Robust Damage Estimation of Typhoon Goni on Coconut Crops with Sentinel-2 Imagery
Typhoon Goni crossed several provinces in the Philippines where agriculture has high socioeconomic importance, including the top-3 provinces in terms of planted coconut trees. We have used a computational model to infer coconut tree density from satellite images before and after the typhoon’s passag...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/21/4302 |
| _version_ | 1827677994046455808 |
|---|---|
| author | Andrés C. Rodríguez Rodrigo Caye Daudt Stefano D’Aronco Konrad Schindler Jan D. Wegner |
| author_facet | Andrés C. Rodríguez Rodrigo Caye Daudt Stefano D’Aronco Konrad Schindler Jan D. Wegner |
| author_sort | Andrés C. Rodríguez |
| collection | DOAJ |
| description | Typhoon Goni crossed several provinces in the Philippines where agriculture has high socioeconomic importance, including the top-3 provinces in terms of planted coconut trees. We have used a computational model to infer coconut tree density from satellite images before and after the typhoon’s passage, and in this way estimate the number of damaged trees. Our area of study around the typhoon’s path covers 15.7 Mha, and includes 47 of the 87 provinces in the Philippines. In validation areas our model predicts coconut tree density with a Mean Absolute Error of 5.9 Trees/ha. In Camarines Sur we estimated that 3.5 M of the 4.6 M existing coconut trees were damaged by the typhoon. Overall we estimated that 14.1 M coconut trees were affected by the typhoon inside our area of study. Our validation images confirm that trees are rarely uprooted and damages are largely due to reduced canopy cover of standing trees. On validation areas, our model was able to detect affected coconut trees with 88.6% accuracy, 75% precision and 90% recall. Our method delivers spatially fine-grained change maps for coconut plantations in the area of study, including unchanged, damaged and new trees. Beyond immediate damage assessment, gradual changes in coconut density may serve as a proxy for future changes in yield. |
| first_indexed | 2024-03-10T05:54:27Z |
| format | Article |
| id | doaj.art-fdabab2cefcd4a1ebe5230cb356e3938 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T05:54:27Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-fdabab2cefcd4a1ebe5230cb356e39382023-11-22T21:31:27ZengMDPI AGRemote Sensing2072-42922021-10-011321430210.3390/rs13214302Robust Damage Estimation of Typhoon Goni on Coconut Crops with Sentinel-2 ImageryAndrés C. Rodríguez0Rodrigo Caye Daudt1Stefano D’Aronco2Konrad Schindler3Jan D. Wegner4EcoVision Lab—Photogrammetry and Remote Sensing, ETH Zürich, Rämistrasse 101, 8092 Zürich, SwitzerlandEcoVision Lab—Photogrammetry and Remote Sensing, ETH Zürich, Rämistrasse 101, 8092 Zürich, SwitzerlandEcoVision Lab—Photogrammetry and Remote Sensing, ETH Zürich, Rämistrasse 101, 8092 Zürich, SwitzerlandEcoVision Lab—Photogrammetry and Remote Sensing, ETH Zürich, Rämistrasse 101, 8092 Zürich, SwitzerlandEcoVision Lab—Photogrammetry and Remote Sensing, ETH Zürich, Rämistrasse 101, 8092 Zürich, SwitzerlandTyphoon Goni crossed several provinces in the Philippines where agriculture has high socioeconomic importance, including the top-3 provinces in terms of planted coconut trees. We have used a computational model to infer coconut tree density from satellite images before and after the typhoon’s passage, and in this way estimate the number of damaged trees. Our area of study around the typhoon’s path covers 15.7 Mha, and includes 47 of the 87 provinces in the Philippines. In validation areas our model predicts coconut tree density with a Mean Absolute Error of 5.9 Trees/ha. In Camarines Sur we estimated that 3.5 M of the 4.6 M existing coconut trees were damaged by the typhoon. Overall we estimated that 14.1 M coconut trees were affected by the typhoon inside our area of study. Our validation images confirm that trees are rarely uprooted and damages are largely due to reduced canopy cover of standing trees. On validation areas, our model was able to detect affected coconut trees with 88.6% accuracy, 75% precision and 90% recall. Our method delivers spatially fine-grained change maps for coconut plantations in the area of study, including unchanged, damaged and new trees. Beyond immediate damage assessment, gradual changes in coconut density may serve as a proxy for future changes in yield.https://www.mdpi.com/2072-4292/13/21/4302natural hazarddeep learningSentinel-2tree density estimationchange detection |
| spellingShingle | Andrés C. Rodríguez Rodrigo Caye Daudt Stefano D’Aronco Konrad Schindler Jan D. Wegner Robust Damage Estimation of Typhoon Goni on Coconut Crops with Sentinel-2 Imagery Remote Sensing natural hazard deep learning Sentinel-2 tree density estimation change detection |
| title | Robust Damage Estimation of Typhoon Goni on Coconut Crops with Sentinel-2 Imagery |
| title_full | Robust Damage Estimation of Typhoon Goni on Coconut Crops with Sentinel-2 Imagery |
| title_fullStr | Robust Damage Estimation of Typhoon Goni on Coconut Crops with Sentinel-2 Imagery |
| title_full_unstemmed | Robust Damage Estimation of Typhoon Goni on Coconut Crops with Sentinel-2 Imagery |
| title_short | Robust Damage Estimation of Typhoon Goni on Coconut Crops with Sentinel-2 Imagery |
| title_sort | robust damage estimation of typhoon goni on coconut crops with sentinel 2 imagery |
| topic | natural hazard deep learning Sentinel-2 tree density estimation change detection |
| url | https://www.mdpi.com/2072-4292/13/21/4302 |
| work_keys_str_mv | AT andrescrodriguez robustdamageestimationoftyphoongonioncoconutcropswithsentinel2imagery AT rodrigocayedaudt robustdamageestimationoftyphoongonioncoconutcropswithsentinel2imagery AT stefanodaronco robustdamageestimationoftyphoongonioncoconutcropswithsentinel2imagery AT konradschindler robustdamageestimationoftyphoongonioncoconutcropswithsentinel2imagery AT jandwegner robustdamageestimationoftyphoongonioncoconutcropswithsentinel2imagery |