Data-driven Prediction Model Research Articles

Predictive modeling for cell culture in commercial manufacturing of biotherapeutics.

The biopharmaceutical industry continually seeks advancements in the commercial manufacturing of therapeutic proteins, where mammalian cell culture plays a pivotal role. The current work presents a novel data-driven predictive modeling application designed to enhance the efficiency and predictability of cell culture processes in biotherapeutic production. The capability of the cloud-based digital data science application, developed using open-source tools, is demonstrated with respect to predicting bioreactor potency from at-line process parameters over a 5-day horizon. The uncertainty in model's prediction is quantified, providing valuable insights for process control and decision-making. Model validation on unseen data confirms the model's robust generalizability. An interactive dashboard, tailored to process scientist's requirements is also developed to streamline biopharmaceutical manufacturing processes, ultimately leading to enhanced productivity and product quality.

Predicting the Average Charring Rate of Mass Timber Using Data-Driven Methods for Structural Calculations

Engineered timber is increasingly in demand for tall buildings due to its positive impact on building sustainability. However, quick adoption raises fire engineering questions regarding flammability and structural performance. Understanding the behaviour of timber in fire is crucial, particularly for structural calculations of tall buildings. The charring rate of timber plays a significant role in its structural performance because the loss of cross section reduces the load bearing capacity of the element. Eurocode-5 (EC5) provides a simple method to calculate the charring rate and it is widely adopted for design in many countries while more complex physics-based models exist but are rarely used for design. For example, we want to know when EC5 underpredicts or overpredicts and by how much. This paper compares different data-driven methods, including statistical and artificial intelligence algorithms, for predicting the average charring rate of timber in fire. A new database of charring rates, VAQT, was created comprised of 231 furnace tests of timber products found in the scientific and technical literature. Statistical methods such as ridge regression (λ = 0.001) predict the charring rate with a minimum 11% error whilst EC5 predicts with 27% error. A trained neural network predicts the charring rate with minimum 9% error. This paper presents a novel database of timber charring experiments and provides a set of data-driven predictive models, all of which calculate the average charring rate with a significantly higher accuracy than EC5 for a wide range of mass timber products.

Cross-model Fairness: Empirical Study of Fairness and Ethics Under Model Multiplicity

While data-driven predictive models are a strictly technological construct, they may operate within a social context in which benign engineering choices entail implicit, indirect and unexpected real-life consequences. Fairness of such systems – pertaining both to individuals and groups – is one relevant consideration in this space; algorithms can discriminate people across various protected characteristics regardless of whether these properties are included in the data or discernible through proxy variables. To date, this notion has predominantly been studied for a fixed model, often under different classification thresholds, striving to identify and eradicate undesirable, discriminative and possibly unlawful aspects of its operation. Here, we backtrack on this fixed model assumption to propose and explore a novel definition of cross-model fairness where individuals can be harmed when one predictor is chosen ad hoc from a group of equally well performing models, i.e., in view of utility-based model multiplicity . Since a person may be classified differently across models that are otherwise considered equivalent, this individual could argue for a predictor granting them the most favourable outcome, employing which may have adverse effects on other people. We introduce this scenario with a two-dimensional example and linear classification; then, we present a comprehensive empirical study based on real-life predictive models and data sets that are popular with the algorithmic fairness community; finally, we investigate analytical properties of cross-model fairness and its ramifications in a broader context. Our findings suggest that such unfairness can be readily found in real life and it may be difficult to mitigate by technical means alone as doing so is likely to degrade predictive performance.

