scholarly journals Perbandingan Model GAM dan Gamboost dalam Fitting Dataset Sea Surface Temperature

2018 ◽  
Vol 18 (1) ◽  
pp. 39-50
Author(s):  
Miftahuddin Miftahuddin
Keyword(s):  
Surface Temperature ◽  
Sea Surface Temperature ◽  
Risk Model ◽  
Generalized Additive Models ◽  
Information Criteria ◽  
Additive Models ◽  
Sea Surface ◽  
Akaike Information Criteria ◽  
Fitting Model

Fitting model GAM (generalized additive models) dan Gamboost (generalized additive models by boosting) untuk dataset SST (sea surface temperature) dimaksudkan sebagai upaya mencapai perbaikan fitting model terhadap data SST. Secara umum, model GAM dapat memvisualisasikan masing-masing kovariat, sedangkan model gamboost dapat memvisualisasikan lebih detail kovariatnya dalam beberapa bentuk, baik secara linier dan nonlinier. Pengukuran performance yang digunakan terhadap model adalah nilai AIC (Akaike Information Criteria) dan CV-risk. Model GAM dengan boosting menunjukkan lebih sesuai dalam struktur model, pemilihan model terbaik dan seleksi variabel pada dataset SST. Fitting model GAM dapat menghasilkan pola dan trend masing-masing kovariat meskipun memiliki beberapa gap, sedangkan pada model gamboost memiliki lebih banyak pilihan simultan dalam bentuk linier, nonlinier dan smooth untuk masing-masing kovariat. Kedua pendekatan fitting memiliki kelebihan yang dapat saling melengkapi dalam memodelkan dataset SST.

scholarly journals Model of Habitat Characteristics of Sardinella lemuru in the Bali Strait, Indonesia

2021 ◽  
Vol 56 (3) ◽  
pp. 229-240
Author(s):  
Adi Wijaya ◽  
Abu Bakar Sambah ◽  
Daduk Setyohadi ◽  
Umi Zakiyah
Keyword(s):  
Surface Temperature ◽  
Sea Surface Temperature ◽  
Chlorophyll A ◽  
Environmental Conditions ◽  
Generalized Additive Models ◽  
Additive Models ◽  
Sea Surface ◽  
Model Parameters ◽  
Photosynthetically Available Radiation ◽  
Chlorophyll A Concentration

This article describes a new approach to the study of the environmental conditions that relate to the Sardinella lemuru habitat in the Bali Strait, through remote sensing data and fish catch data using the generalized additive model. Data that are acquired daily and then compiled into monthly data for sea surface temperature, sea surface chlorophyll-a concentration, photosynthetically available radiation, and sea surface depth (SSD) were used for the years 2008–2010. The objectives of the study are to describe the variability of the environmental conditions in the Bali Strait, to analyze a combination model of environmental factors in estimating the Sardinella lemuru habitat, and to map potential Sardinella lemuru fishing areas. We illustrate the proposed method by constructing seven generalized additive models with catches of Sardinella lemuru as a variable response and use sea surface temperature, sea surface chlorophyll-a concentration, photosynthetically available radiation, and SSD as covariant models for assessing the environmental characteristics of the abundance of Sardinella lemuru. Predicted values were validated using a linear model. Based on the three model parameters, habitat selection for Sardinella lemuru was significantly (P < 0.0001) influenced by photosynthetically available radiation (50–55 Einstein m-2 d-1), sea surface chlorophyll-a concentration (0.2–2.0 mgm-3), sea surface temperature (28.95–29.64 °C), and SSD (60–150 m). Catch predictions show a consistent trend toward environmental conditions and water depth. Our method allows for improvement with the validation of catch predictions that were observed and collected monthly, and the result was significant (P < 0.001, r2 = 0.816). Photosynthetically available radiation explains the highest deviation in continued generalized additive models; therefore, it was considered to be the best predictor of habitat, followed by sea surface chlorophyll-a concentration, sea surface temperature, and then SSD. New research results supplement several previous studies that relate to the analysis of environmental parameters in estimating the fish habitat and can be used in mapping the distribution of potential Sardinella lemuru fishing areas in spatial and temporal scales.

scholarly journals Projecting regions of North Atlantic right whale, Eubalaena glacialis, habitat suitability in the Gulf of Maine for the year 2050

Elem Sci Anth ◽  
2021 ◽  
Vol 9 (1) ◽  
Author(s):  
Camille H. Ross ◽  
Daniel E. Pendleton ◽  
Benjamin Tupper ◽  
David Brickman ◽  
Monica A. Zani ◽  
...  
Keyword(s):  
Surface Temperature ◽  
Sea Surface Temperature ◽  
North Atlantic ◽  
Habitat Suitability ◽  
Gulf Of Maine ◽  
Model Performance ◽  
Additive Models ◽  
Sea Surface ◽  
Eubalaena Glacialis ◽  
Climate Scenarios

