Combining UAV-based hyperspectral imagery and machine learning algorithms for soil moisture content monitoring
Soil moisture content (SMC) is an important factor that affects agricultural development in arid regions. Compared with the space-borne remote sensing system, the unmanned aerial vehicle (UAV) has been widely used because of its stronger controllability and higher resolution. It also provides a more...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2019-05-01
|
| Series: | PeerJ |
| Subjects: | |
| Online Access: | https://peerj.com/articles/6926.pdf |
| _version_ | 1797420232681193472 |
|---|---|
| author | Xiangyu Ge Jingzhe Wang Jianli Ding Xiaoyi Cao Zipeng Zhang Jie Liu Xiaohang Li |
| author_facet | Xiangyu Ge Jingzhe Wang Jianli Ding Xiaoyi Cao Zipeng Zhang Jie Liu Xiaohang Li |
| author_sort | Xiangyu Ge |
| collection | DOAJ |
| description | Soil moisture content (SMC) is an important factor that affects agricultural development in arid regions. Compared with the space-borne remote sensing system, the unmanned aerial vehicle (UAV) has been widely used because of its stronger controllability and higher resolution. It also provides a more convenient method for monitoring SMC than normal measurement methods that includes field sampling and oven-drying techniques. However, research based on UAV hyperspectral data has not yet formed a standard procedure in arid regions. Therefore, a universal processing scheme is required. We hypothesized that combining pretreatments of UAV hyperspectral imagery under optimal indices and a set of field observations within a machine learning framework will yield a highly accurate estimate of SMC. Optimal 2D spectral indices act as indispensable variables and allow us to characterize a model’s SMC performance and spatial distribution. For this purpose, we used hyperspectral imagery and a total of 70 topsoil samples (0–10 cm) from the farmland (2.5 × 104 m2) of Fukang City, Xinjiang Uygur AutonomousRegion, China. The random forest (RF) method and extreme learning machine (ELM) were used to estimate the SMC using six methods of pretreatments combined with four optimal spectral indices. The validation accuracy of the estimated method clearly increased compared with that of linear models. The combination of pretreatments and indices by our assessment effectively eliminated the interference and the noises. Comparing two machine learning algorithms showed that the RF models were superior to the ELM models, and the best model was PIR (R2val = 0.907, RMSEP = 1.477, and RPD = 3.396). The SMC map predicted via the best scheme was highly similar to the SMC map measured. We conclude that combining preprocessed spectral indices and machine learning algorithms allows estimation of SMC with high accuracy (R2val = 0.907) via UAV hyperspectral imagery on a regional scale. Ultimately, our program might improve management and conservation strategies for agroecosystem systems in arid regions. |
| first_indexed | 2024-03-09T06:58:40Z |
| format | Article |
| id | doaj.art-f8d223aee02e4f10bf5396eaf59aac5b |
| institution | Directory Open Access Journal |
| issn | 2167-8359 |
| language | English |
| last_indexed | 2024-03-09T06:58:40Z |
| publishDate | 2019-05-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ |
| spelling | doaj.art-f8d223aee02e4f10bf5396eaf59aac5b2023-12-03T10:00:24ZengPeerJ Inc.PeerJ2167-83592019-05-017e692610.7717/peerj.6926Combining UAV-based hyperspectral imagery and machine learning algorithms for soil moisture content monitoringXiangyu Ge0Jingzhe Wang1Jianli Ding2Xiaoyi Cao3Zipeng Zhang4Jie Liu5Xiaohang Li6Key Laboratory of Smart City and Environment Modelling of Higher Education Institute, College of Resources and Environment Sciences, Xinjiang University, Urumqi, Xinjiang, ChinaKey Laboratory of Smart City and Environment Modelling of Higher Education Institute, College of Resources and Environment Sciences, Xinjiang University, Urumqi, Xinjiang, ChinaKey Laboratory of Smart City and Environment Modelling of Higher Education Institute, College of Resources and Environment Sciences, Xinjiang University, Urumqi, Xinjiang, ChinaKey Laboratory of Smart City and Environment Modelling of Higher Education Institute, College of Resources and Environment Sciences, Xinjiang University, Urumqi, Xinjiang, ChinaKey Laboratory of Smart City and Environment Modelling of Higher Education Institute, College of Resources and Environment Sciences, Xinjiang University, Urumqi, Xinjiang, ChinaKey