Browse
Submit Data
Databases
API
Help

Dataset Information

28 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Predicting regional coastal sea level changes with machine learning.

ABSTRACT: All ocean basins have been experiencing significant warming and rising sea levels in recent decades. There are, however, important regional differences, resulting from distinct processes at different timescales (temperature-driven changes being a major contributor on multi-year timescales). In view of this complexity, it deems essential to move towards more sophisticated data-driven techniques as well as diagnostic and prognostic prediction models to interpret observations of ocean warming and sea level variations at local or regional sea basins. In this context, we present a machine learning approach that exploits key ocean temperature estimates (as proxies for the regional thermosteric sea level component) to model coastal sea level variability and associated uncertainty across a range of timescales (from months to several years). Our findings also demonstrate the utility of machine learning to estimate the possible tendency of near-future regional sea levels. When compared to actual sea-level records, our models perform particularly well in the coastal areas most influenced by internal climate variability. Yet, the models are widely applicable to evaluate the patterns of rising and falling sea levels across many places around the globe. Thus, our approach is a promising tool to model and anticipate sea level changes in the coming (1-3) years, which is crucial for near-term decision making and strategic planning about coastal protection measures.

SUBMITTER: Nieves V

PROVIDER: S-EPMC8027398 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Predicting gene level sensitivity to JAK-STAT signaling perturbation using a mechanistic-to-machine learning framework

Project description:This SuperSeries is composed of the SubSeries listed below.

2023-08-07 | GSE231345 | GEO

Regional level influenza study based on Twitter and machine learning method.

Project description:The significance of flu prediction is that the appropriate preventive and control measures can be taken by relevant departments after assessing predicted data; thus, morbidity and mortality can be reduced. In this paper, three flu prediction models, based on twitter and US Centers for Disease Control's (CDC's) Influenza-Like Illness (ILI) data, are proposed (models 1-3) to verify the factors that affect the spread of the flu. In this work, an Improved Particle Swarm Optimization algorithm to optimize the parameters of Support Vector Regression (IPSO-SVR) was proposed. The IPSO-SVR was trained by the independent and dependent variables of the three models (models 1-3) as input and output. The trained IPSO-SVR method was used to predict the regional unweighted percentage ILI (%ILI) events in the US. The prediction results of each model are analyzed and compared. The results show that the IPSO-SVR method (model 3) demonstrates excellent performance in real-time prediction of ILIs, and further highlights the benefits of using real-time twitter data, thus providing an effective means for the prevention and control of flu.

| S-EPMC6478375 | biostudies-literature

Predicting gene level sensitivity to JAK-STAT signaling perturbation using a mechanistic-to-machine learning framework II

Project description:To inhibit JAK2 upon IL-6 and IL-10-induced JAK-STAT signaling and quantify gene expression in bone marrow derived macrophages (BMDMs). Bulk RNAseq was done on cytokine-stimulated BMDM with and without Fedratinib treatment in order to profile the JAK2-inhibited cytokine-induced response.

2023-08-07 | GSE231344 | GEO

Predicting gene level sensitivity to JAK-STAT signaling perturbation using a mechanistic-to-machine learning framework I

Project description:To link upstream IL-6 and IL-10-induced JAK-STAT signaling to downstream gene expression in bone marrow derived macrophages (BMDMs). Bulk RNAseq was done on cytokine-stimulated BMDM in order to profile cytokine-induced response.

2023-08-07 | GSE231343 | GEO

Sea-level rise exponentially increases coastal flood frequency.

Project description:Sea-level rise will radically redefine the coastline of the 21st century. For many coastal regions, projections of global sea-level rise by the year 2100 (e.g., 0.5-2 meters) are comparable in magnitude to today's extreme but short-lived increases in water level due to storms. Thus, the 21st century will see significant changes to coastal flooding regimes (where present-day, extreme-but-rare events become common), which poses a major risk to the safety and sustainability of coastal communities worldwide. So far, estimates of future coastal flooding frequency focus on endpoint scenarios, such as the increase in flooding by 2050 or 2100. Here, we investigate the continuous shift in coastal flooding regimes by quantifying continuous rates of increase in the occurrence of extreme water-level events due to sea-level rise. We find that the odds of exceeding critical water-level thresholds increases exponentially with sea-level rise, meaning that fixed amounts of sea-level rise of only ~1-10 cm in areas with a narrow range of present-day extreme water levels can double the odds of flooding. Combining these growth rates with established sea-level rise projections, we find that the odds of extreme flooding double approximately every 5 years into the future. Further, we find that the present-day 50-year extreme water level (i.e., 2% annual chance of exceedance, based on historical records) will be exceeded annually before 2050 for most (i.e., 70%) of the coastal regions in the United States. Looking even farther into the future, the present-day 50-year extreme water level will be exceeded almost every day during peak tide (i.e., daily mean higher high water) before the end of the 21st century for 90% of the U.S. coast. Our findings underscore the need for immediate planning and adaptation to mitigate the societal impacts of future flooding.

