Abstract
Grasslands are crucial ecosystems that support and provide a diverse number of ecosystem services. Sown biodiverse pastures rich in legumes (SBP) were developed with the main goal of increasing grassland production while minimizing fertilizers inputs. In this paper, the main properties of SBP in Portugal were estimated using remote sensing and machine learning in six different farms and two production years (spring 2018 and 2019). Four pasture characteristics were considered: aboveground standing biomass, fraction of legumes, plant nitrogen (N) content and plant phosphorus (P) content. Remote sensing data were obtained from Sentinel-2. The spectral bands combined with 5 vegetation indices and 9 covariates were used. Multiple linear regression, LASSO, Ridge, random forests, XGBoost and LightGBM regression models were used. Two cross-validation approaches were used: (1) a random approach with random selection of the folds (RN-CV), and (2) a structured approach where each fold is a unique combination of farm and year, which is subsequently used to assess the performance of the model obtained with the 8 other folds (LLYO-CV). Results showed that the random forest method had the best estimation accuracy for all pasture characteristics. Regarding cross-validation approaches, the algorithms with RN-CV have higher estimation accuracy for all pasture characteristics (on average about 10% lower RMSE and an R2 85% higher), as compared to the algorithms with LLYO-CV. However, LLYO-CV should avoid overfitting and improve generalization of the models because in each fold the model is tested in a farm and year that was not used for training. The RMSE for all variables were significantly low, especially in RN-CV. Plant P is the variable where the choice of CV approach has the least influence (RMSE of test set with RN-CV: 0.71 g P kg− 1; LLYO-CV: 0.72 g P kg− 1). Standing biomass is the variable with the highest difference between CV approaches (RN-CV: 722 kg ha− 1; LLYO-CV: 825 kg ha− 1). The RMSE, of legumes and plant N were moderately affected by the CV approach (legume RN-CV: 0.11; LLYO-CV: 0.12 – plant N RN-CV: 3.96 g N kg− 1; LLYO-CV: 3.99 g N kg− 1). The algorithms developed here were applied for entire parcels in the two farms with the most different climate conditions as demonstration of their potential future use for precision farming.
Similar content being viewed by others
Availability of data and material
The raw input data is used in this work is available in the Supporting Information File S1.
Code Availability
The Python script used in this work is available on Github (https://github.com/tgmorais/SBPproperties).
Change history
07 March 2023
A Correction to this paper has been published: https://doi.org/10.1007/s11119-023-10005-z
References
Adjorlolo, C., Mutanga, O., & Cho, M. A. (2014). Estimation of canopy nitrogen concentration across c3 and c4 grasslands using worldview-2 multispectral data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(11), 4385–4392. https://doi.org/10.1109/JSTARS.2014.2320601
Ali, I., Cawkwell, F., Dwyer, E., Barrett, B., & Green, S. (2016). Satellite remote sensing of grasslands: from observation to management. Journal of Plant Ecology, 9(6), 649–671. https://doi.org/10.1093/jpe/rtw005
APA. (2018). Portuguese National Inventory Report on Greenhouse Gases, 1990–2018. Amadora, Portugal: Portuguese Environmental Agency
Askari, M. S., McCarthy, T., Magee, A., & Murphy, D. J. (2019). Evaluation of Grass Quality under Different Soil Management Scenarios Using Remote Sensing Techniques. Remote Sensing, 11(15), 1835. https://doi.org/10.3390/rs11151835