Laboratory of Smart City and Environment Modelling of Higher Education Institute, College of Resources and Environment Sciences, Xinjiang University, Urumqi, Xinjiang, ChinaKey Laboratory of Smart City and Environment Modelling of Higher Education Institute, College of Resources and Environment Sciences, Xinjiang University, Urumqi, Xinjiang, ChinaSoil moisture content (SMC) is an important factor that affects agricultural development in arid regions. Compared with the space-borne remote sensing system, the unmanned aerial vehicle (UAV) has been widely used because of its stronger controllability and higher resolution. It also provides a more convenient method for monitoring SMC than normal measurement methods that includes field sampling and oven-drying techniques. However, research based on UAV hyperspectral data has not yet formed a standard procedure in arid regions. Therefore, a universal processing scheme is required. We hypothesized that combining pretreatments of UAV hyperspectral imagery under optimal indices and a set of field observations within a machine learning framework will yield a highly accurate estimate of SMC. Optimal 2D spectral indices act as indispensable variables and allow us to characterize a model’s SMC performance and spatial distribution. For this purpose, we used hyperspectral imagery and a total of 70 topsoil samples (0–10 cm) from the farmland (2.5 × 104 m2) of Fukang City, Xinjiang Uygur AutonomousRegion, China. The random forest (RF) method and extreme learning machine (ELM) were used to estimate the SMC using six methods of pretreatments combined with four optimal spectral indices. The validation accuracy of the estimated method clearly increased compared with that of linear models. The combination of pretreatments and indices by our assessment effectively eliminated the interference and the noises. Comparing two machine learning algorithms showed that the RF models were superior to the ELM models, and the best model was PIR (R2val = 0.907, RMSEP = 1.477, and RPD = 3.396). The SMC map predicted via the best scheme was highly similar to the SMC map measured. We conclude that combining preprocessed spectral indices and machine learning algorithms allows estimation of SMC with high accuracy (R2val = 0.907) via UAV hyperspectral imagery on a regional scale. Ultimately, our program might improve management and conservation strategies for agroecosystem systems in arid regions.https://peerj.com/articles/6926.pdfUAVPrecision farmingHyperspectral imageryMachine learning |
| spellingShingle | Xiangyu Ge Jingzhe Wang Jianli Ding Xiaoyi Cao Zipeng Zhang Jie Liu Xiaohang Li Combining UAV-based hyperspectral imagery and machine learning algorithms for soil moisture content monitoring PeerJ UAV Precision farming Hyperspectral imagery Machine learning |
| title | Combining UAV-based hyperspectral imagery and machine learning algorithms for soil moisture content monitoring |
| title_full | Combining UAV-based hyperspectral imagery and machine learning algorithms for soil moisture content monitoring |
| title_fullStr | Combining UAV-based hyperspectral imagery and machine learning algorithms for soil moisture content monitoring |
| title_full_unstemmed | Combining UAV-based hyperspectral imagery and machine learning algorithms for soil moisture content monitoring |
| title_short | Combining UAV-based hyperspectral imagery and machine learning algorithms for soil moisture content monitoring |
| title_sort | combining uav based hyperspectral imagery and machine learning algorithms for soil moisture content monitoring |
| topic | UAV Precision farming Hyperspectral imagery Machine learning |
| url | https://peerj.com/articles/6926.pdf |
| work_keys_str_mv | AT xiangyuge combininguavbasedhyperspectralimageryandmachinelearningalgorithmsforsoilmoisturecontentmonitoring AT jingzhewang combininguavbasedhyperspectralimageryandmachinelearningalgorithmsforsoilmoisturecontentmonitoring AT jianliding combininguavbasedhyperspectralimageryandmachinelearningalgorithmsforsoilmoisturecontentmonitoring AT xiaoyicao combininguavbasedhyperspectralimageryandmachinelearningalgorithmsforsoilmoisturecontentmonitoring AT zipengzhang combininguavbasedhyperspectralimageryandmachinelearningalgorithmsforsoilmoisturecontentmonitoring AT jieliu combininguavbasedhyperspectralimageryandmachinelearningalgorithmsforsoilmoisturecontentmonitoring AT xiaohangli combininguavbasedhyperspectralimageryandmachinelearningalgorithmsforsoilmoisturecontentmonitoring |