| S-EPMC7162943 | biostudies-literature

Coastal barrier stratigraphy for Holocene high-resolution sea-level reconstruction.

Project description:The uncertainties surrounding present and future sea-level rise have revived the debate around sea-level changes through the deglaciation and mid- to late Holocene, from which arises a need for high-quality reconstructions of regional sea level. Here, we explore the stratigraphy of a sandy barrier to identify the best sea-level indicators and provide a new sea-level reconstruction for the central Portuguese coast over the past 6.5?ka. The selected indicators represent morphological features extracted from coastal barrier stratigraphy, beach berm and dune-beach contact. These features were mapped from high-resolution ground penetrating radar images of the subsurface and transformed into sea-level indicators through comparison with modern analogs and a chronology based on optically stimulated luminescence ages. Our reconstructions document a continuous but slow sea-level rise after 6.5?ka with an accumulated change in elevation of about 2?m. In the context of SW Europe, our results show good agreement with previous studies, including the Tagus isostatic model, with minor discrepancies that demand further improvement of regional models. This work reinforces the potential of barrier indicators to accurately reconstruct high-resolution mid- to late Holocene sea-level changes through simple approaches.

| S-EPMC5144086 | biostudies-other

Predicting brain function status changes in critically ill patients via Machine learning.

Project description:ObjectiveIn intensive care units (ICUs), a patient's brain function status can shift from a state of acute brain dysfunction (ABD) to one that is ABD-free and vice versa, which is challenging to forecast and, in turn, hampers the allocation of hospital resources. We aim to develop a machine learning model to predict next-day brain function status changes.Materials and methodsUsing multicenter prospective adult cohorts involving medical and surgical ICU patients from 2 civilian and 3 Veteran Affairs hospitals, we trained and externally validated a light gradient boosting machine to predict brain function status changes. We compared the performances of the boosting model against state-of-the-art models-an ABD predictive model and its variants. We applied Shapley additive explanations to identify influential factors to develop a compact model.ResultsThere were 1026 critically ill patients without evidence of prior major dementia, or structural brain diseases, from whom 12 295 daily transitions (ABD: 5847 days; ABD-free: 6448 days) were observed. The boosting model achieved an area under the receiver-operating characteristic curve (AUROC) of 0.824 (95% confidence interval [CI], 0.821-0.827), compared with the state-of-the-art models of 0.697 (95% CI, 0.693-0.701) with P < .001. Using 13 identified top influential factors, the compact model achieved 99.4% of the boosting model on AUROC. The boosting and the compact models demonstrated high generalizability in external validation by achieving an AUROC of 0.812 (95% CI, 0.812-0.813).ConclusionThe inputs of the compact model are based on several simple questions that clinicians can quickly answer in practice, which demonstrates the model has direct prospective deployment potential into clinical practice, aiding in critical hospital resource allocation.

| S-EPMC8510304 | biostudies-literature

Predicting marsh vulnerability to sea-level rise using Holocene relative sea-level data.

Project description:Tidal marshes rank among Earth's vulnerable ecosystems, which will retreat if future rates of relative sea-level rise (RSLR) exceed marshes' ability to accrete vertically. Here, we assess the limits to marsh vulnerability by analyzing >780 Holocene reconstructions of tidal marsh evolution in Great Britain. These reconstructions include both transgressive (tidal marsh retreat) and regressive (tidal marsh expansion) contacts. The probability of a marsh retreat was conditional upon Holocene rates of RSLR, which varied between -7.7 and 15.2?mm/yr. Holocene records indicate that marshes are nine times more likely to retreat than expand when RSLR rates are ?7.1?mm/yr. Coupling estimated probabilities of marsh retreat with projections of future RSLR suggests a major risk of tidal marsh loss in the twenty-first century. All of Great Britain has a >80% probability of a marsh retreat under Representative Concentration Pathway (RCP) 8.5 by 2100, with areas of southern and eastern England achieving this probability by 2040.

| S-EPMC6043595 | biostudies-literature

Thresholds of sea-level rise rate and sea-level rise acceleration rate in a vulnerable coastal wetland.