High-resolution harvester data for estimating rolling resistance and forest trafficability

Information on terrain conditions is a prerequisite for planning environmentally and economically sustainable forest harvesting operations that avoid negative impact on soils. Current soil data are coarse, and collecting such data with traditional methods is expensive. Forest harvesters can be harnessed to estimate the rolling resistance coefficient (μRR\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\mu _{RR}$$\\end{document}), which is a proxy for forest trafficability. Using spatio-temporal data on engine power used, speed travelled, and machine inclination, μRR\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\mu _{RR}$$\\end{document} can be computed for harvest areas. This study describes an extensive, high-resolution data on μRR\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\mu _{RR}$$\\end{document} collected in a boreal forest landscape in Southern Finland during the non-frost period of 2021, covering roughly 50 km of harvester routes. We report improvements in removing some of the previous restrictions on calculating μRR\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\mu _{RR}$$\\end{document} on steeper slopes, enabling the calculation within a -10∘\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$-10^{\\circ }$$\\end{document} to +10∘\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$+10^{\\circ }$$\\end{document} slope range with a speed range of 0.6–1.2 ms-1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^{-1}$$\\end{document}. We characterise the variation in μRR\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\mu _{RR}$$\\end{document} both between and within 11 test sites harvested during the April-August period. The site mean μRR\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\mu _{RR}$$\\end{document} varies from ∼\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\sim$$\\end{document} 0.14 to 0.19 and shows significant differences between the sites. Using simulations of the hydrological state of the soil and open spatial data on forest and topography, we identify features that best explain the extremes of μRR\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\mu _{RR}$$\\end{document} within the sites. Several wetness-related indices, such as the depth-to-water index with varying thresholds, explain the μRR\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\mu _{RR}$$\\end{document} extremes, while biomass-related stand attributes indirectly explain these through their linkage to site and soil characteristics. Obtaining μRR\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\mu _{RR}$$\\end{document} from actual operational data extends the capabilities of large-scale harvester-based data collection and paves the way for building data-driven models for trafficability prediction.

Predictive modeling of perioperative patient deterioration: combining unanticipated ICU admissions and mortality for improved risk prediction

ObjectiveThis paper presents a comprehensive analysis of perioperative patient deterioration by developing predictive models that evaluate unanticipated ICU admissions and in-hospital mortality both as distinct and combined outcomes.Materials and MethodsWith less than 1% of cases resulting in at least one of these outcomes, we investigated 98 features to identify their role in predicting patient deterioration, using univariate analyses. Additionally, multivariate analyses were performed by employing logistic regression (LR) with LASSO regularization. We also assessed classification models, including non-linear classifiers like Support Vector Machines, Random Forest, and XGBoost.ResultsDuring evaluation, careful attention was paid to the data imbalance therefore multiple evaluation metrics were used, which are less sensitive to imbalance. These metrics included the area under the receiver operating characteristics, precision-recall and kappa curves, and the precision, sensitivity, kappa, and F1-score. Combining unanticipated ICU admissions and mortality into a single outcome improved predictive performance overall. However, this led to reduced accuracy in predicting individual forms of deterioration, with LR showing the best performance for the combined prediction.DiscussionThe study underscores the significance of specific perioperative features in predicting patient deterioration, especially revealed by univariate analysis. Importantly, interpretable models like logistic regression outperformed complex classifiers, suggesting their practicality. Especially, when combined in an ensemble model for predicting multiple forms of deterioration. These findings were mostly limited by the large imbalance in data as post-operative deterioration is a rare occurrence. Future research should therefore focus on capturing more deterioration events and possibly extending validation to multi-center studies.ConclusionsThis work demonstrates the potential for accurate prediction of perioperative patient deterioration, highlighting the importance of several perioperative features and the practicality of interpretable models like logistic regression, and ensemble models for the prediction of several outcome types. In future clinical practice these data-driven prediction models might form the basis for post-operative risk stratification by providing an evidence-based assessment of risk.

