Pemetaan Lamun Mengunakan Machine Learning Dengan Citra Planetscope Di Nusa Lembongan

Seagrass is one community in benthic habitat that has tremendous benefits for the ecosystem, however the existence of seagrass has been frequently marginalized in recent decades. Seagrass beds functions as a blue carbon ecosystem which are able to absorb carbon higher than terrestrial vegetation. Therefore, it is important to detect and map the seagrass beds distribution to calculate the potential carbon uptake from seagrass. The seagrass mapping can be employed efficiently by using remote sensing imagery and the use of machine learning technology. This research aims to examine the utilization of PlanetScope imagery (3.7 m spatial resolution) for seagrass mapping and to subsequently examine, the effect of atmospheric corrections, sun-glint, and the water column corrections on the accuracy of seagrass mapping. In addition, this study also identified the cover changes in seagrass area from 2016 to 2021 in Nusa Lembongan. The study utilized the tree-based machine learning methods such as decision tree and random forest. The results showed that the best model accuracy was generated by using raw PlanetScope data the best model accuracy of 98% and classification accuracy of 94% from decision tree method. Based on the decision tree mapping using PlanetScope data for 2016 and 2021, there was a decline in the seagrass cover from 100.53 hectares to 97.31 hectares. Lamun merupakan salah satu dari ekosistem habitat bentik yang memiliki manfaat yang sangat besar namun sebagai ekosistem, kehadiran lamun sering dikesampingkan beberapa dekade terakhir. Fungsi padang lamun sebagai ekosistem karbon biru mampu menyerap karbon lebih tinggi dibandingkan vegetasi daratan. Karena itu, penting untuk mendeteksi dan memetakan informasi padang lamun untuk memperhitungkan serapan karbon oleh lamun. Pemanfaatan lamun dapat dilakukan secara cepat dan efisien dengan mengunakan teknologi penginderaan jauh dan pemenfaatan teknologi machine learning. Penelitian bertujuan untuk mengkaji pemanfaatan citra PlanetScope untuk memetakan lamun dan selanjutnya menganalisis pengaruh kalibrasi atmosferik, sun-glint, dan kolom air terhadap akurasi pemetaan padang lamun. Selain itu, perubahan tutupan lamun tahun 2016 – 2021 di Nusa Lembongan juga dipetakan. Penelitian ini menggunakan metode machine learning berbasis pohon seperti decision tree dan random forest. Hasil penelitian menunjukkan akurasi model terbaik dihasilkan dengan menggunakan data mentah dengan akurasi model 98% dan akurasi klasifikasi 94% dari metode decision tree. Berdasarkan data PlanetScope tahun 2016 dan 2021 dengan mengunakan metode decision tree terjadi penurunan luasan lamun dari 100,53 Ha menjadi 97,31 Ha.

Seagrass Mapping and Monitoring Along the Coasts of Crete, Greece

Type: Master's Thesis (M.Sc.).School: University of Twente, Faculty of Geo-Information Science and Earth Observation (ITC).Supervisors: Albertus G. (Bert) Toxopeus, Valentijn Venus. Location: Netherlands, Enschede (Overijssel Province).The seagrasses, a unique group of aquatic plants, create complex, extremely diversified and productive ecological systems in the littoral coastal zones. The only flowering plant in the world that is able to live completely submerged, seagrasses play vital role in the marine ecosystems of the World Ocean. Seagrasses are the most important component in the environmental food chain of the coastal ecosystems, being a vital food source for various marine species (e.g. fish, dugongs, turtles, swans), and a producer of organic matter, which is the very basis of the food web. The P.oceanica seagrass is an endemic for the Mediterranean region, and a main species in the marine coastal environment of Greece. Meadows of P.oceanica are subjected to the human activities, because they occur in coastal areas, where they are affected both by anthropogenic and by climatic and environmental factors. Nowadays P.oceanica is in the alarming state of regression, because of the deterioration of the environment in the Mediterranean Sea. Due to these reasons, P.oceanica is a protected species since 1988 in some European countries (France). Monitoring P.oceanica is therefore an important contribution to the saving and protecting the environment of Mediterranean region. The current MSc thesis focuses on the monitoring of seagrass P.oceanica along the northern coasts of Crete Island, Greece, and investigates the application of the remote sensing techniques for the seagrass mapping. This research was articulated in two parts, where the first one involves an ecological approach to the seagrass distribution in various regions around the globe and the experience of seagrass monitoring nowadays. The second part of this work has technical character and investigates the application of the remote sensing techniques towards seagrass mapping. It, furthermore, focuses on the optical properties of the P.oceanica and other seafloor cover types, and studies distinguishability of various seafloor cover types. Studies of the optical characteristics of separate seafloor cover types were made with purpose to clarify, whether their spectral properties change with varying environmental conditions.Special attention has been drawn on the role of environmental factors on the distribution of P.oceanica along the coasts of Crete, and in particular, how the optical properties of the seafloor cover types, i.e. spectral reflectance, are being changed under varying external conditions, e.g. water column, amount of suspended particles and sediments in the seawater, and water temperature. For this purpose we studied differences in the spectral reflectance of P.oceanica and other bottom cover types at three distinct depths. The diverse spectral values entail variations in optical properties of the seafloor cover types at changing environmental conditions. We applied WASI Water Color Simulator (WASI) simulation techniques for the modelling of the optical parameters of various seafloor cover types by various spaceborne imaging spectrometers (MEdium Resolution Imaging Spectrometer (MERIS), Sea-viewing Wide Field-of-view Sensor (SeaWiFS), Coastal Zone Color Scanner (CZCS) and MODerate resolution Imaging Spectroradiometer (MODIS)), in order to understand their suitability and possible limitations for the seagrass mapping. Fieldwork research sites were presented by separate locations on the northern coast of Crete region (Ligaria, Agia Pelagia, Xerocampos). The additional measurements of the reflectance spectra of the seawater with and without sediments have been made in aquarium tank in 2009 by means of Trios-RAMSES spectroradiometer. Parallel to the collection of spectra signatures, we captured the imagery for the seagrass mapping, which consists of the aerial images from the Google Earth website and the satellite Landsat TM and ETM+ scenes.

