Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Purely satellite data-driven deep learning forecast of complicated tropical instability waves.

ABSTRACT: Forecasting fields of oceanic phenomena has long been dependent on physical equation-based numerical models. The challenge is that many natural processes need to be considered for understanding complicated phenomena. In contrast, rules of the processes are already embedded in the time-series observation itself. Thus, inspired by largely available satellite remote sensing data and the advance of deep learning technology, we developed a purely satellite data-driven deep learning model for forecasting the sea surface temperature evolution associated with a typical phenomenon: a tropical instability wave. During the testing period of 9 years (2010-2019), our model accurately and efficiently forecasts the sea surface temperature field. This study demonstrates the strong potential of the satellite data-driven deep learning model as an alternative to traditional numerical models for forecasting oceanic phenomena.

SUBMITTER: Zheng G

PROVIDER: S-EPMC7439441 | biostudies-literature | 2020 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

Purely satellite data-driven deep learning forecast of complicated tropical instability waves.

Zheng Gang G Li Xiaofeng X Zhang Rong-Hua RH Liu Bin B

Science advances 20200715 29

Forecasting fields of oceanic phenomena has long been dependent on physical equation-based numerical models. The challenge is that many natural processes need to be considered for understanding complicated phenomena. In contrast, rules of the processes are already embedded in the time-series observation itself. Thus, inspired by largely available satellite remote sensing data and the advance of deep learning technology, we developed a purely satellite data-driven deep learning model for forecast ...[more]

PMID: 32832620

Similar Datasets

Using Deep Learning to Forecast Maritime Vessel Flows.

Project description:Forecasting vessel flows is important to the development of intelligent transportation systems in the maritime field, as real-time and accurate traffic information has favorable potential in helping a maritime authority to alleviate congestion, mitigate emission of GHG (greenhouse gases) and enhance public safety, as well as assisting individual vessel users to plan better routes and reduce additional costs due to delays. In this paper, we propose three deep learning-based solutions to forecast the inflow and outflow of vessels within a given region, including a convolutional neural network (CNN), a long short-term memory (LSTM) network, and the integration of a bidirectional LSTM network with a CNN (BDLSTM-CNN). To apply those solutions, we first divide the given maritime region into M × N grids, then we forecast the inflow and outflow for all the grids. Experimental results based on the real AIS (Automatic Identification System) data of marine vessels in Singapore demonstrate that the three deep learning-based solutions significantly outperform the conventional method in terms of mean absolute error and root mean square error, with the performance of the BDLSTM-CNN-based hybrid solution being the best.

| S-EPMC7146195 | biostudies-literature

Phase-conjugate mirror for water waves driven by the Faraday instability.

Project description:The Faraday instability appears on liquid baths submitted to vertical oscillations above a critical value. The pattern of standing ripples at half the vibrating frequency that results from this parametric forcing is usually shaped by the boundary conditions imposed by the enclosing receptacle. Here, we show that the time modulation of the medium involved in the Faraday instability can act as a phase-conjugate mirror--a fact which is hidden in the extensively studied case of the boundary-driven regime. We first demonstrate the complete analogy with the equations governing its optical counterpart. We then use water baths combining shallow and deep areas of arbitrary shapes to spatially localize the Faraday instability. We give experimental evidence of the ability of the Faraday instability to generate counterpropagating phase-conjugated waves for any propagating signal wave. The canonical geometries of a point and plane source are implemented. We also verify that Faraday-based phase-conjugate mirrors hold the genuine property of being shape independent. These results show that a periodic modulation of the effective gravity can perform time-reversal operations on monochromatic propagating water waves, with a remarkable efficiency compared with wave manipulation in other fields of physics.

| S-EPMC6500151 | biostudies-literature

Physics-informed deep learning to forecast [Formula: see text] during hydraulic fracturing.