North Atlantic right whales (Eubalaena glacialis) are critically endangered, and recent changes in distribution patterns have been a major management challenge. Understanding the role that environmental conditions play in habitat suitability helps to determine the regions in need of monitoring or protection for conservation of the species, particularly as climate change shifts suitable habitat. This study used three species distribution modeling algorithms, together with historical whale abundance data (1993–2009) and environmental covariate data, to build monthly ensemble models of past E. glacialis habitat suitability in the Gulf of Maine. The model was projected onto the year 2050 for a range of climate scenarios. Specifically, the distribution of the species was modeled using generalized additive models, boosted regression trees, and artificial neural networks, with environmental covariates that included sea surface temperature, bottom water temperature, bathymetry, a modeled Calanus finmarchicus habitat index, and chlorophyll. Year-2050 projections used downscaled climate anomaly fields from Representative Concentration Pathway 4.5 and 8.5. The relative contribution of each covariate changed seasonally, with an increase in the importance of bottom temperature and C. finmarchicus in the summer, when model performance was highest. A negative correlation was observed between model performance and sea surface temperature contribution. The 2050 projections indicated decreased habitat suitability across the Gulf of Maine in the period from July through October, with the exception of narrow bands along the Scotian Shelf. The results suggest that regions outside of the current areas of conservation focus may become increasingly important habitats for E. glacialis under future climate scenarios.

scholarly journals Habitat preferences among three top predators inhabiting a degraded ecosystem, the Black Sea

2017 ◽  
Vol 81 (2) ◽  
pp. 217 ◽  
Author(s):  
Alicia Sánchez-Cabanes ◽  
Maja Nimak-Wood ◽  
Nicola Harris ◽  
Renaud De Stephanis
Keyword(s):  
Surface Temperature ◽  
Sea Surface Temperature ◽  
Black Sea ◽  
Bottlenose Dolphins ◽  
Habitat Preferences ◽  
Additive Models ◽  
Sea Surface ◽  
The Black Sea ◽  
Cetacean Species ◽  
Common Dolphins

This study investigated whether there is evidence of widespread niche partitioning based on environmental factors in the Black Sea and tested the hypothesis that physiographic factors may be employed as predictors. It addresses poorly researched areas with good habitat potential for the only three cetacean subspecies living in this area: the Black Sea short-beaked common dolphin (Delphinus delphis spp. ponticus), the Black Sea bottlenose dolphin (Tursiops truncatus spp. ponticus) and the Black Sea harbour porpoise (Phocoena phocoena spp. relicta). Generalized additive models (GAMs) were used to analyse data collected from multiple sources. In total, 745 sightings of the three species between 1998 and 2010 throughout the Black Sea were included. The analysis found depth and sea surface temperature to be the most important variables for separating the occurrence of the three species. Common dolphins occurred mainly in deep waters and in areas where the sea surface temperature was low, bottlenose dolphins were distributed primarily in shallower and warmer waters than common dolphins, and harbour porpoises were distributed in shallower waters with lower sea surface temperature than bottlenose dolphins. This study suggests strong niche segregation among the three cetacean species. The study is also the first contribution to the basic information of cetacean species distribution and habitat preferences in the Black Sea as a whole. Knowledge of the distribution of the three dolphin species in the study area is essential to establish conservation measures for these populations.

scholarly journals Modeling of Sea Surface Temperature through Fitting Linear Model with Interaction

2021 ◽  
Vol 18 (1) ◽  
pp. 55-66
Author(s):  
Miftahuddin Miftahuddin ◽  
Wanda Sri Noviana
Keyword(s):  
Surface Temperature ◽  
Sea Surface Temperature ◽  
Moving Average ◽  
Statistical Significance ◽  
Peak Effect ◽  
Sea Surface ◽  
P Value ◽  
Linear Fitting ◽  
Statistical Measures ◽  
Fitting Model

Sea surface temperature (SST) is one of the attributes of the world climate system and global warming. The relationship between SST and other climate parameters can be represented in a linearity approach. Through this approach, SST variability shows monthly and yearly effects. Information on these two time effects is important for knowing the period of peak effect as well as other statistical measures in the linear fitting model. The models used include transformation and without covariate transformation, interaction and without covariate interaction, and with centering and with the addition of time covariates in the model. The linear fitting model chosen as the basis for construction is a model with a combination effect of covariate interaction and transformation giving an increase in the magnitude of multiple R2 (56.62%) and adjusted R2 (56.13%) respectively 0.31% and 0.43%. This indicates that the time covariate has a very strong significant effect on the model compared to the continuous covariate. In general, the model has a statistical significance of p-value < 2.2e-16, as well as for the time covariate. However, because the model has an autocorrelation and a large AIC value, this effect is removed by means of an autoregressive moving average. The obtained linear fitting model for SST data is the model with AIC 403.2987.