Badreldin, N., Prieto, B., & Fisher, R. (2021). Remote sensing Mapping Grasslands in Mixed Grassland Ecoregion of Saskatchewan Using Big Remote Sensing Data and Machine Learning. Remote Sensing, 13(24), 4972. https://doi.org/10.3390/rs13244972
Belsky, A. J. (1994). Influences of Trees on Savanna Productivity: Tests of Shade, Nutrients, and Tree-Grass Competition. Ecology, 75(4), 922–932. https://doi.org/10.2307/1939416
Catchpole, W. R., & Wheeler, C. J. (1992). Estimating plant biomass: A review of techniques. Australian Journal of Ecology, 17(2), 121–131. https://doi.org/10.1111/j.1442-9993.1992.tb00790.x
Chatterjee, S., & Hadi, A. S. (2015). Regression analysis by example. New York City, United States: John Wiley & Sons
Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (Vol. 13-17-August-2016). https://doi.org/10.1145/2939672.2939785
Cornes, R. C., van der Schrier, G., van den Besselaar, E. J. M., & Jones, P. D. (2018). An Ensemble Version of the E-OBS Temperature and Precipitation Data Sets. Journal of Geophysical Research: Atmospheres, 123(17), 9391–9409. https://doi.org/10.1029/2017JD028200
Davids, C., Karlsen, S. R., Ancin, M., & Jorgensen, M. (2018). UAV based mapping of grassland yields for forage production in northern Europe. In Sustainable meat and milk production from grasslands. Proceedings of the 27th General Meeting of the European Grassland Federation, (pp. 845–847). Wageningen, The Netherlands: Wageningen Academic Publishers
EC. (2003). European Soil Database (distribution version v2.0). European Commission Joint Research Centre
ESRI (2016). ArcGIS Desktop 10.5 ArcGIS Desktop. Redlands, CA, USA
Fangueiro, D., Surgy, S., Fraga, I., Cabral, F., & Coutinho, J. (2015). Band application of treated cattle slurry as an alternative to slurry injection: Implications for gaseous emissions, soil quality, and plant growth. Agriculture Ecosystems and Environment, 211, 102–111. https://doi.org/10.1016/j.agee.2015.06.003
Fangueiro, D., Ribeiro, H., Vasconcelos, E., Coutinho, J., & Cabral, F. (2009). Treatment by acidification followed by solid-liquid separation affects slurry and slurry fractions composition and their potential of N mineralization. Bioresource Technology, 100(20), 4914–4917. https://doi.org/10.1016/j.biortech.2009.04.032
Flynn, K. C., Frazier, A. E., & Admas, S. (2020). Performance of chlorophyll prediction indices for Eragrostis tef at Sentinel-2 MSI and Landsat-8 OLI spectral resolutions. Precision Agriculture, 21(5), 1057–1071. https://doi.org/10.1007/s11119-020-09708-4
Gao, B. C. (1996). NDWI - A normalized difference water index for remote sensing of vegetation liquid water from space. Remote Sensing of Environment, 58(3), 257–266. https://doi.org/10.1016/S0034-4257(96)00067-3
Garroutte, E., Hansen, A., & Lawrence, R. (2016). Using NDVI and EVI to Map Spatiotemporal Variation in the Biomass and Quality of Forage for Migratory Elk in the Greater Yellowstone Ecosystem. Remote Sensing, 8(5), 404. https://doi.org/10.3390/rs8050404
Gillet, F., Murisier, B., Buttler, A., Gallandat, J. D., & Gobat, J. M. (1999). Influence of tree cover on the diversity of herbaceous communities in subalpine wooded pastures. Applied Vegetation Science, 2(1), 47–54. https://doi.org/10.2307/1478880
Gitelson, A. A., Kaufman, Y. J., & Merzlyak, M. N. (1996). Use of a green channel in remote sensing of global vegetation from EOS-MODIS. Remote Sensing of Environment, 58(3), 289–298. https://doi.org/10.1016/S0034-4257(96)00072-7
