UAV Hyperspectral Characterization of Vegetation Using Entropy-Based Active Sampling for Partial Least Square Regression Models
Source abstract
Abstract
Optimization of agricultural practices is key for facing the challenges of modern agri-food systems, which are expected to satisfy a growing demand of food production in a landscape characterized by a reduction in cultivable lands and an increasing awareness of sustainability issues. In this work, an operational methodology for characterization of vegetation biomass and nitrogen content based on close-range hyperspectral remote sensing is introduced. It is based on an unsupervised active learning technique suitable for the calibration of a partial least square regression. The proposed technique relies on an innovative usage of Shannon’s entropy and allows for the set-up of an incremental monitoring framework from scratch aiming at minimizing field sampling activities. Experimental results concerning the estimation of grassland biomass and nitrogen content returned RMSE values of 2.05 t/ha and 4.68 kg/ha, respectively. They are comparable with the literature, mostly relying on supervised frameworks and confirmed the suitability of the proposed methodology with operational environments.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Remote Sensing in Agriculture · Spectroscopy and Chemometric Analyses · Smart Agriculture and AI
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Italian Aerospace Research Centre, Via Maiorise snc, 81043 Capua, Italy
Funding
Italian Ministry of Economic Development under the aegis of the project “MONICAP—“Monitoraggio di colture agricole in persistenza””
References (64)
Show source-provided references
1. FAO (2022). The State of Food and Agriculture 2022, FAO.
2. Systematic literature review of implementations of precision agriculture10.1016/j.compag.2020.105626 ↗
3. Digital twins in smart farming10.1016/j.agsy.2020.103046 ↗
4. Digital Twin: Enabling Technologies, Challenges and Open Research10.1109/ACCESS.2020.2998358 ↗
5. A control model for object virtualization in supply chain management10.1016/j.compind.2014.12.011 ↗
6. Ranghetti, M., Boschetti, M., Ranghetti, L., Tagliabue, G., Panigada, C., Gianinetto, M., Verrelst, J., and Candiani, G. (2022). Assessment of maize nitrogen uptake from PRISMA hyperspectral data through hybrid modelling. Eur. J. Remote. Sens.10.1080/22797254.2022.2117650 ↗
7. Sousa, J.J., Toscano, P., Matese, A., Di Gennaro, S.F., Berton, A., Gatti, M., Poni, S., Pádua, L., Hruška, J., and Morais, R. (2022). UAV-Based Hyperspectral Monitoring Using Push-Broom and Snapshot Sensors: A Multisite Assessment for Precision Viticulture Applications. Sensors, 22.10.3390/s22176574 ↗
8. Assessing Grapevine Biophysical Parameters From Unmanned Aerial Vehicles Hyperspectral Imagery10.3389/fpls.2022.898722 ↗
9. Franceschini, M.H.D., Becker, R., Wichern, F., and Kooistra, L. (2022). Quantification of Grassland Biomass and Nitrogen Content through UAV Hyperspectral Imagery—Active Sample Selection for Model Transfer. Drones, 6.10.3390/drones6030073 ↗
10. Adão, T., Hruška, J., Pádua, L., Bessa, J., Peres, E., Morais, R., and Sousa, J.J. (2017). Hyperspectral imaging: A review on UAV-based sensors, data processing and applications for agriculture and forestry. Remote Sens., 9.10.3390/rs9111110 ↗