Enhancing efficiency in closed agricultural greenhouses: A data-driven predictive model for energy consumption

Abstract Predicting energy consumption in agricultural greenhouses is essential to effectively allocate resources, enhance plant growth, and minimize energy inefficiencies. Various factors affect the energy consumption inside the greenhouse including external climate conditions and internal microclimate. Proper understanding of these factors is crucial for maintaining an ideal growing environment and optimizing energy efficiency. This drives the need to investigate the interaction between these factors and greenhouse energy consumption, encompassing the energy needed for cooling and the supply of water and nutrients. This work aims at developing a dynamic model that predicts the total energy consumption of a closed agricultural greenhouse to improve microclimate control and energy efficiency. The study is conducted within a closed-loop agricultural greenhouse with no natural ventilation. Inside, the air is cooled and continuously circulated without being exchanged with ambient air through a heating, ventilation, and air conditioning (HVAC) system. The data-driven model encompasses external climate parameters such solar radiation, ambient temperature, and relative humidity; along with microclimate parameters such as internal temperature, humidity, and CO2 concentration to predict overall energy consumption. The study examines two machine learning models, deep neural networks (DNN) and extreme gradient boosting (XGBoost), for forecasting energy consumption, and assesses their performance using the coefficient of determination (R2), the root mean square error (RMSE), and the mean absolute error (MAE). Results reveal that the DNN model surpasses the XGBoost model, exhibiting a superior predictive performance with an R2 of 80.9%, RMSE of 171.1 kWh and MAE of 130.3 kWh. This study demonstrates its practicality in assisting with energy consumption analyses and identifying inefficient energy usage patterns within closed agricultural greenhouses.

Minimum-energy virtual machine placement using embedded sensors and machine learning

Cloud data centers (DCs) consume large amounts of energy and contribute significantly to environmental concerns. Furthermore, with the advent of 5G and B5G networks, increasingly software-oriented and becoming highly dependent on cloud computing, it becomes imperative to optimize their energy consumption. Thus, in this study, we present a virtual machine placement algorithm that minimizes the energy consumption of a cluster of server machines. Our solution is embodied through the use of sensors embedded inside physical server machines, enabling the introduction of new features for sensitive thermal awareness and proactive hot spot avoidance. Leveraging this significantly enhanced feature space, we implement data-driven predictive machine learning models along with a heuristic placement algorithm (CPP), enabling proactive VM placements that are both energy-aware and thermal-aware. Indeed, experiments carried out on a cluster of physical server machines demonstrate high performance by both the ML models and the placement algorithm (CPP). Compared with the best baseline algorithm, our solution reduced power consumption and temperature by 7% and 2%, respectively, while avoiding hot spots and maintaining efficient load distribution, thereby reducing the overhead of physical machines by 28%.

Nonlinear Model Predictive Control with Evolutionary Data-Driven Prediction Model and Particle Swarm Optimization Optimizer for an Overhead Crane

This paper presents a new approach to the nonlinear model predictive control (NMPC) of an underactuated overhead crane system developed using a data-driven prediction model obtained utilizing the regularized genetic programming-based symbolic regression method. Grammar-guided genetic programming combined with regularized least squares was applied to identify a nonlinear autoregressive model with an exogenous input (NARX) prediction model of the crane dynamics from input–output data. The resulting prediction model was implemented in the NMPC scheme, using a particle swarm optimization (PSO) algorithm as a solver to find an optimal sequence of the control actions satisfying multi-objective performance requirements and input constraints. The feasibility and performance of the controller were experimentally verified using a laboratory crane actuated by AC motors and compared with a discrete-time feedback controller developed using the pole placement technique. A series of experiments proved the effectiveness of the controller in terms of robustness against operating condition variation and external disturbances.

A novel data-driven reduced-order model for the fast prediction of gas-solid heat transfer in fluidized beds

Computational fluid dynamics − discrete element method (CFD-DEM) emerges as a promising tool to model dense gas–solid two-phase flow in fluidized beds, yet the numerical efficiency is still far from being satisfactory. Accordingly, this work develops a proper orthogonal decomposition (POD) reduced-order model (ROM) based on the CFD-DEM method for the fast prediction of gas–solid flow and heat transfer in a bubbling fluidized bed (BFB). The POD method is employed to decompose particle coordinates and temperature into spatial modes and time evolution coefficients. The radial basis function neural network (RBFNN) and temporal convolutional neural network (TCN) are utilized to predict the time evolution coefficients. Regarding the POD modes, the particle temperature exhibits an obvious monotonic or periodic characteristic compared to the particle coordinates, indicating the potential for long-term prediction. The RBFNN-ROM and TCN-ROM reconstruct the flow field effectively, achieving acceleration ratios of 2000 and 3000, respectively. The ROM developed in this study holds the potential to enable real-time prediction of industrial processes, thus paving the way for the realization of digital twins.

