Segmentation of Enhalus acoroides seagrass from underwater images using the Mask R-CNN method

Abstract Seagrass is a Spermatophyta plant that has many roles, including as a primary producer in the food chain in the waters. Monitoring of seagrass meadows and conditions needs to be done in order to achieve a healthy marine ecosystem. The steps taken in monitoring seagrass are by detecting and segmenting it. The purpose of the study is to implement and get information about the performance of the Mask R-CNN algorithm in detecting and segmenting the Enhalus acoroides. The dataset consists of 500 Enhalus acoroides images that had gone through a color correction and labelling process. The training process was performed with the configuration of 0.001 learning rate, batch size of 4 and some image augmentation was used to avoid overfitting. The optimum weight value was obtained after conducting the learning process with 100 epochs. A confusion matrix was used to evaluate detection performance, and linear regression was used to evaluate the segmentation produced by the model. The model evaluation results showed an accuracy value of 0.9246, a precision value of 0.9507, a recall value of 0.9712 and a correlation coefficient value of 0.8771. The value indicates that the model can detect and segment the seagrass Enhalus acoroides well and accurately.

Download Full-text

KANDUNGAN PIGMEN PADA LAMUN Enhalus acoroides (Linnaeus f.) DI PERAIRAN PANTAI AMADOKE DESA AKLE KECAMATAN SEMAU SELATAN KABUPATEN KUPANG

Indigenous Biologi : Jurnal Pendidikan dan Sains Biologi ◽

10.33323/indigenous.v3i1.73 ◽

2021 ◽

Vol 3 (1) ◽

pp. 24-31

Author(s):

Ivin Anggraini Bayang ◽

Andriani Rafael ◽

Alfred G.O Kase

Keyword(s):

Thin Layer ◽

Marine Ecosystem ◽

Spectrophotometric Analysis ◽

Ecological Function ◽

High Potential ◽

Pigment Content ◽

Survey Method ◽

Research Use ◽

Shallow Marine ◽

Enhalus Acoroides

ABSTRAK Ekosistem lamun merupakan salah satu ekosistem di laut dangkal yang mempunyai peranan penting dalam kehidupan biota laut dan merupakan salah satu ekosistem bahari yang paling produktif, sehingga mampu mendukung potensi sumber daya yang tinggi pula. Fungsi ekologis ekosistem lamun adalah sebagai produsen, pendaur unsur hara, penstabil substrat, penangkap sedimen, habitat dan makanan serta tempat berlindung organisme laut lainnya. Tujuan dari penelitian ini adalah, untuk mengidentifikasi pigmen dan mengetahui kandungan pigmen yang terdeteksi pada lamun Enhalus acoroides (Linnaeus f.) di Perairan Pantai Amadoke Desa Akle Kecamatan Semau Selatan Kabupaten Kupang. Metode yang digunakan dalam penelitian ini adalah metode Survei, Kromotografi Lapis Tipis, dan metode Spektrofotometer. Lamun ini mengandung pigmen terlihat pada hasil analisis spektrofotometer pada ekstrak pigmen total lamun dan pemisahan pigmen lewat uji Kromotografi Lapis Tipis (KLT). Dalam proses ekstraksi digunakan pelarut aseton untuk penggerusan dan perendaman. Dan pada uji spektrofotometer untuk kandungan klorofil a menggunakan panjang gelombang 645 nm dengan pigmen total 226,85 µg/mL, klorofil b 664 nm dengan pigmen total 368,69 µg/mL dan karotenoid 470 nm dengan pigmen total. 2.923,70 µg/mL. Pada pengujian pigmen lewat KLT terdapat sembilan noda yaitu, klorofil a dengan nilai Rf (0,78, 0,84 dan 0,08) klorofil b dengan nilai Rf (0,04), klorofil c dengan nilai Rf (0,12), feofitin dengan nilai Rf (0,22 dan 0,88), fukosantin dengan nilai Rf (0,48) dan karotenoid dengan nilai Rf (1,00). Kata kunci : E. acoroides (Linnaeus f.), pigmen, klorofil dan KLT ABSTRACT Seagress ecosystem is one of the shallow marine ecosystem that has an important role in the life of marine and is one of the most productive marine ecosystem, so that it can support the high potential of high resources as well. The ecological function of seagress ecosystem is as a producer, nutrient recycler, substrat stabilizer, sedimen capture, food and shelter of other organisme. The purpose of the research was to identifi the pigment and determine the pigment content in Enhalus acoroides (Linnaeus f.) seagress in Amadoke waters beach Akle of village, South Semau.The research use survey method, thin layer chromotographic and spectrophotometer methods. This seagress contains pigment, seen in the result of spectrophotometric analysis in total seagress extract and pigment separation through thin layer chromotography test. In the pisment used acetone for steaming and soaking. The spectrophotometric test for the content of chrolophyll a (λ 645 nm), chrolophyll b (λ 664 nm) and carotenoid (λ 470 nm), respectivelly are 226,85 µg/mL, 368,69 µg/mL and 2923,70 µg/mL. Nine pigments found based on the Rf valuef of TLC analisis are chrolophyll a (Rf 0,78, 0,84, 0,08), chrolophyll b (Rf 0,04), chrolophyll c (Rf 0,12), feofitin (Rf 0,22 dan 0,88) and carotenoid (Rf 1,00)

