Synergy of multi-temporal polarimetric SAR and optical image satellite for mapping of marsh vegetation using object-based random forest algorithm

Indonesia is the world’s fourth largest coffee producer. Coffee plantations cover 1.2 million ha of the country with a production of 500 kg/ha. However, information regarding the distribution of coffee plantations in Indonesia is limited. This study aimed to assess the accuracy of classification model and determine its important variables for mapping coffee plantations. The model obtained 29 variables which derived from the integration of multi-resolution, multi-temporal, and multi-sensor remote sensing data, namely, pan-sharpened GeoEye-1, multi-temporal Sentinel 2, and DEMNAS. Applying a random forest algorithm (tree = 1000, mtry = all variables, minimum node size: 6), this model achieved overall accuracy, kappa statistics, producer accuracy, and user accuracy of 79.333%, 0.774, 92.000%, and 90.790%, respectively. In addition, 12 most important variables achieved overall accuracy, kappa statistics, producer accuracy, and user accuracy 79.333%, 0.774, 91.333%, and 84.570%, respectively. Our results indicate that random forest algorithm is efficient in mapping coffee plantations in an agroforestry system.

Download Full-text

An Assessment of Simulated Compact Polarimetric SAR Data for Wetland Classification Using Random Forest Algorithm

Canadian Journal of Remote Sensing ◽

10.1080/07038992.2017.1381550 ◽

2017 ◽

Vol 43 (5) ◽

pp. 468-484 ◽

Cited By ~ 30

Author(s):

Masoud Mahdianpari ◽

Bahram Salehi ◽

Fariba Mohammadimanesh ◽

Brian Brisco

Keyword(s):

Random Forest ◽

Wetland Classification ◽

Random Forest Algorithm ◽

Polarimetric Sar ◽

Sar Data

Download Full-text

Pemanfaatan Data Landsat Multitemporal Untuk Pemetaan Pola Ekspansi Perkotaan Secara Spasiotemporal (Studi Kasus Pada Tiga Perkotaan Metropolitan Di Pulau Jawa)

Jurnal Nasional Teknologi Terapan (JNTT) ◽

10.22146/jntt.39091 ◽

2018 ◽

Vol 2 (1) ◽

pp. 99

Author(s):

Like Indrawati ◽

Ari Cahyono

Keyword(s):

Random Forest ◽

Land Cover ◽

Urban Expansion ◽

Rapid Expansion ◽

City Size ◽

Digital Data ◽

Urban Systems ◽

Spatiotemporal Pattern ◽

Random Forest Algorithm ◽

Object Based

Utilization of multitemporal remote sensing data among others can be used todetermine thepattern of changes in urban expansion. One of the most important types of cities in urban systems isthe metropolitan urban area that covers several districts and cities. This is because the regiongenerally acts as the capital of the country, the provincial capital, and the center of economicactivities that are national or strategic. Understanding urban expansion at different metropolitanurban levels is important for expanding knowledge in times of urban growth and its impact on theenvironment. Aims in this study are: (1) utilization of multitemporal Landsat data for mapping urbanexpansion patterns, (2) knowing the effectiveness of object-based classification for mapping of urbansettlements and (3) spatiotemporal urban expansion pattern analysis in three metropolitan cities onJava Island.. In this study focused on three metropolitan urban in Java, namely DKI. Jakarta,Surabaya and Semarang. This study utilizing Landsat TM, ETM + and OLI image data to map urbansettlement land cover using object-based classification with Random Forest algorithm. Next,quantifying the typology of urban expansion and compare the spatiotemporal pattern of urbanexpansion during 2005-2015 on the results of land cover mapping. This research has found that (1)object-based classification with Random Forest algorithm is quite effective in terms of time of work tomap urban settlement cover on Landsat digital data having medium spatial resolution; (2) the threeurban metropolia is experiencing rapid and massive development and has a very variedspatiotemporal pattern; (3) Size of the city affect the pattern of urban expansion, followed by rapidexpansion of the region. Larger city size with relatively rapid expansion is more likely to experiencethe edge extension model, while smaller cities tend to develop with outlying models.

