A Novel Model for Soil Organic Matter and Total Nitrogen Detection Based on Visible/Shortwave Near-Infrared Spectroscopy
Soil organic matter (SOM) and total nitrogen (TN) are critical indicators for assessing soil fertility. Although laboratory chemical analysis methods can accurately measure their contents, these techniques are time-consuming and labor-intensive. Spectral technology, characterized by its high sensiti...
| Váldodahkkit: | , , , , , , , , |
|---|---|
| Materiálatiipa: | Artihkal |
| Giella: | English |
| Almmustuhtton: |
MDPI AG
2025-02-01
|
| Ráidu: | Land |
| Fáttát: | |
| Liŋkkat: | https://www.mdpi.com/2073-445X/14/2/329 |
| _version_ | 1826582144243204096 |
|---|---|
| author | Jiangtao Qi Panting Cheng Junbo Zhou Mengyi Zhang Qin Gao Peng He Lujun Li Francis Collins Muga Li Guo |
| author_facet | Jiangtao Qi Panting Cheng Junbo Zhou Mengyi Zhang Qin Gao Peng He Lujun Li Francis Collins Muga Li Guo |
| author_sort | Jiangtao Qi |
| collection | DOAJ |
| description | Soil organic matter (SOM) and total nitrogen (TN) are critical indicators for assessing soil fertility. Although laboratory chemical analysis methods can accurately measure their contents, these techniques are time-consuming and labor-intensive. Spectral technology, characterized by its high sensitivity and convenience, has been increasingly integrated with machine learning algorithms for soil nutrient monitoring. However, the process of spectral data analysis remains complex and requires further optimization for simplicity and efficiency to improve prediction accuracy. This study proposes a novel model to enhance the accuracy of SOM and TN predictions in northeast China’s black soil. Visible/Shortwave Near-Infrared Spectroscopy (Vis/SW-NIRS) data within the 350–1070 nm range were collected, preprocessed, and dimensionality-reduced. The scores of the first nine principal components after a partial least squares (PLS) dimensionality reduction were selected as inputs, and the measured SOM and TN contents were used as outputs to build a back-propagation neural network (BPNN) model. The results show that spectral data processed by the combination of standard normal variate (SNV) and multiple scattering correction (MSC) have the best modeling performance. To improve the accuracy and stability of this model, three algorithms named random search (RS), grid search (GS), and Bayesian optimization (BO) were introduced. The results demonstrate that Vis/SW-NIRS provides reliable predictions of SOM and TN contents, with the PLS-RS-BPNN model achieving the best performance (<i>R</i><sup>2</sup> = 0.980 and 0.972, <i>RMSE</i> = 1.004 and 0.006 for SOM and TN, respectively). Compared to traditional models such as random forests (RF), one-dimensional convolutional neural networks (1D-CNNs), and extreme gradient boosting (XGBoost), the proposed PLS-RS-BPNN model improves <i>R</i><sup>2</sup> by 0.164–0.344 in predicting SOM and by 0.257–0.314 in predicting TN, respectively. These findings confirm the potential of Vis/SW-NIRS technology and the PLS-RS-BPNN model as effective tools for soil nutrient prediction, offering valuable insights for the application of spectral technology in sensing soil information. |
| first_indexed | 2025-03-14T15:01:17Z |
| format | Article |
| id | doaj.art-b9af6ba17fe64d4c8e4b98337d78f39b |
| institution | Directory Open Access Journal |
| issn | 2073-445X |
| language | English |
| last_indexed | 2025-03-14T15:01:17Z |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Land |
| spelling | doaj.art-b9af6ba17fe64d4c8e4b98337d78f39b2025-02-25T13:34:52ZengMDPI AGLand2073-445X2025-02-0114232910.3390/land14020329A Novel Model for Soil Organic Matter and Total Nitrogen Detection Based on Visible/Shortwave Near-Infrared SpectroscopyJiangtao Qi0Panting Cheng1Junbo Zhou2Mengyi Zhang3Qin Gao4Peng He5Lujun Li6Francis Collins Muga7Li Guo8College of Biological and Agricultural Engineering, Jilin University, Changchun 130022, ChinaCollege of Biological and Agricultural Engineering, Jilin University, Changchun 130022, ChinaCollege of Biological and Agricultural Engineering, Jilin University, Changchun 130022, ChinaCollege of Biological and Agricultural Engineering, Jilin University, Changchun 130022, ChinaCollege of Biological and Agricultural Engineering, Jilin University, Changchun 130022, ChinaKey Laboratory of Mollisols Agroecology, Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Harbin 150081, ChinaKey Laboratory of Mollisols Agroecology, Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Harbin 150081, ChinaDepartment of Agricultural and Rural Engineering, University of Venda, Thohoyandou 0950, South AfricaCollege of Biological and Agricultural Engineering, Jilin University, Changchun 130022, ChinaSoil organic matter (SOM) and total nitrogen (TN) are critical indicators for assessing soil fertility. Although laboratory chemical analysis methods can accurately measure their contents, these techniques are time-consuming and labor-intensive. Spectral technology, characterized by its high sensitivity and convenience, has been increasingly integrated with machine learning algorithms for soil nutrient monitoring. However, the process of spectral data analysis remains complex and requires further optimization for simplicity and efficiency to improve prediction