Download Full-text

The future of seagrass meadows

Environmental Conservation ◽

10.1017/s0376892902000127 ◽

2002 ◽

Vol 29 (2) ◽

pp. 192-206 ◽

Cited By ~ 601

Author(s):

Carlos M. Duarte

Keyword(s):

Human Impacts ◽

Marine Ecosystem ◽

Monitoring Network ◽

Global Ocean ◽

Major Barrier ◽

Tropical Regions ◽

Conservation Policies ◽

Positive Effects ◽

Seagrass Meadows ◽

The Future

Seagrasses cover about 0.1–0.2% of the global ocean, and develop highly productive ecosystems which fulfil a key role in the coastal ecosystem. Widespread seagrass loss results from direct human impacts, including mechanical damage (by dredging, fishing, and anchoring), eutrophication, aquaculture, siltation, effects of coastal constructions, and food web alterations; and indirect human impacts, including negative effects of climate change (erosion by rising sea level, increased storms, increased ultraviolet irradiance), as well as from natural causes, such as cyclones and floods. The present review summarizes such threats and trends and considers likely changes to the 2025 time horizon. Present losses are expected to accelerate, particularly in South-east Asia and the Caribbean, as human pressure on the coastal zone grows. Positive human effects include increased legislation to protect seagrass, increased protection of coastal ecosystems, and enhanced efforts to monitor and restore the marine ecosystem. However, these positive effects are unlikely to balance the negative impacts, which are expected to be particularly prominent in developing tropical regions, where the capacity to implement conservation policies is limited. Uncertainties as to the present loss rate, derived from the paucity of coherent monitoring programmes, and the present inability to formulate reliable predictions as to the future rate of loss, represent a major barrier to the formulation of global conservation policies. Three key actions are needed to ensure the effective conservation of seagrass ecosystems: (1) the development of a coherent worldwide monitoring network, (2) the development of quantitative models predicting the responses of seagrasses to disturbance, and (3) the education of the public on the functions of seagrass meadows and the impacts of human activity.

Download Full-text

Short Communication: Restoration of seagrass Enhalus acoroides using a combination of generative and vegetative techniques

Biodiversitas Journal of Biological Diversity ◽

10.13057/biodiv/d201132 ◽

2019 ◽

Vol 20 (11) ◽

Cited By ~ 1

Author(s):

Rohani Ambo-Rappe ◽

Yayu A. La Nafie ◽

Syafiuddin ◽

Steven R. Limbong ◽

Nenni Asriani ◽

...

Keyword(s):

Short Communication ◽

High Energy ◽

Ecosystem Functions ◽

Shade Trees ◽

Short Term ◽

Seagrass Meadows ◽

Enhalus Acoroides ◽

Seagrass Ecosystem ◽

Survival And Growth ◽

Propagation Methods

Abstract. Ambo-Rappe R, La Nafie YA, Syafiuddin, Limbong SR, Asriani N, Handayani NT, Lisdayanti E. 2019. Short Communication: Restoration of seagrass Enhalus acoroides using a combination of generative and vegetative techniques. Biodiversitas 20: 3358-3363. Seagrass areas have been declining in extent worldwide, with associated loss in seagrass ecosystem functions and services. Seagrass restoration is important to mitigate, halt and reverse such declines and their consequences. Generative propagation has benefits in terms of genetic biodiversity, however, survival of seagrass seedlings has often been poor especially in high energy environments. Terrestrial restoration often uses shade trees to protect vulnerable seedlings. This study aimed to evaluate the feasibility of a similar approach in the marine environment, using adult plants to protect seedlings of the tropical seagrass Enhalus acoroides (L.f.) Royle. Enhalus seeds taken from a donor bed were germinated and grown into seedlings, then planted in a location with high hydrodynamic exposure at three different densities (high, medium, and low). Adult Enhalus transplants were co-planted to provide three levels of protection: fifty (high), ten (medium), and none (no protection). Results showed that high-density seedling co-planting with high protection from adult transplants had significantly (p< 0.05) higher six-month survival rate compared to the other treatments. Our results indicate that, even in high energy environments, co-planting seedlings with adult transplants may combine the advantages of generative and vegetative propagation methods, promoting greater short-term effectiveness in terms of seedlings survival and growth in the restored seagrass meadows.

