DeepExtremeCubes: Earth system spatio-temporal data for assessing compound heatwave and drought impacts

Optimisation and interpretation of machine and deep learning models for improved water quality management in Lake Loktak

Indoor environmental quality is crucial for human health and comfort, necessitating precise and efficient computational methods to optimise indoor climate parameters. Recent advancements in machine learning (ML) and computational fluid dynamics (CFD) are promising. However, applying ML to complex building airflow presents challenges. This research aims to investigate the integration of ML with CFD in the context of built environment applications using a systematic review approach. It highlights a critical knowledge gap: the need to synthesise innovative approaches that address the limitations of indoor modelling using data-driven ML methods. The review examines contemporary literature, identifying current developments and suggesting potential future directions. It delves into the innovations in combining ML with CFD to predict thermal comfort and indoor air quality, uncovering key limitations such as the lack of high-quality experimental data for training and validation, the computational complexity of detailed CFD simulations, and the interpretability issues of ‘black-box’ ML models. The emergence of data-driven techniques in fluid mechanics offers promising prospects for modelling in the built environment. Future research should focus on incorporating physics-based rules in ML models, adapting turbulence closure models for indoor flows, and enhancing model validation using real-world datasets. The research emphasises the synergistic relationship between ML and CFD; it proposes pathways to overcome current limitations, aiming to enhance the precision and efficiency of indoor environment modelling through their integration.

BackgroundHeart failure (HF) impacts nearly 6 million individuals in the U.S., with a projected 46% increase by 2030, is creating significant healthcare burdens. Predictive models, particularly machine learning (ML)-based models, offer promising solutions to identify patients at greater risk of adverse outcomes, such as mortality and hospital readmission. This review aims to assess the effectiveness of ML models in predicting HF-related outcomes, with a focus on their potential to improve patient care and clinical decision-making. We aim to assess how effectively machine learning models predict mortality and readmission in heart failure patients to improve clinical outcomes.MethodThe study followed PRISMA 2020 guidelines and was registered in the PROSPERO database (CRD42023481167). We conducted a systematic search in PubMed, Scopus, and Web of Science databases using specific keywords related to heart failure, machine learning, mortality and readmission. Extracted data focused on study characteristics, machine learning details, and outcomes, with AUC or c-index used as the primary outcomes for pooling analysis. The PROBAST tool was used to assess bias risk, evaluating models based on participants, predictors, outcomes, and statistical analysis. The meta-analysis pooled AUCs for different machine learning models predicting mortality and readmission. Prediction accuracy data was categorized by timeframes, with high heterogeneity determined by an I² value above 50%, leading to a random-effects model when applicable. Publication bias was assessed using Egger’s and Begg’s tests, with a p-value below 0.05 considered significantResultA total of 4,505 studies were identified, and after screening, 64 were included in the final analysis, covering 943,941 patients. Of these, 40 studies focused on mortality, 17 on readmission, and 7 on both outcomes. In total, 346 machine learning models were evaluated, with the most common algorithms being random forest, logistic regression, and gradient boosting. The neural network model achieved the highest overall AUC for mortality prediction (0.808), while the support vector machine performed best for readmission prediction (AUC 0.733). The analysis revealed a significant risk of bias, primarily due to reliance on retrospective data and inadequate sample size justification.ConclusionIn conclusion, this review emphasizes the strong potential of ML models in predicting HF readmission and mortality. ML algorithms show promise in improving prognostic accuracy and enabling personalized patient care. However, challenges like model interpretability, generalizability, and clinical integration persist. Overcoming these requires refined ML techniques and a robust regulatory framework to enhance HF outcomes.

The increased frequency of climate extremes in recent years has profoundly affected terrestrial ecosystem functions and the welfare of human society. The carbon cycle is a key process of terrestrial ecosystem changes. Therefore, a better understanding and assessment of the impacts of climate extremes on the terrestrial carbon cycle could provide an important scientific basis to facilitate the mitigation and adaption of our society to climate change. In this paper, we systematically review the impacts of climate extremes (e.g. drought, extreme precipitation, extreme hot and extreme cold) on terrestrial ecosystems and their mechanisms. Existing studies have suggested that drought is one of the most important stressors on the terrestrial carbon sink, and that it can inhibit both ecosystem productivity and respiration. Because ecosystem productivity is usually more sensitive to drought than respiration, drought can significantly reduce the strength of terrestrial ecosystem carbon sinks and even turn them into carbon sources. Large inter-model variations have been found in the simulations of drought-induced changes in the carbon cycle, suggesting the existence of a large gap in current understanding of the mechanisms behind the responses of ecosystem carbon balance to drought, especially for tropical vegetation. The effects of extreme precipitation on the carbon cycle vary across different regions. In general, extreme precipitation enhances carbon accumulation in arid ecosystems, but restrains carbon sequestration in moist ecosystems. However, current knowledge on the indirect effects of extreme precipitation on the carbon cycle through regulating processes such as soil carbon lateral transportation and nutrient loss is still limited. This knowledge gap has caused large uncertainties in assessing the total carbon cycle impact of extreme precipitation. Extreme hot and extreme cold can affect the terrestrial carbon cycle through various ecosystem processes. Note that the severity of such climate extremes depends greatly on their timing, which needs to be investigated thoroughly in future studies. In light of current knowledge and gaps in the understanding of how extreme climates affect the terrestrial carbon cycle, we strongly recommend that future studies should place more attention on the long-term impacts and on the driving mechanisms at different time scales. Studies based on multi-source data, methods and across multiple spatial-temporal scales, are also necessary to better characterize the response of terrestrial ecosystems to climate extremes.

