Detection of oak decline using radiative transfer modelling and machine learning from multispectral and thermal RPAS imagery
Oak trees are declining at an unprecedented rate due to the interaction of many factors, such as pests, diseases, droughts, pollution and flooding. Such abiotic- and biotic-induced stress produces anomalies in plant physiological and functional traits (PTs) that may be spectrally detected, serving t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-03-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843224000335 |
| _version_ | 1797303404485148672 |
|---|---|
| author | A. Hornero P.J. Zarco-Tejada I. Marengo N. Faria R. Hernández-Clemente |
| author_facet | A. Hornero P.J. Zarco-Tejada I. Marengo N. Faria R. Hernández-Clemente |
| author_sort | A. Hornero |
| collection | DOAJ |
| description | Oak trees are declining at an unprecedented rate due to the interaction of many factors, such as pests, diseases, droughts, pollution and flooding. Such abiotic- and biotic-induced stress produces anomalies in plant physiological and functional traits (PTs) that may be spectrally detected, serving to quantify trees’ health status and condition. Previous studies have demonstrated that PTs’ dynamic response can be tracked with hyperspectral and thermal images acquired via aerial platforms. However, the ability to detect the decline at different stages of severity among distinct oak species by using high-resolution multispectral images acquired via miniaturised cameras located aboard unpiloted airborne platforms is still unknown. This cost-effective approach offers improved operability to perform missions with greater continuity and replicability, which is critical to assess the decline progression. In this work, we evaluated the use of airborne multispectral and thermal imagery coupled with a 3-D radiative transfer modelling and machine learning approach for detecting Phytophthora-infected holm oak and cork oak trees. The field study included 2299 trees classified into disease severity classes with a gradient in levels of disease incidence located in Portugal (Ourique and Avis) and Spain (Huelva and Alcuéscar). The classification model achieved an overall accuracy of 76 % (kappa = 0.51) in detecting decline for both species, successfully identifying up to 34 % of declining trees that were not initially detected by visual inspection and confirmed in a reevaluation six months later. When compared against airborne hyperspectral imagery, results yielded comparable accuracy, with a relative decrease of ca. 4 % in overall accuracy and an average Cohen’s kappa decrease of 7 %. The results further showed that classification using only hyperspectral imagery is slightly lower but equivalent to using combined multispectral and thermal data, and those derived from these sensors independently are not adequate to classify the different severity stages. The proposed model has enabled us to effectively discern various stages of decline in cork and holm oak forests across diverse geographical areas. Our study, therefore, demonstrates that the tandem use of multispectral and thermal sensors onboard a remotely piloted aircraft platform, together with a radiative transfer modelling and machine learning approach, helps us to predict the impact of this particularly damaging disease on oak trees. This capability facilitates the detection and swift mapping of disease progression, ensuring a proactive approach to forest management. |
| first_indexed | 2024-03-07T23:52:15Z |
| format | Article |
| id | doaj.art-ab24df35ceed44b3904f860bd6ebc19d |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-03-07T23:52:15Z |
| publishDate | 2024-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-ab24df35ceed44b3904f860bd6ebc19d2024-02-19T04:13:15ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322024-03-01127103679Detection of oak decline using radiative transfer modelling and machine learning from multispectral and thermal RPAS imageryA. Hornero0P.J. Zarco-Tejada1I. Marengo2N. Faria3R. Hernández-Clemente4Instituto de Agricultura Sostenible (IAS), Consejo Superior de Investigaciones Científicas (CSIC), Avenida Menéndez Pidal s/n, 14004 Córdoba, Spain; School of Agriculture, Food and Ecosystem Sciences (SAFES), Faculty of Science (FoS), and Faculty of Engineering and Information Technology (FEIT), University of Melbourne, Melbourne, Victoria, Australia; Corresponding author.School of Agriculture, Food and Ecosystem Sciences (SAFES), Faculty of Science (FoS), and Faculty of Engineering and Information Technology (FEIT), University of Melbourne, Melbourne, Victoria, Australia; Instituto de Agricultura Sostenible (IAS), Consejo Superior de Investigaciones Científicas (CSIC), Avenida Menéndez Pidal s/n, 14004 Córdoba, SpainDepartment of Monitoring and Diagnosis, InnovPlantProtect Associação, 7350-999 Elvas, PortugalDepartment of Monitoring and Diagnosis, InnovPlantProtect Associação, 7350-999 Elvas, PortugalDepartamento de Ingeniería