Mean R2 Values Research Articles

Assessing human exposure to organic contaminants in fish: A modeling approach integrating chemical bioconcentration and food thermal processing

An increasing number of chemicals found in the environment potentially pose a threat to organisms such as fish. Models for risk assessment are vital resources that enable possible measurements of the hazards associated with chemical exposure. Traditional monitoring techniques and experimental procedures, however, are unable to keep up with the compounds that are becoming more and more implicated in environmental problems. Furthermore, a significant amount of data invariably results in inaccuracies. Here, we proposed an integrated approach that combines machine learning and fuzzy logic mathematical methods, assessing the risks associated with chemical exposure from contaminated fish with the least amount of data entry possible. We predicted the concentrations of organic contaminants in the environment, serving as a baseline for quantifying the fuzzy risks during household thermal processing of the fish. With a mean R2 value of 0.78, concentration of chemicals in the aquatic environment emerged as the most influential factor in predicting bioconcentration factors. Heptachlor, Endosulfan-sulfate, Endrin, and Endrin aldehyde are four high-risk pesticides throughout the entire processing process compared to others. The findings underscore the importance of considering processing methods and environmental factors in order to ensure food safety.

Development of novel computational models based on artificial intelligence technique to predict liquids mixtures separation via vacuum membrane distillation

The fundamental objective of this paper is to use Machine Learning (ML) methods for building models on temperature (T) prediction using input features r and z for a membrane separation process. A hybrid model was developed based on computational fluid dynamics (CFD) to simulate the separation process and integrate the results into machine learning models. The CFD simulations were performed to estimate temperature distribution in a vacuum membrane distillation (VMD) process for separation of liquid mixtures. The evaluated ML models include Support Vector Machine (SVM), Elastic Net Regression (ENR), Extremely Randomized Trees (ERT), and Bayesian Ridge Regression (BRR). Performance was improved using Differential Evolution (DE) for hyper-parameter tuning, and model validation was performed using Monte Carlo Cross-Validation. The results clearly indicated the models’ effectiveness in temperature prediction, with SVM outperforming other models in terms of accuracy. The SVM model had a mean R2 value of 0.9969 and a standard deviation of 0.0001, indicating a strong and consistent fit to the membrane data. Furthermore, it exhibited the lowest mean squared error, mean absolute error, and mean absolute percentage error, signifying superior predictive accuracy and reliability. These outcomes highlight the importance of selecting a suitable model and optimizing hyperparameters to guarantee accurate predictions in ML tasks. It demonstrates that using SVM, optimized with DE improves accuracy and consistency for this specific predictive task in membrane separation context.

Structural and functional design of CTAB-geopolymer adsorbents for rapid removal of tetracycline: A comparative study

A powder, inorganic membrane and 3D printing cetyltrimethylammonium bromide (CTAB)-geopolymer adsorbents system for adsorbing tetracycline (TC) was developed. And the adsorption properties, adsorption mechanism, adsorption cycle application based on the dynamic pH of adsorption system were systematically investigated by experiment, characterization and density functional theory (DFT) calculation. The introduction of CTAB significantly increased the adsorption response to TC in the high alkaline environment caused by spontaneous alkali release of geopolymer. The adsorption of CTAB-geopolymer for TC was most efficient in the dynamic pH range corresponding to TC- species. The predominant influencing mechanism between CTAB-geopolymer with TC was electrostatic interaction assisted by the hydrogen bonding and n-π interaction. The powder adsorbent with 11 wt% CTAB can capture 92.38 % TC at 2 min and fitted the pseudo-second-order model, and was also suitable for adsorption of trace TC. Although the extension of the diffusion path of the monolithic adsorbents limited the adsorption rate, the 3D printed adsorbent showed an adsorption efficiency of 84.20 % at 302 min. The outstanding adsorption (4 times)-desorption (3 times) cycle properties of 11 %CT-GA (81.15 % at 24 min, 4th adsorption) and cycle cumulative adsorption efficiency of 11 %CT-3DP (59.23 % at 120 min, 4th adsorption) adsorbent were exhibited. Furthermore, a high accuracy performance prediction model with the mean R2 value tended to 1 and the low root mean square error (0.0747) was provided, which can provide theoretical and technical reference for the subsequent industrial application of CTAB-geopolymer adsorbents.

