Estimation of Total Nitrogen Content in Topsoil Based on Machine and Deep Learning Using Hyperspectral Imaging
Abstract
:1. Introduction
2. Materials and Methods
2.1. Topsoil Sample Collection and Preparation
2.2. Hyperspectral Imaging System
2.3. Collection of Hyperspectral Image (HSI)
2.4. Spectral Preprocessing
2.5. Development of Total Nitrogen (TN) Content Prediction Models
2.5.1. Partial Least Squares Regression (PLSR)
2.5.2. One-Dimensional Convolutional Neural Networks (1D-CNNs)
2.5.3. Model Performance Evaluation
3. Results
3.1. TN Content of Topsoil Samples
3.2. Topsoil Spectral Characteristics
3.3. TN Content Prediction Model
3.3.1. Performance of the PLSR Model
3.3.2. Performance of the 1D-CNN Model
3.4. Regression Coefficient of the PLSR Model
3.5. Performance Evaluation of the Optimal Model for Predicting TN Content in Topsoil
4. Discussion
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Data Availability Statement
Conflicts of Interest
References
- Lim, Y.; Kim, S.; Nam, S.; Chun, K.; Kim, M. A Comparison of Current Trends in Soil Erosion Research Using Keyword Co-occurrence Analysis. Korean J. Environ. Ecol. 2020, 34, 413–424. [Google Scholar] [CrossRef]
- Holz, D.J.; Williard, K.W.J.; Edwards, P.J.; Schoonover, J.E. Soil Erosion in Humid Regions: A Review. J. Contemp. Water Res. Educ. 2015, 154, 48–59. [Google Scholar] [CrossRef]
- Conforti, M.; Matteucci, G.; Buttafuoco, G. Using laboratory Vis-NIR spectroscopy for monitoring some forest soil properties. J. Soils Sediments 2018, 18, 1009–1019. [Google Scholar] [CrossRef]
- Morellos, A.; Pantazi, X.E.; Moshou, D.; Alexandridis, T.; Whetton, R.; Tziotzios, G.; Wiebensohn, J.; Bill, R.; Mouazen, A.M. Machine learning based prediction of soil total nitrogen, organic carbon and moisture content by using VIS-NIR spectroscopy. Biosyst. Eng. 2016, 152, 104–116. [Google Scholar] [CrossRef]
- Lee, J.-H. Derivation of regional annual mean rainfall erosivity for predicting topsoil erosion in Korea. J. Korea Water Resour. Assoc. 2018, 51, 783–793. [Google Scholar] [CrossRef]
- Lee, K.; Sung, H.C.; Seo, J.Y.; Yoo, Y.; Kim, Y.; Kook, J.H.; Jeon, S.W. The Integration of Remote Sensing and Field Surveys to Detect Ecologically Damaged Areas for Restoration in South Korea. Remote Sens. 2020, 12, 3687. [Google Scholar] [CrossRef]
- Lee, J.; Lee, S.; Hong, J.; Lee, D.; Bae, J.H.; Yang, J.E.; Kim, J.; Lim, K.J.; Lee, J.; Lee, S.; et al. Evaluation of Rainfall Erosivity Factor Estimation Using Machine and Deep Learning Models. Water 2021, 13, 382. [Google Scholar] [CrossRef]
- Jeong, G. Evaluating Spectral Preprocessing Methods for Visible and Near Infrared Reflectance Spectroscopy to Predict Soil Carbon and Nitrogen in Mountainous Areas. J. Korean Geogr. Soc. 2016, 51, 509–523. [Google Scholar]
- Datta, D.; Paul, M.; Murshed, M.; Teng, S.W.; Schmidtke, L. Soil Moisture, Organic Carbon, and Nitrogen Content Prediction with Hyperspectral Data Using Regression Models. Sensors 2022, 22, 7998. [Google Scholar] [CrossRef]