HUBUNGAN KERAPATAN LAMUN (SEAGRASS) DENGAN KELIMPAHAN TERIPANG (HOLOTHURIA) DI PANTAI ALANG-ALANG TAMAN NASIONAL KARIMUNJAWA

Pantai Alang-alang terletak di Taman Nasional Karimunjawa yang memiliki ekosistem lamun dengan cukup baik. Banyak biota yang berasosiasi dengan lamun, salah satunya teripang yang merupakan unsur kekayaan keanekaragaman hayati laut. Tingginya harga pasar dan manfaat yang begitu besar bagi manusia, membuat permintaan komoditas tersebut meningkat dari waktu ke waktu sehingga mengancam kelestarian jenis tersebut di habitatnya. Penelitian ini bertujuan untuk mengetahui kerapatan lamun, kelimpahan teripang, dan mengetahui hubungan antara kerapatan lamun dengan kelimpahan teripang di Pantai Alang-alang, Karimunjawa. Pelaksanaan penelitian dilakukan pada bulan Mei 2018 di perairan Pantai Alang-alang, Karimunjawa. Metode yang digunakan dalam penelitian yaitu metode observasi dengan metode samplingnya random sampling. Pengambilan sampel teripang dilakukan pada ketiga stasiun lamun dengan kerapatan jarang, sedang, dan padat. Penghitungan pemetaan lamun dan kelimpahan teripang menggunakan kuadran 1m x 1m dan dilakukan sebanyak 3 kali pengulangan. Hasil penelitian menunjukkan terdapat 4 jenis lamun yaitu Enhallus acoroides, Cymodoceae serulata, Thalasia hemprichii, dan Cymodoceae rotundata. Jumlah tegakan lamun pada kerapatan jarang 5378 tegakkan/80m2, kerapatan sedang 13564 tegakkan/80m2, dan kerapatan padat 28632 tegakkan/80m2. Teripang yang didapatkan di Pantai Alang-alang yaitu sebanyak 1 spesies pada kerapatan padat sejumlah 48 ind/80m2, kerapatan sedang 39 ind/80m2, dan pada kerapatan jarang 16 ind/80m2. Hasil analisa statistika kerapatan lamun dengan kelimpahan teripang terdapat korelasi r = 0,914, menunjukan korelasi erat sehingga semakin tinggi kerapatan lamun akan diikuti oleh melimpahnya teripang. Alang-alang Beach is located in Karimunjawa National Park which has good seagrass ecosystem. Many biota associated with seagrass, one of them is Holothuria which is an element of marine biodiversity richness. The high market price and the enormous benefits for humans, make the demand for these commodities increase over time, thus threatening the sustainability of the species in their habitat. This study aims to determine the density of seagrass, to know the abundance of Holothuria, and to know the relationship between the density of sea grass with the abundance of Holothuria in Alang-alang Beach, Karimunjawa. The research was conducted in May 2018 in the waters of Alang-Alang Beach, Karimunjawa. The method used in the research is the method of observation by the method of sampling random sampling. Sampling of sea cucumbers was done on three seagrass stations with rare density, medium, and solid. Calculation of seagrass mapping and abundance of Holothuria using quadrant 1m x 1m and done as much as 3 times repetition. The results showed that there were 4 types of seagrass: Enhallus acoroides, Cymodoceae serulata, Thalasia hemprichii, and Cymodoceae rotundata. The amount of seagrass standing at rare density 5378 stands / 80m2, medium density 13564 stands / 80m2, and solid density 28632 stands / 80m2. Holothuria are obtained in Alang-alang Beach that is 1 species in solid density of 48 ind / 80m2, medium density 39 ind / 80m2, and at rare density 16 ind / 80m2. The result of statistical analysis of seagrass density with the abundance of Holothuria is correlation r = 0,914, showing the correlation closely so that the higher density of sea grass will be followed by abundance of sea cucumber.