Study on Fast Temporal Prediction Method of Flame Propagation Velocity in Methane Gas Deflagration Experiment Based on Neural Network

To address the challenges of high experimental costs, complexity, and time consumption associated with pre-mixed combustible gas deflagration experiments under semi-open space obstacle conditions, a rapid temporal prediction method for flame propagation velocity based on Ranger-GRU neural networks is proposed. The deflagration experiment data are employed as the training dataset for the neural network, with the coefficient of determination (R2) and mean squared error (MSE) used as evaluation metrics to assess the predictive performance of the network. First, 108 sets of pre-mixed methane gas deflagration experiments were conducted, varying obstacle parameters to investigate methane deflagration mechanisms under different conditions. The experimental results demonstrate that obstacle-to-ignition source distance, obstacle shape, obstacle length, obstacle quantity, and thick and fine wire mesh obstacles all significantly influence flame propagation velocity. Subsequently, the GRU neural network was trained, and different activation functions (Sigmoid, Relu, PReLU) and optimizers (Lookahead, RAdam, Adam, Ranger) were incorporated into the backpropagation updating process of the network. The training results show that the Ranger-GRU neural network based on the PReLU activation function achieves the highest mean R2 value of 0.96 and the lowest mean MSE value of 7.16759. Therefore, the Ranger-GRU neural network with PReLU activation function can be a viable rapid prediction method for flame propagation velocity in pre-mixed methane gas deflagration experiments under semi-open space obstacle conditions.

Optimizing the energy values of solid biofuel through acidic pre-treatment: An evolutionary-based neuro-fuzzy modelling and feature importance analysis

The increasing focus on sustainable energy solutions and eco-friendly fuel alternatives has sparked interest in exploring methods to enhance the energy content of solid biofuels through pre-treatment processes. This study investigates the impact of acidic (H2SO4) pretreatment on the energy content of solid biofuel derived from watermelon peel waste using machine learning methods. The biofuel properties, and calorific value (CV) were determined experimentally for both H2SO4-treated and untreated biofuel samples. Subsequently, an Adaptive neuro-fuzzy inference system (ANFIS) model with Genetic Algorithm (GA) and Grid Partitioning (GP) clustering techniques was developed to predict heating value of the biofuel, with performance evaluation based on root mean square error (RMSE), mean absolute percentage error (MAPE), mean absolute deviation (MAD), Mean Absolute Error (MAE) and R2-values. The decision tree regressor was employed to evaluate the feature importance, predictive power and impact of each input variable on CV prediction based on Gini importance metrics. To establish its superior performance, the hybrid ANFIS-GA-GP model was compared with ordinary-ANFIS and ANN model using same metrics. Results show that acid-pretreatment increased the CV of the solid biofuel by 3.53 MJ/kg (31.83 % improvement) and reduced ash content by 1.77 %. FTIR analysis revealed surface modifications, and a shift in the C-O vibrational stretch, while SEM micrographs displayed denser surfaces and reduced porosity as indicated by a lesser fiber diameter in treated samples. The GP-clustered ANFIS-GA model with a triangular membership function (tri-MF) exhibited superior performance and higher accuracy (RMSE of 0.1309, MAPE of 9.343, MAD of 0.1036, MAE of 0.1110, and R2-value of 0.9773 at model training). Furthermore, a tree decision regressor identified Fixed carbon as the most significant predictor for CV with a Gini importance of 0.988375. This study demonstrates the substantial enhancement in the energy content of biofuel using acidic pre-treatment and insights into a cutting-edge approach of improving the combustion properties of solid biofuel with machine learning models. This significantly contributes to the field of sustainable bioenergy research.

Tiered maize and wheat nutrient removal coefficients estimated from available data

AbstractEstimates of cropland nutrient budgets at national to global scale generally rely on regional or global mean coefficients for quantifying nutrients removed in crop yield and by-products. Use of such mean values masks the variability in these coefficients. Using maize and wheat as examples, we assessed variation in nutrient removal coefficients, namely harvest index (HI), nitrogen (N), phosphorus (P) and potassium (K) concentrations of crop products (Grain N, Grain P and Grain K respectively) and N, P and K concentrations of crop residues (Residue N, Residue P, and Residue K respectively). Variation in these coefficients was assessed by three categories (Tiers) of estimation. Statistical (mixed-effects) and machine learning (random forest regression) models (Tier 3) were used to predict the coefficients using generally available predictor variables at a global level. Mean prediction accuracies (R2) of the mixed-effects and random forest models were 0.32 for maize coefficients and 0.45 for wheat coefficients when based on a random sub-selection of mainly replicated field experiment data. When predictions were applied to on-farm data only, prediction accuracies were lower (mean R2 values of 0.08 and 0.36 for maize and wheat respectively). Variation in, and dearth of on-farm data for the coefficients contributed to these poor prediction accuracies. Until the limitations of on-farm data are overcome, it is recommended to use Tier 2 (regional) coefficient estimates in country and global cropland nutrient balance and nutrient use efficiency estimates. Where Tier 2 values are not available, then global average (Tier 1) coefficients can be used.

