Mangrove Mapping Research Articles

Spatiotemporal Mapping and Monitoring of Mangrove Forests Changes From 1990 to 2019 in the Northern Emirates, UAE Using Random Forest, Kernel Logistic Regression and Naive Bayes Tree Models

Mangrove forests are acting as a green lung for the coastal cities of the United Arab Emirates, providing a habitat for wildlife, storing blue carbon in sediment and protecting shoreline. Thus, the first step toward conservation and a better understanding of the ecological setting of mangroves is mapping and monitoring mangrove extent over multiple spatial scales. This study aims to develop a novel low-cost remote sensing approach for spatiotemporal mapping and monitoring mangrove forest extent in the northern part of the United Arab Emirates (NUAE). The approach was developed based on random forest (RF), Kernel logistic regression (KLR), and Naive Bayes Tree (NBT) machine learning algorithms which use multitemporal Landsat images. Our results of accuracy metrics include accuracy, precision, recall, F1 score revealed that RF outperformed the KLR and NB with an F1 score of more than 0.90. Each pair of produced mangrove maps (1990-2000, 2000-2010, 2010-2019 and 1990-2019) was used to image difference algorithm (ID) to monitor mangrove extent by applying a threshold ranges from +1 to -1. Our results are of great importance to the ecological and research community. The new maps presented in this study will be a good reference and a useful source for the coastal management organization.

PERBANDINGAN ALGORITMA PADA METODE KLASIFIKASI SUPERVISED BERBASIS CITRA ALOS AVNIR-2 UNTUK PEMETAAN MANGROVE

The goal of this research was to provide an appropriate algorithm for mapping the mangrove area in Anday. Supervised classification method applied that consisted of several algorithmic alternatives such as parallel piped, minimum distance algorithm, mahalanobis distance, maximum likelihood, and spectral angle mapper. In addition, this study was conducted by applying the image process of a near-infrared band of ALOS AVNIR-2 and then analysis was carried out to leverage the accuracy of the range of spectral values through field survey and to test the accuracy of mangrove zonation maps which was based the supervised classification method. The results revealed that the overall accuracy of parallelepiped was 29%, and 41.18% for minimum distance algorithm, mahalanobis distance was 58.82%, the maximum likelihood was 50%, and spectral angle mapper was 58.82%.

Delineation of Tree Patches in a Mangrove-Marsh Transition Zone by Watershed Segmentation of Aerial Photographs

Mangrove migration, or transgression in response to global climatic changes or sea-level rise, is a slow process; to capture it, understanding both the present distribution of mangroves at individual patch (single- or clumped trees) scale, and their rates of change are essential. In this study, a new method was developed to delineate individual patches and to estimate mangrove cover from very high-resolution (0.08 m spatial resolution) true color (Red (R), Green (G), and Blue (B) spectral channels) aerial photography. The method utilizes marker-based watershed segmentation, where markers are detected using a vegetation index and Otsu’s automatic thresholding. Fourteen commonly used vegetation indices were tested, and shadows were removed from the segmented images to determine their effect on the accuracy of tree detection, cover estimation, and patch delineation. According to point-based accuracy analysis, we obtained adjusted overall accuracies >90% in tree detection using seven vegetation indices. Likewise, using an object-based approach, the highest overlap accuracy between predicted and reference data was 95%. The vegetation index Excess Green (ExG) without shadow removal produced the most accurate mangrove maps by separating tree patches from shadows and background marsh vegetation and detecting more individual trees. The method provides high precision delineation of mangrove trees and patches, and the opportunity to analyze mangrove migration patterns at the scale of isolated individuals and patches.

