Evaluation of Machine Learning Predictions of a Highly Resolved Time Series of Chlorophyll-a Concentration

Amorim, Felipe de Luca Lopes de; Rick, Johannes; Lohmann, Gerrit; Wiltshire, Karen Helen

doi:10.3390/app11167208

Cited by 14 publications

(5 citation statements)

References 42 publications

(59 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the time of sampling in Helgoland, seston C content was 301 ± 8 µg C L -1 , and the molar C:N ratio was 7.8 ± 0.2, so it is possible that copepods may have been C-limited. The chlorophyll a concentration in the seston at the time and location of sampling was 1.5 ± 0.1 µg chl a L -1 , a low value in comparison to peak values during spring and summer (Amorim et al, 2021), further indicating limited food quantity in the field. The second possibility is that small copepods such as T. longicornis do have some ability to store energy reservesfrom 9.5 to 11.5% body C (this study; Evjemo and Olsen, 1997;Evjemo et al, 2003).…”

Section: Effects Of Experimental Diet On the Tfa Content And Profile ...mentioning

confidence: 89%

To Regulate or Not to Regulate: Assimilation of Dietary Fatty Acids in the Temperate Copepod Temora longicornis

et al. 2022

View full text Add to dashboard Cite

Consumer regulation of lipid composition during assimilation of dietary items is related to their ecology, habitat, and life cycle, and may lead to extra energetic costs associated with the conversion of dietary material into the fatty acids (FAs) necessary to meet metabolic requirements. For example, lipid-rich copepods from temperate and polar latitudes must convert assimilated dietary FAs into wax esters, an efficient type of energy storage which enables them to cope with seasonal food shortages and buoyancy requirements. Lipid-poor copepods, however, tend to not be as constrained by food availability as their lipid-rich counterparts and, thus, should have no need for modifying dietary FAs. Our objective was to test the assumption that Temora longicornis, a proxy species for lipid-poor copepods, does not regulate its lipid composition. Isotopically-enriched (13C) diatoms were fed to copepods during a 5-day laboratory experiment. Compound-specific stable isotope analysis of algae and copepod samples was performed in order to calculate dietary FA assimilation, turnover, and assimilation efficiency into copepod FAs. Approximately 65% of the total dietary lipid carbon (C) assimilated (913 ± 68 ng C ind-1 at the end of the experiment) was recorded as polyunsaturated FAs, with 20 and 15% recorded as saturated and monounsaturated FAs, respectively. As expected, T. longicornis assimilated dietary FAs in an unregulated, non-homeostatic manner, as evidenced by the changes in its FA profile, which became more similar to that of their diet. Copepods assimilated 11% of the total dietary C (or 40% of the dietary lipid C) ingested in the first two days of the experiment. In addition, 34% of their somatic growth (in C) after two days was due to the assimilation of dietary C in FAs. Global warming may lead to increased proportions of smaller copepods in the oceans, and to a lower availability of algae-produced essential FAs. In order for changes in the energy transfer in marine food webs to be better understood, it is important that future investigations assess a broader range of diets as well as lipid-poor zooplankton from oceanographic areas throughout the world’s oceans.

show abstract

Section: Effects Of Experimental Diet On the Tfa Content And Profile ...mentioning

confidence: 89%

To Regulate or Not to Regulate: Assimilation of Dietary Fatty Acids in the Temperate Copepod Temora longicornis

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In the prediction study of chlorophylla, Amorim et al ( 2021) evaluated and compared SVR, MLP, RF, and ARIMA algorithms. Comparing the algorithms, SVR reached the best R2 (0.78) and RMSE (1.113 µg L1), however, these were only slightly better results (MLP = 0.76; 1.144 µg L1 and RF = 0.75; 1.189 µg L1) (Amorim et al, 2021). The advantage of the SVR model in the forecast study is that it can avoid the complexity of the high-level ocean data space and solve the corresponding high-dimensional space decision problem directly in the linearly separable case.…”

Section: Figurementioning

confidence: 95%

A review of artificial intelligence in marine science

Song

Pang²,

Hou³

et al. 2023

Front. Earth Sci.

