scholarly journals MDPrePost-Net: A Spatial-Spectral-Temporal Fully Convolutional Network for Mapping of Mangrove Degradation Affected by Hurricane Irma 2017 Using Sentinel-2 Data

2021 ◽  
Vol 13 (24) ◽  
pp. 5042
Author(s):  
Ilham Jamaluddin ◽  
Tipajin Thaipisutikul ◽  
Ying-Nong Chen ◽  
Chi-Hung Chuang ◽  
Chih-Lin Hu
Keyword(s):  
Coastal Zone ◽  
Satellite Images ◽  
Experimental Results ◽  
Convolutional Network ◽  
Fully Convolutional Network ◽  
Southwest Florida ◽  
Mangrove Area ◽  
Mangrove Degradation ◽  
Hurricane Irma ◽  
Sentinel 2

Mangroves are grown in intertidal zones along tropical and subtropical climate areas, which have many benefits for humans and ecosystems. The knowledge of mangrove conditions is essential to know the statuses of mangroves. Recently, satellite imagery has been widely used to generate mangrove and degradation mapping. Sentinel-2 is a volume of free satellite image data that has a temporal resolution of 5 days. When Hurricane Irma hit the southwest Florida coastal zone in 2017, it caused mangrove degradation. The relationship of satellite images between pre and post-hurricane events can provide a deeper understanding of the degraded mangrove areas that were affected by Hurricane Irma. This study proposed an MDPrePost-Net that considers images before and after hurricanes to classify non-mangrove, intact/healthy mangroves, and degraded mangroves classes affected by Hurricane Irma in southwest Florida using Sentinel-2 data. MDPrePost-Net is an end-to-end fully convolutional network (FCN) that consists of two main sub-models. The first sub-model is a pre-post deep feature extractor used to extract the spatial–spectral–temporal relationship between the pre, post, and mangrove conditions after the hurricane from the satellite images and the second sub-model is an FCN classifier as the classification part from extracted spatial–spectral–temporal deep features. Experimental results show that the accuracy and Intersection over Union (IoU) score by the proposed MDPrePost-Net for degraded mangrove are 98.25% and 96.82%, respectively. Based on the experimental results, MDPrePost-Net outperforms the state-of-the-art FCN models (e.g., U-Net, LinkNet, FPN, and FC-DenseNet) in terms of accuracy metrics. In addition, this study found that 26.64% (41,008.66 Ha) of the mangrove area was degraded due to Hurricane Irma along the southwest Florida coastal zone and the other 73.36% (112,924.70 Ha) mangrove area remained intact.

scholarly journals A comprehensive transferability evaluation of U-Net and ResU-Net for landslide detection from Sentinel-2 data (case study areas from Taiwan, China, and Japan)

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Omid Ghorbanzadeh ◽  
Alessandro Crivellari ◽  
Pedram Ghamisi ◽  
Hejar Shahabi ◽  
Thomas Blaschke
Keyword(s):  
Satellite Images ◽  
Patch Size ◽  
Window Size ◽  
Convolutional Network ◽  
Digital Elevation ◽  
High Resolution Satellite Images ◽  
Elevation Model ◽  
Very High ◽  
Sentinel 2

AbstractEarthquakes and heavy rainfalls are the two leading causes of landslides around the world. Since they often occur across large areas, landslide detection requires rapid and reliable automatic detection approaches. Currently, deep learning (DL) approaches, especially different convolutional neural network and fully convolutional network (FCN) algorithms, are reliably achieving cutting-edge accuracies in automatic landslide detection. However, these successful applications of various DL approaches have thus far been based on very high resolution satellite images (e.g., GeoEye and WorldView), making it easier to achieve such high detection performances. In this study, we use freely available Sentinel-2 data and ALOS digital elevation model to investigate the application of two well-known FCN algorithms, namely the U-Net and residual U-Net (or so-called ResU-Net), for landslide detection. To our knowledge, this is the first application of FCN for landslide detection only from freely available data. We adapt the algorithms to the specific aim of landslide detection, then train and test with data from three different case study areas located in Western Taitung County (Taiwan), Shuzheng Valley (China), and Eastern Iburi (Japan). We characterize three different window size sample patches to train the algorithms. Our results also contain a comprehensive transferability assessment achieved through different training and testing scenarios in the three case studies. The highest f1-score value of 73.32% was obtained by ResU-Net, trained with a dataset from Japan, and tested on China’s holdout testing area using the sample patch size of 64 × 64 pixels.

