Search

Biodiversity of benthic habitats is among the highest of all ecological communities. This study was conducted to model benthic habitat biodiversity indices using a remote sensing approach in optica...

There are not many discussion or previous works that specifically address the issue of integrating small field plot size (1 m2) and image at different spatial resolutions in the seagrass percent cover (PC) mapping using remote sensing. This is important to determine the spatial resolution of image that can still be effectively integrated with 1 × 1 m plot size field data. This research aimed at assessing the accuracy and spatial distribution of seagrass PC map modelled from image at different spatial resolutions, using seagrass field data measure at 1 m2 plot size. Two multispectral satellite images namely WorldView-2 (2 m) and PlanetScope (3 m) were used for this research and simulated to 5 m, 10 m, 15 m, and 30 m. Kemujan and Lombok Island were selected as the study area, and seagrass beds in each island have different characteristics. Machine learning random forest regression was used to perform empirical modelling and the mapping accuracy was assessed using independent seagrass PC samples. The results indicated that 1 m2 plot size is still effective to be integrated with image up to 30 m spatial resolution, where the RMSE and overall seagrass PC pattern is relatively similar but the level of information precision is reduced at lower spatial resolution. Furthermore, we found out that the main factor that strongly determines the success use of 1 m2 plot size and the mapping accuracy is the configuration of the seagrass bed in the study area. Seagrass PC in the more continuous seagrass bed can be mapped with higher accuracy than in patchy seagrass bed.

This paper presents the first assessment of PlanetScope image for benthic habitat and seagrass species mapping in optically shallow water. PlanetScope image is equipped with ideal resolutions for b...

We presented the use of Random Forest (RF) classification to map benthic habitat in two small islands using different parameter scenario, which are the number of trees, the function to determine the number of randomly selected features, and the function to determine the impurity in a node. The results indicated that RF is a consistent performer with accuracy difference of 1.3% and 5.8% for the two Islands. Furthermore, different scenarios also producing similar benthic habitat spatial distribution and misclassification pattern.

This research was aimed at developing the mapping model of benthic habitat mapping using machine-learning classification algorithms and tested the applicability of the model in different areas. We integrated in situ benthic habitat data and image processing of WorldView-2 (WV2) image to parameterise the machine-learning algorithm, namely: Random Forest (RF), Classification Tree Analysis (CTA), and Support Vector Machine (SVM). The classification inputs are sunglint-free bands, water column corrected bands, Principle Component (PC) bands, bathymetry, and the slope of underwater topography. Kemujan Island was used in developing the model, while Karimunjawa, Menjangan Besar, and Menjangan Kecil Islands served as test areas. The results obtained indicated that RF was more accurate than any other classification algorithm based on the statistics and benthic habitats spatial distribution. The maximum accuracy of RF was 94.17% (4 classes) and 88.54% (14 classes). The accuracies from RF, CTA, and SVM were consistent across different input bands for each classification scheme. The application of RF model in the classification of benthic habitat in other areas revealed that it is recommended to make use of the more general classification scheme in order to avoid several issues regarding benthic habitat variations. The result also established the possibility of mapping a benthic habitat without the use of training areas.

The availability of frequently updated maps has always been the ultimate goal of remote sensing in benthic habitat data acquisition. Although the techniques offer cost and time effectiveness, the lack of consistency of inputted images can cause issues in successfully performing accurate multi-temporal mapping with minimum effort. This research aimed to assess the consistency of Sentinel-2 images for benthic habitat mapping in the waters of Labuan Bajo, East Nusa Tenggara, Indonesia. We employed two approaches: 1) assessing the consistency of Sentinel-2 image used to map four classes of benthic habitat from 2017 to 2019 and 2) an in-depth analysis of three images in May 2019 to assess the consistency of four-class benthic habitat mapping (coral reef, seagrass, macroalgae and bare substratum). This research incorporated atmospheric, sunglint and water column corrections and four classification algorithms: Isodata, Random Forest, Support Vector Machine, and Maximum Likelihood. The consistency of Sentinel-2 images was assessed using overall accuracy (OA), agreement percentage (AP) and total classification performance (TCP). Our results indicate that Sentinel-2 images are reliable enough for accurate benthic habitat mapping with OA >80% and consistent with agreement >80% in both approaches given the right image conditions, which are minimum cloud cover, haze, and sunglint. These factors strongly contribute to the consistency of the resulting benthic habitat classification from the Sentinel-2 images. Also, to maximize the rich image availability in the Sentinel-2 archive database, we suggest selecting images with minimal atmospheric and sunglint disturbances instead of performing image corrections that may introduce noise, leading to lower accuracy and consistency. Finally, we encourage the use of Sentinel-2 images in benthic habitat monitoring since the long-term plan of the Sentinel-2 mission guarantees the availability of these datasets.