accuracy. This study proposes a novel model to enhance the accuracy of SOM and TN predictions in northeast China’s black soil. Visible/Shortwave Near-Infrared Spectroscopy (Vis/SW-NIRS) data within the 350–1070 nm range were collected, preprocessed, and dimensionality-reduced. The scores of the first nine principal components after a partial least squares (PLS) dimensionality reduction were selected as inputs, and the measured SOM and TN contents were used as outputs to build a back-propagation neural network (BPNN) model. The results show that spectral data processed by the combination of standard normal variate (SNV) and multiple scattering correction (MSC) have the best modeling performance. To improve the accuracy and stability of this model, three algorithms named random search (RS), grid search (GS), and Bayesian optimization (BO) were introduced. The results demonstrate that Vis/SW-NIRS provides reliable predictions of SOM and TN contents, with the PLS-RS-BPNN model achieving the best performance (<i>R</i><sup>2</sup> = 0.980 and 0.972, <i>RMSE</i> = 1.004 and 0.006 for SOM and TN, respectively). Compared to traditional models such as random forests (RF), one-dimensional convolutional neural networks (1D-CNNs), and extreme gradient boosting (XGBoost), the proposed PLS-RS-BPNN model improves <i>R</i><sup>2</sup> by 0.164–0.344 in predicting SOM and by 0.257–0.314 in predicting TN, respectively. These findings confirm the potential of Vis/SW-NIRS technology and the PLS-RS-BPNN model as effective tools for soil nutrient prediction, offering valuable insights for the application of spectral technology in sensing soil information.https://www.mdpi.com/2073-445X/14/2/329visible/shortwave near-infrared spectroscopysoil organic mattertotal nitrogendimensionality reductionmachine learning |
| spellingShingle | Jiangtao Qi Panting Cheng Junbo Zhou Mengyi Zhang Qin Gao Peng He Lujun Li Francis Collins Muga Li Guo A Novel Model for Soil Organic Matter and Total Nitrogen Detection Based on Visible/Shortwave Near-Infrared Spectroscopy Land visible/shortwave near-infrared spectroscopy soil organic matter total nitrogen dimensionality reduction machine learning |
| title | A Novel Model for Soil Organic Matter and Total Nitrogen Detection Based on Visible/Shortwave Near-Infrared Spectroscopy |
| title_full | A Novel Model for Soil Organic Matter and Total Nitrogen Detection Based on Visible/Shortwave Near-Infrared Spectroscopy |
| title_fullStr | A Novel Model for Soil Organic Matter and Total Nitrogen Detection Based on Visible/Shortwave Near-Infrared Spectroscopy |
| title_full_unstemmed | A Novel Model for Soil Organic Matter and Total Nitrogen Detection Based on Visible/Shortwave Near-Infrared Spectroscopy |
| title_short | A Novel Model for Soil Organic Matter and Total Nitrogen Detection Based on Visible/Shortwave Near-Infrared Spectroscopy |
| title_sort | novel model for soil organic matter and total nitrogen detection based on visible shortwave near infrared spectroscopy |
| topic | visible/shortwave near-infrared spectroscopy soil organic matter total nitrogen dimensionality reduction machine learning |
| url | https://www.mdpi.com/2073-445X/14/2/329 |
| work_keys_str_mv | AT jiangtaoqi anovelmodelforsoilorganicmatterandtotalnitrogendetectionbasedonvisibleshortwavenearinfraredspectroscopy AT pantingcheng anovelmodelforsoilorganicmatterandtotalnitrogendetectionbasedonvisibleshortwavenearinfraredspectroscopy AT junbozhou anovelmodelforsoilorganicmatterandtotalnitrogendetectionbasedonvisibleshortwavenearinfraredspectroscopy AT mengyizhang anovelmodelforsoilorganicmatterandtotalnitrogendetectionbasedonvisibleshortwavenearinfraredspectroscopy AT qingao anovelmodelforsoilorganicmatterandtotalnitrogendetectionbasedonvisibleshortwavenearinfraredspectroscopy AT penghe anovelmodelforsoilorganicmatterandtotalnitrogendetectionbasedonvisibleshortwavenearinfraredspectroscopy AT lujunli anovelmodelforsoilorganicmatterandtotalnitrogendetectionbasedonvisibleshortwavenearinfraredspectroscopy AT franciscollinsmuga anovelmodelforsoilorganicmatterandtotalnitrogendetectionbasedonvisibleshortwavenearinfraredspectroscopy AT liguo anovelmodelforsoilorganicmatterandtotalnitrogendetectionbasedonvisibleshortwavenearinfraredspectroscopy AT jiangtaoqi novelmodelforsoilorganicmatterandtotalnitrogendetectionbasedonvisibleshortwavenearinfraredspectroscopy AT pantingcheng novelmodelforsoilorganicmatterandtotalnitrogendetectionbasedonvisibleshortwavenearinfraredspectroscopy AT junbozhou novelmodelforsoilorganicmatterandtotalnitrogendetectionbasedonvisibleshortwavenearinfraredspectroscopy AT mengyizhang novelmodelforsoilorganicmatterandtotalnitrogendetectionbasedonvisibleshortwavenearinfraredspectroscopy AT qingao novelmodelforsoilorganicmatterandtotalnitrogendetectionbasedonvisibleshortwavenearinfraredspectroscopy AT penghe novelmodelforsoilorganicmatterandtotalnitrogendetectionbasedonvisibleshortwavenearinfraredspectroscopy AT lujunli novelmodelforsoilorganicmatterandtotalnitrogendetectionbasedonvisibleshortwavenearinfraredspectroscopy AT franciscollinsmuga novelmodelforsoilorganicmatterandtotalnitrogendetectionbasedonvisibleshortwavenearinfraredspectroscopy AT liguo novelmodelforsoilorganicmatterandtotalnitrogendetectionbasedonvisibleshortwavenearinfraredspectroscopy |