ANÁLISE DA EVOLUÇÃO TEMPORAL E DA DINÂMICA SEDIMENTAR DA DUNA DO PÔR DO SOL, JERICOACOARA, CEARÁ – BRASIL

2019 ◽  
Vol 21 (2) ◽  
pp. 656-673
Author(s):  
Adely Pereira Silveira ◽  
Fábio Perdigão Vasconcelos ◽  
Vanda Carneiro de Claudino Sales
Keyword(s):  
Coastal Zone ◽  
Satellite Images ◽  
Temporal Analysis ◽  
Coastal Dynamics ◽  
The Public ◽  
Public Managers ◽  
Mobile Dunes ◽  
The Waves ◽  
Adequate Management

No presente trabalho voltamos nossa atenção para as dunas móveis que são interfaces litorâneas, áreas continuamente modeladas pelas ações dos ventos e das ondas, importantes reservatórios de sedimentos que atuam na manutenção do fluxo sedimentar da faixa praial. Partindo deste universo, concentramos nossos estudos na Praia de Jericoacoara, município de Jijoca de Jericoacoara-CE, tendo como objetivo analisar a dinâmica morfossedimentar da Duna do Pôr do Sol na Praia de Jericoacoara, a partir da análise temporal de imagens de satélites; realização de perfis de praia,  cálculo do grau de declividade da face de avalanche da duna, da área e do volume sedimentar da duna; e da observação da evolução dos tipos de uso e de ocupação. Os resultados desta pesquisa possibilitaram a elaboração de diagnósticos e prognósticos evolutivos para a área estudada, fornecendo dados e informações que podem vir a subsidiar os gestores públicos na gestão adequada da zona costeira e na compreensão dos riscos ambientais.Palavras-chave: Dinâmica Costeira; Duna; Jericoacoara/CE. ABSTRACTIn the present work we turn our attention to the mobile dunes that are coastal interfaces and represent areas continuously modeled by the action of the winds and the waves, important reservoirs of sediments for  the maintenance of the sedimentary flow of the praial band. Starting from this universe, we concentrated our studies in the Beach of Jericoacoara, municipality of Jijoca of Jericoacoara-CE, aiming to analyze the morphosedimentary dynamics of the Dune of the Sunset on the Beach of Jericoacoara, based on the temporal analysis of satellite images; the realization of beach profiles, the calculation of the degree of slope of the slip face, the area and the sedimentary volume of the dune; and the observation of the evolution of types of use and occupation. The results of this research enabled the elaboration of diagnoses and evolutionary prognoses for the studied area, providing data and information that can subsidize the public managers in the adequate management of the coastal zone and in the understanding of the environmental risks.Keywords: Coastal Dynamics; Dune; Jericoacoara / CE. RESUMENEn el presente trabajo dirigimos nuestra atención a las dunas móviles que son interfaces costeras, áreas continuamente modeladas por las acciones de vientos y olas, importantes depósitos de sedimentos que actúan para mantener el flujo sedimentario de la playa. Desde este universo, enfocamos nuestros estudios en Jericoacoara Beach, Jijoca de Jericoacoara-CE, con el objetivo de analizar la dinámica morfosedimentaria de Sunset Dune en Jericoacoara Beach, a partir del análisis temporal de imágenes de satélite; haciendo perfiles de playa, calculando la pendiente de la cara de avalancha de dunas, el área y el volumen sedimentario de la duna; y observando la evolución de los tipos de uso y ocupación. Los resultados de esta investigación permitieron la elaboración de diagnósticos y pronósticos evolutivos para el área estudiada, proporcionando datos e información que pueden ayudar a los administradores públicos en el manejo adecuado de la zona costera y en la comprensión de los riesgos ambientales.Palabras clave: Dinámica costera; Duna; Jericoacoara / CE.

scholarly journals MaskNet: A Fully-Convolutional Network to Estimate Inlier Points

2020 ◽  
Author(s):  
Vinit Sarode ◽  
Animesh Dhagat ◽  
Rangaprasad Arun Srivatsan ◽  
Nicolas Zevallos ◽  
Simon Lucey ◽  
...  
Keyword(s):  
Convolutional Network ◽  
Fully Convolutional Network

scholarly journals Parallel Fully Convolutional Network for Semantic Segmentation

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 673-682
Author(s):  
Jian Ji ◽  
Xiaocong Lu ◽  
Mai Luo ◽  
Minghui Yin ◽  
Qiguang Miao ◽  
...  
Keyword(s):  
Semantic Segmentation ◽  
Convolutional Network ◽  
Fully Convolutional Network
Sign in / Sign up

Export Citation Format

Share Document