Download Full-text

G2Basy: A framework to improve the RNN language model and ease overfitting problem

PLoS ONE ◽

10.1371/journal.pone.0249820 ◽

2021 ◽

Vol 16 (4) ◽

pp. e0249820

Author(s):

Lu Yuwen ◽

Shuyu Chen ◽

Xiaohan Yuan

Keyword(s):

Language Model ◽

Word Embedding ◽

Language Models ◽

Batch Size ◽

Training Process ◽

Improve Performance ◽

Step Size ◽

Learning Rates ◽

Speed Up ◽

Overfitting Problem

Recurrent neural networks are efficient ways of training language models, and various RNN networks have been proposed to improve performance. However, with the increase of network scales, the overfitting problem becomes more urgent. In this paper, we propose a framework—G2Basy—to speed up the training process and ease the overfitting problem. Instead of using predefined hyperparameters, we devise a gradient increasing and decreasing technique that changes the parameters training batch size and input dropout simultaneously by a user-defined step size. Together with a pretrained word embedding initialization procedure and the introduction of different optimizers at different learning rates, our framework speeds up the training process dramatically and improves performance compared with a benchmark model of the same scale. For the word embedding initialization, we propose the concept of “artificial features” to describe the characteristics of the obtained word embeddings. We experiment on two of the most often used corpora—the Penn Treebank and WikiText-2 datasets—and both outperform the benchmark results and show potential towards further improvement. Furthermore, our framework shows better results with the larger and more complicated WikiText-2 corpus than with the Penn Treebank. Compared with other state-of-the-art results, we achieve comparable results with network scales hundreds of times smaller and within fewer training epochs.

Download Full-text

Observations on the female flowers and fruiting of Tape Grass Enhalus acoroides from South Andaman Islands, India

Journal of Threatened Taxa ◽

10.11609/jott.4253.11.5.13617-13621 ◽

2019 ◽

Vol 11 (5) ◽

pp. 13617-13621

Author(s):

Vardhan Patankar ◽

Tanmay Wagh ◽

Zoya Tyabji

Keyword(s):

Life Cycle ◽

National Parks ◽

Monitoring Program ◽

Average Density ◽

Andaman Islands ◽

Seagrass Meadows ◽

Enhalus Acoroides ◽

South Andaman ◽

The Mean

Documenting phenologic events is crucial in obtaining deeper insights into the life cycle of seagrasses. We documented and compared the flowering and fruiting of the seagrass Enhalus acoroides from multispecies seagrass meadows at two sites, Henry Lawrence and Tarmugli islands located inside the marine national parks in South Andaman Islands. At these two locations, the average density of shoots ranged between 30.9/m2 and 18.16/m2, fruits between 5/m2 and 2.33/m2, and flowers between 6.7/m2 and 3.83/m2, whereas the mean length of the peduncles ranged from 40.59cm at Henry Lawrence to 32.44cm at Tarmugli Island. We observed significant differences between the densities of shoots and fruits and peduncle lengths in the two sites. The density of flowers, however, did not vary significantly. These observations of fruiting and flowering in E. acoroides establish an important reproductive stage in the life cycle of the species and open avenues for further seagrass research in the Andaman Islands. We describe the findings and emphasize on the need to establish a long-term phenology monitoring program for E. acoroides in the Andaman Archipelago.

