Explore the vast range of titles available.

Human activities and climate change have exacerbated the frequency of extreme weather events such as rainstorms and floods, which makes it difficult to accurately quantify the uncertainty characteristics in runoff prediction. Therefore, the lower and upper boundary estimation method (LUBE) has become an important means to quantify uncertainty and has been widely used. However, the traditional interval prediction evaluation system only relies on coverage and width indicators, and performs poorly in single-objective optimization methods, which limits the large-scale application of the LUBE method. Based on this, this study innovatively proposes the prediction interval fitting coefficient (PIFC), and combines the prediction interval coverage probability (PICP) and normalized average width index (PINAW) to construct the coverage width fitting-based criterion (CWFC) for the first time, which broadens and improves the interval prediction evaluation dimension system. Further, the single-objective and multi-objective LUBE interval forecasting models based on the randomized weighted particle swarm algorithm (RWPSO) and the non-dominated sorting genetic algorithms III (NSGA-III) are constructed in this study. The verification results of cascade hydropower stations in the Yalong river basin show that the calculation efficiency and prediction effect of the single target interval prediction model are both improved after the introduction of PIFC. Under the CWFC objective function, the PINAW and PIFC indexes in the prediction interval are significantly better, and the PICP gap is smaller. Under multi-objective conditions (PICP, PINAW and PIFC), the Pareto non-inferior solution set can provide more choices for decision makers. During the flood season, PICP can reach more than 93%, PINAW is controlled below 10%, and PIFC can reach more than 0.95. This fully proves that the performance of interval prediction has been significantly improved after the introduction of PIFC, and the research results can provide a new way for basin interval prediction.

Accurate computational identification of B-cell epitopes is crucial for the development of vaccines, therapies, and diagnostic tools. However, current structure-based prediction methods face limitations due to the dependency on experimentally solved structures. Here, we introduce DiscoTope-3.0, a markedly improved B-cell epitope prediction tool that innovatively employs inverse folding structure representations and a positive-unlabelled learning strategy, and is adapted for both solved and predicted structures. Our tool demonstrates a considerable improvement in performance over existing methods, accurately predicting linear and conformational epitopes across multiple independent datasets. Most notably, DiscoTope-3.0 maintains high predictive performance across solved, relaxed and predicted structures, alleviating the need for experimental structures and extending the general applicability of accurate B-cell epitope prediction by 3 orders of magnitude. DiscoTope-3.0 is made widely accessible on two web servers, processing over 100 structures per submission, and as a downloadable package. In addition, the servers interface with RCSB and AlphaFoldDB, facilitating large-scale prediction across over 200 million cataloged proteins. DiscoTope-3.0 is available at: https://services.healthtech.dtu.dk/service.php?DiscoTope-3.0 .

Natural disasters have frequently occurred and caused great harm. Although the remote sensing technology can effectively provide disaster data, it still needs to consider the relevant information from multiple aspects for disaster analysis. It is hard to build an analysis model that can integrate the remote sensing and the large-scale relevant information, particularly at the sematic level. This paper proposes a disaster prediction knowledge graph for disaster prediction by integrating remote sensing information, relevant geographic information, with the expert knowledge in the field of disaster analysis. This paper constructs the conceptual layer and instance layer of the knowledge graph by building a common semantic ontology of disasters and a unified spatio-temporal framework benchmark. Moreover, this paper represents the disaster prediction model in the forms of knowledge of disaster prediction. This paper demonstrates experiments and cases studies regarding the forest fire and geological landslide risk. These investigations show that the proposed method is beneficial to multi-source spatio-temporal information integration and disaster prediction.

As a cutting-edge field of artificial intelligence in education (AIEd) that depends on advanced computing technologies, AI performance prediction model is widely used to identify at-risk students that tend to fail, establish student-centered learning pathways, and optimize instructional design and development. A majority of the existing AI prediction models focus on the development and optimization of the accuracy of AI algorithms rather than applying AI models to provide student with in-time and continuous feedback and improve the students’ learning quality. To fill this gap, this research integrated an AI performance prediction model with learning analytics approaches with a goal to improve student learning effects in a collaborative learning context. Quasi-experimental research was conducted in an online engineering course to examine the differences of students’ collaborative learning effect with and without the support of the integrated approach. Results showed that the integrated approach increased student engagement, improved collaborative learning performances, and strengthen student satisfactions about learning. This research made contributions to proposing an integrated approach of AI models and learning analytics (LA) feedback and providing paradigmatic implications for future development of AI-driven learning analytics.HighlightsIntegrated approach was used to combine AI with learning analytics (LA) feedbackQuasi-experiment research was conducted to investigate student learning effectsIntegrated approach to foster student engagement, performances and satisfactionsParadigmatic implication was proposed for develop AI-driven learning analyticsClosed loop was established for both AI model development and educational application.