Development and application of a new mangrove vegetation index (MVI) for rapid and accurate mangrove mapping

Advancement in Remote Sensing allows rapid mangrove mapping without the need for data-intensive methodologies, complex classifiers, and skill-dependent classification techniques. This study proposes a new index, the Mangrove Vegetation Index (MVI), to rapidly and accurately map mangroves extent from remotely-sensed imageries. The MVI utilizes three Sentinel-2 bands green, Near Infrared (NIR) and Shortwave Infrared (SWIR) in the form |NIR-Green|/|SWIR-Green| to discriminate the distinct greenness and moisture of mangroves from terrestrial vegetation and other land cover. Spectral band analysis shows that the |NIR-Green| part of MVI captures the differences of greenness between mangrove forests and terrestrial vegetation. The |SWIR-Green| part of the index expresses the distinct moisture of mangroves without the need for additional intertidal data and water indices. The MVI value increases with the increasing probability of a pixel being classified as mangroves. Eleven mangrove forests in the Philippines and one mangrove park in Japan were then mapped using MVI. Accuracy assessment was done using field inventory data and high-resolution drone orthophotos. MVI have successfully separated the mangroves from other cover especially terrestrial vegetation, with an overall index accuracy of 92%. The MVI was applied to Landsat 8 images using the equivalent bands to test the universality of the index. Comparable MVI mangrove maps were produced between Sentinel-2 and Landsat images, with an optimal minimum threshold of 4.5 and 4.6, respectively. MVI can effectively highlight the greenness and moisture information in mangroves as reflected by its moderate to high correlation value (r = 0.63 and 0.84, α = 0.05) with the Sentinel-derived chlorophyll-a (Ca) and canopy water (Cw) biophysical products. This study developed and implemented two automated platforms: an offline IDL-based ‘MVI Mapper’ and an online Google Earth Engine-based MVI mapping interface. The MVI implemented in Google Earth Engine was used in generating the latest mangrove extent map of the Philippines. Additionally, the application of MVI were tested to four additional mangrove forests in Southeast Asia: Thailand, Vietnam, Indonesia and Cambodia; and to selected mangroves forests in South America, Africa and Australia.

A preliminary study on machine learning and google earth engine for mangrove mapping

The alarming rate of global mangrove forest degradation corroborates the need for providing fast, up-to-date and accurate mangrove maps. Conventional scene by scene image classification approach is inefficient and time consuming. The development of Google Earth Engine (GEE) provides a cloud platform to access and seamlessly process large amount of freely available satellite imagery. The GEE also provides a set of the state-of-the-art classifiers for pixel-based classification that can be used for mangrove mapping. This study is an initial effort which is aimed to combine machine learning and GEE for mapping mangrove extent. We used two Landsat 8 scenes over Agats and Timika Papua area as pilot images for this study; path 102 row 64 (2014/10/19) and path 103 row 63 (2013/05/16). The first image was used to develop local training areas for the machine learning classification, while the second one was used as a test image for GEE on the cloud. A total of 838 points samples were collected representing mangroves (244), non-mangroves (161), water bodies (311), and cloud (122) class. These training areas were used by support vector machine classifier in GEE to classify the first image. The classification result show mangrove objects could be efficiently delineated by this algorithm as confirmed by visual checking. This algorithm was then applied to the second image in GEE to check the consistency of the result. A simultaneous view of both classified images shows a corresponding pattern of mangrove forest, which mean the mangrove object has been consistently delineated by the algorithm.

GEOBIA for mangrove mapping using UAV-modified NIR 1 camera sensor

Mangrove ecosystem is a natural resource that can be beneficial for coastal community. One of its benefits is it can be utilized as an ecotourism spot such as Baros Mangrove Conservation Area in Kretek, Bantul. Hence, mangrove ecosystem must be conserved or expanded if possible. The first step to conserving mangrove ecosystem is to map its existing condition. UAV can be used to acquire a high-resolution imagery quickly. With modified near-infrared (NIR) sensor from a pocket camera can produce three band i.e. NIR, green, and blue that can be used to calculate several vegetation indices such as Simple Ration (SR), Normalized Difference Vegetation Index (NDVI), and Enhanced Difference Vegetation Index (ENDVI). Those bands and vegetation indices then used to map mangrove using Geographic Object-Based Image Analysis approach. The result indicated that high-resolution imagery from modified NIR camera sensor can be used to detect mangrove and distinguish it from other object using supervised classification. The digitally classified imagery then compared to manually digitized mangrove map to calculate the total error of the map.