Artificial Intelligence-Based Surgery Support Model Using Intraoperative Radiographs for Assessing the Acetabular Component Angle

BackgroundThis study aimed to develop an artificial intelligence–based surgical support model for assessing the acetabular component angle using intraoperative radiographs during total hip arthroplasty and verify its accuracy. MethodsA total of 268 hips were analyzed. At first, 268 preoperative and intraoperative anteroposterior pelvic radiographs were amplified to 536. These radiographs were used to create a learning model to estimate the acetabular component angle from the radiographs intraoperatively. The ground truth was the anteversion and inclination angles obtained from the computed tomography–based navigation system intraoperatively. Bone landmarks on the preoperative and intraoperative radiographs were manually annotated. The distances and angles between each landmark were used as predictor variables. The estimation accuracy was assessed for internal and external test datasets. Mean absolute error (MAE) and R2 values were used as accuracy measures. ResultsThe MAE and R2 for the internal test set showed 2.19 and 0.850 for anteversion, and 1.18 and 0.805 for inclination, respectively. The MAE and R2 for the external test set showed 2.78 and 0.789 for anteversion, and 1.56 and 0.744 for inclination, respectively. ConclusionsWe developed an artificial intelligence–based surgical support model for accurately assessing the acetabular component angle using intraoperative radiographs. Excellent estimation accuracy was confirmed for the external test set. In the future, the model may help to reduce the risk of adverse postoperative events.

TransRUL: A Transformer-Based Multihead Attention Model for Enhanced Prediction of Battery Remaining Useful Life

The efficient operation of power-electronic-based systems heavily relies on the reliability and longevity of battery-powered systems. An accurate prediction of the remaining useful life (RUL) of batteries is essential for their effective maintenance, reliability, and safety. However, traditional RUL prediction methods and deep learning-based approaches face challenges in managing battery degradation processes, such as achieving robust prediction performance, to ensure scalability and computational efficiency. There is a need to develop adaptable models that can generalize across different battery types that operate in diverse operational environments. To solve these issues, this research work proposes a TransRUL model to enhance battery RUL prediction. The proposed model incorporates advanced approaches of a time series transformer using a dual encoder with integration positional encoding and multi-head attention. This research utilized data collected by the Centre for Advanced Life Cycle Engineering (CALCE) on CS_2-type lithium-ion batteries that spanned four groups that used a sliding window technique to generate features and labels. The experimental results demonstrate that TransRUL obtained superior performance as compared with other methods in terms of the following evaluation metrics: mean absolute error (MAE), root-mean-squared error (RMSE), and R2 values. The efficient computational power of the TransRUL model will facilitate the real-time prediction of the RUL, which is vital for power-electronic-based appliances. This research highlights the potential of the TransRUL model, which significantly enhances the accuracy of battery RUL prediction and additionally improves the management and control of battery-based systems.

Predicting Particle Size and Soil Organic Carbon of Soil Profiles Using VIS-NIR-SWIR Hyperspectral Imaging and Machine Learning Models

Modeling spectral reflectance data using machine learning algorithms presents a promising approach for estimating soil attributes. Nevertheless, a comprehensive investigation of the most effective models, parameters, wavelengths, and data acquisition techniques is essential to ensure optimal predictive accuracy. This work aimed to (a) explore the potential of the soil spectral signature obtained in different spectral bands (VIS-NIR, SWIR, and VIS-NIR-SWIR) and, by using hyperspectral imaging and non-imaging sensors, in the predictive modeling of soil attributes; and (b) analyze the accuracy of different ML models in predicting particle size and soil organic carbon (SOC) applied to the spectral signature of different spectral bands. Six soil monoliths, located in the central north region of Parana, Brazil, were collected and scanned via hyperspectral cameras (VIS-NIR camera and SWIR camera) and spectroradiometer (VIS-NIR-SWIR) in the laboratory. The spectral signature of the soils was analyzed and subsequently applied to ML models to predict particle size and SOC. Each set of data obtained by the different sensors was evaluated separately. The algorithms used were k-nearest neighbors (KNN), support vector machine (SVM), random forest (RF), linear regression (LR), artificial neural network (NN), and partial least square regression (PLSR). The most promising predictive performance was observed for the complete VIS-NIR-SWIR spectrum, followed by SWIR and VIS-NIR. Meanwhile, KNN, RF, and NN models were the most promising algorithms in estimating soil attributes for the dataset obtained from both sensors. The general mean R2 (determination coefficient) values obtained using these models, considering the different spectral bands evaluated, were around 0.99, 0.98, and 0.97 for sand prediction, and around 0.99, 0.98, and 0.96 for clay prediction. The lower performances, obtained for the datasets from both sensors, were observed for silt and SOC, with R2 results between 0.40 and 0.59 for these models. KNN demonstrated the best predictive performance. Integrating effective ML models with robust sample databases, obtained by advanced hyperspectral imaging and spectroradiometers, can enhance the accuracy and efficiency of soil attribute prediction.

