Accounting for minimum data required to train a machine learning model to accurately monitor Australian dairy pastures using remote sensing.
Machine learning
Model training
Pasture grazing management
Remote sensing
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
23 Jul 2024
23 Jul 2024
Historique:
received:
06
03
2024
accepted:
19
07
2024
medline:
24
7
2024
pubmed:
24
7
2024
entrez:
23
7
2024
Statut:
epublish
Résumé
Precision in grazing management is highly dependent on accurate pasture monitoring. Typically, this is often overlooked because existing approaches are labour-intensive, need calibration, and are commonly perceived as inaccurate. Machine-learning processes harnessing big data, including remote sensing, can offer a new era of decision-support tools (DST) for pasture monitoring. Its application on-farm remains poor because of a lack of evidence about its accuracy. This study aimed at evaluating and quantifying the minimum data required to train a machine-learning satellite-based DST focusing on accurate pasture biomass prediction using this approach. Management data from 14 farms in New South Wales, Australia and measured pasture biomass throughout 12 consecutive months using a calibrated rising plate meter (RPM) as well as pasture biomass estimated using a DST based on high temporal/spatial resolution satellite images were available. Data were balanced according to farm and week of each month and randomly allocated for model evaluation (20%) and for progressive training (80%) as follows: 25% training subset (1W: week 1 in each month); 50% (2W: week 1 and 3); 75% (3W: week 1, 3, and 4); and 100% (4W: week 1 to 4). Pasture biomass estimates using the DST across all training datasets were evaluated against a calibrated rising plate meter (RPM) using mean-absolute error (MAE, kg DM/ha) among other statistics. Tukey's HSD test was used to determine the differences between MAE across all training datasets. Relative to the control (no training, MAE: 498 kg DM ha
Identifiants
pubmed: 39043833
doi: 10.1038/s41598-024-68094-3
pii: 10.1038/s41598-024-68094-3
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
16927Informations de copyright
© 2024. The Author(s).
Références
Roche, J. R. et al. A 100-year review: A century of change in temperate grazing dairy systems. J. Dairy Sci. 100, 10189–10233. https://doi.org/10.3168/jds.2017-13182 (2017).
doi: 10.3168/jds.2017-13182
pubmed: 29153162
Roche, J. R. et al. Review: New considerations to refine breeding objectives of dairy cows for increasing robustness and sustainability of grass-based milk production systems. Animal 12, 350–362. https://doi.org/10.1017/S1751731118002471 (2018).
doi: 10.1017/S1751731118002471
Moscovici Joubran, A., Pierce, K. M., Garvey, N., Shalloo, L. & O’Callaghan, T. F. Invited review: A 2020 perspective on pasture-based dairy systems and products. J. Dairy Sci. 104, 7364–7382. https://doi.org/10.3168/jds.2020-19776 (2020).
doi: 10.3168/jds.2020-19776
Daley, C. A., Abbott, A., Doyle, P. S., Nader, G. A. & Larson, S. A review of fatty acid profiles and antioxidant content in grass-fed and grain-fed beef. Nutr. J. 9, 1–12. https://doi.org/10.1186/1475-2891-9-10 (2010).
doi: 10.1186/1475-2891-9-10
Elgersma, A. Grazing increases the unsaturated fatty acid concentration of milk from grass-fed cows: A review of the contributing factors, challenges and future perspectives. Eur. J. Lipid Sci. Technol. 117, 1345–1369. https://doi.org/10.1002/ejlt.201400469 (2015).
doi: 10.1002/ejlt.201400469
van Zanten, H. H. E., Mollenhorst, H., Klootwijk, C. W., van Middelaar, C. E. & de Boer, I. J. M. Global food supply: Land use efficiency of livestock systems. Int. J. Life Cycle Assess. 21, 747–758. https://doi.org/10.1007/s11367-015-0944-1 (2016).
doi: 10.1007/s11367-015-0944-1
García, S. C. & Fulkerson, W. Opportunities for future Australian dairy systems: a review. Aust. J. Exp. Res. 45, 1041–1055. https://doi.org/10.1071/EA04143 (2005).
doi: 10.1071/EA04143
Hanrahan, L. et al. Factors associated with profitability in pasture-based systems of milk production. J. Dairy Sci. 101, 5474–5485. https://doi.org/10.3168/jds.2017-13223 (2018).
doi: 10.3168/jds.2017-13223
pubmed: 29525299
Shalloo, L. et al. Review: Grass-based dairy systems, data and precision technologies. Animal 12, s262–s271. https://doi.org/10.1017/S175173111800246X (2018).