Evaluating Combinations of Sentinel-2 Data and Machine-Learning Algorithms for Mangrove Mapping in West Africa

Creating a national baseline for natural resources, such as mangrove forests, and monitoring them regularly often requires a consistent and robust methodology. With freely available satellite data archives and cloud computing resources, it is now more accessible to conduct such large-scale monitoring and assessment. Yet, few studies examine the reproducibility of such mangrove monitoring frameworks, especially in terms of generating consistent spatial extent. Our objective was to evaluate a combination of image processing approaches to classify mangrove forests along the coast of Senegal and The Gambia. We used freely available global satellite data (Sentinel-2), and cloud computing platform (Google Earth Engine) to run two machine learning algorithms, random forest (RF), and classification and regression trees (CART). We calibrated and validated the algorithms using 800 reference points collected using high-resolution images. We further re-ran 10 iterations for each algorithm, utilizing unique subsets of the initial training data. While all iterations resulted in thematic mangrove maps with over 90% accuracy, the mangrove extent ranges between 827–2807 km2 for Senegal and 245–1271 km2 for The Gambia with one outlier for each country. We further report “Places of Agreement” (PoA) to identify areas where all iterations for both methods agree (506.6 km2 and 129.6 km2 for Senegal and The Gambia, respectively), thus have a high confidence in predicting mangrove extent. While we acknowledge the time- and cost-effectiveness of such methods for the landscape managers, we recommend utilizing them with utmost caution, as well as post-classification on-the-ground checks, especially for decision making.

Incorporating the Plant Phenological Trajectory into Mangrove Species Mapping with Dense Time Series Sentinel-2 Imagery and the Google Earth Engine Platform

Information on mangrove species composition and distribution is key to studying functions of mangrove ecosystems and securing sustainable mangrove conservation. Even though remote sensing technology is developing rapidly currently, mapping mangrove forests at the species level based on freely accessible images is still a great challenge. This study built a Sentinel-2 normalized difference vegetation index (NDVI) time series (from 2017-01-01 to 2018-12-31) to represent phenological trajectories of mangrove species and then demonstrated the feasibility of phenology-based mangrove species classification using the random forest algorithm in the Google Earth Engine platform. It was found that (i) in Zhangjiang estuary, the phenological trajectories (NDVI time series) of different mangrove species have great differences; (ii) the overall accuracy and Kappa confidence of the classification map is 84% and 0.84, respectively; and (iii) Months in late winter and early spring play critical roles in mangrove species mapping. This is the first study to use phonological signatures in discriminating mangrove species. The methodology presented can be used as a practical guideline for the mapping of mangrove or other vegetation species in other regions. However, future work should pay attention to various phenological trajectories of mangrove species in different locations.

Mangrove Mapping and Above-Ground Biomass Change Detection using Satellite Images in Coastal Areas of Thai Binh Province, Vietnam

Mangroves are recognized as a highly valuable resource due to their provision of multiple ecosystem services. Therefore, mangrove ecosystems mapping and monitoring is a crucial objective, especially for tropical regions. Thai Binh province is one of the most important mangrove ecosystems in Vietnam. The mangrove ecosystem in this province has faced threats of deforestation from urban development, land reclamation, tourism activities, and natural disasters. Recently, to maintain the fundamental functions of the ecosystems, a large mangrove area was planted in Thai Binh. The aim of this research is to detect the change in the mangrove areas and to create an aboveground biomass map for mangrove forests in Thai Binh province. Landsat and Sentinel-2 satellite images from 1998 to 2018 were analysed using the supervised classification method to detect mangrove area change. Mangrove Above-ground Biomass (AGB) was estimated using linear regression between vegetation indices and field AGB survey. The accuracy assessment for the classified images of 1998, 2003 and 2007, 2013 and 2018 are 93%, 86%, 96%, 94% and 91% respectively with kappa of 0.8881, 0.7953, 0.9357, 0.9114 and 0.8761. The mangrove cover in the study area was estimated at 5874.93 ha in 1998. This figure decreased significantly to 4433.85 ha in 2007, before recovery began to take place in the study area, which was estimated at 6587.88 ha in 2018. In 1998, the average AGB in this study area was 22.57 ton/ha, and in 2018 it was 37.74 ton/ha with a standard error of 12.41 ton/ha and the root mean square error (RMSE) was ±12.08 ton/ha.

