Dimensionality Reduction Statistical Models for Soil Attribute Prediction Based on Raw Spectral Data
Abstract
:1. Introduction
2. Materials and Methods
2.1. Soil Samples
2.2. Physical and Chemical Attributes Analyses
2.3. Spectral Data Acquisition
2.4. Data Modeling
3. Results and Discussion
4. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Wollenhaupt, N.C.; Wolkowski, R.P.; Clayton, M.K. Mapping Soil Test Phosphorus and Potassium for Variable-Rate Fertilizer Application. J. Prod. Agric. 1994, 7, 441–448. [Google Scholar] [CrossRef]
- Cherubin, M.R.; Santi, A.L.; Eitelwein, M.T.; Amado, T.J.C.; Simon, D.H.; Damian, J.M. Dimensão da malha amostral para caracterização da variabilidade espacial de fósforo e potássio em Latossolo Vermelho. Pesqui. Agropecuária Bras. 2015, 50, 168–177. (In Portuguese) [Google Scholar] [CrossRef]
- Viscarra Rossel, R.A.; Adamchuk, V.I.; Sudduth, K.A.; McKenzie, N.J.; Lobsey, C. Proximal soil sensing: An effective approach for soil measurements in space and time. In Advances in Agronomy; Sparks, D.L., Ed.; Academic Press: London, UK, 2011; pp. 243–291. [Google Scholar]
- Wang, D.; Chakraborty, S.; Weindorf, D.C.; Li, B.; Sharma, A.; Paul, S.; Ali, N. Synthesized use of VisNIR DRS and PXRF for soil characterization: Total carbon and total nitrogen. Geoderma 2015, 243–244, 157–167. [Google Scholar] [CrossRef]
- Molin, J.P.; Tavares, T.R. Sensor Systems for Mapping Soil Fertility Attributes: Challenges, Advances, and Perspectives in Brazilian Tropical Soils. Eng. Agrícola 2019, 39, 126–147. [Google Scholar] [CrossRef]
- Kuang, B.; Mahmood, H.S.; Quraishi, M.Z.; Hoogmoed, W.B.; Mouazen, A.M.; van Henten, E.J. Sensing soil properties in the laboratory, in situ, and on-line: A review. In Advances in Agronomy; Sparks, D.L., Ed.; Academic Press: London, UK, 2012; pp. 155–223. [Google Scholar]
- Sharma, R.; Kamble, S.S.; Gunasekaran, A.; Kumar, V.; Kumar, A. A systematic literature review on machine learning applications for sustainable agriculture supply chain performance. Comput. Oper. Res. 2020, 119, 104926. [Google Scholar] [CrossRef]
- Rossi, P.; Mangiavacchi, P.L.; Monarca, D.; Cecchini, M. Smart Machinery and Devices for Reducing Risks from Human-Machine Interference in Agriculture: A Review. In Safety, Health and Welfare in Agriculture and Agro-food Systems; Biocca, M., Cavallo, E., Cecchine, M., Failla, S., Romano, E., Eds.; Springer: Cham, Switzerland, 2022; pp. 195–204. [Google Scholar]
- Nocita, M.; Stevens, A.; van Wesemael, B.; Aitkenhead, M.; Bachmann, M.; Barthès, B.; Dor, E.B.; Brown, D.J.; Clairotte, M.; Csorba, A.; et al. Soil spectroscopy: An alternative to wet chemistry for soil monitoring. In Advances in Agronomy; Sparks, D.L., Ed.; Academic Press: London, UK, 2015; pp. 139–159. [Google Scholar]
- Pasquini, C. Near infrared spectroscopy: A mature analytical technique with new perspectives–A review. Anal. Chim. Acta 2018, 1026, 8–36. [Google Scholar] [CrossRef]
- Bönecke, E.; Meyer, S.; Vogel, S.; Schröter, I.; Gebbers, R.; Kling, C.; Kramer, E.; Lück, K.; Nagel, A.; Philipp, G.; et al. Guidelines for precise lime management based on high-resolution soil pH, texture and SOM maps generated from proximal soil sensing data. Precis. Agric. 2020, 22, 493–523. [Google Scholar] [CrossRef]