Gitelson, A., & Merzlyak, M. N. (1994). Quantitative estimation of chlorophyll-a using reflectance spectra: Experiments with autumn chestnut and maple leaves. Journal of Photochemistry and Photobiology B: Biology, 22(3), 247–252. https://doi.org/10.1016/1011-1344(93)06963-4
Harris, C. R., Millman, K. J., van der Walt, S. J., Gommers, R., Virtanen, P., Cournapeau, D., et al. (2020). Array programming with NumPy. Nature, 585(7825), 357–362. https://doi.org/10.1038/s41586-020-2649-2
Head, T., Kumar, M., Nahrstaedt, H., Louppe, G., & Shcherbatyi, I. (2020). scikit-optimize/scikit-optimize. Zenodo. https://doi.org/10.5281/zenodo.4014775
IPMA (2018). Climate normals. http://www.ipma.pt/en/index.html. Accessed 9 May 2022
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., et al. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30, 3146–3154
Kleinebecker, T., Weber, H., & Hölzel, N. (2011). Effects of grazing on seasonal variation of aboveground biomass quality in calcareous grasslands. Plant Ecology, 212(9), 1563–1576. https://doi.org/10.1007/s11258-011-9931-1
Liu, K., Zhou, Q. B., Wu, W., Bin, Xia, T., & Tang, H. J. (2016, February 1). Estimating the crop leaf area index using hyperspectral remote sensing. Journal of Integrative Agriculture, 15(2), 475–491.https://doi.org/10.1016/S2095-3119(15)61073-5
Magalhães, M. R., Pena, S. B., Müller, A., Cunha, N. S., Silva, J. F., Cardoso, S., A., et al. (2018). de ordenamento do território (in English: “EPIC WebGIS- Knowledge sharing as a tool to integrate the landscape into land use planning policies”). Revista Cartográfica, (96), 159–176. https://doi.org/10.35424/rcar.v0i96.193. EPIC WebGIS-A partilha de conhecimento como ferramenta de integração da paisagem nas políticas
Magalhães, M. R. (2001). A arquitectura paisagista: morfologia e complexidade (in English: “Landscape architecture: morphology and complexity”). Editorial Estampa
Mariano, D. A., Santos, C. A. C., dos, Wardlow, B. D., Anderson, M. C., Schiltmeyer, A. V., Tadesse, T., et al. (2018). Use of remote sensing indicators to assess effects of drought and human-induced land degradation on ecosystem health in Northeastern Brazil. Remote Sensing of Environment, 213, 129–143. https://doi.org/10.1016/J.RSE.2018.04.048
McKinney, W. (2010). Data Structures for Statistical Computing in Python. In S. van der Walt & J. Millman (Eds.), Proceedings of the 9th Python in Science Conference (pp. 56–61). https://doi.org/10.25080/Majora-92bf1922-00a
Meyer, H., Lehnert, L. W., Wang, Y., Reudenbach, C., Nauss, T., & Bendix, J. (2017). From local spectral measurements to maps of vegetation cover and biomass on the Qinghai-Tibet-Plateau: Do we need hyperspectral information? International Journal of Applied Earth Observation and Geoinformation, 55, 21–31. https://doi.org/10.1016/j.jag.2016.10.001
Morais, T. G., Teixeira, R. F. M., & Domingos, T. (2018a). The Effects on Greenhouse Gas Emissions of Ecological Intensification of Meat Production with Rainfed Sown Biodiverse Pastures. Sustainability, 10(11), 4184. https://doi.org/10.3390/su10114184
Morais, T. G., Teixeira, R. F. M., & Domingos, T. (2019). Detailed global modelling of soil organic carbon in cropland, grassland and forest soils. PLOS ONE, 14(9), e0222604. https://doi.org/10.1371/journal.pone.0222604
Morais, T. G., Teixeira, R. F. M., Rodrigues, N. R., & Domingos, T. (2018b). Characterizing livestock production in Portuguese sown rainfed grasslands: Applying the inverse approach to a process-based model. Sustainability, 10(12), 4437. https://doi.org/10.3390/su10124437
