A multimodality test outperforms three machine learning classifiers for identifying and mapping paddocks using time series satellite imagery

References

• Ali I, Cawkwell F, Dwyer E, Barrett B, Green S. 2016. Satellite remote sensing of grasslands: from observation to management. J Plant Ecol. 9(6):649–671.
   Web of Science ®Google Scholar
• Ameijeiras-Alonso J, Crujeiras RM, Rodriguez-Casal A. 2021. multimode: an R package for mode assessment. J Stat Soft. 97(9):1–32.
   Web of Science ®Google Scholar
• Baetens L, Desjardins C, Hagolle O. 2019. Validation of Copernicus Sentinel-2 cloud masks obtained from MAJA, Sen2Cor, and FMask processors using reference cloud masks generated with a supervised active learning procedure. Remote Sens. 11(4):433.
   Google Scholar
• Bilotta GS, Brazier RE, Haygarth PM. 2007. The impacts of grazing animals on the quality of soils, vegetation, and surface waters in intensively managed grasslands. In: Sparks DL, editor. Advances in agronomy. San Diego: Academic Press; p. 237–280.
   Google Scholar
• Breiman L. 2001. Random forests. Mach Learn. 45(1):5–32.
   Web of Science ®Google Scholar
• Cawkwell F, Barrett B, Nitze I, Green S, Black K, Hallahan P. 2017. The Irish Land Mapping Observatory: mapping and monitoring land cover, use and change. Johnstown Castle, Wexford: Environmental Protection Agency.
   Google Scholar
• Central Statistics Office. 2020. Statistical Yearbook of Ireland 2019. Cork.
   Google Scholar
• Centre National d'Etudes Spatiales. 2021. La Plateforme d'Exploitation des Produits Sentinel. Paris (France): Centre National d'Estudes Spatiales; [accessed 2021 Oct 5]. https://peps.cnes.fr/.
   Google Scholar
• Chang J, Ciais P, Viovy N, Vuichard N, Sultan B, Soussana JF. 2015. The greenhouse gas balance of European grasslands. Glob Chang Biol. 21(10):3748–3761.
   PubMed Web of Science ®Google Scholar
• Chen T, Guestrin C. 2016. XGBoost: a scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York (NY): Association for Computing Machinery. p. 785–794.
   Google Scholar
• Chen T, He T, Benesty M, Khotilovich V, Tang Y, Cho H, Chen K, Mitchell R, Cano I, Zhou T, et al. 2020. xgboost: extreme gradient boosting [Version: 1.2.0.1]. R package. Vienna: R Core Team, R Foundation for Statistical Computing; [accessed 2021 Oct 5]. https://CRAN.R-project.org/package=xgboost.
   Google Scholar
• Clay N, Garnett T, Lorimer J. 2020. Dairy intensification: drivers, impacts and alternatives. Ambio. 49(1):35–48.
   PubMed Web of Science ®Google Scholar
• Conant R, Cerri C, Osborne B, Paustian K. 2017. Grassland management impacts on soil carbon stocks: a new synthesis. Ecol Appl. 27(2):662–668.
   PubMed Web of Science ®Google Scholar
• Cortes C, Vapnik V. 1995. Support-vector networks. Mach Learn. 20(3):273–297.
   Web of Science ®Google Scholar
• Crabbe RA, Lamb D, Edwards C, Andersson K, Schneider D. 2019. A preliminary investigation of the potential of Sentinel-1 RADAR to estimate pasture biomass in a grazed pasture landscape. Remote Sens. 11(7):872.
   Google Scholar
• d'Andrimont R, Yordanov M, Martinez-Sanchez L, Eiselt B, Palmieri A, Dominici P, Gallego J, Reuter HI, Joebges C, Lemoine G, et al. 2020. Harmonised LUCAS in-situ land cover and use database for field surveys from 2006 to 2018 in the European Union. Sci Data. 7(1):352.
   PubMed Web of Science ®Google Scholar
• Department of Agriculture Food and the Marine. 2020. Information on LULUCF actions to limit or reduce emissions and maintain or increase removals from activities defined under Decision 529/2013/EU. Dublin: Department of Agriculture Food and the Marine; p. 58.
   Google Scholar
• Dusseux P, Corpetti T, Hubert-Moy L, Corgne S. 2014. Combined use of multi-temporal optical and RADA satellite images for grassland monitoring. Remote Sens. 6(7):6163–6182.