A Historical Review of Data and Information of Indonesian Mangroves Area

Quantification of the mangrove area in Indonesia was very diverse, which is quantified in the pre and post development of remote sensing technology. This causes uncertainty comprehensive information of mangrove in Indonesia. The planners at national and international level of faced with the problems of uncertainty information that has implications for the quality of data availability. Therefore, it is important to develop a comprehensive of mangrove extent and distribution database. The method used in-depth study literature on various publications related mangrove mapping in Indonesia and comparative analysis. This study aims to identify comprehensive information mangrove forests of Indonesia and analyze the factors which cause diversity of quantification area and reliability of data. We found 42 publications containing data and information on Indonesia's mangrove forests area, with 17 sources including detailed information per province. The study results showed that the difference mangrove quantification area was influenced by several main factors including analysis periode, differences in the concept and mangrove boundaries, basic data and scale, method of mangrove mapping, as well as regional coverage. Keywords: historical data, Indonesia, mangrove area

Mapping mangroves using LISS-IV and Hyperion data in part of the Indian Sundarban

ABSTRACTMangroves in different part of the globe including world’s largest halophytic population in Sundarban are under tremendous pressure due to global warming, sea level rise, natural disasters and ever-increasing influence of human population. In such an alarming situation conservation of mangrove population has been recommended by the experts. Species-level mapping of mangroves is one of the important steps for sustainable conservation of mangrove ecosystem. This study demonstrates the efficiency of a combination of Hyperion hyperspectral and IRS Resourcesat-2 LISS-IV multispectral data for discriminating and mapping some mangrove species at Lothian Island and Saptamukhi Reserve Forest located in the western part of Sundarban Biosphere Reserve of India. The spectral signature drawn on Hyperion data helped to extrapolate field samples of various pure pixels of the mangrove plant species using a region growing approach. Those training samples were used to apply Object-based Image Analysis (OBIA) classification on 5 m spatial resolution LISS-IV data. Mostly dominant mangrove species like Aegialitis rotundifolia, Aegiceras corniculatum, Avicennia community, Ceriops community, Excoecaria agallocha, Lumnitzera racemosa and Phoenix paludosa have been successfully classified along with other associated landuse/landcover in these islands. The methodology used in the study has a huge potential in identification, mapping and management through restoration of mangroves in difficult terrain like the Sundarban.

Mapping the multi-decadal mangrove dynamics of the Australian coastline

Mangroves globally provide a diverse array of ecosystem services but these are impacted upon by both natural and anthropogenic drivers of change. In Australia, mangroves are protected by law and hence the natural drivers predominate. To determine annual national level changes in mangroves between 1987 and 2016, their extent (by canopy cover type) and dynamics were quantified using dense time-series (nominally every 16 days cloud permitting) of 25 m spatial resolution Landsat sensor data available within Digital Earth Australia (DEA). The potential area that mangroves occupied over this period was established as the union of mangrove maps generated for 1996, 2007–2010 and 2015/16 through the Global Mangrove Watch (GMW). Within this area, the green vegetation fractional cover (GVpc) was retrieved from each available cloud-masked Landsat scene through linear spectral unmixing. The 10th percentile (GVpc10) was then determined for each calendar year by comparing these data in a time-series. The percentage Planimetric Canopy Cover (PCC%) for each Landsat pixel was then estimated using a relationship between GVpc10 and LiDAR-derived PCC% (<1 m resolution and based on acquisitions from all states supporting mangroves, excluding Victoria). The resulting annual maps of mangrove extent and cover for Australia are the first to be generated at a continental scale and on an annual basis. These indicated that the total area of mangrove forest (canopy cover >20%; resolvable at the Landsat resolution) varied from a minima of 10,715 ± 36 km2 (95% confidence interval) in 1992 to a maxima of 11,388 km2 ± 38 km2 (95% CI) in 2010, declining to 11,142 ± 57 km2 (95% CI) in 2017. In 2010 (maximum extent), the forests were classified as closed canopy (38.8%), open canopy (49.0%) and woodland mangrove (12.2%). The majority of change occurred along the northern Australian coastline and was concentrated in the major gulfs and sounds. The 30 national maps of annual mangrove extent represent a reference dataset, which is publicly available through the Terrestrial Environment Research Network (TERN) landscapes portal. Future efforts are focusing on the routine production of annual mangrove maps beyond 2019 as part of Australia's efforts to monitor the coastal environment.

