TY - JOUR

T1 - U-shaped deep-learning models for island ecosystem type classification, a case study in Con Dao Island of Vietnam

AU - Dang, Kinh Bac

AU - Nguyen, Thi Ha Thanh

AU - Nguyen, Huu Duy

AU - Truong, Quang Hai

AU - Vu, Thi Phuong

AU - Pham, Hanh Nguyen

AU - Duong, Thi Thuy

AU - Giang, Van Trong

AU - Nguyen, Duc Minh

AU - Bui, Thu Huong

AU - Burkhard, Benjamin

PY - 2022/2/14

Y1 - 2022/2/14

N2 - The monitoring of ecosystem dynamics utilises time and resources from scientists and land-use managers, especially in wetland ecosystems in islands that have been affected significantly by both the current state of oceans and human-made activities. Deep-learning models for natural and anthropogenic ecosystem type classification, based on remote sensing data, have become a tool to potentially replace manual image interpretation. This study proposes a U-Net model to develop a deep learning model for classifying 10 island ecosystems with cloud- and shadow-based data using Sentinel-2, ALOS and NOAA remote sensing data. We tested and compared different optimiser methods with two benchmark methods, including support vector machines and random forests. In total, 48 U-Net models were trained and compared. The U-Net model with the Adadelta optimiser and 64 filters showed the best result, because it could classify all island ecosystems with 93 percent accuracy and a loss function value of 0.17. The model was used to classify and successfully manage ecosystems on a particular island in Vietnam. Compared to island ecosystems, it is not easy to detect coral reefs due to seasonal ocean currents. However, the trained deep-learning models proved to have high performances compared to the two traditional methods. The best U-Net model, which needs about two minutes to create a new classification, could become a suitable tool for island research and management in the future.

AB - The monitoring of ecosystem dynamics utilises time and resources from scientists and land-use managers, especially in wetland ecosystems in islands that have been affected significantly by both the current state of oceans and human-made activities. Deep-learning models for natural and anthropogenic ecosystem type classification, based on remote sensing data, have become a tool to potentially replace manual image interpretation. This study proposes a U-Net model to develop a deep learning model for classifying 10 island ecosystems with cloud- and shadow-based data using Sentinel-2, ALOS and NOAA remote sensing data. We tested and compared different optimiser methods with two benchmark methods, including support vector machines and random forests. In total, 48 U-Net models were trained and compared. The U-Net model with the Adadelta optimiser and 64 filters showed the best result, because it could classify all island ecosystems with 93 percent accuracy and a loss function value of 0.17. The model was used to classify and successfully manage ecosystems on a particular island in Vietnam. Compared to island ecosystems, it is not easy to detect coral reefs due to seasonal ocean currents. However, the trained deep-learning models proved to have high performances compared to the two traditional methods. The best U-Net model, which needs about two minutes to create a new classification, could become a suitable tool for island research and management in the future.

KW - Con Dao Island

KW - Decoder

KW - Encoder

KW - Neural network

KW - RAMSAR

UR - http://www.scopus.com/inward/record.url?scp=85130585253&partnerID=8YFLogxK

U2 - 10.3897/oneeco.7.e79160

DO - 10.3897/oneeco.7.e79160

M3 - Article

VL - 7

JO - One Ecosystem

JF - One Ecosystem

M1 - e79160

ER -