Soil Moisture, Organic Carbon, and Nitrogen Content Prediction with Hyperspectral Data Using Regression Models
Soil moisture, soil organic carbon, and nitrogen content prediction are considered significant fields of study as they are directly related to plant health and food production. Direct estimation of these soil properties with traditional methods, for example, the oven-drying technique and chemical an...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/20/7998 |
| _version_ | 1797469907084902400 |
|---|---|
| author | Dristi Datta Manoranjan Paul Manzur Murshed Shyh Wei Teng Leigh Schmidtke |
| author_facet | Dristi Datta Manoranjan Paul Manzur Murshed Shyh Wei Teng Leigh Schmidtke |
| author_sort | Dristi Datta |
| collection | DOAJ |
| description | Soil moisture, soil organic carbon, and nitrogen content prediction are considered significant fields of study as they are directly related to plant health and food production. Direct estimation of these soil properties with traditional methods, for example, the oven-drying technique and chemical analysis, is a time and resource-consuming approach and can predict only smaller areas. With the significant development of remote sensing and hyperspectral (HS) imaging technologies, soil moisture, carbon, and nitrogen can be estimated over vast areas. This paper presents a generalized approach to predicting three different essential soil contents using a comprehensive study of various machine learning (ML) models by considering the dimensional reduction in feature spaces. In this study, we have used three popular benchmark HS datasets captured in Germany and Sweden. The efficacy of different ML algorithms is evaluated to predict soil content, and significant improvement is obtained when a specific range of bands is selected. The performance of ML models is further improved by applying principal component analysis (PCA), a dimensional reduction method that works with an unsupervised learning method. The effect of soil temperature on soil moisture prediction is evaluated in this study, and the results show that when the soil temperature is considered with the HS band, the soil moisture prediction accuracy does not improve. However, the combined effect of band selection and feature transformation using PCA significantly enhances the prediction accuracy for soil moisture, carbon, and nitrogen content. This study represents a comprehensive analysis of a wide range of established ML regression models using data preprocessing, effective band selection, and data dimension reduction and attempt to understand which feature combinations provide the best accuracy. The outcomes of several ML models are verified with validation techniques and the best- and worst-case scenarios in terms of soil content are noted. The proposed approach outperforms existing estimation techniques. |
| first_indexed | 2024-03-09T19:29:35Z |
| format | Article |
| id | doaj.art-403459cc268149a3bb6f66a0a9c090d7 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T19:29:35Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-403459cc268149a3bb6f66a0a9c090d72023-11-24T02:30:04ZengMDPI AGSensors1424-82202022-10-012220799810.3390/s22207998Soil Moisture, Organic Carbon, and Nitrogen Content Prediction with Hyperspectral Data Using Regression ModelsDristi Datta0Manoranjan Paul1Manzur Murshed2Shyh Wei Teng3Leigh Schmidtke4School of Computing, Mathematics, and Engineering, Charles Sturt University, Bathurst, NSW 2795, AustraliaSchool of Computing, Mathematics, and Engineering, Charles Sturt University, Bathurst, NSW 2795, AustraliaCentre for Smart Analytics, Federation University Australia, Berwick, VIC 3806, AustraliaInstitute of Innovation, Science and Sustainability, Federation University Australia, Berwick, VIC 3806, AustraliaGulbali Institue, Charles Sturt University, Wagga Wagga, NSW 2650, AustraliaSoil moisture, soil organic carbon, and nitrogen content prediction are considered significant fields of study as they are directly related to plant health and food production. Direct estimation of these soil properties with traditional methods, for example, the oven-drying technique and chemical analysis, is a time and resource-consuming approach and can predict only smaller areas. With the significant development of remote sensing and hyperspectral (HS) imaging technologies, soil moisture, carbon, and nitrogen can be estimated over vast areas. This paper presents a generalized approach to predicting three different essential soil contents using a comprehensive study of various machine learning (ML) models by considering the dimensional reduction in feature spaces. In this study, we have used three popular benchmark HS datasets captured in Germany and Sweden. The efficacy of different ML algorithms is evaluated to predict soil content, and significant improvement is obtained when a specific range of bands is selected. The performance of ML models is further improved by applying principal component analysis (PCA), a dimensional reduction method that works with an unsupervised learning method. The effect of soil temperature on soil moisture prediction is evaluated in this study, and the results show that when the soil temperature is considered with the HS band, the soil moisture prediction accuracy does not improve. However, the combined effect of band selection and feature transformation using PCA significantly enhances the prediction accuracy for soil moisture, carbon, and nitrogen content. This study represents a comprehensive analysis of a wide range of established ML regression models using data preprocessing, effective band selection, and data dimension reduction and attempt to understand which feature combinations provide the best accuracy. The outcomes of several ML models are verified with validation techniques and the best- and worst-case scenarios in terms of soil content are noted. The proposed approach outperforms existing estimation techniques.https://www.mdpi.com/1424-8220/22/20/7998LUCAS databand selectionmachine learningprincipal component analysisk-fold cross validation |
| spellingShingle | Dristi Datta Manoranjan Paul Manzur Murshed Shyh Wei Teng Leigh Schmidtke Soil Moisture, Organic Carbon, and Nitrogen Content Prediction with Hyperspectral Data Using Regression Models Sensors LUCAS data band selection machine learning principal component analysis k-fold cross validation |
| title | Soil Moisture, Organic Carbon, and Nitrogen Content Prediction with Hyperspectral Data Using Regression Models |
| title_full | Soil Moisture, Organic Carbon, and Nitrogen Content Prediction with Hyperspectral Data Using Regression Models |
| title_fullStr | Soil Moisture, Organic Carbon, and Nitrogen Content Prediction with Hyperspectral Data Using Regression Models |
| title_full_unstemmed | Soil Moisture, Organic Carbon, and Nitrogen Content Prediction with Hyperspectral Data Using Regression Models |
| title_short | Soil Moisture, Organic Carbon, and Nitrogen Content Prediction with Hyperspectral Data Using Regression Models |
| title_sort | soil moisture organic carbon and nitrogen content prediction with hyperspectral data using regression models |
| topic | LUCAS data band selection machine learning principal component analysis k-fold cross validation |
| url | https://www.mdpi.com/1424-8220/22/20/7998 |
| work_keys_str_mv | AT dristidatta soilmoistureorganiccarbonandnitrogencontentpredictionwithhyperspectraldatausingregressionmodels AT manoranjanpaul soilmoistureorganiccarbonandnitrogencontentpredictionwithhyperspectraldatausingregressionmodels AT manzurmurshed soilmoistureorganiccarbonandnitrogencontentpredictionwithhyperspectraldatausingregressionmodels AT shyhweiteng soilmoistureorganiccarbonandnitrogencontentpredictionwithhyperspectraldatausingregressionmodels AT leighschmidtke soilmoistureorganiccarbonandnitrogencontentpredictionwithhyperspectraldatausingregressionmodels |