Download Full-text

Submarine Groundwater Discharge (SGD) to Coastal Waters of Saipan (Commonwealth of the Northern Mariana Islands, USA): Implications for Nitrogen Sources, Transport and Ecological Effects

Water ◽

10.3390/w12113029 ◽

2020 ◽

Vol 12 (11) ◽

pp. 3029

Author(s):

Melissa A. Knapp ◽

Naomi Geeraert ◽

Kiho Kim ◽

Karen L. Knee

Keyword(s):

Water Quality ◽

Primary Production ◽

Coastal Waters ◽

Submarine Groundwater Discharge ◽

Nutrient Loading ◽

Groundwater Discharge ◽

Seagrass Meadows ◽

Nitrogen Inputs ◽

Submarine Groundwater ◽

Primary Producer

Seagrass meadows and coral reefs along the coast of Saipan, a US commonwealth in the Northern Pacific, have been declining since the 1940s, possibly due to nutrient loading. This study investigated whether submarine groundwater discharge (SGD) contributes to nutrient loading and supports primary production on Saipan’s coast. SGD can be an important source of freshwater, nutrients, and other pollutants to coastal waters, especially in oceanic islands without well-developed stream systems. Ra and Rn isotopes were used as natural tracers of SGD. Nitrate, phosphate, and ammonium concentrations, ancillary water quality parameters, δ15N and δ18O of dissolved nitrate, and δ15N of primary producer tissue were measured. Our results pointed to discharge of low-salinity groundwater containing elevated concentrations of sewage-derived N at specific locations along Saipan’s coast. High SGD areas had lower salinity and pH, higher dissolved inorganic nitrogen concentrations, and elevated primary producer δ15N, indicative of sewage nitrogen inputs. We estimated that SGD could support 730–6400 and 3000–15,000 mol C d−1 of primary production in Tanapag and Garapan Lagoons, respectively, or up to approximately 60% of primary production in Garapan Lagoon. Efforts to improve water quality, reduce nutrient loading, and preserve coastal ecosystems must account for groundwater, since our results demonstrate that it is an important pathway of nitrogen delivery.

Download Full-text

Keanekaragaman Perifiton Daun Lamun Enhalus acoroides dan Cymodocea serrulata di Teluk Awur, Jepara

Journal of Marine Research ◽

10.14710/jmr.v10i2.30506 ◽

2021 ◽

Vol 10 (2) ◽

pp. 306-312

Author(s):

Adelia Hilma Sugiarto ◽

Raden Ario ◽

Ita Riniatsih

Keyword(s):

Marine Ecosystem ◽

Survey Method ◽

Line Transect ◽

Cross Sectional ◽

High Productivity ◽

Enhalus Acoroides ◽

Seagrass Ecosystem ◽

Morisita Index ◽

Cymodocea Serrulata ◽

Seagrass Density

Ekosistem padang lamun merupakan ekosistem bahari yang memiliki keanekaragaman hayati dan memiliki produktivitas tinggi di perairan dangkal. Adanya keberadaan perifiton yang menempel pada daun lamun diduga dijadikan sebagai faktor penunjang produktivitas primer di kawasan ekosistem lamun. Penelitian ini bertujuan untuk mengetahui kelimpahan perifiton, distribusi perifiton dan hubungan kerapatan lamun terhadap kelimpahan perifiton di Perairan Teluk Awur, Jepara. Penelitian ini menggunakan metode survei dan penentuan lokasi dipilih dengan menggunakan metode sampling purposive method, sedangkan metode pengambilan data lamun mengacu pada metode line transek kuadran. Pengambilan daun lamun untuk pengamatan perifiton menggunakan metode sapuan daun yang selanjutnya diamati dengan menggunakan mikroskop. Nilai kelimpahan perifiton pada daun lamun Enhalus acoroides di Stasiun 1, Stasiun 2, dan Stasiun 3 berturut-turut adalah 105 ind/cm2, 167,5 ind/cm2, dan 101,25 ind/cm2. Sedangkan kelimpahan perifiton pada daun lamun Cymodocea serrulata di Stasiun 1 tidak ada lalu Stasiun 2 dan Stasiun 3 berturut-turut adalah 80 ind/cm2 dan 135 ind/cm2. Kelimpahan tertinggi perifiton terdapat pada jenis lamun E. acoroides diduga karena E. acoroides mempunyai luas penampang daun yang lebih lebar dibandingkan C.serrulata. Perifiton yang mendominasi di lokasi ini berasal dari Kelas Bacillariophyceae. Sebaran perifiton berdasarkan perhitungan indeks morisita yaitu berkelompok dan terdapat hubungan antara kelimpahan perifiton dengan kerapatan lamun. The seagrass ecosystem is a marine ecosystem that has biodiversity and is high productivity in shallow waters. The presence of periphyton attached to seagrass leaves is thought to be used as a primary productivity supporting factor in the seagrass ecosystem. This research aims to determine the periphyton abundance, periphyton distribution and seagrass density relationship towards periphyton abundance in Teluk Awur, Jepara. The survey method and location determination were selected based on purposive sampling method, while the seagrass data collection method refers to the quadrant line transect method. The taking of seagrass leaf for periphyton observation used leaf drainage method was then observed using a microscope. Periphyton abundance value on seagrass leaves of Enhalus acoroides in Station 1, Station 2, and Station 3 are respectively 105 ind / cm2, 167,5 ind / cm2, and 101, 25 ind / cm2. Periphyton abundance in seagrass leaves Cymodocea serrulata in Station 1 was not found while Station 2 and Station 3 are 80 ind / cm2 and 135 ind / cm2 respectively. The highest abundance of periphyton is in the type of seagrass E. acoroides because E. acoroides has a wider leaf cross-sectional area than C. serrulata. Periphyton that dominates the waters of Teluk Awur comes from the Bacillariophyceae class. Periphyton distribution based on the morisita index calculation is clustered and there is a relationship between periphyton abundance and seagrass density.