doi: 10.1017/S175173111800246X
pubmed: 30345940
Wales, W. J. & Kolver, E. S. Challenges of feeding dairy cows in Australia and New Zealand. Anim. Prod. Sci. 57, 1366–1383. https://doi.org/10.1071/AN16828 (2017).
doi: 10.1071/AN16828
García, S. C., Islam, M. R., Clark, C. E. F. & Martin, P. M. Kikuyu-based pasture for dairy production: A review. Crop Pasture Sci. 65, 787–797. https://doi.org/10.1071/cp13414 (2014).
doi: 10.1071/cp13414
Chapman, D. Using ecophysiology to improve farm efficiency: Application in temperate dairy grazing systems. Agriculture 6, 17–36. https://doi.org/10.3390/agriculture6020017 (2016).
doi: 10.3390/agriculture6020017
Macdonald, K. A., Glassey, C. B. & Rawnsley, R. P. in 4th Australasian Dairy Science Symposium. p. 199–209 (2010).
García, S. C. & Holmes, C. Seasonality of calving in pasture-based dairy systems: its effects on herbage production, utilisation and dry matter intake. Aust. J. Exp. Res. 45, 1–9. https://doi.org/10.1071/EA00110 (2005).
doi: 10.1071/EA00110
Fariña, S., Garcia, S. C. & Fulkerson, W. J. A complementary forage system whole-farm study: forage utilisation and milk production. Anim. Prod. Sci. 51, 460–470. https://doi.org/10.1071/AN10242 (2011).
doi: 10.1071/AN10242
Fariña, S., Garcia, S. C., Fulkerson, W. J. & Barchia, I. M. Pasture-based dairy farm systems increasing milk production through stocking rate or milk yield per cow: Pasture and animal responses. Grass Forage Sci. 66, 316–332. https://doi.org/10.1111/j.1365-2494.2011.00795.x (2011).
doi: 10.1111/j.1365-2494.2011.00795.x
Fulkerson, W. J. & Donaghy, D. J. Plant-soluble carbohydrate reserves and senescence - key criteria for developing an effective grazing management system for ryegrass-based pastures: a review. Aust. J. Exp. Agric. 41, 261–275 (2001).
doi: 10.1071/EA00062
García, S. C. et al. in 22nd International Grassland Congress. p. 1709–1716 (2013).
Heins, B. J., Pereira, G. M. & Sharpe, K. T. Precision technologies to improve dairy grazing systems. JDS Commun. 4, 308–315. https://doi.org/10.3168/jdsc.2022-0308 (2023).
doi: 10.3168/jdsc.2022-0308
Ortega, G. et al. Monitoring herbage mass and pasture growth rate of large grazing areas: A comparison of the correspondence, cost and reliability of indirect methods. J. Agric. Sci. 161, 502–511. https://doi.org/10.1017/s0021859623000333 (2023).
doi: 10.1017/s0021859623000333
Fulkerson, W. J. & Slack, K. Estimating mass of temperate and tropical pastures in the subtropics. Aust. J. Exp. Agric. 33, 865–869 (1993).
doi: 10.1071/EA9930865
Reeves, M., Fulkerson, W. J. & Kellaway, R. C. Forage quality of kikuyu (Penisetum clandestinum): Time of defoliation and nitrogen fertiliser application and in comparison with perennail ryegrass (Lolium perenne). Aust. J. Agric. Res. 47, 1349–1359 (1996).
doi: 10.1071/AR9961349
López-Díaz, J. E., Roca-Fernández, A. I. & González-Rodríguez, A. Measuring herbage mass by Non-destructive methods: A review. J. Agric. Sci. Technol. 1, 303–314 (2011).
Reinermann, S., Asam, S. & Kuenzer, C. Remote sensing of grassland production and management—A review. Remote Sens. 12, 1949–1981. https://doi.org/10.3390/rs12121949 (2020).
doi: 10.3390/rs12121949
French, P., O’Brien, B. & Shalloo, L. Development and adoption of new technologies to increase the efficiency and sustainability of pasture-based systems. Anim. Prod. Sci. 55, 931–935. https://doi.org/10.1071/an14896 (2015).
doi: 10.1071/an14896
McSweeney, D., Coughlan, N. E., Cuthbert, R. N., Halton, P. & Ivanov, S. Micro-sonic sensor technology enables enhanced grass height measurement by a rising plate meter. Inf. Process. Agric. 6, 279–284. https://doi.org/10.1016/j.inpa.2018.08.009 (2019).
doi: 10.1016/j.inpa.2018.08.009
Doonan, B. M. & Irvine, L. D. Pasture management for Tasmanian dairy farmers. 1–61 (Tasmania, 2006).