- Vibhute, A.D.; Kale, K.V.; Gaikwad, S.V.; Dhumal, R.K. Estimation of soil nitrogen in agricultural regions by VNIR reflectance spectroscopy. SN Appl. Sci. 2020, 2, 1523. [Google Scholar] [CrossRef]
- Xu, S.; Wang, M.; Shi, X.; Yu, Q.; Zhang, Z. Integrating hyperspectral imaging with machine learning techniques for the high-resolution mapping of soil nitrogen fractions in soil profiles. Sci. Total Environ. 2021, 754, 142135. [Google Scholar] [CrossRef] [PubMed]
- Jwaideh, M.A.A.; Sutanudjaja, E.H.; Dalin, C. Global impacts of nitrogen and phosphorus fertiliser use for major crops on aquatic biodiversity. Int. J. Life Cycle Assess. 2022, 27, 1058–1080. [Google Scholar] [CrossRef]
- Balasuriya, B.T.G.; Ghose, A.; Gheewala, S.H.; Prapaspongsa, T. Assessment of eutrophication potential from fertiliser application in agricultural systems in Thailand. Sci. Total Environ. 2022, 833, 154993. [Google Scholar] [CrossRef]
- de Santana, F.B.; de Souza, A.M.; Poppi, R.J. Green methodology for soil organic matter analysis using a national near infrared spectral library in tandem with learning machine. Sci. Total Environ. 2019, 658, 895–900. [Google Scholar] [CrossRef] [PubMed]
- Choe, E.; Hong, S.Y.; Kim, Y.; Song, K.; Zhang, Y. Quantification of Soil Properties using Visible-NearInfrared Reflectance Spectroscopy. Korean J. Soil Sci. Fertil. 2009, 42, 522–528. [Google Scholar]
- Ma, J.; Cheng, J.; Wang, J.; Pan, R.; He, F.; Yan, L.; Xiao, J. Rapid detection of total nitrogen content in soil based on hyperspectral technology. Inf. Process. Agric. 2022, 9, 566–574. [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]
- Peng, Y.; Zhao, L.; Hu, Y.; Wang, G.; Wang, L.; Liu, Z. Prediction of soil nutrient contents using visible and near-infrared reflectance spectroscopy. ISPRS Int. J. Geo-Inf. 2019, 8, 437. [Google Scholar] [CrossRef]
- Kim, M.J.; Lim, J.; Kwon, S.W.; Kim, G.; Kim, M.S.; Cho, B.K.; Baek, I.; Lee, S.H.; Seo, Y.; Mo, C. Geographical origin discrimination of white rice based on image pixel size using hyperspectral fluorescence imaging analysis. Appl. Sci. 2020, 10, 5794. [Google Scholar] [CrossRef]
- Gomez, C.; Lagacherie, P.; Coulouma, G. Regional predictions of eight common soil properties and their spatial structures from hyperspectral Vis-NIR data. Geoderma 2012, 189–190, 176–185. [Google Scholar] [CrossRef]
- Sorenson, P.T.; Quideau, S.A.; Rivard, B. High resolution measurement of soil organic carbon and total nitrogen with laboratory imaging spectroscopy. Geoderma 2018, 315, 170–177. [Google Scholar] [CrossRef]
- Yu, H.; Kong, B.; Wang, G.; Du, R.; Qie, G. Prediction of soil properties using a hyperspectral remote sensing method. Arch. Agron. Soil Sci. 2018, 64, 546–559. [Google Scholar] [CrossRef]
- Qi, H.; Paz-Kagan, T.; Karnieli, A.; Jin, X.; Li, S. Evaluating calibration methods for predicting soil available nutrients using hyperspectral VNIR data. Soil Tillage Res. 2018, 175, 267–275. [Google Scholar] [CrossRef]
- Alomar, S.; Mireei, S.A.; Hemmat, A.; Masoumi, A.A.; Khademi, H. Comparison of Vis/SWNIR and NIR spectrometers combined with different multivariate techniques for estimating soil fertility parameters of calcareous topsoil in an arid climate. Biosyst. Eng. 2021, 201, 50–66. [Google Scholar] [CrossRef]