11. Remote sensing for agricultural applications: A meta-review10.1016/j.rse.2019.111402 ↗
12. SIMPLS: An alternative approach to partial least squares regression10.1016/0169-7439(93)85002-X ↗
13. Forest aboveground biomass estimation using Landsat 8 and Sentinel-1A data with machine learning algorithms10.1038/s41598-020-62922-y ↗
14. Estimation of green grass/herb biomass from airborne hyperspectral imagery using spectral indices and partial least squares regression
15. Non-linear partial least square regression increases the estimation accuracy of grass nitrogen and phosphorus using in situ hyperspectral and environmental data10.1016/j.isprsjprs.2013.04.012 ↗
16. Different units of measurement of carotenoids estimation in cotton using hyperspectral indices and partial least square regression10.1016/j.isprsjprs.2014.01.004 ↗
17. Domain Adaptation for the Classification of Remote Sensing Data: An Overview of Recent Advances10.1109/MGRS.2016.2548504 ↗
18. Berger, K., Caicedo, J.R., Martino, L., Wocher, M., Hank, T., and Verrelst, J. (2021). A survey of active learning for quantifying vegetation traits from terrestrial earth observation data. Remote Sens., 13.10.3390/rs13020287 ↗
19. An Active Learning Approach with Uncertainty, Representativeness, and Diversity10.1155/2014/827586 ↗
20. Lu, X., Zhang, J., Li, T., and Zhang, Y. (2016). Incorporating Diversity into Self-Learning for Synergetic Classification of Hyperspectral and Panchromatic Images. Remote Sens., 8.10.3390/rs8100804 ↗
21. Kernel ridge regression with active learning for wind speed prediction10.1016/j.apenergy.2012.09.055 ↗
22. Yuan, B., Wu, Z., Zhang, K., Li, D., and Ma, Q. (2021, January 28–31). Application of Active Learning in Carbonate Lithologic Identification. Proceedings of the 4th International Conference on Artificial Intelligence and Big Data, Chengdu, China.10.1109/ICAIBD51990.2021.9459104 ↗
23. Batch-Mode Active-Learning Methods for the Interactive Classification of Remote Sensing Images10.1109/TGRS.2010.2072929 ↗
24. Non-destructive estimation of foliar chlorophyll and carotenoid contents: Focus on informative spectral bands
25. Nondestructive and intuitive determination of circadian chlorophyll rhythms in soybean leaves using multispectral imaging10.1038/srep11108 ↗
26. Mapping of Chlorophyll and SPAD Distribution in Pepper Leaves During Leaf Senescence Using Visible and Near-Infrared Hyperspectral Imaging10.13031/trans.59.10536 ↗
27. A Mathematical Theory of Communication10.1002/j.1538-7305.1948.tb00917.x ↗
28. A Lightweight Hyperspectral Mapping System and Photogrammetric Processing Chain for Unmanned Aerial Vehicles10.3390/rs61111013 ↗
29. Estimating plant traits of grasslands from uav-acquired hyperspectral images: A comparison of statistical approaches10.3390/ijgi4042792 ↗
30. A Fast Cluster-Assumption Based Active-Learning Technique for Classification of Remote Sensing Images10.1109/TGRS.2010.2083673 ↗
31. Neter, J., Wasserman, W., and Whitmore, G.A. (2000). Applied Statistics, Allyn & Bacon. [4th ed.].
32. Profillidis, V., and Botzoris, G. (2019). Modeling of Transport Demand, Elsevier.10.1016/B978-0-12-811513-8.00003-0 ↗
33. Using hyperspectral remote sensing data for retrieving canopy chlorophyll and nitrogen content10.1109/JSTARS.2011.2176468 ↗