- Vogel, S.; Bönecke, E.; Kling, C.; Kramer, E.; Lück, K.; Philipp, G.; Rühlmann, J.; Schröter, I.; Gebbers, R. Direct prediction of site-specific lime requirement of arable fields using the base neutralizing capacity and a multi-sensor platform for on-the-go soil mapping. Precis. Agric. 2022, 23, 127–149. [Google Scholar] [CrossRef]
- Munnaf, M.A.; Haesaert, G.; Van Meirvenne, M.; Mouazen, A.M. Multi-sensors data fusion approach for site-specific seeding of consumption and seed potato production. Precis. Agric. 2021, 22, 1890–1917. [Google Scholar] [CrossRef]
- Kalnicky, D.J.; Singhvi, R. Field portable XRF analysis of environmental samples. J. Hazard. Mater. 2001, 83, 93–122. [Google Scholar] [CrossRef] [Green Version]
- Nawar, S.; Delbecque, N.; Declercq, Y.; De Smedt, P.; Finke, P.; Verdoodt, A.; Mouazen, A.M. Can spectral analyses improve measurement of key soil fertility parameters with X-ray fluorescence spectrometry? Geoderma 2019, 350, 29–39. [Google Scholar] [CrossRef]
- Tavares, T.R.; Molin, J.P.; Javadi, S.H.; De Carvalho, H.W.P.; Mouazen, A.M. Combined Use of Vis-NIR and XRF Sensors for Tropical Soil Fertility Analysis: Assessing Different Data Fusion Approaches. Sensors 2021, 21, 148. [Google Scholar] [CrossRef] [PubMed]
- Munnaf, M.A.; Guerrero, A.; Nawar, S.; Haesaert, G.; Van Meirvenne, M.; Mouazen, A.M. A combined data mining approach for on-line prediction of key soil quality indicators by Vis-NIR spectroscopy. Soil Tillage Res. 2021, 205, 104808. [Google Scholar] [CrossRef]
- Javadi, S.H.; Munnaf, M.A.; Mouazen, A.M. Fusion of Vis-NIR and XRF spectra for estimation of key soil attributes. Geoderma 2021, 385, 114851. [Google Scholar] [CrossRef]
- Mishra, P.; Rutledge, D.N.; Roger, J.-M.; Wali, K.; Khan, H.A. Chemometric pre-processing can negatively affect the performance of near-infrared spectroscopy models for fruit quality prediction. Talanta 2021, 229, 122303. [Google Scholar] [CrossRef] [PubMed]
- Jolliffe, I. Principal Component Analysis (pp. 1094–1096). Springer Berlin Heidelberg. RESUME SELİN DEĞİRMECİ Marmara University, Goztepe Campus ProQuest Number: ProQuest). Copyright of the Dissertation Is Held by the Author. All Rights Reserved, 28243034; Springer: New York, NY, USA, 2011. [Google Scholar]
- Agarwal, A.; Shah, D.; Shen, D.; Song, D. On robustness of principal component regression. J. Am. Stat. Assoc. 2021, 10, 1–34. [Google Scholar] [CrossRef]
- Lee, J.H.; Shi, Z.; Gao, Z. On LASSO for predictive regression. J. Econ. 2021, 229, 322–349. [Google Scholar] [CrossRef]
- Pudełko, A.; Chodak, M. Estimation of total nitrogen and organic carbon contents in mine soils with NIR reflectance spectroscopy and various chemometric methods. Geoderma 2020, 368, 114306. [Google Scholar] [CrossRef]
- Bricklemyer, R.S.; Brown, D.J.; Turk, P.J.; Clegg, S. Comparing vis-NIRS, LIBS, and combined vis-NIRS-LIBS for intact soil core soil carbon measurement. Soil Sci. Soc. Am. J. 2018, 82, 1482–1496. [Google Scholar] [CrossRef]