Forestal, Universidad de Córdoba, Campus de Rabanales, Crta, IV, km. 396, E-14071 Córdoba, Spain; Department of Geography, Swansea University, SA2 8PP Swansea, United KingdomOak trees are declining at an unprecedented rate due to the interaction of many factors, such as pests, diseases, droughts, pollution and flooding. Such abiotic- and biotic-induced stress produces anomalies in plant physiological and functional traits (PTs) that may be spectrally detected, serving to quantify trees’ health status and condition. Previous studies have demonstrated that PTs’ dynamic response can be tracked with hyperspectral and thermal images acquired via aerial platforms. However, the ability to detect the decline at different stages of severity among distinct oak species by using high-resolution multispectral images acquired via miniaturised cameras located aboard unpiloted airborne platforms is still unknown. This cost-effective approach offers improved operability to perform missions with greater continuity and replicability, which is critical to assess the decline progression. In this work, we evaluated the use of airborne multispectral and thermal imagery coupled with a 3-D radiative transfer modelling and machine learning approach for detecting Phytophthora-infected holm oak and cork oak trees. The field study included 2299 trees classified into disease severity classes with a gradient in levels of disease incidence located in Portugal (Ourique and Avis) and Spain (Huelva and Alcuéscar). The classification model achieved an overall accuracy of 76 % (kappa = 0.51) in detecting decline for both species, successfully identifying up to 34 % of declining trees that were not initially detected by visual inspection and confirmed in a reevaluation six months later. When compared against airborne hyperspectral imagery, results yielded comparable accuracy, with a relative decrease of ca. 4 % in overall accuracy and an average Cohen’s kappa decrease of 7 %. The results further showed that classification using only hyperspectral imagery is slightly lower but equivalent to using combined multispectral and thermal data, and those derived from these sensors independently are not adequate to classify the different severity stages. The proposed model has enabled us to effectively discern various stages of decline in cork and holm oak forests across diverse geographical areas. Our study, therefore, demonstrates that the tandem use of multispectral and thermal sensors onboard a remotely piloted aircraft platform, together with a radiative transfer modelling and machine learning approach, helps us to predict the impact of this particularly damaging disease on oak trees. This capability facilitates the detection and swift mapping of disease progression, ensuring a proactive approach to forest management.http://www.sciencedirect.com/science/article/pii/S1569843224000335MultispectralThermalRadiative transferDisease detectionArtificial intelligenceRPAS |
| spellingShingle | A. Hornero P.J. Zarco-Tejada I. Marengo N. Faria R. Hernández-Clemente Detection of oak decline using radiative transfer modelling and machine learning from multispectral and thermal RPAS imagery International Journal of Applied Earth Observations and Geoinformation Multispectral Thermal Radiative transfer Disease detection Artificial intelligence RPAS |
| title | Detection of oak decline using radiative transfer modelling and machine learning from multispectral and thermal RPAS imagery |
| title_full | Detection of oak decline using radiative transfer modelling and machine learning from multispectral and thermal RPAS imagery |
| title_fullStr | Detection of oak decline using radiative transfer modelling and machine learning from multispectral and thermal RPAS imagery |
| title_full_unstemmed | Detection of oak decline using radiative transfer modelling and machine learning from multispectral and thermal RPAS imagery |
| title_short | Detection of oak decline using radiative transfer modelling and machine learning from multispectral and thermal RPAS imagery |
| title_sort | detection of oak decline using radiative transfer modelling and machine learning from multispectral and thermal rpas imagery |
| topic | Multispectral Thermal Radiative transfer Disease detection Artificial intelligence RPAS |
| url | http://www.sciencedirect.com/science/article/pii/S1569843224000335 |
| work_keys_str_mv | AT ahornero detectionofoakdeclineusingradiativetransfermodellingandmachinelearningfrommultispectralandthermalrpasimagery AT pjzarcotejada detectionofoakdeclineusingradiativetransfermodellingandmachinelearningfrommultispectralandthermalrpasimagery AT imarengo detectionofoakdeclineusingradiativetransfermodellingandmachinelearningfrommultispectralandthermalrpasimagery AT nfaria detectionofoakdeclineusingradiativetransfermodellingandmachinelearningfrommultispectralandthermalrpasimagery AT rhernandezclemente detectionofoakdeclineusingradiativetransfermodellingandmachinelearningfrommultispectralandthermalrpasimagery |