Probabilistic physics-integrated neural differentiable modeling for isothermal chemical vapor infiltration process

Chemical vapor infiltration (CVI) is a widely adopted manufacturing technique used in producing carbon-carbon and carbon-silicon carbide composites. These materials are especially valued in the aerospace and automotive industries for their robust strength and lightweight characteristics. The densification process during CVI critically influences the final performance, quality, and consistency of these composite materials. Experimentally optimizing the CVI processes is challenging due to the long experimental time and large optimization space. To address these challenges, this work takes a modeling-centric approach. Due to the complexities and limited experimental data of the isothermal CVI densification process, we have developed a data-driven predictive model using the physics-integrated neural differentiable (PiNDiff) modeling framework. An uncertainty quantification feature has been embedded within the PiNDiff method, bolstering the model’s reliability and robustness. Through comprehensive numerical experiments involving both synthetic and real-world manufacturing data, the proposed method showcases its capability in modeling densification during the CVI process. This research highlights the potential of the PiNDiff framework as an instrumental tool for advancing our understanding, simulation, and optimization of the CVI manufacturing process, particularly when faced with sparse data and an incomplete description of the underlying physics.

Data-driven prediction model for periodontal disease based on correlational feature analysis and clinical validation

ObjectivesThis study aimed to investigate the performance and reliability of data-driven models employing correlational feature analysis and clinical validation for predicting periodontal disease. MethodsThe 7th Korea National Health and Nutrition Examination Survey (n = 10,654) was used for correlation analysis to identify significant risk factors for periodontitis. Periodontal prediction models were developed with the selected factors and database, followed by internal validation with 5-fold cross-validation and 1000 bootstrap resampling. External validation was conducted with clinical data (n = 120) collected through self-reported questionnaires, clinical periodontal parameters, and radiographic image analysis. Predictive performance was assessed for logistics regression, support vector machine, random forest, XGBoost, and neural network algorithms using the area under the receiver operating characteristic curves (AUC) and other performance metrics. ResultsCorrelation analysis identified 16 features from over 1000 potential risk factors for periodontitis. The best data-driven model (XGBoost) showed AUC values of 0.823 and 0.796 for internal and external validations, respectively. Modeling with clinical data revealed those same measures to be 0.836 and 0.649, respectively. In addition, the data-driven model could predict other clinical periodontal parameters including severe bone loss (AUC = 0.813), gingival bleeding (AUC = 0.694), and tooth loss (AUC = 0.734). A patient case study about prognostic predictions revealed that the probability of periodontitis can be reduced by 6.0 % (stop smoking) and 0.6 % (stop drinking) on average. ConclusionsData-driven models for predicting periodontitis and other periodontal parameters were developed from 16 risk factors, demonstrating enhanced prediction performance and reproducibility in internal–external validations.

Capturing Local Temperature Evolution During Additive Manufacturing Through Fourier Neural Operators

Abstract High-fidelity, data-driven models that can quickly simulate thermal behavior during additive manufacturing (AM) are crucial for improving the performance of AM technologies in multiple areas, such as part design, process planning, monitoring, and control. However, complexities of part geometries make it challenging for current models to maintain high accuracy across a wide range of geometries. In addition, many models report a low mean-square error (MSE) across the entire domain of a part. However, in each time-step, most areas of the domain do not experience significant changes in temperature, except for the regions near recent depositions. Therefore, the MSE-based fidelity measurement of the models may be overestimated. This article presents a data-driven model that uses the Fourier neural operator to capture the local temperature evolution during the AM process. Besides MSE, the model is also evaluated using the R2 metric, which places great weight on the regions where the temperature changes significantly than MSE. The model was trained and tested on numerical simulations based on the discontinuous Galerkin finite element method for the direct energy deposition AM process. The results shows that the model maintains 0.983−0.999 R2 over geometries not included in the training data, which is higher than convolutional neural networks and graph convolutional neural networks we implemented, the two widely used architectures in data-driven predictive modeling.