- Kuang, B.; Tekin, Y.; Mouazen, A.M. Comparison between artificial neural network and partial least squares for on-line visible and near infrared spectroscopy measurement of soil organic carbon, pH and clay content. Soil Tillage Res. 2015, 146, 243–252. [Google Scholar] [CrossRef]
- Knox, N.; Grunwald, S.; McDowell, M.; Bruland, G.; Myers, D.; Harris, W. Modelling soil carbon fractions with visible near-infrared (VNIR) and mid-infrared (MIR) spectroscopy. Geoderma 2015, 239–240, 229–239. [Google Scholar] [CrossRef]
- Wold, S.; Sjöström, M.; Eriksson, L. PLS-regression: A basic tool of chemometrics. Chemom. Intell. Lab. Syst. 2001, 58, 109–130. [Google Scholar] [CrossRef]
- Bellon-Maurel, V.; McBratney, A. Near-infrared (NIR) and mid-infrared (MIR) spectroscopic techniques for assessing the amount of carbon stock in soils–Critical review and research perspectives. Soil Biol. Biochem. 2011, 43, 1398–1410. [Google Scholar] [CrossRef]
- Rossel, R.V.; Behrens, T. Using data mining to model and interpret soil diffuse reflectance spectra. Geoderma 2010, 158, 46–54. [Google Scholar] [CrossRef]
- Tavares, T.R.; Molin, J.P.; Nunes, L.C.; Alves, E.E.N.; Krug, F.J.; de Carvalho, H.W.P. Spectral data of tropical soils using dry-chemistry techniques (Vis-NIR, XRF, and LIBS): A dataset for soil fertility prediction. Data Brief 2022, 41, 108004. [Google Scholar] [CrossRef]
- Van Raij, B.; Andrade, J.C.; Cantarela, H.; Quaggio, J.A. Análise Química Para Avaliação de Solos Tropicais; IAC: Campinas, Brazil, 2001; 285p. (In Portuguese) [Google Scholar]
- Tavares, T.R.; Molin, J.P.; Nunes, L.C.; Alves, E.E.N.; Melquiades, F.L.; de Carvalho, H.W.P.; Mouazen, A.M. Effect of X-Ray Tube Configuration on Measurement of Key Soil Fertility Attributes with XRF. Remote Sens. 2020, 12, 963. [Google Scholar] [CrossRef]
- R Core Team. R: A Language and Environment for Statistical Computing; R Foundation for Statistical Computing: Vienna, Austria, 2018. [Google Scholar]
- Olive, D.J. Linear Regression, 1st ed.; Springer: Cham, Switzerland, 2017; Multiple linear regression; pp. 17–83. [Google Scholar]
- Tibshirani, R. Regression Shrinkage and Selection via the Lasso: A retrospective. J. R. Stat. Soc. 2011, 73, 267–288. [Google Scholar] [CrossRef]
- Kuhn, M. Building Predictive Models in R Using the caret Package. J. Stat. Softw. 2008, 28, 1548–7660. [Google Scholar] [CrossRef]
- Tracy, T.; Fu, Y.; Roy, I.; Jonas, E.; Glendenning, P. High Performance Computing; Kunkel, J., Balaji, P., Dongarra, J., Eds.; Springer: Cham, Switzerland, 2015; pp. 200–218. [Google Scholar]
- Seasholtz, M.B.; Kowalski, B. The parsimony principle applied to multivariate calibration. Anal. Chim. Acta 1993, 277, 165–177. [Google Scholar] [CrossRef]
- Abdul Munnaf, M.; Nawar, S.; Mouazen, A.M. Estimation of Secondary Soil Properties by Fusion of Laboratory and On-Line Measured Vis–NIR Spectra. Remote. Sens. 2019, 11, 2819. [Google Scholar] [CrossRef] [Green Version]
- Mouazen, A.M.; Kuang, B. On-line visible and near infrared spectroscopy for in-field phosphorous management. Soil Tillage Res. 2016, 155, 471–477. [Google Scholar] [CrossRef]