Project description:Feedbacks among inundation, sediment trapping, and vegetation productivity help maintain coastal wetlands facing sea-level rise (SLR). However, when the SLR rate exceeds a threshold, coastal wetlands can collapse. Understanding the threshold helps address key challenges in ecology-nonlinear response of ecosystems to environmental change, promotes communication between ecologists and resource managers, and facilitates decision-making in climate change policies. We studied the threshold of SLR rate and developed a new threshold of SLR acceleration rate on sustainability of coastal wetlands as SLR is likely to accelerate due to enhanced anthropogenic forces. Deriving these two thresholds depends on the temporal scale, the interaction of SLR with other environmental factors, and landscape metrics, which have not been fully accounted for before this study. We chose a representative marine-dominated estuary in the northern Gulf of Mexico, Grand Bay in Mississippi, to test the concept of SLR thresholds. We developed a mechanistic model to simulate wetland change and then derived the SLR thresholds for Grand Bay. The model results show that the threshold of SLR rate in Grand Bay is 11.9 mm/year for 2050, and it drops to 8.4 mm/year for 2100 using total wetland area as a landscape metric. The corresponding SLR acceleration rate thresholds are 3.02 × 10-4 m/year2 and 9.62 × 10-5 m/year2 for 2050 and 2100, respectively. The newly developed SLR acceleration rate threshold can help quantify the temporal lag before the rapid decline in wetland area becomes evident after the SLR rate threshold is exceeded, and cumulative SLR a wetland can adapt to under the SLR acceleration scenarios. Based on the thresholds, SLR that will adversely impact the coastal wetlands in Grand Bay by 2100 will fall within the likely range of SLR under a high warming scenario (RCP8.5), highlighting the need to avoid RCP8.5 to preserve these marshes.

| S-EPMC5743734 | biostudies-literature

Quasi zenith satellite system-reflectometry for sea-level measurement and implication of machine learning methodology.

Project description:The tide gauge measurements from global navigation satellite system reflectometry (GNSS-R) observables are considered to be a promising alternative to the traditional tide gauges in the present days. In the present paper, we deliver a comparative analysis of tide-gauge (TG) measurements retrieved by quasi-zenith satellite system-reflectometry (QZSS-R) and the legacy TG recordings with additional observables from other constellations viz. GPS-R and GLONASS-R. The signal-to-noise ratio data of QZSS (L1, L2, and L5 signals) retrieved at the P109 site of GNSS Earth Observation Network in Japan (37.815° N; 138.281° E; 44.70 m elevation in ellipsoidal height) during 01 October 2019 to 31 December 2019. The results from QZSS observations at L1, L2, and L5 signals show respective correlation coefficients of 0.8712, 0.6998, and 0.8763 with observed TG measurements whereas the corresponding root means square errors were 4.84 cm, 4.26 cm, and 4.24 cm. The QZSS-R signals revealed almost equivalent precise results to that of GPS-R (L1, L2, and L5 signals) and GLONASS-R (L1 and L2 signals). To reconstruct the tidal variability for QZSS-R measurements, a machine learning technique, i.e., kernel extreme learning machine (KELM) is implemented that is based on variational mode decomposition of the parameters. These KELM reconstructed outcomes from QZSS-R L1, L2, and L5 observables provide the respective correlation coefficients of 0.9252, 0.7895, and 0.9146 with TG measurements. The mean errors between the KELM reconstructed outcomes and observed TG measurements for QZSS-R, GPS-R, and GLONASS-R very often lies close to the zero line, confirming that the KELM-based estimates from GNSS-R observations can provide alternative unbiased estimations to the traditional TG measurement. The proposed method seems to be effective, foreseeing a dense tide gauge estimations with the available QZSS-R along with other GNSS-R observables.

| S-EPMC9744832 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data