Physically based vs. data-driven models for streamflow and reservoir volume prediction at a data-scarce semi-arid basin

Physically based or data-driven models can be used for understanding basinwide hydrological processes and creating predictions for future conditions. Physically based models use physical laws and principles to represent hydrological processes. In contrast, data-driven models focus on input–output relationships. Although both approaches have found applications in hydrology, studies that compare these approaches are still limited for data-scarce, semi-arid basins with altered hydrological regimes. This study aims to compare the performances of a physically based model (Soil and Water Assessment Tool (SWAT)) and a data-driven model (Nonlinear AutoRegressive eXogenous model (NARX)) for reservoir volume and streamflow prediction in a data-scarce semi-arid region. The study was conducted in the Tersakan Basin, a semi-arid agricultural basin in Türkiye, where the basin hydrology was significantly altered due to reservoirs (Ladik and Yedikir Reservoir) constructed for irrigation purposes. The models were calibrated and validated for streamflow and reservoir volumes. The results show that (1) NARX performed better in the prediction of water volumes of Ladik and Yedikir Reservoirs and streamflow at the basin outlet than SWAT (2). The SWAT and NARX models both provided the best performance when predicting water volumes at the Ladik reservoir. Both models provided the second best performance during the prediction of water volumes at the Yedikir reservoir. The model performances were the lowest for prediction of streamflow at the basin outlet (3). Comparison of physically based and data-driven models is challenging due to their different characteristics and input data requirements. In this study, the data-driven model provided higher performance than the physically based model. However, input data used for establishing the physically based model had several uncertainties, which may be responsible for the lower performance. Data-driven models can provide alternatives to physically-based models under data-scarce conditions.

Forecasting daily PM2.5 concentrations in Wuhan with a spatial-autocorrelation-based long short-term memory model

Accurate daily air pollution forecasts play a pivotal role in enabling government to implement timely emergency responses and helping alert individuals sensitive to air pollution to take preventive measures. The atmospheric continuity fosters spatial correlations among air pollutants at various locations, which is a factor frequently overlooked in contemporary research focused on harnessing data-driven models for air quality prediction. Therefore, this study proposed a Spatial-Autocorrelation-based Long Short-Term Memory (SALSTM) model for the daily forecasting in Wuhan, Hubei Province, China. Using a multivariate prediction approach with daily air pollution data and meteorological data from Wuhan, as well as air pollution data from surrounding cities, from 2021 to 2022 as input, the model was applied for projecting the daily PM2.5 for Wuhan during the year 2023 and conducting accuracy cross-validation. The results were compared with a univariate prediction approach utilizing the Autoregressive Integrated Moving Average (ARIMA) model and the original Long Short-Term Memory (LSTM) model. Furthermore, this study utilized Dynamic Time Warping (DTW) for feature selection in multivariate prediction, comparing the accuracy of prediction results before and after feature selection. Experimental results indicated that the SALSTM model, incorporating the DTW method, achieved a Root Mean Squared Error (RMSE) of 6.92 μg/m3, a Mean Absolute Error (MAE) of 4.07 μg/m3 and a coefficient of determination (R2) of 0.95. Compared to the univariate forecasting method, the three accuracy metrics RMSE, MAE, and R2 have improved by 54.74%, 58.68%, and 37.68%, respectively. In comparison with the original LSTM, the improvement is 23.79%, 30.90%, and 4.40%. In conclusion, the SALSTM model established in this study demonstrates accurate daily forecasting of PM2.5 concentrations.

