Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Deep learning for bias correction of MJO prediction.

ABSTRACT: Producing accurate weather prediction beyond two weeks is an urgent challenge due to its ever-increasing socioeconomic value. The Madden-Julian Oscillation (MJO), a planetary-scale tropical convective system, serves as a primary source of global subseasonal (i.e., targeting three to four weeks) predictability. During the past decades, operational forecasting systems have improved substantially, while the MJO prediction skill has not yet reached its potential predictability, partly due to the systematic errors caused by imperfect numerical models. Here, to improve the MJO prediction skill, we blend the state-of-the-art dynamical forecasts and observations with a Deep Learning bias correction method. With Deep Learning bias correction, multi-model forecast errors in MJO amplitude and phase averaged over four weeks are significantly reduced by about 90% and 77%, respectively. Most models show the greatest improvement for MJO events starting from the Indian Ocean and crossing the Maritime Continent.

SUBMITTER: Kim H

PROVIDER: S-EPMC8149422 | biostudies-literature | 2021 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

Deep learning for bias correction of MJO prediction.

Kim H H Ham Y G YG Joo Y S YS Son S W SW

Nature communications 20210525 1

Producing accurate weather prediction beyond two weeks is an urgent challenge due to its ever-increasing socioeconomic value. The Madden-Julian Oscillation (MJO), a planetary-scale tropical convective system, serves as a primary source of global subseasonal (i.e., targeting three to four weeks) predictability. During the past decades, operational forecasting systems have improved substantially, while the MJO prediction skill has not yet reached its potential predictability, partly due to the sys ...[more]

PMID: 34035294

Similar Datasets

Fairness and bias correction in machine learning for depression prediction across four study populations.

Project description:A significant level of stigma and inequality exists in mental healthcare, especially in under-served populations. Inequalities are reflected in the data collected for scientific purposes. When not properly accounted for, machine learning (ML) models learned from data can reinforce these structural inequalities or biases. Here, we present a systematic study of bias in ML models designed to predict depression in four different case studies covering different countries and populations. We find that standard ML approaches regularly present biased behaviors. We also show that mitigation techniques, both standard and our own post-hoc method, can be effective in reducing the level of unfair bias. There is no one best ML model for depression prediction that provides equality of outcomes. This emphasizes the importance of analyzing fairness during model selection and transparent reporting about the impact of debiasing interventions. Finally, we also identify positive habits and open challenges that practitioners could follow to enhance fairness in their models.

| S-EPMC10991528 | biostudies-literature

Explainable Deep Learning for Glaucomatous Visual Field Prediction: Artifact Correction Enhances Transformer Models.

Project description:PurposeThe purpose of this study was to develop a deep learning approach that restores artifact-laden optical coherence tomography (OCT) scans and predicts functional loss on the 24-2 Humphrey Visual Field (HVF) test.MethodsThis cross-sectional, retrospective study used 1674 visual field (VF)-OCT pairs from 951 eyes for training and 429 pairs from 345 eyes for testing. Peripapillary retinal nerve fiber layer (RNFL) thickness map artifacts were corrected using a generative diffusion model. Three convolutional neural networks and 2 transformer-based models were trained on original and artifact-corrected datasets to estimate 54 sensitivity thresholds of the 24-2 HVF test.ResultsPredictive performances were calculated using root mean square error (RMSE) and mean absolute error (MAE), with explainability evaluated through GradCAM, attention maps, and dimensionality reduction techniques. The Distillation with No Labels (DINO) Vision Transformers (ViT) trained on artifact-corrected datasets achieved the highest accuracy (RMSE, 95% confidence interval [CI] = 4.44, 95% CI = 4.07, 4.82 decibel [dB], MAE = 3.46, 95% CI = 3.14, 3.79 dB), and the greatest interpretability, showing improvements of 0.15 dB in global RMSE and MAE (P < 0.05) compared to the performance on original maps. Feature maps and visualization tools indicate that artifacts compromise DINO-ViT's predictive ability but improve with artifact correction.ConclusionsCombining self-supervised ViTs with generative artifact correction enhances the correlation between glaucomatous structures and functions.Translational relevanceOur approach offers a comprehensive tool for glaucoma management, facilitates the exploration of structure-function correlations in research, and underscores the importance of addressing artifacts in the clinical interpretation of OCT.

| S-EPMC11758932 | biostudies-literature

Age-level bias correction in brain age prediction.

Project description:The predicted age difference (PAD) between an individual's predicted brain age and chronological age has been commonly viewed as a meaningful phenotype relating to aging and brain diseases. However, the systematic bias appears in the PAD achieved using machine learning methods. Recent studies have designed diverse bias correction methods to eliminate it for further downstream studies. Strikingly, here we demonstrate that bias still exists in the PAD of samples with the same age even after kind of correction. Therefore, current PAD may not be taken as a reliable phenotype and more investigations are needed to solve this fundamental defect. To this end, we propose an age-level bias correction method and demonstrate its efficacy in numerical experiments.

| S-EPMC9860514 | biostudies-literature

Deep Representation Learning Improves Prediction of LacI-mediated Transcriptional Repression

Project description:We analyze LacI mutations with the goal to understand and better predict basal transcriptional repression function after mutation. This study utilized lac repressor variants from the Taylor, et al. 2015 Nature Methods study including ten tiles of synthesized single mutations (NCBI GEO Series GSE75009), and an additional six tiles corresponding to higher-order mutations (this study).