   Google Scholar
• Estel S, Mader S, Levers C, Verburg PH, Baumann M, Kuemmerle T. 2018. Combining satellite data and agricultural statistics to map grassland management intensity in Europe. Environ Res Lett. 13(7):074020.
   Web of Science ®Google Scholar
• European Commission. 2003. Council Regulation (EC) No 1782/2003 of 29 September 2003 establishing common rules for direct support schemes under the common agricultural policy and establishing certain support schemes for farmers and amending Regulations (EEC) No 2019/93, (EC) No 1452/2001, (EC) No 1453/2001, (EC) No 1454/2001, (EC) No 1868/94, (EC) No 1251/1999, (EC) No 1254/1999, (EC) No 1673/2000, (EEC) No 2358/71 and (EC) No 2529/2001. Official J Eur Union. 270:1–103.
   Google Scholar
• Fealy R, Fealy RM. 2008. The spatial variation in degree days derived from locational attributes for the 1961 to 1990 period. Irish J Agric Food Res. 47(1):1–11.
   Web of Science ®Google Scholar
• Finch T, Ryan P. 1966. Soils of Co. Limerick. Dublin: An Foras Taluntais.
   Google Scholar
• Gitelson A, Merzlyak MN. 1994. Spectral reflectance changes associated with autumn senescence of Aesculus hippocastanum L. and Acer platanoides L. Leaves. Spectral features and relation to chlorophyll estimation. J Plant Physiol. 143(3):286–292.
   Web of Science ®Google Scholar
• Green S, Cawkwell F, Dwyer E. 2018. How current environmental and weather conditions affect time critical decision making on Irish dairy farms. Int J Agric Manage. 7(1):50–58.
   Google Scholar
• Green S, O’Hara R, Zimmermann J. 2021. The role of remote sensing in practical grassland farming. In: Astor T, Dzene I, editors. Sensing – New insights into grassland science and practice. Kiel: European Grassland Federation; p. 166–171.
   Google Scholar
• Hall P, York M. 2001. On the calibration of Silvermans test for multimodality. Stat Sin. 11(2):515–536.
   Web of Science ®Google Scholar
• Hanrahan L, McHugh N, Hennessy T, Moran B, Kearney R, Wallace M, Shalloo L. 2018. Factors associated with profitability in pasture-based systems of milk production. J Dairy Sci. 101(6):5474–5485.
   PubMed Web of Science ®Google Scholar
• Haralick RM, Shanmugam K, Dinstein I. 1973. Textural features for image classification. IEEE Trans Syst Man Cybern. SMC-3(6):610–621.
   Web of Science ®Google Scholar
• Harrell FE Jr, Dupont C. 2020. Hmisc: Harrell miscellaneous [Version: 4.4-2]. R package. Vienna: R Core Team, R Foundation for Statistical Computing; [accessed 2021 Oct 6]. https://CRAN.R-project.org/package=Hmisc.
   Google Scholar
• Haughey E. 2021. Climate change and land use in Ireland. Wexford: Environmental Protection Agency.
   Google Scholar
• Hijmans R. 2020. Raster: geographic data analysis and modeling [Version: 3.4-5]. R package. [accessed 2021 Oct 5]. https://CRAN.R-project.org/package=raster.
   Google Scholar
• Hurtado-Uria C, Hennessy D, Shalloo L, O'Connor D, Delaby L. 2013. Relationships between meteorological data and grass growth over time in the south of Ireland. Ir Geogr. 46(3):175–201.
   Google Scholar
• IPCC. 2019. Climate Change and Land: an IPCC special report on climate change, desertification, land degradation, sustainable land management, food security, and greenhouse gas fluxes in terrestrial ecosystems.
   Google Scholar
• Jones H, Vaughan R. 2010. Remote sensing of vegetation: principles, techniques and applications UK: Oxford University Press.
   Google Scholar
• Kuemmerle T, Erb K, Meyfroidt P, Müller D, Verburg PH, Estel S, Haberl H, Hostert P, Jepsen M, Kastner T, et al. 2013. Challenges and opportunities in mapping land use intensity globally. Curr Opin Environ Sustain. 5(5):484–493.
   PubMed Web of Science ®Google Scholar
• Kuhn M. 2020. Caret: classification and regression training. [Version: 6.0-86.]. R package. Vienna: R Core Team, R Foundation for Statistical Computing; [accessed 2021 Oct 16]. https://CRAN.R-project.org/package=caret.