Morais, T. G., Teixeira, R. F. M., Figueiredo, M., & Domingos, T. (2021, November 1). The use of machine learning methods to estimate aboveground biomass of grasslands: A review. Ecological Indicators. 130, 108081. https://doi.org/10.1016/j.ecolind.2021.108081
Moreno-Opo, R., Pina, M., & Mogena, A. (2021). Sowing enriched pastures for extensive livestock enhances the abundance of birds and arthropods in Mediterranean grasslands. European Journal of Wildlife Research, 67(3), 1–12. https://doi.org/10.1007/s10344-021-01486-2
Murphy, D. J., Shine, P., Brien, B. O., Donovan, M. O., & Murphy, M. D. (2021). Utilising grassland management and climate data for more accurate prediction of herbage mass using the rising plate meter. Precision Agriculture, 22(4), 1189–1216. https://doi.org/10.1007/S11119-020-09778-4/TABLES/7
Naidoo, R., Balmford, A., Costanza, R., Fisher, B., Green, R. E., Lehner, B., et al. (2008). Global mapping of ecosystem services and conservation priorities. Proceedings of the National Academy of Sciences, 105(28), 9495–9500. https://doi.org/10.1073/PNAS.0707823105
Nelson, D. W., & Sommers, L. E. (1973). Determination of Total Nitrogen in Plant Material 1. Agronomy Journal, 65(1), 109–112. https://doi.org/10.2134/agronj1973.00021962006500010033x
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., et al. (2011). Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12, 2825–2830
Pereira, H. M., Domingos, T., Marta-Pedroso, C., Proença, V., Rodrigues, P., Ferreira, M., et al. (2009). Uma avaliação dos serviços dos ecossistemas em Portugal. Ecossistemas e Bem-Estar Humano Avaliação para Portugal do Millennium Ecosystem Assessment (in English: “Portuguese Millennium Ecosystem Assessment: State of the Assessment Report”) (pp. 687–716). Lisboa, Portugal: Escolar Editora
Phiri, D., Simwanda, M., Salekin, S., Nyirenda, V. R., Murayama, Y., & Ranagalage, M. (2020, July 1). Sentinel-2 data for land cover/use mapping: A review. Remote Sensing. 12(14), 2291 https://doi.org/10.3390/rs12142291
Prado, A., del, Brown, L., Schulte, R., Ryan, M., & Scholefield, D. (2006). Principles of Development of a Mass Balance N Cycle Model for Temperate Grasslands: An Irish Case Study. Nutrient Cycling in Agroecosystems, 74(2), 115–131. https://doi.org/10.1007/s10705-005-5769-z
Pullanagari, R. R., Yule, I. J., Tuohy, M. P., Hedley, M. J., Dynes, R. A., & King, W. M. (2012). In-field hyperspectral proximal sensing for estimating quality parameters of mixed pasture. Precision Agriculture, 13(3), 351–369. https://doi.org/10.1007/s11119-011-9251-4
Ramoelo, A., Cho, M. A., Mathieu, R., Madonsela, S., van de Kerchove, R., Kaszta, Z., et al. (2015). Monitoring grass nutrients and biomass as indicators of rangeland quality and quantity using random forest modelling and WorldView-2 data. International Journal of Applied Earth Observation and Geoinformation, 43, 43–54. https://doi.org/10.1016/j.jag.2014.12.010
Ren, H., Zhou, G., & Zhang, X. (2011). Estimation of green aboveground biomass of desert steppe in Inner Mongolia based on red-edge reflectance curve area method. Biosystems Engineering, 109(4), 385–395. https://doi.org/10.1016/J.BIOSYSTEMSENG.2011.05.004
Ribeiro, I., Proença, V., Serra, P., Palma, J., Domingo-Marimon, C., Pons, X., et al. (2019). Remotely sensed indicators and open-access biodiversity data to assess bird diversity patterns in Mediterranean rural landscapes. Scientific Reports, 9(1), 6826. https://doi.org/10.1038/s41598-019-43330-3
Rouse, J. W., Haas, R. H., Schell, J. A., & Deeering, D. (1973). Monitoring vegetation systems in the Great Plains with ERTS (Earth Resources Technology Satellite). In Third Earth Resources Technology Satellite-1 Symposium (Vol. 1, pp. 309–317)