- Yu, G.; Ma, B.; Chen, J.; Li, X.; Li, Y.; Li, C. Nondestructive identification of pesticide residues on the Hami melon surface using deep feature fusion by Vis/NIR spectroscopy and 1D-CNN. J. Food Process Eng. 2021, 44, e13602. [Google Scholar] [CrossRef]
- Vohland, M.; Besold, J.; Hill, J.; Fründ, H.C. Comparing different multivariate calibration methods for the determination of soil organic carbon pools with visible to near infrared spectroscopy. Geoderma 2011, 166, 198–205. [Google Scholar] [CrossRef]
- Jung, A.; Vohland, M.; Thiele-Bruhn, S. Use of a portable camera for proximal soil sensing with hyperspectral image data. Remote Sens. 2015, 7, 11434–11448. [Google Scholar] [CrossRef]
- Zhang, T.; Li, L.; Zheng, B. Estimation of agricultural soil properties with imaging and laboratory spectroscopy. J. Appl. Remote Sens. 2013, 7, 073587. [Google Scholar] [CrossRef]
- Šestak, I.; Mihaljevski Boltek, L.; Mesić, M.; Zgorelec, Ž.; Perčin, A. Hyperspectral sensing of soil ph, total carbon and total nitrogen content based on linear and non-linear calibration methods. J. Cent. Eur. Agric. 2019, 20, 504–523. [Google Scholar] [CrossRef]
- Xu, S.; Zhao, Y.; Wang, M.; Shi, X. Comparison of multivariate methods for estimating selected soil properties from intact soil cores of paddy fields by Vis–NIR spectroscopy. Geoderma 2018, 310, 29–43. [Google Scholar] [CrossRef]
- Kang, D.; Sung, K.; Yeo, U.; Chung, Y.; Lee, S.-M. Riparian Area Characteristics of the Middle and Lower Reaches of the Nakdong River, Korea Riparian Area Characteristics of the Middle and Lower Reaches of the Nakdong River, Korea. J. Environ. Impact Assess. 2008, 17, 189–200. [Google Scholar]
- Kim, M.J.; Lee, H.I.; Choi, J.H.; Lim, K.J.; Mo, C. Development of a Soil Organic Matter Content Prediction Model Based on Supervised Learning Using Vis-NIR/SWIR Spectroscopy. Sensors 2022, 22, 5129. [Google Scholar] [CrossRef] [PubMed]
- Bremner, J.M. Determination of nitrogen in soil by the Kjeldahl method. J. Agric. Sci. 1960, 55, 11–33. [Google Scholar] [CrossRef]
- Kim, W.-K.; Hong, S.-J.; Cui, J.; Kim, H.-J.; Park, J.; Yang, S.-H.; Kim, G. Application of NIR Spectroscopy and Artificial Neural Network Techniques for Real-Time Discrimination of Soil Categories. J. Korean Soc. Nondestruct. Test. 2017, 37, 148–157. [Google Scholar] [CrossRef]
- Barra, I.; Haefele, S.M.; Sakrabani, R.; Kebede, F. Soil spectroscopy with the use of chemometrics, machine learning and pre-processing techniques in soil diagnosis: Recent advances—A review. TrAC Trends Anal. Chem. 2021, 135, 116166. [Google Scholar] [CrossRef]
- Tiecher, T.; Moura-Bueno, J.M.; Caner, L.; Minella, J.P.G.; Evrard, O.; Ramon, R.; Naibo, G.; Barros, C.A.P.; Silva, Y.J.A.B.; Amorim, F.F.; et al. Improving the quantification of sediment source contributions using different mathematical models and spectral preprocessing techniques for individual or combined spectra of ultraviolet–visible, near- and middle-infrared spectroscopy. Geoderma 2021, 384, 114815. [Google Scholar] [CrossRef]