   Google Scholar
• Lesiv M, Laso Bayas J, See L, Duerauer M, Dahlia D, Durando N, Hazarika R, Kumar Sahariah P, Vakolyuk M, Blyshchyk V, et al. 2019. Estimating the global distribution of field size using crowdsourcing. Glob Chang Biol. 25(1):174–186.
   PubMed Web of Science ®Google Scholar
• Lonjou V, Desjardins C, Hagolle O, Petrucci B, Tremas T, Dejus M, Makarau A, Auer S. 2016. MACCS-ATCOR joint algorithm (MAJA). Proc SPIE. 1000107.
   Google Scholar
• Main-Knorn M, Pflug B, Louis J, Debaecker V, Müller-Wilm U, Gascon F. 2017. Sen2Cor for Sentinel-2. Proc SPIE. 10427(04):1–12.
   Google Scholar
• Malenovský Z, Rott H, Cihlar J, Schaepman ME, García-Santos G, Fernandes R, Berger M. 2012. Sentinels for science: potential of Sentinel-1, -2, and -3 missions for scientific observations of ocean, cryosphere, and land. Remote Sens Environ. 120:91–101.
   Web of Science ®Google Scholar
• Mayne S, McCaughey J, Ferris C. 2011. Dairy farm management systems | non-seasonal, pasture-based milk production systems in Western Europe. In: Fuquay JW, editor. Encyclopedia of dairy sciences. 2nd ed. San Diego: Academic Press; p. 44–51.
   Google Scholar
• Moran MS, Inoue Y, Barnes EM. 1997. Opportunities and limitations for image-based remote sensing in precision crop management. Remote Sens Environ. 61(3):319–346.
   Web of Science ®Google Scholar
• Morlin CF, Angeli Furlani CE, Zerbato C, Candida de Menezes P, da Silva Gírio LA, Freire de Oliveira M. 2020. Comparison between vegetation indices for detecting spatial and temporal variabilities in soybean crop using canopy sensors. Precision Agric. 21 (5):979–1007.
   Web of Science ®Google Scholar
• Myrgiotis V, Harris P, Revill A, Sint H, Williams M. 2021. Inferring management and predicting sub-field scale C dynamics in UK grasslands using biogeochemical modelling and satellite-derived leaf area data. Agric for Meteorol. 307:108466.
   Web of Science ®Google Scholar
• North HC, Pairman D, Belliss S. 2014. Paddock segmentation using multi-temporal satellite imagery. 2014 IEEE Geoscience and Remote Sensing Symposium. Quebec (Canada): IEEE IGARSS; p. 1596–1599.
   Google Scholar
• Oenema O, de Klein C, Alfaro M. 2014. Intensification of grassland and forage use: driving forces and constraints. Crop Pasture Sci. 65(6):524–537.
   Web of Science ®Google Scholar
• Ordnance Survey Ireland. 2018. Prime 2 Concepts. 30. Dublin, Ireland.
   Google Scholar
• Persello C, Tolpekin VA, Bergado JR, de By RA. 2019. Delineation of agricultural fields in smallholder farms from satellite images using fully convolutional networks and combinatorial grouping. Remote Sens Environ. 231:111253–111253.
   PubMed Web of Science ®Google Scholar
• R Core Team. 2021. R: a language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing.
   Google Scholar
• Rath M, Peel S. 2005. Grassland in Ireland and the UK. In: DA McGilloway, editor. Grassland: a global resource. Wageningen: Wagenigen Academic Publishers; p. 3–17.
   Google Scholar
• Reinermann S, Asam S, Kuenzer C. 2020. Remote sensing of grassland production and management—a review. Remote Sens. 12(12):1949.
   Google Scholar
• Rouse J, Haas R, Schell J, Deering D. 1974. Monitoring vegetation systems in the Great Plains with ERTSed. Third ERTS Symposium, Washington DC: NASA; p. 309–317.
   Google Scholar
• Rydberg A, Borgefors G. 2001. Integrated method for boundary delineation of agricultural fields in multispectral satellite images. IEEE Trans Geosci Remote Sens. 39(11):2514–2520.
   Web of Science ®Google Scholar
• Sawitzki G. 1996. The excess mass approach and the analysis of multi-modality. In: Gaul W, Pfeifer D, editors. From data to knowledge. Berlin, Heidelberg: Springer Berlin Heidelberg; p. 203–211.