An interpretable data-driven prediction model to anticipate scoliosis in spinal muscular atrophy in the era of (gene-) therapies

5q-spinal muscular atrophy (SMA) is a neuromuscular disorder (NMD) that has become one of the first 5% treatable rare diseases. The efficacy of new SMA therapies is creating a dynamic SMA patient landscape, where disease progression and scoliosis development play a central role, however, remain difficult to anticipate. New approaches to anticipate disease progression and associated sequelae will be needed to continuously provide these patients the best standard of care. Here we developed an interpretable machine learning (ML) model that can function as an assistive tool in the anticipation of SMA-associated scoliosis based on disease progression markers. We collected longitudinal data from 86 genetically confirmed SMA patients. We selected six features routinely assessed over time to train a random forest classifier. The model achieved a mean accuracy of 0.77 (SD 0.2) and an average ROC AUC of 0.85 (SD 0.17). For class 1 ‘scoliosis’ the average precision was 0.84 (SD 0.11), recall 0.89 (SD 0.22), F1-score of 0.85 (SD 0.17), respectively. Our trained model could predict scoliosis using selected disease progression markers and was consistent with the radiological measurements. During post validation, the model could predict scoliosis in patients who were unseen during training. We also demonstrate that rare disease data sets can be wrangled to build predictive ML models. Interpretable ML models can function as assistive tools in a changing disease landscape and have the potential to democratize expertise that is otherwise clustered at specialized centers.

Potential of Progressive and Disruptive Innovation-Driven Cost Reductions of Green Hydrogen Production.

Green hydrogen from water electrolysis is a key driver for energy and industrial decarbonization. The prediction of the future green hydrogen cost reduction is required for investment and policy-making purposes but is complicated due to a lack of data, incomplete accounting for costs, and difficulty justifying trend predictions. A new AI-assisted data-driven prediction model is developed for an in-depth analysis of the current and future levelized costs of green hydrogen, driven by both progressive and disruptive innovations. The model uses natural language processing to gather data and generate trends for the technological development of key aspects of electrolyzer technology. Through an uncertainty analysis, green hydrogen costs have been shown to likely reach the key target of <$2.5 kg-1 by 2030 via progressive innovations, and beyond this point, disruptive technological developments are required to affect significantly further decease cost. Additionally, the global distribution of green hydrogen costs has been calculated. This work creates a comprehensive analysis of the levelized cost of green hydrogen, including the important balance of plant components, both now and as electrolyzer technology develops, and offers a likely prediction for how the costs will develop over time.

A cascading model for nudging employees towards energy-efficient behaviour in tertiary buildings.

Energy-related occupant behaviour in the built environment is considered crucial when aiming towards Energy Efficiency (EE), especially given the notion that people are most often unaware and disengaged regarding the impacts of energy-consuming habits. In order to affect such energy-related behaviour, various approaches have been employed, being the most common the provision of recommendations towards more energy-efficient actions. In this work, the authors extend prior research findings in an effort to automatically identify the optimal Persuasion Strategy (PS), out of ten pre-selected by experts, tailored to a user (i.e., the context to trigger a message, allocate a task or providing cues to enact an action). This process aims to successfully influence the employees' decisions about EE in tertiary buildings. The framework presented in this study utilizes cultural traits and socio-economic information. It is based on one of the largest survey datasets on this subject, comprising responses from 743 users collected through an online survey in four countries across Europe (Spain, Greece, Austria and the UK). The resulting framework was designed as a cascade of sequential data-driven prediction models. The first step employs a particular case of matrix factorisation to rank the ten PP in terms of preference for each user, followed by a random forest regression model that uses these rankings as a filtering step to compute scores for each PP and conclude with the best selection for each user. An ex-post assessment of the individual steps and the combined ensemble revealed increased accuracy over baseline non-personalised methods. Furthermore, the analysis also sheds light on important user characteristics to take into account for future interventions related to EE and the most effective persuasion strategies to adopt based on user data. Discussion and implications of the reported results are provided in the text regarding the flourishing field of personalisation to motivate pro-environmental behaviour change in tertiary buildings.