View full text Add to dashboard Cite

Utilization and exploitation of marine resources by humans have contributed to the growth of marine research. As technology progresses, artificial intelligence (AI) approaches are progressively being applied to maritime research, complementing traditional marine forecasting models and observation techniques to some degree. This article takes the artificial intelligence algorithmic model as its starting point, references several application trials, and methodically elaborates on the emerging research trend of mixing machine learning and physical modeling concepts. This article discusses the evolution of methodologies for the building of ocean observations, the application of artificial intelligence to remote sensing satellites, smart sensors, and intelligent underwater robots, and the construction of ocean big data. We also cover the method of identifying internal waves (IW), heatwaves, El Niño-Southern Oscillation (ENSO), and sea ice using artificial intelligence algorithms. In addition, we analyze the applications of artificial intelligence models in the prediction of ocean components, including physics-driven numerical models, model-driven statistical models, traditional machine learning models, data-driven deep learning models, and physical models combined with artificial intelligence models. This review shows the growth routes of the application of artificial intelligence in ocean observation, ocean phenomena identification, and ocean elements forecasting, with examples and forecasts of their future development trends from several angles and points of view, by categorizing the various uses of artificial intelligence in the ocean sector.

show abstract

“…This method has been further explored with different sample configurations and hyperparameter combinations [41] and employed to ascertain the significance of a set of predictor variables based on the respective evaluation criterion [42,43]. Random forests can depict nonlinear relationships, are relatively insensitive to correlated predictors and have been successfully applied in various remote sensing contexts [44].…”

Section: Previous Workmentioning

confidence: 99%

Land Cover Classification in the Antioquia Region of the Tropical Andes Using NICFI Satellite Data Program Imagery and Semantic Segmentation Techniques

Gomez-Ossa,

Sanchez-Torres,

Branch-Bedoya

2023

Data

View full text Add to dashboard Cite

Land cover classification, generated from satellite imagery through semantic segmentation, has become fundamental for monitoring land use and land cover change (LULCC). The tropical Andes territory provides opportunities due to its significance in the provision of ecosystem services. However, the lack of reliable data for this region, coupled with challenges arising from its mountainous topography and diverse ecosystems, hinders the description of its coverage. Therefore, this research proposes the Tropical Andes Land Cover Dataset (TALANDCOVER). It is constructed from three sample strategies: aleatory, minimum 50%, and 70% of representation per class, which address imbalanced geographic data. Additionally, the U-Net deep learning model is applied for enhanced and tailored classification of land covers. Using high-resolution data from the NICFI program, our analysis focuses on the Department of Antioquia in Colombia. The TALANDCOVER dataset, presented in TIF format, comprises multiband R-G-B-NIR images paired with six labels (dense forest, grasslands, heterogeneous agricultural areas, bodies of water, built-up areas, and bare-degraded lands) with an estimated 0.76 F1 score compared to ground truth data by expert knowledge and surpassing the precision of existing global cover maps for the study area. To the best of our knowledge, this work is a pioneer in its release of open-source data for segmenting coverages with pixel-wise labeled NICFI imagery at a 4.77 m resolution. The experiments carried out with the application of the sample strategies and models show F1 score values of 0.70, 0.72, and 0.74 for aleatory, balanced 50%, and balanced 70%, respectively, over the expert segmented sample (ground truth), which suggests that the personalized application of our deep learning model, together with the TALANDCOVER dataset offers different possibilities that facilitate the training of deep architectures for the classification of large-scale covers in complex areas, such as the tropical Andes. This advance has significant potential for decision making, emphasizing sustainable land use and the conservation of natural resources.

show abstract

Evaluation of Machine Learning Predictions of a Highly Resolved Time Series of Chlorophyll-a Concentration

Cited by 14 publications

References 42 publications

To Regulate or Not to Regulate: Assimilation of Dietary Fatty Acids in the Temperate Copepod Temora longicornis

To Regulate or Not to Regulate: Assimilation of Dietary Fatty Acids in the Temperate Copepod Temora longicornis

A review of artificial intelligence in marine science

Land Cover Classification in the Antioquia Region of the Tropical Andes Using NICFI Satellite Data Program Imagery and Semantic Segmentation Techniques

Contact Info

Product

Resources

About