A review of the application of multispectral remote sensing in the study of mangrove ecosystems with special emphasis on image processing techniques

Much progress has been made since the first published report on application of remote sensing in mangrove mapping nearly 40 years ago. Remote sensing is now a widely used proxy in mangrove ecosystem related research mostly due to increased affordability of data and ease of access. This work reviews previous works on mangrove forests using remote sensing techniques with an aim to identify the best combinations of sensors, methods of image processing and vegetation indices for future studies. It was observed that higher accuracies were directly related to sensor resolution and expertise of the authors. From the imageries used, Quickbird had the highest accuracies (~ 100%) whereas aerial photos had ~ 93% accuracy and IRS LISS recorded (76–97%). Accuracies for Landsat images classified using hybrid approaches were up to 88% while AVIRIS and ASTER, gave up to 99% accuracies. Sentinel images also produced very high accuracy levels. Non parametric methods using machine learning techniques produced the highest levels of accuracy (up to 99%). But not all datasets are freely available and the cost of procuring datasets varies from country to country. This suggests that remote sensing of mangrove vegetation pose some serious challenges that require careful considerations in order to obtain better results. An in-depth understanding of the factors affecting the interaction between electro-magnetic radiation and mangrove vegetations in the environment, selection of images with appropriate spatial and spectral resolution and use of proper processing techniques for extracting spectral information is a must. This review paper thus, can be considered as a convenient asset to the researchers involved in assessing the mangrove environment by remote sensing technique.

Identification of mangrove forest change using object-based analysis in Bontang, East Kalimantan

In past half century, 35-86% of global mangrove forest already loss due to conversion into ponds, urban development and timber harvest. This is become challenging because in some area we don’t have data about distribution and what mangrove species in that forest. We mapping mangrove forest in Bontang city using PlanetScope images acquired at 2017 and 2018. Remote sensing analysis using OBIA method we obtain mangrove extend in Bontang City in 2017 and 2018 are 2,659.2 ha and 3,155.9 ha respectively. With this result, we already loss 491 ha or 13.5% from the initial extend in 1988. Our finding on this research are although have high accuracy, mangrove mapping with 3-meter resolution gave not quite good result. This is because we only obtain mangrove and non-mangrove classification, not until species determination. The factor mainly atmosphere condition which Bontang area have cloud or many aerosols that hamper light transmission. In future need to mapping with species differentiation with this challenge.

An object-based classification of mangrove land cover using Support Vector Machine Algorithm

Accurate mapping of mangrove is necessary for effective planning and management of ecosystem and resources, due to the function of mangrove as a provider of natural products The use of satellite remote sensing to map mangrove has become widespread as it can provide accurate, effecient, and repeatable assessments. The type of remote sensing that is based on imaging using the pixel method sometimes results in the misclassification of the imaging due to the “salt and pepper effects”. The aim of this study to use approach support vector machine (SVM) algorithm to classification mangrove land cover using sentinel-2B and Landsat 8 OLI imagery based on object-based classification method (OBIA). The field observation was done using Unmanned Aerial Vehicle (UAV) at Liong River, Bengkalis, Riau Province. The result by show overall accuracy classification using Sentinel-2B was better than Landsat 8 OLI imagery the value of 78.7% versus 62.7% and them were different significantly 7.23%.