scholarly journals Catch per Unit Effort Dynamic of Yellowfin Tuna Related to Sea Surface Temperature and Chlorophyll in Southern Indonesia

Fishes ◽  
2020 ◽  
Vol 5 (3) ◽  
pp. 28
Author(s):  
Budy Wiryawan ◽  
Neil Loneragan ◽  
Ulfah Mardhiah ◽  
Sonja Kleinertz ◽  
Prihatin Ika Wahyuningrum ◽  
...  
Keyword(s):  
Surface Temperature ◽  
Sea Surface Temperature ◽  
Chlorophyll A ◽  
Yellowfin Tuna ◽  
Additive Models ◽  
Sea Surface ◽  
Catch Per Unit Effort ◽  
Unit Effort ◽  
The Government ◽  
Tuna Fisheries

Tuna fisheries are the most valuable fisheries in the world, with an estimated market value of at least US$42 billion in 2018. Indonesia plays an important role in the global tuna fisheries and has committed to improve its fisheries management; therefore, a pilot of long-term spatial-temporal data bases was developed in 2012, however none have utilized data to have better understanding for management improvement. In this study, the annual and seasonal variation of large (≥10 kg) Yellowfin Tuna (YFT) catch per unit effort (CPUE) have been investigated and the influence of sea surface temperature (SST) and chlorophyll-a on these variables examined. We used fish landing data from West Nusa Tenggara recorded every month between 2012 and 2017 and analyzed using generalized linear models and generalized additive models. We found a seasonal and annual pattern of tuna abundance affected by SST and chlorophyll-a (chl a) and related to upwelling and El Nino event. These results also suggest that a two-month closure to fishing in August and September in southern Lombok is worth considering by the Government to maximize conservation of stocks due to a high abundance of juveniles emerging during the upwelling months from June to August.

Holocene sea surface temperature variations recorded in corals from Kikai Island, Japan

2017 ◽  
Vol 51 (4) ◽  
pp. e9-e14 ◽  
Author(s):  
Hiroto Kajita ◽  
Atsuko Yamazaki ◽  
Takaaki Watanabe ◽  
Chung-Che Wu ◽  
Chuan-Chou Shen ◽  
...  
Keyword(s):  
Surface Temperature ◽  
Sea Surface Temperature ◽  
Sea Surface ◽  
Temperature Variations

PENENTUAN DAERAH POTENSIAL BUDIDAYA RUMPUT LAUT KAPPAPHYCUS ALVAREZII DI PROVINSI NUSA TENGGARA TIMUR

2019 ◽  
Vol 3 ◽  
pp. 929
Author(s):  
Marianus Filipe Logo ◽  
N M. R. R. Cahya Perbani ◽  
Bayu Priyono
Keyword(s):  
Dissolved Oxygen ◽  
Surface Temperature ◽  
Sea Surface Temperature ◽  
Kappaphycus Alvarezii ◽  
Sea Surface

Provinsi Nusa Tenggara Timur (NTT) merupakan penghasil rumput laut kappaphycus alvarezii kedua terbesar di Indonesia berdasarkan data Badan Pusat Statistik (2016). Oleh karena itu diperlukan zonasi daerah potensial budidaya rumput laut kappaphycus alvarezii untuk pengembangan lebih lanjut. Penelitian ini bertujuan untuk menentukan daerah yang potensial untuk budidaya rumput laut kappaphycus alvarezii di Provinsi NTT berdasarkan parameter sea surface temperature (SST), salinitas, kedalaman, arus, dissolved oxygen (DO), nitrat, fosfat, klorofil-a, dan muara sungai. Penentuan kesesuaian lokasi budidaya dilakukan dengan memberikan bobot dan skor bagi setiap parameter untuk budidaya rumput laut kappaphycus alvarezii menggunakan sistem informasi geografis melalui overlay peta tematik setiap parameter. Dari penelitian ini diperoleh bahwa kadar nitrat, arus, kedalaman, dan lokasi muara sungai menjadi parameter penentu utama. Jarak maksimum dari bibir pantai adalah sekitar 10 km. Potensial budidaya rumput laut kappaphycus alvarezii ditemukan di Pulau Flores bagian barat, kepulauan di Kabupaten Flores Timur dan Alor, selatan Pulau Sumba, Pulau Rote, dan Teluk Kupang.

Sign in / Sign up

Export Citation Format

Share Document