- Geladi, P.; Kowalski, B.R. Partial least-squares regression: A tutorial. Anal. Chim. Acta 1986, 185, 1–17. [Google Scholar] [CrossRef]
- Kiala, Z.; Odindi, J.; Mutanga, O.; Peerbhay, K. Comparison of partial least squares and support vector regressions for predicting leaf area index on a tropical grassland using hyperspectral data. J. Appl. Remote Sens. 2016, 10, 036015. [Google Scholar] [CrossRef]
- Zhang, X.; Yang, J.; Lin, T.; Ying, Y. Food and agro-product quality evaluation based on spectroscopy and deep learning: A review. Trends Food Sci. Technol. 2021, 112, 431–441. [Google Scholar] [CrossRef]
- Yuan, Q.; Wang, J.; Zheng, M.; Wang, X. Hybrid 1D-CNN and attention-based Bi-GRU neural networks for predicting moisture content of sand gravel using NIR spectroscopy. Constr. Build. Mater. 2022, 350, 128799. [Google Scholar] [CrossRef]
- Kawamura, K.; Nishigaki, T.; Andriamananjara, A.; Rakotonindrina, H.; Tsujimoto, Y.; Moritsuka, N.; Rabenarivo, M.; Razafimbelo, T. Using a one-dimensional convolutional neural network on visible and near-infrared spectroscopy to improve soil phosphorus prediction in Madagascar. Remote Sens. 2021, 13, 1519. [Google Scholar] [CrossRef]
- Feng, J.; Wang, L.; Yu, H.; Jiao, L.; Zhang, X. Divide-and-conquer dual-architecture convolutional neural network for classification of hyperspectral images. Remote Sens. 2019, 11, 484. [Google Scholar] [CrossRef]
- Roger, J.M.; Chauchard, F.; Bellon-Maurel, V. EPO-PLS external parameter orthogonalisation of PLS application to temperature-independent measurement of sugar content of intact fruits. Chemom. Intell. Lab. Syst. 2003, 66, 191–204. [Google Scholar] [CrossRef]
- Tahmasbian, I.; Xu, Z.; Boyd, S.; Zhou, J.; Esmaeilani, R.; Che, R.; Hosseini Bai, S. Laboratory-based hyperspectral image analysis for predicting soil carbon, nitrogen and their isotopic compositions. Geoderma 2018, 330, 254–263. [Google Scholar] [CrossRef]
- Rodríguez-Pérez, J.R.; Marcelo, V.; Pereira-Obaya, D.; García-Fernández, M.; Sanz-Ablanedo, E. Estimating Soil Properties and Nutrients by Visible and Infrared Diffuse Reflectance Spectroscopy to Characterize Vineyards. Agronomy 2021, 11, 1895. [Google Scholar] [CrossRef]
- Yang, H.; Kuang, B.; Mouazen, A.M. Quantitative analysis of soil nitrogen and carbon at a farm scale using visible and near infrared spectroscopy coupled with wavelength reduction. Eur. J. Soil Sci. 2012, 63, 410–420. [Google Scholar] [CrossRef]
- Raj, A.; Chakraborty, S.; Duda, B.M.; Weindorf, D.C.; Li, B.; Roy, S.; Sarathjith, M.C.; Das, B.S.; Paulette, L. Soil mapping via diffuse reflectance spectroscopy based on variable indicators: An ordered predictor selection approach. Geoderma 2018, 314, 146–159. [Google Scholar] [CrossRef]
- Viscarra Rossel, R.A.; Behrens, T.; Ben-Dor, E.; Chabrillat, S.; Demattê, J.A.M.; Ge, Y.; Gomez, C.; Guerrero, C.; Peng, Y.; Ramirez-Lopez, L.; et al. Diffuse reflectance spectroscopy for estimating soil properties: A technology for the 21st century. Eur. J. Soil Sci. 2022, 73, e13271. [Google Scholar] [CrossRef]