Using multi-indices approach to quantify mangrove changes over the Western Arabian Gulf along Saudi Arabia coast

Mangroves habitat present an important resource for large coastal communities benefiting from activities such as fisheries, forest products and clean water as well as protection against coastal erosion and climate related extreme events. Yet they are increasingly threatened by natural pressure and anthropogenic activities. We observed an inaccurate distribution of mangroves over the Western Arabian Gulf (WAG) which is a vital habitat and resource for the local ecosystem, according to the United Stated Geological Survey (USGS) mangrove database through spectral analysis. Change detection analysis is conducted on mangrove forests along the Saudi Arabian coast of the WAG for the years 2000, 2010 and 2018 using Landsat 7 & 8 data. Three supervised classification methodologies are employed for mangrove mapping, including Supported Vector Machine (SVM), Decision Tree (DT), referred to as Classification and Regression Trees (CART) and Random Forest (RF). CART’s accuracy was recorded to be >95% while other classifiers were >90%. The CART supervised learning classifier, mapping mangroves’ distribution and biomass using Google Earth Engine (GEE) online platform, indicates an overall increase in the northern Tarut Bay and Tarut Island, by 0.21 km2 from 2000 to 2010 and by 1.4 km2 from 2010 to 2018. The increase might be due to mitigation strategies such as mangrove breeding and plantation. It can be challenging to detect changes in certain regions due to the inadequate resolution of Landsat where submerged mangroves can be confused with salt marshes and macro algae. We employed a new method to identify and analyze submerged mangrove forests distribution via a submerged mangrove recognition index (SMRI) and Normalized Difference Vegetation Index (NDVI) in Abu Ali Island. Our results show the robustness of SMRI as an effective indicator to detect submerged mangroves in both high and medium spatial resolution satellite images. NDVI values differentiated submerged mangroves from tidal flats between Landsat 7 & 8 as well as during conditions of low and high tides. High resolution WorldView-2 image showed agreement of mangroves distribution with the SMRI and NDVI results.

A small-patched convolutional neural network for mangrove mapping at species level using high-resolution remote-sensing image

ABSTRACTThe understanding of mangrove forest structure and dynamics at species level is essential for mangrove conservation and management. To classify mangrove species, remote-sensing technologies provide a better way with high spatial resolution image. The spatial structure is usually viewed as effective complementary information for classification. However, it is still a challenge to design handcrafted features for mangrove species due to their non-structure texture. To leverage the advantage of convolutional neural networks (CNNs) in abstract feature exploration, a small patch-based CNN is proposed to overcome the requirement of fixed and large input which limits the applicability of CNNs to fringe mangrove forests. The function of down-sampling technology was substantially reduced to make deeper network for small input in our work. Meanwhile, the inception structure is used to exploit the multi-scale features of mangrove forests. Furthermore, the network is optimized with lesser convolution kernels and a single fully connected layer to reduce overfitting via reducing the training parameters. Compared to the features of grey level co-occurrence matrix with support vector machine, our proposed CNN shows better performance in classification accuracy. Moreover, the differences between mangrove species can be perceptive via CNN visualization, which offers better understanding of mangrove forests.

Monitoring mangrove forest cover declination at kilim karst geoforest park, Langkawi from 2005 to 2017 using geospatial technology

Mangrove forests are commonly found in the coastlines and estuaries of tropical and subtropical regions. Besides having commercial values, mangroves play major roles as coastal protection, buffer zone, and nursery grounds for various types of marine organisms. Since this forest ecosystem has face problems like degradation, there are increasing efforts to monitor and assess this ecosystem for better conservation and management. Conventional mangrove mapping and field survey requires labour intensive, expensive and takes long time to complete. However, geospatial techniques comprising of Remote Sensing (RS) and Geographical Information System (GIS) today become an alternative method that can be used to access the mangrove area, especially for the difficult area. Therefore, this study aims to use geospatial approach to monitor the mangrove area at Kilim Karst Geoforest Park (KKGP), Langkawi. Object-based image analysis (OBIA) method which is involved multi-resolution and classification steps is used to extract and delineate mangrove area from very high resolution (VHR) satellite imagery from 2005 to 2017. Both segmentation and classification processes were conducted using e-Cognition software. The mangrove area from 2005 to 2017 were assessed using overlay technique in ArcGIS software to determine and evaluate the degraded area. The overall degraded mangrove area was approximately 5.632 ha. Factors affecting the decline of the mangrove cover in this study area are also determined. As conclusion, the results indicated the applicability of geospatial technique to be used to monitor and assess mangrove extent for better management and conservation proposes.