Project description:Short-term forecasting of estimated maximum magnitude ([Formula: see text]) is crucial to mitigate risks of induced seismicity during fluid stimulation. Most previous methods require real-time injection data, which are not always available. This study proposes two deep learning (DL) approaches, along with two data-partitioning methods, that rely solely on preceding patterns of seismicity. The first approach forecasts [Formula: see text] directly using DL; the second incorporates physical constraints by using DL to forecast seismicity rate, which is then used to estimate [Formula: see text]. These approaches are tested using a hydraulic-fracture monitoring dataset from western Canada. We find that direct DL learns from previous seismicity patterns to provide an accurate forecast, albeit with a time lag that limits its practical utility. The physics-informed approach accurately forecasts changes in seismicity rate, but sometimes under- (or over-) estimates [Formula: see text]. We propose that significant exceedance of [Formula: see text] may herald the onset of runaway fault rupture.

| S-EPMC10423224 | biostudies-literature

Deep Learning Prediction of Cancer Prevalence from Satellite Imagery.

Project description:The worldwide growth of cancer incidence can be explained in part by changes in the prevalence and distribution of risk factors. There are geographical gaps in the estimates of cancer prevalence, which could be filled with innovative methods. We used deep learning (DL) features extracted from satellite images to predict cancer prevalence at the census tract level in seven cities in the United States. We trained the model using detailed cancer prevalence estimates from 2018 available in the CDC (Center for Disease Control) 500 Cities project. Data from 3500 census tracts covering 14,483,366 inhabitants were included. Features were extracted from 170,210 satellite images with deep learning. This method explained up to 64.37% (median = 43.53%) of the variation of cancer prevalence. Satellite features are highly correlated with individual socioeconomic and health measures that are linked to cancer prevalence (age, smoking and drinking status, and obesity). A higher similarity between two environments is associated with better generalization of the model (p = 1.10-6). This method can be used to accurately estimate cancer prevalence at a high spatial resolution without using surveys at a fraction of the cost.

| S-EPMC7766226 | biostudies-literature

Deep learning predicts chromosomal instability from histopathology images.

Project description:Chromosomal instability (CIN) is a hallmark of human cancer yet not readily testable for patients with cancer in routine clinical setting. In this study, we sought to explore whether CIN status can be predicted using ubiquitously available hematoxylin and eosin histology through a deep learning-based model. When applied to a cohort of 1,010 patients with breast cancer (Training set: n = 858, Test set: n = 152) from The Cancer Genome Atlas where 485 patients have high CIN status, our model accurately classified CIN status, achieving an area under the curve of 0.822 with 81.2% sensitivity and 68.7% specificity in the test set. Patch-level predictions of CIN status suggested intra-tumor heterogeneity within slides. Moreover, presence of patches with high predicted CIN score within an entire slide was more predictive of clinical outcome than the average CIN score of the slide, thus underscoring the clinical importance of intra-tumor heterogeneity.

| S-EPMC8099498 | biostudies-literature

Temporal latitudinal-gradient dynamics and tropical instability of deep-sea species diversity.

Project description:A benthic microfaunal record from the equatorial Atlantic Ocean over the past four glacial-interglacial cycles was investigated to understand temporal dynamics of deep-sea latitudinal species diversity gradients (LSDGs). The results demonstrate unexpected instability and high amplitude fluctuations of species diversity in the tropical deep ocean that are correlated with orbital-scale oscillations in global climate: Species diversity is low during glacial and high during interglacial periods. This implies that climate severely influences deep-sea diversity, even at tropical latitudes, and that deep-sea LSDGs, while generally present for the last 36 million years, were weakened or absent during glacial periods. Temporally dynamic LSDGs and unstable tropical diversity require reconsideration of current ecological hypotheses about the generation and maintenance of biodiversity as they apply to the deep sea, and underscore the potential vulnerability and conservation importance of tropical deep-sea ecosystems.

| S-EPMC2799869 | biostudies-literature

Whale counting in satellite and aerial images with deep learning.

