone-based remote sensing of crops and soils for smart farming–a review. Soil Science and Plant Nutrition, 66 (6), 798-810. https://doi.org/10.1080/00380768.2020.1738899 DOI: https://doi.org/10.1080/00380768.2020.1738899
- Jaconi, A., Vos, C., & Don, A. (2019). Near infrared spectroscopy as an easy and precise method to estimate soil texture. Geoderma, 337, 906-913. DOI: https://doi.org/10.1016/j.geoderma.2018.10.038
- Justin-George, K., Kumar, S., & Raj, R. A. (2020). Soil organic carbon prediction using visible-near infrared reflectance spectroscopy employing artificial neural network modelling. Current Science, 119 (2), 377-381. DOI: https://doi.org/10.18520/cs/v119/i2/377-381
- Kurmai-Takács, Z., & Csorba, Á. (2015). A reflektancia spektroszkópia alkalmazása talajok kémhatásának becslésében. Journal of Central European Green Innovation, 3 (3), 113-132.
- Kurz, T. H., & Buckley, S. J. (2016). A review of hyperspectral imaging in close range applications. XXIII ISPRS The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences Congress, XLI-B5, 865-870. DOI: https://doi.org/10.5194/isprsarchives-XLI-B5-865-2016
- Lagacherie, P., Baret, F., Feret, J. B., Netto, J. M., & Robbez-Masson, J. M. (2008). Estimation of soil clay and calcium carbonate using laboratory, field and airborne hyperspectral measurements. Remote Sensing of Environment, 112 (3), 825-835. https://doi.org/10.1016/j.rse.2007.06.014.44133. DOI: https://doi.org/10.1016/j.rse.2007.06.014
- Lei, S., Bao, N., Liu, S., & Liu, X. (2016). Modelling and Predicting of Soil Electrical Conductivity and PH from Semi-arid Grassland Using VIS-NIR Spectroscopy Technology. International Conference on Computer and Computing Technologies in Agriculture, 442-453. DOI: https://doi.org/10.1007/978-3-030-06155-5_45
- Li, H., Jia, S., & Le, Z. (2019). Quantitative Analysis of Soil Total Nitrogen Using Hyperspectral Imaging Technology with Extreme Learning Machine. Sensors, 19 (20), 1-13. https://doi:10.3390/s19204355.47245. DOI: https://doi.org/10.3390/s19204355
- Liu, H., Zhang, Y., & Zhang, B. (2009). Novel hyperspectral reflectance models for estimating black-soil organic matter in Northeast China. Environmental monitoring and assessment, 154 (1), 147-154. https://doi:10.1007/s10661-008-0385-4 DOI: https://doi.org/10.1007/s10661-008-0385-4
- Liu, S., Shen, H., Chen, S., Zhao, X., Biswas, A., Jia, X., ... & Fang, J. (2019). Estimating forest soil organic carbon content using vis-NIR spectroscopy: Implications for large-scale soil carbon spectroscopic assessment. Geoderma, 348, 37-44. DOI: https://doi.org/10.1016/j.geoderma.2019.04.003
- Lu, B., Dao, P. D., Liu, J., He, Y., & Shang, J. (2020). Recent advances of hyperspectral imaging technology and applications in agriculture. Remote Sensing, 12 (16), 1-44. https://doi.org/10.3390/rs12162659 DOI: https://doi.org/10.3390/rs12162659
- Malmir, M., Tahmasbian, I., Xu, Z., Farrar, M. B., & Bai, S. H. (2019). Prediction of soil macro-and micro-370elements in sieved and ground air-dried soils using laboratory-based hyperspectral imaging371 technique. Geoderma, 340, 70-80. https://doi.org/10.1016/j.geoderma.2018.12.049 DOI: https://doi.org/10.1016/j.geoderma.2018.12.049
- Mustafa, A. E. R. A., & Moursy, A. R. (2020). Using a multivariate regression model and hyperspectral reflectance data to predict soil parameters of Agra, India. International Journal of Geography, Geology and Environment, 2 (1), 4-9. https://doi.org/10.22271/27067483.2020.v2.i1a.12 DOI: https://doi.org/10.22271/27067483.2020.v2.i1a.12
- Nawar, S., & Mouazen, A. M. (2018). Optimal sample selection for measurement of soil organic carbon using on-line vis-NIR spectroscopy. Computers and Electronics in Agriculture, 151, 469-477. DOI: https://doi.org/10.1016/j.compag.2018.06.042
- Olatunde, K. A. (2021). Estimation of soil organic carbon using chemometrics: a comparison between mid-infrared and visible near infrared diffuse reflectance spectroscopy. West African Journal of Applied Ecology, 29 (2), 1-11.