Background This study aimed to establish and validate a machine learning (ML) model for predicting in-hospital mortality in critically ill patients with chronic kidney disease (CKD). Methods This study collected data on CKD patients from 2008 to 2019 using the Medical Information Mart for Intensive Care IV. Six ML approaches were used to build the model. Accuracy and area under the curve (AUC) were used to choose the best model. In addition, the best model was interpreted using SHapley Additive exPlanations (SHAP) values. Results There were 8527 CKD patients eligible for participation; the median age was 75.1 (interquartile range: 65.0–83.5) years, and 61.7% (5259/8527) were male. We developed six ML models with clinical variables as input factors. Among the six models developed, the eXtreme Gradient Boosting (XGBoost) model had the highest AUC, at 0.860. According to the SHAP values, the sequential organ failure assessment score, urine output, respiratory rate, and simplified acute physiology score II were the four most influential variables in the XGBoost model. Conclusions In conclusion, we successfully developed and validated ML models for predicting mortality in critically ill patients with CKD. Among all ML models, the XGBoost model is the most effective ML model that can help clinicians accurately manage and implement early interventions, which may reduce mortality in critically ill CKD patients with a high risk of death.

The application of Machine Learning (ML) in Electronic Design Automation (EDA) for Very Large-Scale Integration (VLSI) design has garnered significant research attention. Despite the requirement for extensive datasets to build effective ML models, most studies are limited to smaller, internally generated datasets due to the lack of comprehensive public resources. In response, we introduce EDALearn, the first holistic, open-source benchmark suite specifically for ML tasks in EDA. This benchmark suite presents an end-to-end flow from synthesis to physical implementation, enriching data collection across various stages. It fosters reproducibility and promotes research into ML transferability across different technology nodes. Accommodating a wide range of VLSI design instances and sizes, our benchmark aptly represents the complexity of contemporary VLSI designs. Additionally, we provide an in-depth data analysis, enabling users to fully comprehend the attributes and distribution of our data, which is essential for creating efficient ML models. Our contributions aim to encourage further advances in the ML-EDA domain.

This study evaluates and predicts six water quality indices such as sodium adsorption ratio (SAR), Kelly's ratio (KR), percentage sodium (%Na), permeability index (PI), exchangeable sodium percentage (ESP), and irrigation water quality index (IWQI) using multivariate regression models (MLR, PLSR, PCR, and WLSR) and machine learning (ML) algorithms (ANN, SVM, CART, CRRF, and KNN). The study analyzes data from 360 dug wells in Sundargarh district, India, during 2014–2021 with 70% used for training and 30% for testing. Spatial mapping of SAR, KR, ESP, and PI exhibits higher suitability of groundwater. The Mann–Kendall test of trend analysis shows a monotonic increasing and decreasing trend for SAR, KR, %Na, ESP, PI, and IWQI, respectively, at p > 0.05 during 2014–2021. Principal component analysis and discriminant analysis identify Na+, SAR, KR, %Na, and PI as the most influential WQ variables affecting the groundwater quality for this study area. MLR and WLSR models are superior in predicting SAR and ESP, while ANN is the best-suited ML model for SAR, KR, %Na, PI, and ESP. CRRF predicts IWQI with a relatively higher accuracy. These findings demonstrate the effectiveness of ML models in improving irrigation water quality assessment, providing valuable insights for groundwater-based crop management.