Project description:Despite their interest and threat status, the number of whales in world's oceans remains highly uncertain. Whales detection is normally carried out from costly sighting surveys, acoustic surveys or through high-resolution images. Since deep convolutional neural networks (CNNs) are achieving great performance in several computer vision tasks, here we propose a robust and generalizable CNN-based system for automatically detecting and counting whales in satellite and aerial images based on open data and tools. In particular, we designed a two-step whale counting approach, where the first CNN finds the input images with whale presence, and the second CNN locates and counts each whale in those images. A test of the system on Google Earth images in ten global whale-watching hotspots achieved a performance (F1-measure) of 81% in detecting and 94% in counting whales. Combining these two steps increased accuracy by 36% compared to a baseline detection model alone. Applying this cost-effective method worldwide could contribute to the assessment of whale populations to guide conservation actions. Free and global access to high-resolution imagery for conservation purposes would boost this process.

| S-EPMC6776647 | biostudies-literature

Effective generation mechanisms of tropical instability waves as represented by high-resolution coupled atmosphere-ocean prediction experiments.

Project description:Cusp-shaped fluctuations of the sea surface temperature (SST) front in the tropical Pacific, now known as tropical instability waves (TIWs), were discovered by remote sensing in the 1970s. Their discovery was followed by both theoretical and analytical studies, which, along with in situ observations, identified several possible generation mechanisms. Although modeling studies have shown that TIWs strongly influence the heat budget, their influence on local variations of realistically initialized predictions is not yet understood. We here evaluate a series of medium-range (up to ~ 10 days) coupled atmosphere-ocean predictions by a coupled model with different horizontal resolutions. Observational SST, surface wind stress, heat flux, and pressure data showed that representation of temporally and spatially local variations was improved by resolving fine-scale SST variations around the initialized coarse-scale SST front fluctuations of TIWs. Our study thus demonstrates the advantage of using high-resolution coupled models for medium-range predictions. In addition, analysis of TIW energetics showed two dominant sources of energy to anticyclonic eddies: barotropic instability between equatorial zonal currents and baroclinic instability due to intense density fronts. In turn, the eddy circulation strengthened both instabilities in the resolved simulations. This revealed feedback process refines our understanding of the generation mechanisms of TIWs.

| S-EPMC10485077 | biostudies-literature

Purely elastic turbulence in pressure-driven channel flows.

Project description:Solutions of long, flexible polymer molecules are complex fluids that simultaneously exhibit fluid-like and solid-like behavior. When subjected to an external flow, dilute polymer solutions exhibit elastic turbulence-a unique, chaotic flow state absent in Newtonian fluids, like water. Unlike its Newtonian counterpart, elastic turbulence is caused by polymer molecules stretching and aligning in the flow, and can occur at vanishing inertia. While experimental realizations of elastic turbulence are well-documented, there is currently no understanding of its mechanism. Here, we present large-scale direct numerical simulations of elastic turbulence in pressure-driven flows through straight channels. We demonstrate that the transition to elastic turbulence is sub-critical, giving rise to spot-like flow structures that, further away from the transition, eventually spread throughout the domain. We provide evidence that elastic turbulence is organized around unstable coherent states that are localized close to the channel midplane.

| S-EPMC10907231 | biostudies-literature

Forecast of Dengue Cases in 20 Chinese Cities Based on the Deep Learning Method.

Project description:Dengue fever (DF) is one of the most rapidly spreading diseases in the world, and accurate forecasts of dengue in a timely manner might help local government implement effective control measures. To obtain the accurate forecasting of DF cases, it is crucial to model the long-term dependency in time series data, which is difficult for a typical machine learning method. This study aimed to develop a timely accurate forecasting model of dengue based on long short-term memory (LSTM) recurrent neural networks while only considering monthly dengue cases and climate factors. The performance of LSTM models was compared with the other previously published models when predicting DF cases one month into the future. Our results showed that the LSTM model reduced the average the root mean squared error (RMSE) of the predictions by 12.99% to 24.91% and reduced the average RMSE of the predictions in the outbreak period by 15.09% to 26.82% as compared with other candidate models. The LSTM model achieved superior performance in predicting dengue cases as compared with other previously published forecasting models. Moreover, transfer learning (TL) can improve the generalization ability of the model in areas with fewer dengue incidences. The findings provide a more precise forecasting dengue model and could be used for other dengue-like infectious diseases.

| S-EPMC7014037 | 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