- Padarian, J., Minasny, B., & McBratney, A. B. (2020). Machine learning and soil sciences: A review aided by machine learning tools. Soil, 6 (1), 35-52. https://doi.org/10.5194/soil-6-35-2020 DOI: https://doi.org/10.5194/soil-6-35-2020
- Qi, H., Paz, T., Karnieli, A., Jin, X., & Li, S. (2018). Evaluating calibration methods for predicting soil available nutrients using hyperspectral VNIR data. Soil and Tillage Research, 175, 267-275. https://doi.org/10.1016/j.still.2017.09.006.447 DOI: https://doi.org/10.1016/j.still.2017.09.006
- Santra, P., Singh, R., Sarathjith, M., Panwar, N., Varghese, P., & Das, B. (2015). Reflectance spectroscopic approach for estimation of soil properties in hot arid western Rajasthan, India. Environmental Earth Sciences, 74 (5), 4233-4245. https://doi.org/10.1007/s12665-015-4383-x DOI: https://doi.org/10.1007/s12665-015-4383-x
- Shi, P., Castaldi, F., van Wesemael, B., & Van Oost, K. (2020). Vis-NIR spectroscopic assessment of soil aggregate stability and aggregate size distribution in the Belgian Loam Belt. Geoderma, 357, 1-9. https://doi.org/10.1016/j.geoderma.2019.113958 DOI: https://doi.org/10.1016/j.geoderma.2019.113958
- Song, Y. Q., Zhao, X., Su, H. Y., Li, B., Hu, Y. M., & Cui, X. S. (2018). Predicting Spatial Variations in Soil Nutrients with Hyperspectral Remote Sensing at Regional Scale. Sensors, 18 (9), 1-18. https://doi:42410.3390/s18093086.42526 DOI: https://doi.org/10.3390/s18093086
- Sur, K., & Chauhan, P. (2019). Imaging spectroscopic approach for land degradation studies: a case study from the arid land of India. Geomatics, Natural Hazards and Risk, 10 (1), 898-911. https://doi:51710.1080/19475705.2018.1552629.51864 DOI: https://doi.org/10.1080/19475705.2018.1552629
- Vašát, R., Kodešová, R., & Borvka, L. (2017). Ensemble predictive model for more accurate soil organic carbon spectroscopic estimation. Computers & Geosciences, 104, 75-83. https://doi.org/10.1016/j.cageo.2017.04.008 DOI: https://doi.org/10.1016/j.cageo.2017.04.008
- Vohland, M., Ludwig, M., Sören, T.B., & Ludwig, B. (2017). Quantification of Soil Properties with Hyperspectral Data: Selecting Spectral Variables with Different Methods to Improve Accuracies and Analyze Prediction Mechanisms. Remote Sensing, 9 (11), 1-24. https://doi:10.3390/rs9111103.40719. DOI: https://doi.org/10.3390/rs9111103
- Wei, L., Yuan, Z., Wang, Z., Zhao, L., Zhang, Y., Lu, X., & Cao, L. (2020). Hyperspectral inversion of soil organic matter content based on a combined spectral index model. Sensors, 20 (10), 1-17. https://doi.org/10.3390/s20102777 DOI: https://doi.org/10.3390/s20102777
- Wu, T., Yu, J., Lu, J., Zou, X., & Zhang, W. (2020). Research on inversion model of cultivated soil moisture content based on hyperspectral imaging analysis. Agriculture, 10 (7), 1-14. https://doi.org/10.3390/agriculture10070292 DOI: https://doi.org/10.3390/agriculture10070292
- Yunus, Y., Satriyo, P., & Munawar, A. A. (2019). Rapid Prediction of Soil Quality Indices Using Near Infrared Spectroscopy. IOP Conference Series: Earth and Environmental Science, 365, 1-7. IOP Publishing. https://doi.org/10.1088/1755-1315/365/1/012043 DOI: https://doi.org/10.1088/1755-1315/365/1/012043