Nickmilder, C. et al. Development of machine learning models to predict compressed sward height in walloon pastures based on sentinel-1, sentinel-2 and meteorological data using multiple data transformations. Remote Sens. 13, 408–437. https://doi.org/10.3390/rs13030408 (2021).
doi: 10.3390/rs13030408
Edirisinghe, A., Clark, D. & Waugh, D. Spatio-temporal modelling of biomass of intensively grazed perennial dairy pastures using multispectral remote sensing. Int. J. Appl. Earth Obs. Geoinf. 16, 5–16. https://doi.org/10.1016/j.jag.2011.11.006 (2012).
doi: 10.1016/j.jag.2011.11.006
Edirisinghe, A., Hill, M. J., Donald, G. E. & Hyder, M. Quantitative mapping of pasture biomass using satellite imagery. Int. J. Remote Sens. 32, 2699–2724. https://doi.org/10.1080/01431161003743181 (2011).
doi: 10.1080/01431161003743181
Piñeiro, G., Oesterheld, M. & Paruelo, J. M. Seasonal variation in aboveground production and radiation-use efficiency of temperate rangelands estimated through remote sensing. Ecosystem 9, 357–373. https://doi.org/10.1007/s10021-005-0013-x (2006).
doi: 10.1007/s10021-005-0013-x
Sellers, P. J. Canopy reflectance, photosynthesis and transpiration. Int. J. Remote Sens. 6, 1335–1372. https://doi.org/10.1080/01431168508948283 (1985).
doi: 10.1080/01431168508948283
LIC. SPACE
Pasture.io. Pasture.io-pasture measurement on autopilot, https://pasture.io/ . Accessed 12 May 2023.
Stumpe, C., Leukel, J. & Zimpel, T. Prediction of pasture yield using machine learning-based optical sensing: A systematic review. Precis. Agric. 25, 430–459. https://doi.org/10.1007/s11119-023-10079-9 (2023).
doi: 10.1007/s11119-023-10079-9
Ara, I. et al. Application, adoption and opportunities for improving decision support systems in irrigated agriculture: A review. Agric. Water Manag. 257, 107161–107177. https://doi.org/10.1016/j.agwat.2021.107161 (2021).
doi: 10.1016/j.agwat.2021.107161
Ogungbuyi, M. G., Mohammed, C., Ara, I., Fischer, A. M. & Harrison, M. T. Advancing skyborne technologies and high-resolution satellites for pasture monitoring and improved management: A review. Remote Sens. 15, 4866. https://doi.org/10.3390/rs15194866 (2023).
doi: 10.3390/rs15194866
Belgiu, M. & Drăguţ, L. Random forest in remote sensing: A review of applications and future directions. ISPRS J. Photogramm. Remote Sens. 114, 24–31. https://doi.org/10.1016/j.isprsjprs.2016.01.011 (2016).
doi: 10.1016/j.isprsjprs.2016.01.011
de Togeiro Alckmin, G., Kooistra, L., Rawnsley, R. & Lucieer, A. Comparing methods to estimate perennial ryegrass biomass: Canopy height and spectral vegetation indices. Precis. Agric. 22, 205–225. https://doi.org/10.1007/s11119-020-09737-z (2020).
doi: 10.1007/s11119-020-09737-z
Kallenbach, R. L. Describing the dynamic: Measuring and assessing the value of plants in the pasture. Crop Sci. 55, 2531–2539. https://doi.org/10.2135/cropsci2015.01.0065 (2015).
doi: 10.2135/cropsci2015.01.0065
L'Huillier, P. J. & Thomson, N. A. in Proceedings of New Zealand Grassland Association. p. 117–122 (1988).
King, W. M. G., Rennie, G. M., Dalley, D. E., Dynes, R. A. & Upsdell, M. P. in 4th Australasian Dairy Science Symposium. p. 233–238 (2010).