34. Estimating PAR absorbed by vegetation from bidirectional reflectance measurements10.1016/0034-4257(94)00114-3 ↗
35. Guyot, G., and Baret, F. (1988). Spectral Signatures of Objects in Remote Sensing, European Space Agency.
36. Exploring the relationship between reflectance red edge and chlorophyll concentration in slash pine leaves10.1093/treephys/15.3.203 ↗
37. Evaluation of the MERIS terrestrial chlorophyll index (MTCI)10.1016/j.asr.2006.02.034 ↗
38. Estimating Corn Leaf Chlorophyll Concentration from Leaf and Canopy Reflectance10.1016/S0034-4257(00)00113-9 ↗
39. Estimating chlorophyll content from hyperspectral vegetation indices: Modeling and validation10.1016/j.agrformet.2008.03.005 ↗
40. Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies: Modeling and validation in the context of precision agriculture10.1016/j.rse.2003.12.013 ↗
41. The modified normalized difference vegetation index (mNDVI) a new index to determine frost damages in agriculture based on Landsat TM data10.1080/014311697216810 ↗
42. A soil-adjusted vegetation index (SAVI)10.1016/0034-4257(88)90106-X ↗
43. Overview of the radiometric and biophysical performance of the MODIS vegetation indices10.1016/S0034-4257(02)00096-2 ↗
44. Comparing prediction power and stability of broadband and hyperspectral vegetation indices for estimation of green leaf area index and canopy chlorophyll density10.1016/S0034-4257(00)00197-8 ↗
45. Remote Sensing of Water Content in Eucalyptus Leaves10.1071/BT98042 ↗
46. Estimation of Nitrogen Vertical Distribution by Bi-Directional Canopy Reflectance in Winter Wheat10.3390/s141120347 ↗
47. A narrow-waveband spectral index that tracks diurnal changes in photosynthetic efficiency10.1016/0034-4257(92)90059-S ↗
48. Vincini, M., Frazzi, E., and Alessio, P. (2006, January 19–21). Angular Dependence of Maize and Sugar Beet VIs from Directional CHRIS/Proba Data. Proceedings of the 4th ESA CHRIS PROBA Workshop, online.
49. An investigation into robust spectral indices for leaf chlorophyll estimation10.1016/j.isprsjprs.2011.08.001 ↗
50. Gonenc, A., Ozerdem, M.S., and Acar, E. (2019, January 16–19). Comparison of NDVI and RVI Vegetation Indices Using Satellite Images. Proceedings of the 2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics), Istanbul, Turkey.10.1109/Agro-Geoinformatics.2019.8820225 ↗
51. Red edge spectral measurements from sugar maple leaves10.1080/01431169308953986 ↗
52. Comparison of the variable importance in projection (VIP) and of the selectivity ratio (SR) methods for variable selection and interpretation10.1002/cem.2736 ↗
53. Chemometric Methods for Classification and Feature Selection10.1016/bs.coac.2018.08.006 ↗
54. PLS-Regression: A Basic Tool of Chemometrics10.1016/S0169-7439(01)00155-1 ↗
55. Prediction error estimation: A comparison of resampling methods10.1093/bioinformatics/bti499 ↗
56. Active learning for regression using greedy sampling10.1016/j.ins.2018.09.060 ↗
57. Wang, C., Nie, S., Xi, X., Luo, S., and Sun, X. (2016). Estimating the Biomass of Maize with Hyperspectral and LiDAR Data. Remote Sens., 9.10.3390/rs9010011 ↗
58. Machine learning estimators for the quantity and quality of grass swards used for silage production using drone-based imaging spectrometry and photogrammetry10.1016/j.rse.2020.111830 ↗
59. A feasibility study on diagnosing wheat water status using spectral reflectance10.1007/BF03182831 ↗
60. Improving the Accuracy of the Hyperspectral Model for Apple Canopy Water Content Prediction using the Equidistant Sampling Method10.1038/s41598-017-11545-x ↗
61. Intelligent Sampling for Vegetation Nitrogen Mapping Based on Hybrid Machine Learning Algorithms10.1109/LGRS.2020.3014676 ↗
62. Jin, J., and Wang, Q. (2019). Evaluation of informative bands used in different pls regressions for estimating leaf biochemical contents from hyperspectral reflectance. Remote Sens., 11.10.3390/rs11020197 ↗
63. An assessment of the jackknife and bootstrap procedures on uncertainty estimation in the variable importance in the projection metric10.1016/j.chemolab.2014.05.016 ↗
64. Estimating dry biomass and plant nitrogen concentration in pre-Alpine grasslands with low-cost UAS-borne multispectral data—A comparison of sensors, algorithms, and predictor sets10.5194/bg-19-2699-2022 ↗