PurposeRisk classification of primary prostate cancer in clinical routine is mainly based on prostate-specific antigen (PSA) levels, Gleason scores from biopsy samples, and tumor-nodes-metastasis (TNM) staging. This study aimed to investigate the diagnostic performance of positron emission tomography/magnetic resonance imaging (PET/MRI) in vivo models for predicting low-vs-high lesion risk (LH) as well as biochemical recurrence (BCR) and overall patient risk (OPR) with machine learning.MethodsFifty-two patients who underwent multi-parametric dual-tracer [18F]FMC and [68Ga]Ga-PSMA-11 PET/MRI as well as radical prostatectomy between 2014 and 2015 were included as part of a single-center pilot to a randomized prospective trial (NCT02659527). Radiomics in combination with ensemble machine learning was applied including the [68Ga]Ga-PSMA-11 PET, the apparent diffusion coefficient, and the transverse relaxation time-weighted MRI scans of each patient to establish a low-vs-high risk lesion prediction model (MLH). Furthermore, MBCR and MOPR predictive model schemes were built by combining MLH, PSA, and clinical stage values of patients. Performance evaluation of the established models was performed with 1000-fold Monte Carlo (MC) cross-validation. Results were additionally compared to conventional [68Ga]Ga-PSMA-11 standardized uptake value (SUV) analyses.ResultsThe area under the receiver operator characteristic curve (AUC) of the MLH model (0.86) was higher than the AUC of the [68Ga]Ga-PSMA-11 SUVmax analysis (0.80). MC cross-validation revealed 89% and 91% accuracies with 0.90 and 0.94 AUCs for the MBCR and MOPR models respectively, while standard routine analysis based on PSA, biopsy Gleason score, and TNM staging resulted in 69% and 70% accuracies to predict BCR and OPR respectively.ConclusionOur results demonstrate the potential to enhance risk classification in primary prostate cancer patients built on PET/MRI radiomics and machine learning without biopsy sampling.

We study distribution‐free, non‐parametric prediction bands with a focus on their finite sample behaviour. First we investigate and develop different notions of finite sample coverage guarantees. Then we give a new prediction band by combining the idea of ‘conformal prediction’ with non‐parametric conditional density estimation. The proposed estimator, called COPS (conformal optimized prediction set), always has a finite sample guarantee. Under regularity conditions the estimator converges to an oracle band at a minimax optimal rate. A fast approximation algorithm and a data‐driven method for selecting the bandwidth are developed. The method is illustrated in simulated and real data examples.

The prediction of interresidue contacts and distances from coevolutionary data using deep learning has considerably advanced protein structure prediction. Here, we build on these advances by developing a deep residual network for predicting interresidue orientations, in addition to distances, and a Rosetta-constrained energy-minimization protocol for rapidly and accurately generating structure models guided by these restraints. In benchmark tests on 13th Community-Wide Experiment on the Critical Assessment of Techniques for Protein Structure Prediction (CASP13)- and Continuous Automated Model Evaluation (CAMEO)-derived sets, the method outperforms all previously described structure-prediction methods. Although trained entirely on native proteins, the network consistently assigns higher probability to de novo-designed proteins, identifying the key fold-determining residues and providing an independent quantitative measure of the “ideality” of a protein structure. The method promises to be useful for a broad range of protein structure prediction and design problems.

Quantifying signals and uncertainties in climate models is essential for the detection, attribution, prediction and projection of climate change 1 – 3 . Although inter-model agreement is high for large-scale temperature signals, dynamical changes in atmospheric circulation are very uncertain 4 . This leads to low confidence in regional projections, especially for precipitation, over the coming decades 5 , 6 . The chaotic nature of the climate system 7 – 9 may also mean that signal uncertainties are largely irreducible. However, climate projections are difficult to verify until further observations become available. Here we assess retrospective climate model predictions of the past six decades and show that decadal variations in North Atlantic winter climate are highly predictable, despite a lack of agreement between individual model simulations and the poor predictive ability of raw model outputs. Crucially, current models underestimate the predictable signal (the predictable fraction of the total variability) of the North Atlantic Oscillation (the leading mode of variability in North Atlantic atmospheric circulation) by an order of magnitude. Consequently, compared to perfect models, 100 times as many ensemble members are needed in current models to extract this signal, and its effects on the climate are underestimated relative to other factors. To address these limitations, we implement a two-stage post-processing technique. We first adjust the variance of the ensemble-mean North Atlantic Oscillation forecast to match the observed variance of the predictable signal. We then select and use only the ensemble members with a North Atlantic Oscillation sufficiently close to the variance-adjusted ensemble-mean forecast North Atlantic Oscillation. This approach greatly improves decadal predictions of winter climate for Europe and eastern North America. Predictions of Atlantic multidecadal variability are also improved, suggesting that the North Atlantic Oscillation is not driven solely by Atlantic multidecadal variability. Our results highlight the need to understand why the signal-to-noise ratio is too small in current climate models 10 , and the extent to which correcting this model error would reduce uncertainties in regional climate change projections on timescales beyond a decade. Current models are too noisy to predict climate usefully on decadal timescales, but two-stage post-processing of model outputs greatly improves predictions of decadal variations in North Atlantic winter climate.

Purpose of Review Recent Atlantic climate prediction studies are an exciting new contribution to an extensive body of research on Atlantic decadal variability and predictability that has long emphasized the unique role of the Atlantic Ocean in modulating the surface climate. We present a survey of the foundations and frontiers in our understanding of Atlantic variability mechanisms, the role of the Atlantic Meridional Overturning Circulation (AMOC), and our present capacity for putting that understanding into practice in actual climate prediction systems. Recent Findings The AMOC—or more precisely, the buoyancy-forced thermohaline circulation (THC) that encompasses both overturning and gyre circulations—appears to underpin decadal timescale prediction skill in the subpolar North Atlantic in retrospective forecasts. Skill in predicting more wide-ranging climate variations, including those over land, is more limited, but there are indications this could improve with more advanced models. Summary Preliminary successes in the field of initialized Atlantic climate prediction confirm the climate relevance of low-frequency Atlantic Ocean dynamics and suggest that useful decadal climate prediction is a realizable goal.