Abstract
This work describes an approach to calculate pedological parameter maps using hyperspectral remote sensing and soil sensors. These maps serve as information basis for automated and precise agricultural treatments by tractors and field robots. Soil samples are recorded by a handheld hyperspectral sensor and analyzed in the laboratory for pedological parameters. The transfer of the correlation between these two data sets to aerial hyperspectral images leads to 2D-parameter maps of the soil surface. Additionally, rod-like soil sensors provide local 3D-information of pedological parameters under the soil surface. The goal is to combine the area-covering 2D-parameter maps with the local 3D-information to extrapolate large-scale 3D-parameter maps using AI approaches.
Zusammenfassung
Diese Arbeit beschreibt einen Ansatz zur Erstellung bodenkundlicher Parameterkarten mittels hyperspektraler Fernerkundung und Bodensensorik, als Informationsgrundlage für automatisierte und präzise landwirtschaftliche Anwendungen durch Traktoren und Feldroboter. Dazu werden Bodenproben hyperspektral untersucht und pedologische Parameter im Labor analysiert. Die Übertragung der Korrelation zwischen diesen beiden Datensätzen auf hyperspektrale Luftbilder erzeugt 2D-Parameterkarten der Bodenoberfläche. Zusätzlich werden stabähnliche Bodensensoren im Feld versenkt, die lokal 3D-Information über pedologische Parameter liefern. Ziel ist die Verknüpfung der flächendeckenden 2D-Parameterkarten mit lokaler 3D-Information durch KI, um flächendeckende 3D-Parameterkarten zu erstellen.
About the authors
Simon Schreiner received his Master of Science degree in Applied Geoinformatics at the University of Trier, Germany, in 2016. He was research assistant at this University from 2012 until 2016. In 2017, he was cartographer at the City Department of Surveying in Stuttgart, Germany. Since 2018, he has been employed at the Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB in Ettlingen, Germany. His research focusses on hyperspectral remote sensing for defense technologies and precision farming applications.
Dubravko Culibrk is a Full Professor of Information Systems Engineering at the Department of Industrial Engineering and Management of the Faculty of Technical Sciences, University of Novi Sad, Serbia. While pursuing his PhD degree (2003–2006) at the Florida Atlantic University, USA, he was affiliated with the Center for Coastline Security and the Center for Cryptology and Information Security. He spent two years (2013–2015) as a postdoc researcher at the University of Trento, Italy with the Multimedia and Human Understanding Group. His current research interests include: Neural Networks and Deep Learning, Computer Vision, Machine Learning and Data Science, Multimedia, Remote Sensing and Image/Video Processing. He is an NVIDIA Deep Learning Institute University Ambassador.
Michele Bandecchi is the CEO of SmartCloudFarming GmbH and he is supervising the business and technology development of the company’s products. He received his two Master degrees in (i) Plant Biotechnology with specialization plant genomics and (ii) Management, Marketing and Consumer Studies with a specialization in Innovation Management at the Wageningen University Research (The Netherlands). He gained experience in marketing and sales during an internship with GRASSLANDZ TECHNOLOGY LTD. in New Zealand and for ten years in his family business in marketing and sales and business development.
Wolfgang Gross was born in Karlsruhe, Germany, in 1985. He received the Diploma in technomathematics from the Karlsruhe Institute of Technology KIT, Germany, in 2011. In 2019, he received his Ph. D. in engineering from the University of Stuttgart, Faculty for Aerospace Engineering and Geodesy. He is currently employed by the Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB, His current research includes the development of algorithms for hyperspectral analysis regarding data-driven automatic preprocessing, classification and manifold alignment for data synthesis.
Dr. Wolfgang Middelmann is the head of the image interpretation group at Fraunhofer IOSB. He got his diploma in mathematics at University Dortmund (Germany) in 1993. In 1998 he received his PhD (Dr. rer. nat.) in mathematics at Friedrich-Schiller-University Jena (Germany). Until 2002 he worked as software engineering manager for ESA projects and as project manager of international military projects at Daimler-Chrysler Aerospace. Since 2002 he was project manager and scientist for ATR and reconnaissance systems at FGAN-FOM Research Institute for Optronics and Pattern Recognition (2010 merged into Fraunhofer IOSB), Ettlingen (Germany). In 2008 he advanced to the head of the image interpretation group. Currently he is responsible for concepts, development and assessment of airborne and spaceborne ISR systems.