Rubel, F., & Kottek, M. (2010). Observed and projected climate shifts 1901–2100 depicted by world maps of the Köppen-Geiger climate classification. Meteorologische Zeitschrift, 19(2), 135–141. https://doi.org/10.1127/0941-2948/2010/0430
Saleem, M. H., Potgieter, J., & Mahmood Arif, K. (2021). & Mahmood Arif karif, K. Automation in Agriculture by Machine and Deep Learning Techniques: A Review of Recent Developments. Precision Agriculture, 22, 2053–2091. https://doi.org/10.1007/s11119-021-09806-x
Serrano, J., Shahidian, S., da Silva, J. M., & Carvalho, M. (2016). Monitoring of soil organic carbon over 10 years in a Mediterranean silvo-pastoral system: potential evaluation for differential management. Precision Agriculture, 17(3), 274–295. https://doi.org/10.1007/s11119-015-9419-4
Sinha, S., Jeganathan, C., Sharma, L. K., & Nathawat, M. S. (2015). A review of radar remote sensing for biomass estimation. International Journal of Environmental Science and Technology, 12(5), 1779–1792. https://doi.org/10.1007/s13762-015-0750-0
Sloat, L. L., Gerber, J. S., Samberg, L. H., Smith, W. K., Herrero, M., Ferreira, L. G., et al. (2018). Increasing importance of precipitation variability on global livestock grazing lands. Nature Climate Change, 8(3), 214–218. https://doi.org/10.1038/s41558-018-0081-5
Teixeira, R. F. M., Barão, L., Morais, T. G., & Domingos, T. (2019). “BalSim”: A carbon, nitrogen and greenhouse gas mass balance model for pastures. Sustainability, 11(1), 53. https://doi.org/10.3390/su11010053
Teixeira, R. F. M., Proença, V., Crespo, D., Valada, T., & Domingos, T. (2015). A conceptual framework for the analysis of engineered biodiverse pastures. Ecological Engineering, 77, 85–97. https://doi.org/10.1016/j.ecoleng.2015.01.002
Tong, X., Duan, L., Liu, T., & Singh, V. P. (2019). Combined use of in situ hyperspectral vegetation indices for estimating pasture biomass at peak productive period for harvest decision. Precision Agriculture, 20(3), 477–495. https://doi.org/10.1007/S11119-018-9592-3
Ullah, S., Si, Y., Schlerf, M., Skidmore, A. K., Shafique, M., & Iqbal, I. A. (2012). Estimation of grassland biomass and nitrogen using MERIS data. International Journal of Applied Earth Observation and Geoinformation, 19, 196–204. https://doi.org/10.1016/J.JAG.2012.05.008
UNFCCC. (2015). Measurements for Estimation of Carbon Stocks in Afforestation and Reforestation Project Activities under the Clean Development Mechanism: A Field Manual. Bonn, Germany: United Nations Climate Change Secretariat (UNFCCC)
Vallentin, C., Harfenmeister, K., Itzerott, S., Kleinschmit, B., Conrad, C., & Spengler, D. (2021). Suitability of satellite remote sensing data for yield estimation in northeast Germany. Precision Agriculture, 2021, 1–31. https://doi.org/10.1007/S11119-021-09827-6
Vilar, P., Morais, T. G., Rodrigues, N. R., Gama, I., Monteiro, M. L., Domingos, T., et al. (2020). Object-Based Classification Approaches for Multitemporal Identification and Monitoring of Pastures in Agroforestry Regions using Multispectral Unmanned Aerial Vehicle Products. Remote Sensing, 12(5), 814. https://doi.org/10.3390/rs12050814
Xia, J., Ma, M., Liang, T., Wu, C., Yang, Y., Zhang, L., et al. (2018). Estimates of grassland biomass and turnover time on the Tibetan Plateau. Environmental Research Letters, 13(1), https://doi.org/10.1088/1748-9326/aa9997
Xu, B., Yang, X. C., Tao, W. G., Qin, Z. H., Liu, H. Q., Miao, J. M., et al. (2008). MODIS-based remote sensing monitoring of grass production in China. International Journal of Remote Sensing, 29(17–18), 5313–5327. https://doi.org/10.1080/01431160802036276