Gargiulo, J. et al. Spatial and temporal pasture biomass estimation integrating electronic plate meter, planet cubesats and sentinel-2 satellite data. Remote Sens. 12, 3222–3238. https://doi.org/10.3390/rs12193222 (2020).
doi: 10.3390/rs12193222
Botha, P. R., Meeske, R. & Snyman, H. A. Kikuyu over-sown with ryegrass and clover; dry matter production, botanical composition and nutritional value. Afr. J. Range Forage Sci. 25, 93–101. https://doi.org/10.2989/AJRF.2008.25.3.1.598 (2008).
doi: 10.2989/AJRF.2008.25.3.1.598
Alvarez-Mendoza, C. I. et al. Predictive modeling of above-ground biomass in brachiaria pastures from satellite and UAV imagery using machine learning approaches. Remote Sens. 14, 5870–5891. https://doi.org/10.3390/rs14225870 (2022).
doi: 10.3390/rs14225870
Morse-McNabb, E. M., Hasan, M. F. & Karunaratne, S. A multi-variable sentinel-2 random forest machine learning model approach to predicting perennial ryegrass biomass in commercial dairy farms in southeast Australia. Remote Sens. 15, 2915–2946. https://doi.org/10.3390/rs15112915 (2023).
doi: 10.3390/rs15112915
Punalekar, S. M. et al. Application of Sentinel-2A data for pasture biomass monitoring using a physically based radiative transfer model. Remote Sens. Environ. 218, 207–220. https://doi.org/10.1016/j.rse.2018.09.028 (2018).
doi: 10.1016/j.rse.2018.09.028
Anderson, G. & McNaughton, L. in 8th Australasian Dairy Symposium. p. 191–195 (2018).
Woodward, S. J. R., Neal, M. B. & Cross, P. S. Preliminary investigation into the feasibility of combining satellite and GPS data to identify pasture growth and grazing. J. N. Z. Grassl. 81, 47–54. https://doi.org/10.33584/jnzg.2019.81.404 (2019).
doi: 10.33584/jnzg.2019.81.404
Harrison, M. T., Roggero, P. P. & Zavattaro, L. Simple, efficient and robust techniques for automatic multi-objective function parameterisation: Case studies of local and global optimisation using APSIM. Environ. Model. Softw. 117, 109–133. https://doi.org/10.1016/j.envsoft.2019.03.010 (2019).
doi: 10.1016/j.envsoft.2019.03.010
Handcock, R. N. et al. in Innovations in remote sensing and photogrammetry lecture notes in geoinformation and cartography (eds Simon Jones & Karin Reinke) Ch. Chapter 24, 309–321 (Springer, 2009).
Mata, G. et al. in Proceedings of New Zealand Grassland Association. p. 109–114 (2011).
Ogungbuyi, M. G. et al. Enabling regenerative agriculture using remote sensing and machine learning. Land 12, 1142. https://doi.org/10.3390/land12061142 (2023).
doi: 10.3390/land12061142
Fulkerson, W. J., Slack, K. & Havilah, E. The effect of defoliation interval and height on growth and herbage quality of kikuyu grass (Pennisetum clandestinum). Trop. Grassl. 33, 138–145 (1999).
Anderson, G. et al. Use of pasture botanical composition data on the accuracy of satellite pasture biomass estimates. J. N. Z. Grassl. 81, 249–254. https://doi.org/10.33584/jnzg.2019.81.367 (2019).
doi: 10.33584/jnzg.2019.81.367
Reeves, M., Fulkerson, W. J., Kellaway, R. C. & Dove, H. A comparison of three techniques to determine the herbage intake of dairy cows grazing kikuyu (Pennisetum clandestinum) pasture. Aust. J. Agric. Res. 36, 23–30 (1996).
doi: 10.1071/EA9960023
Numata, I. et al. Characterization of pasture biophysical properties and the impact of grazing intensity using remotely sensed data. Remote Sens. Environ. 109, 314–327. https://doi.org/10.1016/j.rse.2007.01.013 (2007).
doi: 10.1016/j.rse.2007.01.013
Australian Bureau of Meteorology. Historical weather data, http://www.bom.gov.au/climate/data-services/data-requests.shtml/ . Accessed 9 April 2022.
Chang-Fung-Martel, J., Harrison, M. T., Rawnsley, R., Smith, A. P. & Meinke, H. The impact of extreme climatic events on pasture-based dairy systems: A review. Crop Pasture Sci. 68, 1158–1169. https://doi.org/10.1071/cp16394 (2017).
doi: 10.1071/cp16394
R Development Core Team. R: A language and environment for statistical computing. (2009).
Planet Team. Planet Imagery Product Specifications, https://www.planet.com/products/planet-imagery/ . Accessed 15 Nov 2022.
European Space Agency. Sentinel-2, https://sentinel.esa.int/web/sentinel/missions/sentinel-2/ . Accessed 10 Oct 2022.
Bibby, J. & Toutenburg, H. Improved estimation and prediction. J. Appl. Math. Mech 58, 45–49. https://doi.org/10.1002/zamm.19780580108 (1978).
doi: 10.1002/zamm.19780580108