Acknowledgment
The authors would like to thank the German Aerospace Center for providing EnMAP simulations based on HySpex data and Dylan Warren Raffa for the agronomic insights and expertise.
References
1. Gomiero, T., D. Pimentel and M. G. Paoletti. 2011. Environmental impact of different agricultural management practices: conventional vs. organic agriculture. Critical Reviews in Plant Sciences 30 (1-2): 95–124. DOI: 10.1080/07352689.2011.554355.Search in Google Scholar
2. Finger, R., S. M. Swinton, N. El Benni and A. Walter. 2019. Precision farming at the nexus of agricultural production and the environment. Annual Review of Resource Economics 11 (1): 313–335.10.1146/annurev-resource-100518-093929Search in Google Scholar
3. Ge, Y., J. A. Thomasson and R. Sui. 2011. Remote sensing of soil properties in precision agriculture: A review. Front. Earth Sci. 5: 229. DOI: 10.1007/s11707-011-0175-0.Search in Google Scholar
4. Bellon-Maurel, V. and A. McBratney. 2011. Near-infrared (NIR) and mid-infrared (MIR) spectroscopic techniques for assessing the amount of carbon stock in soils – critical review and research perspectives. Soil Biology and Biochemistry 43 (7): 1398–1410. DOI: 10.1016/j.soilbio.2011.02.019.Search in Google Scholar
5. Stoner, E. R. and M. F. Baumgardner. 1981. Characteristic variations in reflectance of surface soils 1. Soil Science Society of America Journal 45(6): 1161. DOI: 10.2136/sssaj1981.03615995004500060031x.Search in Google Scholar
6. Stevens, A., T. Udelhoven, A. Denis, B Tychon, R. Lioy, L. Hoffmann and B. van Wesemael. 2010. Measuring soil organic carbon in croplands at regional scale using airborne imaging spectroscopy. Geoderma 158 (1-2): 32–45. DOI: 10.1016/j.geoderma.2009.11.032.Search in Google Scholar
7. Viscarra Rossel, R. A., S. R. Cattle, A. Ortega and Y. Fouad. 2009. In situ measurements of soil colour, mineral composition and clay content by vis–NIR spectroscopy. Geoderma 150 (3-4): 253–266. DOI: 10.1016/j.geoderma.2009.01.025.Search in Google Scholar
8. Aldabaa, A. A. A., D. C. Weindorf, S. Chakraborty, A. Sharma and B. Li. 2015. Combination of proximal and remote sensing methods for rapid soil salinity quantification. Geoderma 239–240: 34–46. DOI: 10.1016/j.geoderma.2014.09.011.Search in Google Scholar
9. Stenberg, B. 2010. Effects of soil sample pretreatments and standardised rewetting as interacted with sand classes on Vis-NIR predictions of clay and soil organic carbon. Geoderma 158 (1-2): 15–22. DOI: 10.1016/j.geoderma.2010.04.008.Search in Google Scholar
10. Keller, S., F. M. Riese, N. Allroggen, C. Jackisch and S. Hinz. 2018. Modeling subsurface soil moisture based on hyperspectral data – first results of a multilateral field campaign. In: Tagungsband der 38. Wissenschaftlich-Technischen Jahrestagung der DGPF e. V., vol. 27, pp. 34–48.Search in Google Scholar
11. Schreiner, S., H. Buddenbaum, C. Emmerling and M. Steffens. 2015. VNIR/SWIR laboratory imaging spectroscopy for wall-to-wall mapping of elemental concentrations in soil cores. Photogrammetrie - Fernerkundung - Geoinformation 2015 (6): 423–435. DOI: 10.1127/pfg/2015/0279.Search in Google Scholar
12. Qian, J. H., J. W. Doran, K. L. Weier, A. R. Mosier, T. A. Peterson and J. F. Power. 1997. Soil denitrification and nitrous oxide losses under corn irrigated with high-nitrate groundwater. Journal of Environmental Quality 26 (2).10.2134/jeq1997.00472425002600020004xSearch in Google Scholar