- dos Santos, E.P.; Moreira, M.C.; Fernandes-Filho, E.I.; Demattê, J.A.M.; dos Santos, U.J.; da Silva, D.D.; Cruz, R.R.P.; Moura-Bueno, J.M.; Santos, I.C.; de Sá Barreto Sampaio, E.V. Improving the generalization error and transparency of regression models to estimate soil organic carbon using soil reflectance data. Ecol. Inform. 2023, 77, 102240. [Google Scholar] [CrossRef]
Preprocessing | Gap Size | Characteristic [35] | ||
---|---|---|---|---|
VNIR (1) (nm) | NIR (2) (nm) | |||
Smoothing (Moving average) | 6 | 7.23 | remove the high-frequency noise from samples | |
Savitzky–Golay first-order derivatives | 10 | 16.87 | eliminate baseline drift and highlight certain peaks in the spectral information | |
14 | 21.69 | |||
18 | 26.51 | |||
Savitzky–Golay second-order derivatives | 10 | 16.87 | eliminate drift of the baseline and identify inflection points in the spectrum | |
14 | 21.69 | |||
18 | 26.51 | |||
Normalization | Maximum | - | - | scales all spectral data to a value between 0 and 1 and minimizes errors presented due to the sample preparation step |
Range | - | - | ||
Mean | - | - | ||
SNV | - | - | eliminate the effects of the instrument’s optical path | |
MSC | - | - | alleviate problems arising from scattered light |
Index | Total | HR (1) | NR (2) | SR (3) | GR (4) |
---|---|---|---|---|---|
Calibration dataset | 834 | 300 | 180 | 174 | 180 |
Prediction dataset | 417 | 150 | 90 | 87 | 90 |
Layer | Filters | Filter Size | Padding | Stride | Activation |
---|---|---|---|---|---|
Convolutional (Conv1) | 64 | 5 | same | - | ReLU (1) |
Max-pooling (Max pooling 1) | - | 3 | - | 2 | - |
Convolutional (Conv2) | 64 | 5 | same | - | ReLU |
Max-pooling (Max pooling 2) | - | 3 | - | 2 | - |
Convolutional (Conv3) | 64 | 5 | same | - | ReLU |
Max-pooling (Max pooling 3) | - | 3 | - | 2 | - |
Flatten | - | - | - | - | - |
Dropout (0.5) | - | - | - | - | - |
Fully connected (Dense1) | 10 | - | - | - | ReLU |
Fully connected (Dense2) | 1 | - | - | - | - |
Wavelength | Pixel Size (Pixel) | Dataset | Total | HR (1) | NR (2) | SR (3) | GR (4) |
---|---|---|---|---|---|---|---|
VNIR | 600 | Calibration | 834 | 300 | 180 | 174 | 180 |
Prediction | 417 | 150 | 90 | 87 | 90 | ||
75 150 300 | Calibration | 8340 | 3000 | 1800 | 1740 | 1800 | |
Prediction | 4170 | 1500 | 900 | 870 | 900 | ||
NIR | 1800 | Calibration | 834 | 300 | 180 | 174 | 180 |
Prediction | 417 | 150 | 90 | 87 | 90 | ||
225 450 900 | Calibration | 8340 | 3000 | 1800 | 1740 | 1800 | |
Prediction | 4170 | 1500 | 900 | 870 | 900 |
Topsoil Sample | Count | TN Content (g kg−1) | |||
---|---|---|---|---|---|
Min. | Max. | Ave. | Std. | ||
Total | 139 | 0.07 | 6.54 | 1.33 | 0.87 |
HR (1) | 50 | 0.13 | 2.64 | 1.32 | 0.57 |
NR (2) | 30 | 0.07 | 2.34 | 1.09 | 0.51 |
SR (3) | 29 | 0.21 | 4.68 | 1.72 | 1.10 |
GR (4) | 30 | 0.10 | 6.54 | 1.22 | 1.18 |
Topsoil Sample | Wavelength Range (nm) | Preprocessing | Rc2 | RMSEC (g kg−1) | Rv2 | RMSEV (g kg−1) | Factor |
---|---|---|---|---|---|---|---|