Ultra-low cycle fatigue life prediction of stainless steel based on transfer learning guided artificial neural network

Determining ultra-low cycle fatigue (ULCF) life of stainless steel typically involves laborious and time-consuming tests. While machine learning offers an efficient solution for fatigue life prediction, the inherent demand for sufficient training data remains unaddressed. To solve this challenge, a novel method to predict ULCF life using small datasets was proposed by combining artificial neural network (ANN) and transfer learning (TL). A TL-guided ANN (TLNN) framework was developed, wherein the knowledge gained from a pre-trained ANN model for structural steels was transferred to ULCF life prediction of stainless steel. The TLNN model exhibits enhanced predictive capabilities for stainless steel under small amounts of training datasets, with mean R2 (coefficient of determination) value of 0.88 and average MAPE (mean absolute percentage error) value of 25.52%. In comparison, the directly trained ANN model shows lower performance, possessing that the average R2 and MAPE are 0.69 and 47.58%, respectively. We pioneeringly explored and found that adding synthetic data enhancement had no positive effect on the predictive ability of the TLNN model. Furthermore, the dependence of predictive capacity by the TLNN model on the number of training data availability was studied. The prediction process of the TLNN model was interpreted by SHAP (SHapley Additive exPlanations) method. In general, the developed TLNN model can efficiently predict the ULCF life of stainless steel with high accuracy and reduce the cost of consecutive fatigue property evaluation.

Non-contrast magnetic resonance evaluation of active multiple sclerosis lesions: Emerging role of quantitative synthetic magnetic resonance imaging.

The current study aims to explore the utility of novel synthetic MRI-derived quantitative parameters including myelin-correlated volume (MyC) in identifying active MS lesions without injecting gadolinium contrast. 43 MS patients underwent institutional MS protocol including 3D FLAIR and post-contrast 3D T1VIBE sequence on a 1.5T MR Scanner in addition to synthetic MRI sequence. MS plaques were categorised into enhancing (C) and non-enhancing (N) lesions. They were also sub-categorised based on location into periventricular WM lesions (P), deep WM lesions (D), infratentorial lesions (I) and cortical-juxtacortical (C) lesions. ROIs were placed on Synthetic FLAIR images in MS lesions and quantitative parameters of R1, R2, PD and myelin-correlated volume (MyC) obtained. Sensitivity and specificity for various cut-off values to differentiate enhancing from non-enhancing multiple sclerosis lesions were calculated by performing ROC curve analysis and logistic regression analysis. Contrast enhancing lesions demonstrated significantly higher mean R1, R2 values and lower mean PD values in comparison to non-enhancing lesions (p < 0.05) but with limited specificity. Region-wise analysis revealed high AUC values for mean R1 and R2 at cortical-juxtacortical lesions (p < 0.001) followed by periventricular lesions (p < 0.003) for differentiating enhancing from non-enhancing lesions with no significant contribution from MyC and PD values. Synthetic MRI-derived quantitative parameters of mean R1, R2, MyC and PD hold value in differentiating contrast enhancing and non-enhancing MS lesions without administering gadolinium-based contrast agent. However, the current study did not achieve significant specificity for establishing the same.

Spatiotemporal variations of fossil fuel CO2 emissions in China: A sectoral allocation approach based on multi-source data

Fossil fuel (FF) CO2 emissions account for the largest portion of human-related CO2 emissions. It is essential to accurately understand the spatial distribution of high-resolution FFCO2 emissions to formulate different carbon emission reduction policies in different regions. Therefore, a sectoral allocation approach was proposed to estimate FFCO2 emissions in China from 2000 to 2021 based on multi-source data. Furthermore, the spatiotemporal characteristics of FFCO2 emissions in different sectors were analyzed at different scales, and the spatial correlation of FFCO2 emissions in the service sector and industrial sector was also evaluated through Moran's index. The results showed that the mean R2 value of the sectoral allocation approach (0.89) exceeds that of the approach using only nighttime light (0.72). Moreover, the calculated results were utilized to analyze the Spatiotemporal variation of FFCO2 emissions. The analysis revealed that China's FFCO2 emissions increased from 3173 Mt in 2000–10662 Mt in 2021. The high emissions of FFCO2 mainly come from the industrial sectors in North China and Central China, as well as the service sectors in the eastern coastal cities and other provincial capital cities. The spatial dependence of FFCO2 emissions in the industrial sector was stronger than that in the service sector, but the spatial dependence of FFCO2 emissions in the service sector showed an increasing trend from 2000 to 2021. These results have important references and implications for region-specific carbon emission reduction policies.