Mapping and monitoring of mangrove along the Odisha coast based on remote sensing and GIS techniques

Digital image processing techniques using multi-temporal satellite imagery are widely used to understand landscape dynamics. In this study, we analysed the spatio-temporal changes of mangrove along the Odisha coast, India using Landsat satellite images of four different time periods, i.e., Landsat-5 Thematic Mapper satellite images of 1990 and 2009, Landsat-7 Enhanced Thematic Mapper Plus satellite images of 2000 and Landsat-8 Operational Land Imager satellite images of 2015. Normalized Difference Vegetation Index (NDVI), Soil-Adjusted Vegetation Index (SAVI) and Normalized Difference Wetland Index (NDWI) are used to extract and classify the mangroves into three classes such as dense mangrove, sparse mangrove and open mangrove. The study reveals that total mangrove of the study area increased from 18573.49 ha (1990) to 23871.49 ha (2015) during the last three decades. This may be attributed to mangrove plantation, restoration and proper coastal zone management plan. The paper highlights the importance of digital change detection techniques using NDVI, SAVI and NDWI for mangrove mapping and monitoring along the Odisha coast. This study aids Odisha coastal zone management authority to take timely decisions for conservation of mangrove and future mangrove plantation plans with help of satellite image processing in GIS environment.

The advantages of using drones over space-borne imagery in the mapping of mangrove forests.

Satellite data and aerial photos have proved to be useful in efficient conservation and management of mangrove ecosystems. However, there have been only very few attempts to demonstrate the ability of drone images, and none so far to observe vegetation (species-level) mapping. The present study compares the utility of drone images (DJI-Phantom-2 with SJ4000 RGB and IR cameras, spatial resolution: 5cm) and satellite images (Pleiades-1B, spatial resolution: 50cm) for mangrove mapping—specifically in terms of image quality, efficiency and classification accuracy, at the Setiu Wetland in Malaysia. Both object- and pixel-based classification approaches were tested (QGIS v.2.12.3 with Orfeo Toolbox). The object-based classification (using a manual rule-set algorithm) of drone imagery with dominant land-cover features (i.e. water, land, Avicennia alba, Nypa fruticans, Rhizophora apiculata and Casuarina equisetifolia) provided the highest accuracy (overall accuracy (OA): 94.0±0.5% and specific producer accuracy (SPA): 97.0±9.3%) as compared to the Pleiades imagery (OA: 72.2±2.7% and SPA: 51.9±22.7%). In addition, the pixel-based classification (using a maximum likelihood algorithm) of drone imagery provided better accuracy (OA: 90.0±1.9% and SPA: 87.2±5.1%) compared to the Pleiades (OA: 82.8±3.5% and SPA: 80.4±14.3%). Nevertheless, the drone provided higher temporal resolution images, even on cloudy days, an exceptional benefit when working in a humid tropical climate. In terms of the user-costs, drone costs are much higher, but this becomes advantageous over satellite data for long-term monitoring of a small area. Due to the large data size of the drone imagery, its processing time was about ten times greater than that of the satellite image, and varied according to the various image processing techniques employed (in pixel-based classification, drone >50 hours, Pleiades <5 hours), constituting the main disadvantage of UAV remote sensing. However, the mangrove mapping based on the drone aerial photos provided unprecedented results for Setiu, and was proven to be a viable alternative to satellite-based monitoring/management of these ecosystems. The improvements of drone technology will help to make drone use even more competitive in the future.