2021-06-22 | GSE175456 | GEO

A Deep Learning based Efficacy Prediction System for Drug Discovery

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

2023-03-31 | GSE165175 | GEO

A deep learning approach for 18F-FDG PET attenuation correction.

Project description:BACKGROUND:To develop and evaluate the feasibility of a data-driven deep learning approach (deepAC) for positron-emission tomography (PET) image attenuation correction without anatomical imaging. A PET attenuation correction pipeline was developed utilizing deep learning to generate continuously valued pseudo-computed tomography (CT) images from uncorrected 18F-fluorodeoxyglucose (18F-FDG) PET images. A deep convolutional encoder-decoder network was trained to identify tissue contrast in volumetric uncorrected PET images co-registered to CT data. A set of 100 retrospective 3D FDG PET head images was used to train the model. The model was evaluated in another 28 patients by comparing the generated pseudo-CT to the acquired CT using Dice coefficient and mean absolute error (MAE) and finally by comparing reconstructed PET images using the pseudo-CT and acquired CT for attenuation correction. Paired-sample t tests were used for statistical analysis to compare PET reconstruction error using deepAC with CT-based attenuation correction. RESULTS:deepAC produced pseudo-CTs with Dice coefficients of 0.80?±?0.02 for air, 0.94?±?0.01 for soft tissue, and 0.75?±?0.03 for bone and MAE of 111?±?16 HU relative to the PET/CT dataset. deepAC provides quantitatively accurate 18F-FDG PET results with average errors of less than 1% in most brain regions. CONCLUSIONS:We have developed an automated approach (deepAC) that allows generation of a continuously valued pseudo-CT from a single 18F-FDG non-attenuation-corrected (NAC) PET image and evaluated it in PET/CT brain imaging.

| S-EPMC6230542 | biostudies-other

A Deep Learning based Efficacy Prediction System for Drug Discovery [Trametinib]

Project description:Target protein-based drug and research compound discovery has been undeniably successful strategy in life science research, yet many diseases and biological processes lack obvious targets to enable these approaches. Here, to overcome this major challenge we have developed a deep-learning based efficacy prediction system (DLEPS) to identify potent agents to treat diverse diseases; DLEPS was trained using L1000 project chemical induced “changes of transcriptional profiles” (CTP) data as input. Strikingly, we found that the CTPs for previously unexamined molecules were precisely predicted (0.74 Pearson correlation coefficient). We used DLEPS to examine 4 disorders, and experimentally validated that perillen, chikusetsusaponin IV, trametinib, and liquiritin confer disease-relevant impacts against obesity, hyperuricemia, NASH, and COVID-19, respectively. Importantly, DLEPS also uncovered the biological insight that the MEK-ERK signaling pathway should be understood as a target for developing anti-NASH agents. Beyond illustrating that DLEPS is an effective tool for drug repurposing and development with diverse diseases (including those lacking targets), our study shows how diverse transcriptomics datasets can be harnessed to identify inhibitors and activator chemicals that can expand the scope of biological investigations well beyond mutant-bases analyses.

2023-03-31 | GSE165174 | GEO

A Deep Learning based Efficacy Prediction System for Drug Discovery [Perillen]

2023-03-31 | GSE165173 | GEO

Pathways to Better Prediction of the MJO: 2. Impacts of Atmosphere-Ocean Coupling on the Upper Ocean and MJO Propagation.

Project description:This study investigates effects of atmosphere-ocean coupling on MJO precipitation and eastward propagation, and upper ocean conditions during and after MJO passage. To explore pathways for improving MJO prediction, three model experiments are conducted using the Unified Wave Interface-Coupled Model at convection-permitting (4 km) resolution: (a) uncoupled atmosphere-only, (b) coupled atmosphere-ocean, and (c) coupled atmosphere-ocean with improved air-sea flux algorithm simulations. The model simulations are compared with observations from the DYNAMO field campaign in 2011. Both coupled atmosphere-ocean simulations produced eastward propagation of the MJO where the uncoupled, atmosphere-only simulation did not. The uncoupled model overestimates both precipitation and surface winds associated with the MJO, while coupled model simulations substantially reduce model bias. Improved air-sea fluxes lead to systematic improvements in precipitation, winds, sea surface temperature, and the ocean mixed layer when compared to the original coupled simulation. This leads to further improvement of the MJO's eastward propagation speed compared with observations. Despite these improvements, the regional coupled simulations still have difficulty representing the extent of convectively suppressed conditions in the Indian Ocean after MJO passage, which indicates the importance of the large-scale environment from lateral boundary conditions. Coupled model simulations also reveal some issues in the representation of upper ocean stratification in the ocean model, especially errors in salinity, which result in overestimation of the mixed layer depth after MJO passage.

| S-EPMC9286837 | biostudies-literature

High-throughput deep learning variant effect prediction with Sequence UNET

Project description: Not available

| S-BSST732 | biostudies-other