- Stenberg, B.; Viscarra-Rossel, R.A.; Mouazen, A.M.; Wetterlind, J. Visible and near infrared spectroscopy in soil science. In Advances in Agronomy; Sparks, D.L., Ed.; Academic Press: London, UK, 2010; pp. 163–215. [Google Scholar]
- Tavares, T.; Molin, J.; Nunes, L.; Wei, M.; Krug, F.; de Carvalho, H.; Mouazen, A. Multi-Sensor Approach for Tropical Soil Fertility Analysis: Comparison of Individual and Combined Performance of VNIR, XRF, and LIBS Spectroscopies. Agronomy 2021, 11, 1028. [Google Scholar] [CrossRef]
- Chang, C.-W.; Laird, D.A.; Mausbach, M.J.; Hurburgh, C.R., Jr. Near-Infrared Reflectance Spectroscopy-Principal Components Regression Analyses of Soil Properties. Soil Sci. Soc. Am. J. 2001, 65, 480–490. [Google Scholar] [CrossRef]
- Li, S.; Ji, W.; Chen, S.; Peng, J.; Zhou, Y.; Shi, Z. Potential of VIS-NIR-SWIR Spectroscopy from the Chinese Soil Spectral Library for Assessment of Nitrogen Fertilization Rates in the Paddy-Rice Region, China. Remote Sens. 2015, 7, 7029–7043. [Google Scholar] [CrossRef]
- Wijewardane, N.K.; Ge, Y.; Morgan, C.L.S. Moisture insensitive prediction of soil properties from Vis-NIR reflectance spectra based on external parameter orthogonalization. Geoderma 2016, 267, 92–101. [Google Scholar] [CrossRef]
- Franceschini, M.; Demattê, J.; Kooistra, L.; Bartholomeus, H.; Rizzo, R.; Fongaro, C.; Molin, J. Effects of external factors on soil reflectance measured on-the-go and assessment of potential spectral correction through orthogonalisation and standardisation procedures. Soil Tillage Res. 2018, 177, 19–36. [Google Scholar] [CrossRef]
- Benedet, L.; Faria, W.M.; Silva, S.H.G.; Mancini, M.; Demattê, J.A.M.; Guilherme, L.R.G.; Curi, N. Soil texture prediction using portable X-ray fluorescence spectrometry and visible near-infrared diffuse reflectance spectroscopy. Geoderma 2020, 376, 114553. [Google Scholar] [CrossRef]
- Kopačková, V.; Ben-Dor, E.; Carmon, N.; Notesco, G. Modelling Diverse Soil Attributes with Visible to Longwave Infrared Spectroscopy Using PLSR Employed by an Automatic Modelling Engine. Remote Sens. 2017, 9, 134. [Google Scholar] [CrossRef]
- Velliangiri, S.; Alagumuthukrishnan, S.; Joseph, S.I.T. A Review of Dimensionality Reduction Techniques for Efficient Computation. Procedia Comput. Sci. 2019, 165, 104–111. [Google Scholar] [CrossRef]
Sensor | Target Variable | Number of Components Used | Variance Explained (%) | Validation | Tavares et al. [42] | ||
---|---|---|---|---|---|---|---|
RMSE | R2 | RMSE | R2 | ||||
Vis-NIR | Clay | 2 | 84.91 | 42.80 | 0.80 | 27.32 | 0.93 |
OM | 7 | 72.29 | 2.95 | 0.72 | 2.10 | 0.86 | |
CEC | 10 | 71.39 | 18.91 | 0.56 | 18.66 | 0.51 | |
pH | 19 | 70.47 | 0.28 | 0.58 | 0.34 | 0.19 | |
V% | 2 | 75.99 | 10.60 | 0.79 | 10.38 | 0.80 | |
P | 3 | 11.87 | 13.76 | 0.03 | 12.05 | 0.07 | |
K | 4 | 66.29 | 0.90 | 0.82 | 1.20 | 0.74 | |
Ca | 2 | 69.61 | 12.80 | 0.63 | 10.98 | 0.68 | |
Mg | 10 | 71.05 | 9.34 | 0.59 | 8.85 | 0.52 | |
XRF | Clay | 1 | 83.00 | 45.63 | 0.78 | 29.40 | 0.92 |
OM | 19 | 66.28 | 3.89 | 0.52 | 3.01 | 0.74 | |
CEC | 4 | 72.46 | 15.37 | 0.70 | 10.19 | 0.88 | |
pH | 13 | 53.80 | 0.24 | 0.68 | 0.33 | 0.34 | |