Yan, F., Wu, B., & Wang, Y. (2013). Estimating aboveground biomass in Mu Us Sandy Land using Landsat spectral derived vegetation indices over the past 30 years. Journal of Arid Land, 5(4), 521–530. https://doi.org/10.1007/s40333-013-0180-0
Yang, J., Guo, X., Li, Y., Marinello, F., Ercisli, S., & Zhang, Z. (2022). A survey of few-shot learning in smart agriculture: developments, applications, and challenges. Plant Methods, 2022 18:1(1), 1–12. https://doi.org/10.1186/S13007-022-00866-2. 18
Yang, S., Feng, Q., Liang, T., Liu, B., Zhang, W., & Xie, H. (2018). Modeling grassland above-ground biomass based on artificial neural network and remote sensing in the Three-River Headwaters Region. Remote Sensing of Environment, 204, 448–455. https://doi.org/10.1016/J.RSE.2017.10.011
Yu, H., Wu, Y., Niu, L., Chai, Y., Feng, Q., Wang, W., et al. (2021). A method to avoid spatial overfitting in estimation of grassland above-ground biomass on the Tibetan Plateau. Ecological Indicators, 125, 107450. https://doi.org/10.1016/j.ecolind.2021.107450
Zhang, C., Kovacs, J. M., Zhang, C., & Kovacs, J. M. (2012). The application of small unmanned aerial systems for precision agriculture: a review. Precision Agriculture, 13, 693–712. https://doi.org/10.1007/s11119-012-9274-5
Zhao, F., Xu, B., Yang, X., Jin, Y., Li, J., Xia, L., et al. (2014). Remote Sensing Estimates of Grassland Aboveground Biomass Based on MODIS Net Primary Productivity (NPP): A Case Study in the Xilingol Grassland of Northern China. Remote Sensing, 6(6), 5368–5386. https://doi.org/10.3390/rs6065368
Zheng, D., Rademacher, J., Chen, J., Crow, T., Bresee, M., Le Moine, J., et al. (2004). Estimating aboveground biomass using Landsat 7 ETM + data across a managed landscape in northern Wisconsin, USA. Remote Sensing of Environment, 93(3), 402–411. https://doi.org/10.1016/J.RSE.2004.08.008
Funding
This work was supported by Fundação para a Ciência e Tecnologia through projects “LEAnMeat - Lifecycle-based Environmental Assessment and impact reduction of Meat production with a novel multi-level tool” (PTDC/EAM-AMB/30809/2017) and “GrassData - Development of algorithms for identification, monitoring, compliance checks and quantification of carbon sequestration in pastures” (DSAIPA/DS/0074/2019), projects UIDB/04129/2020, UIDP/04129/2020 and UIDB/05183/2020, and by grants SFRH/BD/115407/2016 (T. Morais) and CEECIND/00365/2018 (R. Teixeira). The work was also supported by FCT/MCTES (PIDDAC) through project UID/EEA/50009/2019 and by Programa de desenvolvimento rural (PDR2020) through “Viabilização de pastagens semeadas biodiversas através da otimização da fertilização fosfatada” (PDR2020-101-030690) and “GO SOLO: Avaliação da dinâmica da matéria orgânica em solos de pastagens semeadas biodiversas através do desenvolvimento de um método de monitorização expedito e a baixo custo” (PDR2020-101-031243).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest/Competing interests
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Ethics approval
Not applicable.
Consent to participate
Not applicable.
Consent for publication
Not applicable.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Morais, T.G., Jongen, M., Tufik, C. et al. Characterization of portuguese sown rainfed grasslands using remote sensing and machine learning. Precision Agric 24, 161–186 (2023). https://doi.org/10.1007/s11119-022-09937-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11119-022-09937-9