The role of higher moments in predicting China's oil futures volatility: Evidence from machine learning models

BackgroundCervical spondylotic myelopathy (CSM) is a prevalent degenerative condition resulting from spinal cord compression and injury. Laminectomy with posterior spinal fusion (LPSF) is a commonly employed treatment approach for CSM patients. This study aimed to assess the effectiveness of machine learning models (MLMs) in predicting clinical outcomes in CSM patients undergoing LPSF.MethodsA retrospective analysis was conducted on 329 CSM patients who underwent LPSF at our institution from Jul 2017 to Jul 2023. Neurological outcomes were evaluated using the modified Japanese Orthopaedic Association (mJOA) scale preoperatively and at the final follow-up. Patients were categorized into two groups based on clinical outcomes: the favorable group (recovery rates ≥ 52.8%) and the unfavorable group (recovery rates < 52.8%). Potential predictors for poor clinical outcomes were compared between the groups. Four MLMs—random forest (RF), logistic regression (LR), support vector machine (SVM), and k-nearest neighborhood (k-NN)—were utilized to predict clinical outcome. RF model was also employed to identify factors associated with poor clinical outcome.ResultsOut of the 329 patients, 185 were male (56.2%) and 144 were female (43.4%), with an average follow-up period of 17.86 ± 1.74 months. Among them, 267 patients (81.2%) had favorable clinical outcomes, while 62 patients (18.8%) did not achieve favorable results. Analysis using binary logistic regression indicated that age, preoperative mJOA scale, and symptom duration (p < 0.05) were independent predictors of unfavorable clinical outcomes. All models performed satisfactorily, with RF achieving the highest accuracy of 0.922. RF also displayed superior sensitivity and specificity (sensitivity = 0.851, specificity = 0.944). The Area under the Curve (AUC) values for RF, Logistic LR, SVM, and k-NN were 0.905, 0.827, 0.851, and 0.883, respectively. The RF model identified preoperative mJOA scale, age, symptom duration, and MRI signal changes as the most significant variables associated with poor clinical outcomes in descending order.ConclusionsThis study highlighted the effectiveness of machine learning models in predicting the clinical outcomes of CSM patients undergoing LPSF. These models have the potential to forecast clinical outcomes in this patient population, providing valuable prognostic insights for preoperative counseling and postoperative management.

The burgeoning field of Machine Learning (ML) has revolutionized various aspects of our lives. However, the reliance on vast amounts of data, often containing personal information, raises concerns about individual privacy. Striking a balance between effective ML model training and protecting sensitive data is crucial for responsible development and ethical implementation. This paper explores the challenges and potential solutions for preserving privacy in ML training, focusing on differential privacy (DP). The advantages of implementing DP in ML training include robust protection of individual data, enabling meaningful insights from large datasets while maintaining privacy. This is essential for ethical and responsible data usage in machine learning applications. However, DP in ML training presents challenges including scalability issues and trade-offs between utility and privacy. The paper also covers the mathematical mechanisms of Laplace and Gaussian and their noise addition, followed by a comparative analysis of their efficiency within the dataset.

Software exploitable Hardware Trojan Horses (HTHs) inserted into commercial CPUs allow the attacker to run his/her own software or to gain unauthorized privileges. Recently a novel menace raised: HTHs inserted by CAD tools. A consequence of such scenario is that HTHs must be considered a serious threat not only by academy but also by industry. In this paper we try to answer to the following question: can Machine Learning (ML) help designers of microprocessor softcores implemented onto SRAM-based FPGAs at detecting HTHs introduced by the employed CAD tool during the generation of the bitstream? We present a comparative analysis of the ability of several ML models at detecting the presence of HTHs in the bitstream by exploiting a previously performed characterization of the microprocessor softcore and an associated ML training. An experimental analysis has been carried out targeting the IBEX RISC-V microprocessor running a set of benchmark programs. A detailed comparison of multiple ML models is conducted, showing that many of them achieve accuracy above 98%, and κ values above 0.97. By identifying the most effective ML models and the best features to be employed, this paper lays the foundation for the integration of a ML-based bitstream verification flow.

Artificial Intelligence (AI) tools based on Machine learning (ML) have demonstrated their potential in modeling climate-related phenomena. However, their application to quantifying greenhouse gas emissions in cities remains under-researched. Here, we introduce a ML-based bottom-up framework to predict hourly CO2 emissions from vehicular traffic at fine spatial resolution (30 × 30 m). Using data-driven algorithms, traffic counts, spatio-temporal features, and meteorological data, our model predicted hourly traffic flow, average speed, and CO2 emissions for passenger cars (PC) and heavy-duty trucks (HDT) at the street scale in Berlin. Even with limited traffic information, the model effectively generalized to new road segments. For PC, the Relative Mean Difference (RMD) was +16% on average. For HDT, RMD was 19% for traffic flow and 2.6% for average speed. We modeled seven years of hourly CO2 emissions from 2015 to 2022 and identified major highways as hotspots for PC emissions, with peak values reaching 1.639 kgCO2 m−2 d−1. We also analyzed the impact of COVID-19 lockdown and individual policy stringency on traffic CO2 emissions. During the lockdown period (March 15 to 1 June 2020), weekend emissions dropped substantially by 25% (−18.3 tCO2 day−1), with stay-at-home requirements, workplace closures, and school closures contributing significantly to this reduction. The continuation of these measures resulted in sustained reductions in traffic flow and CO2 emissions throughout 2020 and 2022. These results highlight the effectiveness of ML models in quantifying vehicle traffic CO2 emissions at a high spatial resolution. Our ML-based bottom-up approach offers a useful tool for urban climate research, especially in areas lacking detailed CO2 emissions data.