13. Moon, T., T. I. Ahn and J. E. Son. 2018. Forecasting root-zone electrical conductivity of nutrient solutions in closed-loop soilless cultures via a recurrent neural network using environmental and cultivation information. Frontiers in Plant Science 9: 859.10.3389/fpls.2018.00859Search in Google Scholar
14. Hochreiter, S. and J. Schmidhuber. 1997. Long short-term memory. Neural Comput. 9: 1735–1780. DOI: 10.1162/neco.1997.9.8.1735.Search in Google Scholar
15. Fang, K., M. Pan and C. Shen. 2018. The value of SMAP for long-term soil moisture estimation with the help of deep learning. IEEE Transactions on Geoscience and Remote Sensing 57 (4): 2221–2233.10.1109/TGRS.2018.2872131Search in Google Scholar
16. Zhu, J.-H., M. M. Zaman and S. A. Anderson. 1998. Modelling of shearing behavior of a residual soil with Recurrent Neural Network. International Journal for Numerical and Analytical Methods in Geomechanics 22 (8).10.1002/(SICI)1096-9853(199808)22:8<671::AID-NAG939>3.0.CO;2-YSearch in Google Scholar
17. Li, Q, Y. Zhao and F. Yu. 2020. A novel multichannel long short-term memory method with time series for soil temperature modeling. IEEE Access 8: 182026–182043. DOI: 10.1109/ACCESS.2020.3028995.Search in Google Scholar
18. Lenz, A., H. Schilling and W. Middelmann. 2014. Umwelt- und Katastrophenschutz mit einem luftgetragenen hyperspektralen Multisensorsystem. Technische Sicherheit 4 (2014): 33–36. ISSN: 2191-0073.Search in Google Scholar
19. Kokaly, R. and R. N. Clark. 1999. Spectroscopic determination of leaf biochemistry using band-depth analysis of absorption features and stepwise multiple linear regression. Remote Sensing of Environment 67 (3): 267–287. DOI: 10.1016/S0034-4257(98)00084-4.Search in Google Scholar
20. Wold, S., M. Sjöström and L. Eriksson. 2001. PLS-regression. A basic tool of chemometrics. Chemometrics and Intelligent Laboratory Systems 58 (2), 109–130. DOI: 10.1016/S0169-7439(01)00155-1.Search in Google Scholar
21. Steffens, M. and H. Buddenbaum. 2013. Laboratory imaging spectroscopy of a stagnic Luvisol profile – high resolution soil characterisation, classification and mapping of elemental concentrations. Geoderma 195–196: 122–132. DOI: 10.1016/j.goderma.2012.11.011.Search in Google Scholar
22. Marabel, M. and F. Alvarez-Taboada. 2013. Spectroscopic determination of aboveground biomass in grasslands using spectral transformations, support vector machine and partial least squares regression. Sensors 13 (8): 10027–10051. DOI: 10.3390/s130810027.Search in Google Scholar
23. Vohland, M. and C. Emmerling. 2011. Determination of total soil organic C and hot water-extractable C from VIS-NIR soil reflectance with partial least squares regression and spectral feature selection techniques. European Journal of Soil Science 62 (4): 598–606. DOI: 10.1111/j.1365-2389.2011.01369.x.Search in Google Scholar
24. Ben-Dor, E., D. Heller and A. Chudnovsky. 2008. A novel method of classifying soil profiles in the field using optical means. Soil Science Society of America Journal 72 (4): 1113. DOI: 10.2136/sssaj2006.0059.Search in Google Scholar
25. Becker, M., S. Schreiner, S. Auer, D. Cerra. P. Gege, M. Bachmann, A. Roitzsch, U. Mitschke and W. Middelmann. 2018. Reconnaissance of coastal areas using simulated EnMAP data in an ERDAS IMAGINE environment. In: SPIE Remote Sensing, Proceedings, vol. 10790. DOI: 10.1117/12.2325402.Search in Google Scholar
© 2021 Walter de Gruyter GmbH, Berlin/Boston