V% | 1 | 78.87 | 9.68 | 0.83 | 5.60 | 0.95 | |
P | 15 | 41.26 | 11.39 | 0.33 | 13.27 | 0.01 | |
K | 2 | 67.47 | 0.82 | 0.85 | 0.53 | 0.95 | |
Ca | 1 | 72.06 | 11.99 | 0.68 | 4.09 | 0.96 | |
Mg | 4 | 71.54 | 8.13 | 0.68 | 4.28 | 0.89 |
Sensor | Target Variable | α | λ | Validation | Tavares et al. [42] | ||
---|---|---|---|---|---|---|---|
RMSE | R2 | RMSE | R2 | ||||
Vis-NIR | Clay | 0.10 | 5.140 | 38.03 | 0.84 | 27.32 | 0.93 |
OM | 0.10 | 0.218 | 2.95 | 0.71 | 2.10 | 0.86 | |
CEC | 0.10 | 1.149 | 21.27 | 0.44 | 18.66 | 0.51 | |
pH | 0.55 | 0.044 | 0.35 | 0.33 | 0.34 | 0.19 | |
V% | 0.10 | 1.140 | 10.98 | 0.78 | 10.38 | 0.80 | |
P | 1.00 | 3.220 | 13.30 | 0.06 | 12.05 | 0.07 | |
K | 0.10 | 0.387 | 0.94 | 0.81 | 1.20 | 0.74 | |
Ca | 0.55 | 0.929 | 12.95 | 0.62 | 10.98 | 0.68 | |
Mg | 0.10 | 0.557 | 10.72 | 0.45 | 8.85 | 0.52 | |
XRF | Clay | 0.10 | 5.554 | 42.23 | 0.81 | 29.40 | 0.92 |
OM | 0.10 | 2.513 | 3.58 | 0.59 | 3.01 | 0.74 | |
CEC | 0.55 | 4.329 | 16.45 | 0.68 | 10.19 | 0.88 | |
pH | 0.10 | 0.148 | 0.24 | 0.70 | 0.33 | 0.34 | |
V% | 0.10 | 4.051 | 4.63 | 0.96 | 5.60 | 0.95 | |
P | 1.00 | 4.432 | 12.42 | 0.34 | 13.27 | 0.01 | |
K | 0.10 | 0.145 | 0.60 | 0.92 | 0.53 | 0.95 | |
Ca | 1.00 | 1.110 | 7.91 | 0.86 | 4.09 | 0.96 | |
Mg | 0.10 | 0.660 | 6.63 | 0.81 | 4.28 | 0.89 |
Sensor | Target Variable | Validation | Tavares et al. [42] | ||
---|---|---|---|---|---|
RMSE | R2 | RMSE | R2 | ||
Vis-NIR | Clay | 158.60 | 0.32 | 27.32 | 0.93 |
OM | 38.98 | 0.01 | 2.10 | 0.86 | |
CEC | 86.61 | 0.10 | 18.66 | 0.51 | |
pH | 1.37 | 0.01 | 0.34 | 0.19 | |
V% | 81.66 | 0.15 | 10.38 | 0.80 | |
P | 70.10 | 0.03 | 12.05 | 0.07 | |
K | 9.54 | 0.22 | 1.20 | 0.74 | |
Ca | 83.37 | 0.07 | 10.98 | 0.68 | |
Mg | 35.72 | 0.09 | 8.85 | 0.52 | |
XRF | Clay | 448.21 | 0.02 | 29.40 | 0.92 |
OM | 33.79 | 0.13 | 3.01 | 0.74 | |
CEC | 444.65 | 0.01 | 10.19 | 0.88 | |
pH | 10.20 | 0.01 | 0.33 | 0.34 | |
V% | 482.51 | 0.00 | 5.60 | 0.95 | |
P | 51.07 | 0.09 | 13.27 | 0.01 | |
K | 23.35 | 0.01 | 0.53 | 0.95 | |
Ca | 394.45 | 0.00 | 4.09 | 0.96 | |
Mg | 314.98 | 0.03 | 4.28 | 0.89 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Wei, M.C.F.; Canal Filho, R.; Tavares, T.R.; Molin, J.P.; Vieira, A.M.C. Dimensionality Reduction Statistical Models for Soil Attribute Prediction Based on Raw Spectral Data. AI 2022, 3, 809-819. https://doi.org/10.3390/ai3040049
Wei MCF, Canal Filho R, Tavares TR, Molin JP, Vieira AMC. Dimensionality Reduction Statistical Models for Soil Attribute Prediction Based on Raw Spectral Data. AI. 2022; 3(4):809-819. https://doi.org/10.3390/ai3040049
Chicago/Turabian StyleWei, Marcelo Chan Fu, Ricardo Canal Filho, Tiago Rodrigues Tavares, José Paulo Molin, and Afrânio Márcio Corrêa Vieira. 2022. "Dimensionality Reduction Statistical Models for Soil Attribute Prediction Based on Raw Spectral Data" AI 3, no. 4: 809-819. https://doi.org/10.3390/ai3040049
APA StyleWei, M. C. F., Canal Filho, R., Tavares, T. R., Molin, J. P., & Vieira, A. M. C. (2022). Dimensionality Reduction Statistical Models for Soil Attribute Prediction Based on Raw Spectral Data. AI, 3(4), 809-819. https://doi.org/10.3390/ai3040049