In today's increasingly interconnected digital world, ensuring the security and reliability of network traffic has become a critical concern. Traditional rule-based and signature-driven approaches to network anomaly detection are often inadequate in identifying novel and evolving cyber threats. Machine learning (ML) techniques provide a powerful solution by learning patterns from historical network traffic data and detecting deviations that may indicate security threats or network malfunctions. This paper explores the application of various machine learning models, such as supervised, unsupervised, and deep learning techniques, for real-time anomaly detection in network traffic. Key challenges, including data preprocessing, feature selection, and the handling of class imbalance, are addressed. Through a comparative analysis of algorithms such as Decision Trees, Support Vector Machines (SVMs), and Neural Networks, we demonstrate the effectiveness of machine learning models in identifying both known and unknown network anomalies. The results highlight the potential of hybrid models and ensemble techniques to improve detection accuracy and reduce false positives. This study underscores the importance of leveraging advanced machine learning techniques to strengthen network security frameworks and maintain the integrity of digital communications.

This research suggests using machine learning to predict air quality in smart cities.By analysing past data and using advanced algorithms, the model forecasts future air quality levels.Real-time sensor data is incorporated, making predictions more accurate and enabling prompt actions to reduce pollution.The study indicates that implementing this predictive system can proactively manage the environment in cities, fostering healthier living conditions and supporting sustainable urban development.Smart cities are rapidly adopting technologies to improve the quality of life for their residents, with a focus on addressing environmental challenges like air pollution.Machine learning algorithms have emerged as powerful tools for predicting air quality parameters, such as particulate matter (PM), sulfur dioxide (SO2), nitrogen dioxide (NO2), carbon monoxide (CO), and ozone (O3).This paper presents a literature survey on the application of machine learning, specifically the random forest algorithm, in predicting air quality in smart cities.The study reviews various methodologies, data sources, feature selection techniques, and evaluation metrics used in existing research.The results and discussions highlight the effectiveness of machine learning models in accurately forecasting air quality levels, aiding in decision-making processes for pollution control and public health management in smart cities.

This study investigates the effectiveness of machine learning models in estimating ground-level PM2.5 concentrations using satellite-derived aerosol optical depth (AOD) in Kampala, a city with limited ground monitoring. Multivariate Linear Regression, Random Forest, and Multi-Layer Perceptron are compared using data from reference-grade and low-cost monitors. The study uses MODIS MAIAC AOD and PM2.5 measurements from January 2022 to December 2023 from two collocation sites. The results indicate that Random Forest consistently outperforms other methods, demonstrating strong performance despite limited data; achieving the lowest RMSE: (7.72 $$\upmu \hbox{g}/\hbox{m}^3$$ μ g / m 3 ) and MAE: (5.5 $$\upmu \hbox{g}/\hbox{m}^3$$ μ g / m 3 ), R2 of (0.72) and correlation of 0.85. Models trained on combined datasets from multiple devices and sites generally yielded better results than those trained on individual devices’ data, suggesting the benefits of data integration for robust PM2.5 estimation. Uniquely, the study demonstrates the viability of using low-cost sensor data as ground-truth for PM2.5 estimation, with a model trained on low-cost sensor data achieving a RMSE: 10.9 $$\upmu \hbox{g}/\hbox{m}^3$$ μ g / m 3 , MAE: 8.6 $$\upmu \hbox{g}/\hbox{m}^3$$ μ g / m 3 , R2: 0.59 and Correlation: 0.78, when validated against collocated reference-grade monitors. The results show promise for using low-cost sensor data as ground truth in PM2.5 estimation from satellite AOD, though further refinements are needed. This study contributes to the growing body of research on satellite-based air quality monitoring, particularly in cities in low- and middle-income countries where ground monitoring is limited. The results highlight the potential of using satellite data, machine learning techniques and low-cost sensors to improve PM2.5 monitoring in under-resourced regions.