Download Full-text

OBJECT BASED BURNED AREA MAPPING WITH RANDOM FOREST ALGORITHM

International Journal of Engineering and Geosciences ◽

10.26833/ijeg.455595 ◽

2019 ◽

Author(s):

RESUL ÇÖMERT ◽

DİLEK KÜÇÜK MATCI ◽

UĞUR AVDAN

Keyword(s):

Random Forest ◽

Burned Area ◽

Random Forest Algorithm ◽

Object Based ◽

Burned Area Mapping

Download Full-text

Object-Based Building Damage Assessment Methodology Using Only Post Event ALOS-2/PALSAR-2 Dual Polarimetric SAR Intensity Images

Journal of Disaster Research ◽

10.20965/jdr.2017.p0259 ◽

2017 ◽

Vol 12 (2) ◽

pp. 259-271 ◽

Cited By ~ 18

Author(s):

Yanbing Bai ◽

◽

Bruno Adriano ◽

Erick Mas ◽

Hideomi Gokon ◽

...

Keyword(s):

Machine Learning ◽

Random Forest ◽

Damage Assessment ◽

Building Damage ◽

Machine Learning Algorithms ◽

Assessment Methodology ◽

K Nearest Neighbor ◽

Polarimetric Sar ◽

Object Based ◽

Sar Imagery

Earthquake-induced building damage assessment is an indispensable prerequisite for disaster impact assessment, and the increasing availability of high-resolution Synthetic Aperture Radar (SAR) imagery has made it possible to construct damaged building inventories soon after earthquakes strike. However, the shortage of pre-seismic SAR datasets and the lack of available building footprint data pose challenges for rapid building damage assessment. Taking advantage of recent advances in machine learning algorithms, this study proposes an object-based building damage assessment methodology that uses only post-event SAR imagery. A Random Forest machine learning-based object classification, a simplified approach to the extraction of built-up areas, was developed and tested on two ALOS2/PALSAR-2 dual polarimetric SAR images acquired in affected areas soon after the 2015 Nepal earthquake. In addition, a series of texture metrics as well as the random scattering metric and reflection symmetry metric were found to significantly enhance classification accuracy. The feature selection was found to have a positive effect on overall performance. Moreover, the proposed Random Forest framework resulted in overall accuracies of 93% with a kappa coefficient of 0.885 when the object scale of 60 × 60 pixels and 15 features were adopted. A comparative experiment with the k-nearest neighbor framework demonstrated that the Random Forest framework is a significant step toward the achievement of a balanced, two-class classification.

Download Full-text

Coastal Wetland Classification with GF-3 Polarimetric SAR Imagery by Using Object-Oriented Random Forest Algorithm

Sensors ◽

10.3390/s21103395 ◽

2021 ◽

Vol 21 (10) ◽

pp. 3395

Author(s):

Xiaotong Zhang ◽

Jia Xu ◽

Yuanyuan Chen ◽

Kang Xu ◽

Dongmei Wang

Keyword(s):

Random Forest ◽

Land Cover ◽

Coastal Wetlands ◽

Coastal Wetland ◽

Object Oriented ◽

Wetland Classification ◽

Random Forest Algorithm ◽

Polarimetric Sar ◽

Land Cover Types ◽

Sar Imagery

When the use of optical images is not practical due to cloud cover, Synthetic Aperture Radar (SAR) imagery is a preferred alternative for monitoring coastal wetlands because it is unaffected by weather conditions. Polarimetric SAR (PolSAR) enables the detection of different backscattering mechanisms and thus has potential applications in land cover classification. Gaofen-3 (GF-3) is the first Chinese civilian satellite with multi-polarized C-band SAR imaging capability. Coastal wetland classification with GF-3 polarimetric SAR imagery has attracted increased attention in recent years, but it remains challenging. The aim of this study was to classify land cover in coastal wetlands using an object-oriented random forest algorithm on the basis of GF-3 polarimetric SAR imagery. First, a set of 16 commonly used SAR features was extracted. Second, the importance of each SAR feature was calculated, and the optimal polarimetric features were selected for wetland classification by combining random forest (RF) with sequential backward selection (SBS). Finally, the proposed algorithm was utilized to classify different land cover types in the Yancheng Coastal Wetlands. The results show that the most important parameters for wetland classification in this study were Shannon entropy, Span and orientation randomness, combined with features derived from Yamaguchi decomposition, namely, volume scattering, double scattering, surface scattering and helix scattering. When the object-oriented RF classification approach was used with the optimal feature combination, different land cover types in the study area were classified, with an overall accuracy of up to 92%.

Download Full-text