Download Full-text

Sparse Cost Volume for Efficient Stereo Matching

Remote Sensing ◽

10.3390/rs10111844 ◽

2018 ◽

Vol 10 (11) ◽

pp. 1844 ◽

Cited By ~ 6

Author(s):

Chuanhua Lu ◽

Hideaki Uchiyama ◽

Diego Thomas ◽

Atsushi Shimada ◽

Rin-ichiro Taniguchi

Keyword(s):

Processing Time ◽

Stereo Matching ◽

Learning Task ◽

High Accuracy ◽

Batch Size ◽

Fast Computation ◽

Training Process ◽

Ill Posed ◽

Memory Cost ◽

The Cost

Stereo matching has been solved as a supervised learning task with convolutional neural network (CNN). However, CNN based approaches basically require huge memory use. In addition, it is still challenging to find correct correspondences between images at ill-posed dim and sensor noise regions. To solve these problems, we propose Sparse Cost Volume Net (SCV-Net) achieving high accuracy, low memory cost and fast computation. The idea of the cost volume for stereo matching was initially proposed in GC-Net. In our work, by making the cost volume compact and proposing an efficient similarity evaluation for the volume, we achieved faster stereo matching while improving the accuracy. Moreover, we propose to use weight normalization instead of commonly-used batch normalization for stereo matching tasks. This improves the robustness to not only sensor noises in images but also batch size in the training process. We evaluated our proposed network on the Scene Flow and KITTI 2015 datasets, its performance overall surpasses the GC-Net. Comparing with the GC-Net, our SCV-Net achieved to: (1) reduce 73.08 % GPU memory cost; (2) reduce 61.11 % processing time; (3) improve the 3PE from 2.87 % to 2.61 % on the KITTI 2015 dataset.

Download Full-text

Species richness accelerates marine ecosystem restoration in the Coral Triangle

Proceedings of the National Academy of Sciences ◽

10.1073/pnas.1707962114 ◽

2017 ◽

Vol 114 (45) ◽

pp. 11986-11991 ◽

Cited By ~ 23

Author(s):

Susan L. Williams ◽

Rohani Ambo-Rappe ◽

Christine Sur ◽

Jessica M. Abbott ◽

Steven R. Limbong

Keyword(s):

Marine Ecosystem ◽

Ecosystem Restoration ◽

Well Being ◽

Coastal Ecosystems ◽

Coastal Development ◽

Marine Biodiversity ◽

Coral Triangle ◽

Mangrove Forests ◽

Positive Role ◽

Seagrass Meadows

Ecosystem restoration aims to restore biodiversity and valuable functions that have been degraded or lost. The Coral Triangle is a hotspot for marine biodiversity held in its coral reefs, seagrass meadows, and mangrove forests, all of which are in global decline. These coastal ecosystems support valuable fisheries and endangered species, protect shorelines, and are significant carbon stores, functions that have been degraded by coastal development, destructive fishing practices, and climate change. Ecosystem restoration is required to mitigate these damages and losses, but its practice is in its infancy in the region. Here we demonstrate that species diversity can set the trajectory of restoration. In a seagrass restoration experiment in the heart of the Coral Triangle (Sulawesi, Indonesia), plant survival and coverage increased with the number of species transplanted. Our results highlight the positive role biodiversity can play in ecosystem restoration and call for revision of the common restoration practice of establishing a single target species, particularly in regions having high biodiversity. Coastal ecosystems affect human well-being in many important ways, and restoration will become ever more important as conservation efforts cannot keep up with their loss.

Download Full-text