Automatic tree species classification from Sentinel-2 images using deficient inventory data

Sinica-Sinavskis, Juris; Dinuls, R.; Zarins, Juris; Mednieks, Ints

doi:10.1109/bec49624.2020.9276810

Cited by 3 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also in Sweden, an 87% TA was obtained for the same species [53] with the Bayesian inference method, using 23 pieces of S-2 images. From Latvia, a 92-94% TA was reported with three S-2 images on Scots pine, Norway spruce, silver birch, and black alder [58]. With the RF method, Puletti et al [32] obtained an 86.2% TA on four mixed forest types, emphasising that the multitemporal imagery made of different phenological periods was more accurate and proved to be better than single satellite images.…”

Section: Discussionmentioning

confidence: 99%

Forest Disturbance Monitoring Using Cloud-Based Sentinel-2 Satellite Imagery and Machine Learning

Molnár,

Király

2024

J. Imaging

View full text Add to dashboard Cite

Forest damage has become more frequent in Hungary in the last decades, and remote sensing offers a powerful tool for monitoring them rapidly and cost-effectively. A combined approach was developed to utilise high-resolution ESA Sentinel-2 satellite imagery and Google Earth Engine cloud computing and field-based forest inventory data. Maps and charts were derived from vegetation indices (NDVI and Z∙NDVI) of satellite images to detect forest disturbances in the Hungarian study site for the period of 2017–2020. The NDVI maps were classified to reveal forest disturbances, and the cloud-based method successfully showed drought and frost damage in the oak-dominated Nagyerdő forest of Debrecen. Differences in the reactions to damage between tree species were visible on the index maps; therefore, a random forest machine learning classifier was applied to show the spatial distribution of dominant species. An accuracy assessment was accomplished with confusion matrices that compared classified index maps to field-surveyed data, demonstrating 99.1% producer, 71% user, and 71% total accuracies for forest damage and 81.9% for tree species. Based on the results of this study and the resilience of Google Earth Engine, the presented method has the potential to be extended to monitor all of Hungary in a faster, more accurate way using systematically collected field-data, the latest satellite imagery, and artificial intelligence.

show abstract

Section: Discussionmentioning

confidence: 99%

Forest Disturbance Monitoring Using Cloud-Based Sentinel-2 Satellite Imagery and Machine Learning

Molnár,

Király

2024

J. Imaging

View full text Add to dashboard Cite

show abstract

“…Also in Sweden, 87% TA was obtained for the same species [48] with the Bayesian inference method using 23 pieces of S-2 images. From Latvia, 92-94% TA was reported with three S-2 images and K-means clustering and DynLand methods on Scots pine, Norway spruce, silver birch, and black alder (Alnus glutinosa) [53]. In Italy, Puletti et al [29] obtained 86.2% TA with the RF method on four mixed forest types, emphasizing that the collection of multitemporal images at different phenological periods is required.…”

Section: Discussionmentioning

confidence: 99%

Forest Monitoring Based on Sentinel-2 Satellite Imagery, Google Earth Engine Cloud Computing, and Machine Learning

Molnár¹,

Király²

2023

Preprint

View full text Add to dashboard Cite

Forest damage has become more frequent in Europe in the last decades, and remote sensing offers a powerful tool for monitoring them rapidly and cost-effectively. A novel approach was developed to utilize high-resolution ESA Sentinel-2 satellite imagery and Google Earth Engine cloud computing. The processing, analysing, and visualization of vegetation and water index (NDVI, NDVIch, Z NDVI, EVI, NDWI) maps and charts derived from satellite images took place in the cloud to ensure the detection of forest disturbances in the Hungarian study site for the period 2017-2020. The index maps were classified to reveal forest disturbances, and the cloud-based method successfully showed drought and frost damage in the oak-dominated Nagyerdő forest of Debrecen. Differences in the reaction to damage between tree species were visible in the index values, therefore a Random Forest Machine Learning classifier was applied to show the spatial distribution of dominant species. Accuracy assessment was accomplished with confusion matrices that compared classified index maps to field-surveyed data, demonstrating 71% Total Accuracy for forest damage and 76% for tree species. Based on the results of this study and the resilience of Google Earth Engine, the presented method has the potential to be extended to monitor the entire Hungary.

show abstract

Forest Stand Volume Estimation by Species from Sentinel-2 and LiDAR Data Using Regression Models

Sinica-Sinavskis

Grube

2022

2022 18th Biennial Baltic Electronics Conference (BEC)

View full text Add to dashboard Cite

Automatic tree species classification from Sentinel-2 images using deficient inventory data

Cited by 3 publications

References 11 publications

Forest Disturbance Monitoring Using Cloud-Based Sentinel-2 Satellite Imagery and Machine Learning

Forest Disturbance Monitoring Using Cloud-Based Sentinel-2 Satellite Imagery and Machine Learning

Forest Monitoring Based on Sentinel-2 Satellite Imagery, Google Earth Engine Cloud Computing, and Machine Learning

Forest Stand Volume Estimation by Species from Sentinel-2 and LiDAR Data Using Regression Models

Contact Info

Product

Resources

About