Total | 400–1000 | Mean Normalization | 0.668 | 0.50 | 0.658 | 0.51 | 4 |
895–1720 | Maximum Normalization | 0.761 | 0.42 | 0.736 | 0.45 | 13 | |
HR (1) | 400–1000 | Moving average | 0.649 | 0.33 | 0.590 | 0.36 | 7 |
895–1720 | Moving average | 0.825 | 0.24 | 0.778 | 0.27 | 14 | |
NR (2) | 400–1000 | Mean Normalization | 0.895 | 0.16 | 0.765 | 0.25 | 10 |
895–1720 | Maximum Normalization | 0.884 | 0.17 | 0.766 | 0.25 | 16 | |
SR (3) | 400–1000 | Moving average | 0.882 | 0.37 | 0.837 | 0.44 | 7 |
895–1720 | Maximum Normalization | 0.965 | 0.20 | 0.933 | 0.28 | 14 | |
GR (4) | 400–1000 | Mean Normalization | 0.925 | 0.32 | 0.916 | 0.34 | 4 |
895–1720 | Maximum Normalization | 0.911 | 0.35 | 0.871 | 0.42 | 13 |
VNIR (400–1000 nm) | Average (600 pixels) | 75 pixels | 150 pixels | 300 pixels | |
Rv2 | 0.684 | 0.759 | 0.955 | 0.903 | |
RMSEV (g kg−1) | 0.55 | 0.42 | 0.18 | 0.27 | |
Rp2 | 0.651 | 0.731 | 0.844 | 0.839 | |
RMSEP (g kg−1) | 0.51 | 0.45 | 0.34 | 0.35 | |
NIR (895–1720 nm) | Average (1800 pixels) | 225 pixels | 450 pixels | 900 pixels | |
Rv2 | 0.360 | 0.760 | 0.887 | 0.931 | |
RMSEV (g kg−1) | 0.78 | 0.42 | 0.29 | 0.23 | |
Rp2 | 0.334 | 0.730 | 0.816 | 0.793 | |
RMSEP (g kg−1) | 0.71 | 0.45 | 0.37 | 0.39 |
Wavelength Range (nm) | Preprocessing | Rv2 | RMSEV (g kg−1) | Rp2 | RMSEP (g kg−1) | |
---|---|---|---|---|---|---|
Total | 400–1000 | 1st derivative (10 nm) | 0.954 | 0.19 | 0.852 | 0.33 |
895–1720 | SNV | 0.982 | 0.11 | 0.922 | 0.24 | |
HR (1) | 400–1000 | 1st derivative (10 nm) | 0.962 | 0.11 | 0.822 | 0.24 |
895–1720 | SNV | 0.978 | 0.08 | 0.877 | 0.20 | |
NR (2) | 400–1000 | 1st derivative (10 nm) | 0.972 | 0.09 | 0.921 | 0.14 |
895–1720 | Moving average | 0.972 | 0.09 | 0.844 | 0.20 | |
SR (3) | 400–1000 | RAW | 0.966 | 0.29 | 0.928 | 0.29 |
895–1720 | 1st derivative (16.87 nm) | 0.986 | 0.14 | 0.947 | 0.25 | |
GR (4) | 400–1000 | SNV | 0.991 | 0.11 | 0.982 | 0.16 |
895–1720 | 1st derivative (12.05 nm) | 0.994 | 0.09 | 0.991 | 0.11 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 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
Kim, M.-J.; Lee, J.-E.; Back, I.; Lim, K.J.; Mo, C. Estimation of Total Nitrogen Content in Topsoil Based on Machine and Deep Learning Using Hyperspectral Imaging. Agriculture 2023, 13, 1975. https://doi.org/10.3390/agriculture13101975
Kim M-J, Lee J-E, Back I, Lim KJ, Mo C. Estimation of Total Nitrogen Content in Topsoil Based on Machine and Deep Learning Using Hyperspectral Imaging. Agriculture. 2023; 13(10):1975. https://doi.org/10.3390/agriculture13101975
Chicago/Turabian StyleKim, Min-Jee, Jae-Eun Lee, Insuck Back, Kyoung Jae Lim, and Changyeun Mo. 2023. "Estimation of Total Nitrogen Content in Topsoil Based on Machine and Deep Learning Using Hyperspectral Imaging" Agriculture 13, no. 10: 1975. https://doi.org/10.3390/agriculture13101975
APA StyleKim, M. -J., Lee, J. -E., Back, I., Lim, K. J., & Mo, C. (2023). Estimation of Total Nitrogen Content in Topsoil Based on Machine and Deep Learning Using Hyperspectral Imaging. Agriculture, 13(10), 1975. https://doi.org/10.3390/agriculture13101975