Improved freezing rain forecast using machine learning

Freezing rain is one of the most damaging weather phenomena in winter or early spring in many parts of the world, affecting traffic, power lines and agriculture. Thus, reliable and computationally efficient prediction of its occurrence is urgently needed in weather forecast operations. However, there are different thermodynamic processes that can lead to freezing rain, resulting in unsatisfactory forecasting performance of the state-of-the-art Numerical Weather Prediction (NWP) models. Here a data-driven forecasting method for freezing rain using machine learning technologies is proposed. Observations of weather phenomenon collected from 2 515 national weather stations of China for winter of 2016–2019 and the corresponding atmospheric predictors derived from ERA5 reanalysis are used. The prediction function is constructed based on the classification and regression tree, and the predicting variables include temporal and vertical profiles of fundamental thermodynamic and kinematic parameters from 500 hPa to 1000 hPa, with a total dimension of 2 304. The LightGBM (Light Gradient Boosting Machine) framework is adopted to train our prediction model and an algorithm-level approach of modifying the loss function is used to address the imbalance of classes to improve forecasting skill. Results show that the data-driven prediction model, namely DDFR (data driven forecast of freezing rain), out-performs the benchmark NWP, i.e., ECMWF IFS product. It's improvements in terms of TS score range from 120% to 258% depending on different forecast leading times, which range from 0 to 12 h. In addition, DDFR is applied in an operational NWP model of China. The problem of domain adaptation is tackled and transfer learning method is employed to adapt the original DDFR to this NWP model. The effectiveness of such adaptation has been demonstrated by its performance on both training and testing datasets.

A data-driven soft sensor model for coal-fired boiler SO2 concentration prediction with non-stationary characteristic

Environmental issues have received significant global attention, and achieving ultra-low emission has become a crucial goal for thermal power plant. Pollutant prediction is essential to achieving ultra-low emission control. Due to the frequent adjustment of operating conditions, the coal-fired power generation process is a typical non-stationary process with complex changes along the time direction. A single model cannot effectively portray the complex non-stationary characteristics and model mismatch may occur in the prediction, which brings new challenges for modeling coal-fired SO2 emission. Therefore, the condition-driven category boosting (CatBoost) soft sensor model is proposed for real-time prediction of SO2 concentration. First, the thermal process time series is rearranged into different data slices. These data slices vary along the direction of the condition indicator, which can characterize the process characteristics on different slices. Second, the load-based sequential condition division (LSCD) algorithm is designed to realize the division of boiler operation process. The characteristics of process are effectively captured by variational auto-encoder (VAE), and the data slices with similar process characteristics are merged into the same mode. Non-stationary process along the time direction is reorganized into different condition modes along the load direction. Finally, the high-resolution local CatBoost models under different modes are constructed to achieve fine-grained prediction of SO2 concentration. The effectiveness of the proposed condition-driven model is verified by an industrial example of 1000 MW coal-fired boiler. The prediction results show that the proposed model can effectively divide the operation conditions and achieve accurate prediction of SO2 concentration. In the typical models in SO2 predicting, the proposed model has better performance with a determination coefficient of 0.92.

Data-Driven Prediction Model for Analysis of Sensor Data

In view of Industry 4.0, data generation and analysis are challenges. For example, machine health monitoring and remaining useful life prediction use sensor signals, which are difficult to analyze using traditional methods and mathematical techniques. Machine and deep learning algorithms have been used extensively in Industry 4.0 to process sensor signals and improve the accuracy of predictions. Therefore, this paper proposes and validates the data-driven prediction model to analyze sensor data, including in the data transformation phase Principal Component Analysis tested by Fourier Transformation and Wavelet Transformation, and the modeling phase based on machine and deep learning algorithms. The machine learning algorithms used for tests in this research are Random Forest Regression (RFR), Multiple Linear Regression (MLR), and Decision Tree Regression (DTR). For the deep learning comparison, the algorithms are Deep Learning Regression and Convolutional network with LeNet-5 Architecture. The experimental results indicate that the models show promising results in predicting wear values and open the problem to further research, reaching peak values of 92.3% accuracy for the first dataset and 62.4% accuracy for the second dataset.