   Google Scholar
• Sollenberger L, Kohmann M, Dubeux J Jr, Silveira M. 2019. Grassland management affects delivery of regulating and supporting ecosystem services. Crop Sci. 59(2):441–459.
   Web of Science ®Google Scholar
• Tang Y, Qiu F, Jing L, Shi F, Li X. 2021. A recurrent curve matching classification method integrating within-object spectral variability and between-object spatial association. Int J Appl Earth Obs Geoinf. 101:102367.
   Web of Science ®Google Scholar
• Tarantino C, Forte L, Blonda P, Vicario S, Tomaselli V, Beierkuhnlein C, Adamo M. 2021. Intra-annual Sentinel-2 time-series supporting grassland habitat discrimination. Remote Sens. 13(2):277.
   Google Scholar
• Taravat A, Wagner MP, Bonifacio R, Petit D. 2021. Advanced fully convolutional networks for agricultural field boundary detection. Remote Sens. 13(4):722.
   Google Scholar
• Tarrio K, Tang X, Masek J, Claverie M, Ju J, Qiu S, Zhu Z, Woodcock C. 2020. Comparison of cloud detection algorithms for Sentinel-2 imagery. Sci Remote Sens. 2:100010.
   Google Scholar
• Togeiro de Alckmin G, Kooistra L, Rawnsley R, Lucieer A. 2021. Comparing methods to estimate perennial ryegrass biomass: canopy height and spectral vegetation indices. Precision Agric. 22(1):205–225.
   Web of Science ®Google Scholar
• Toure S, Stow D, Weeks J, Kumar S. 2013. Histogram curve matching approaches for object-based image classification of land cover and land use. Photogramm Eng Remote Sens. 79(5):433–440.
   Web of Science ®Google Scholar
• Ustin S, Jacquemoud S. 2020. How the optical properties of leaves modify the absorption and scattering of energy and enhance leaf functionality. In Cavender-Bares J, Gamon J, Townsend P, editors. Remote sensing of plant biodiversity. Cham: Springer International Publishing; p. 349–384.
   Google Scholar
• Vreugdenhil M, Navacchi C, Bauer-Marschallinger B, Hahn S, Steele-Dunne S, Pfeil I, Dorigo W, Wagner W. 2020. Sentinel-1 cross ratio and vegetation optical depth: a comparison over Europe. Remote Sens. 12(20):3404.
   Google Scholar
• Wagner MP, Oppelt N. 2020. Extracting agricultural fields from remote sensing imagery using graph-based growing contours. Remote Sens. 12(7):1205.
   Google Scholar
• Waldner F, Diakogiannis FI, Batchelor K, Ciccotosto-Camp M, Cooper-Williams E, Herrmann C, Mata G, Toovey A. 2021. Detect, consolidate, delineate: scalable mapping of field boundaries using satellite images. Remote Sens. 13(11):2197.
   Google Scholar
• Watkins B, Van Niekerk A. 2019. Automating field boundary delineation with multi-temporal Sentinel-2 imagery. Comput Electron Agric. 167:105078.
   Web of Science ®Google Scholar
• Wilkinson M, Lee M, Rivero J, Chamberlain T. 2020. Some challenges and opportunities for grazing dairy cows on temperate pastures. Grass Forage Sci. 75(1):1–17.
   PubMed Web of Science ®Google Scholar
• Xue J, Su B. 2017. Significant remote sensing vegetation indices: a review of developments and applications. J Sens. 2017:1–17.
   Web of Science ®Google Scholar
• Zhu Z, Wang S, Woodcock C. 2015. Improvement and expansion of the Fmask algorithm: cloud, cloud shadow, and snow detection for Landsats 4–7, 8, and Sentinel 2 images. Remote Sens Environ. 159:269–277.
   Web of Science ®Google Scholar
• Zimmermann J. 2018. Average field sizes in Ireland calculated per townland. Dublin (Ireland): Teagasc. [accessed 2021 Oct 6]. https://www.teagasc.ie/rural-economy/rural-economy/spatial-analysis/gis-monthly-maps/2018-archive/.
   Google Scholar
• Zimmermann J, Fealy R, Lydon K, Mockler E, O'Brien P, Packham I, Smith G, Green S. 2016. The Irish Land-Parcels Identification System (LPIS): experiences in ongoing and recent environmental research and land cover mapping. Biol Environ. 116B(1):53–62.
   Google Scholar