Long-range linkage disequilibrium events on the genome of dromedary camels as a signal of epistatic and directional positive selection

The genome of dromedary camels has been subjected to various evolutionary forces, such as genetic admixture, natural positive selection, and epistatic selection. These forces are considered as main factors associated with the formation of long-range linkage disequilibrium (LRLD) events. We have analyzed whole-genome data of 56 dromedary camel samples from different geographical regions across the Arabian Peninsula for two main purposes: first, to assess the level of linkage disequilibrium, and second, to identify autosomal LRLD events. The analysis revealed a mean r2 value of 0.25 (±0.028) over the dromedary autosomes, with a continuous decay until reaching a plateau at inter-variant distances >400 kb. A total of 1847 LRLD events were identified within the dromedary autosomes, which harbor 36 prevalent haplotypes. A level of genetic admixture was observed among the dromedary populations analyzed, which might be a source for the observed LRLD events. Four functional interactions were revealed among the genes found within the LRLD events, with some genes overlapping with prevalent haplotypes, indicative of potential epistatic selection. Genes related to renal function, fertility, thermal regulation, bone structure, and insulin regulation were found among the LRLD genes. These genes, along with the defined prevalent haplotypes, can be considered as hotspots for natural positive selection associated with the LRLD distribution on dromedary genomes. In this study, we have for the first time analyzed the genome of dromedary camels for LRLD events possibly influenced by forces including genetic admixture, epistatic and positive selection. The revealed LRLD elements and prevalent haplotypes should be accounted for when designing breeding programmes to conserve the genetic stock of this well-adapted domestic species.

Flame propagation speed prediction model of premixed methane gas deflagration experiments based on Adamax-LSTM for FLNG

A time-series prediction method based on AdaMax-LSTM neural network is proposed for predicting the flame propagation speed in premixed methane gas deflagration experiments, which can provide a decision-making basis for emergency operation of FLNG combustible gas deflagration accidents. Firstly, 54 sets of premixed methane gas deflagration experiments under semi-open duct obstacle conditions were conducted to investigate the different deflagration mechanisms by changing the obstacle parameters. The experimental results demonstrate that the distance between the obstacle and ignition source, obstacle length and obstacle shape will all effect the flame propagation speed and deflagration overpressure. Secondly, the LSTM neural network is employed to setup a novel method which can predict the flame speed in time series via calculating the Reynolds number and determining the turbulence of the flame accurately. The deflagration experiments results were used as the dataset for AI training for the proposed prediction method. In addition, the AdaMax optimizer is added into the backpropagation process of the proposed LSTM neural network to maximize the prediction accuracy of the method. The analysis results indicate that the AdaMax-LSTM neural network with sigmoid activation function can achieve the highest level of accuracy prediction, with the mean R2 value reaching 0.95, and can identify anomaly data and the most different deflagration mechanisms experimental condition. The proposed method provides an efficient and accurate way to predict and analyze the deflagration mechanisms via employing cutting-edge AI technology.

From drought hazard to risk: A spring wheat vulnerability assessment in the Canadian Prairies

The Canadian drought monitor (CDM) provides monthly assessments of drought severity but does not provide guidance on the potential agricultural impacts. This study extends the CDM to a comprehensive risk assessment framework by assessing the vulnerability of spring wheat to drought timing and severity in the Canadian Prairies. To achieve this, a bayesian neural network (BNN) model was developed that predicts high-resolution wheat yields and uncertainties using the CDM and normalized difference vegetation index (NDVI) data from 2010 to 2021. Model performance is comparable to previous studies, with errors ranging from 13% to 18% of mean yields and R2 values from 0.43 to 0.70 that peak in early August. The model was then applied under various drought conditions to evaluate how different drought timings and severities affect yield vulnerability. The results demonstrate that drought exposure from June to August reduces wheat yields in proportion to drought severity while abnormally dry conditions may have a positive impact of yield, particularly in August. Yield uncertainty decreases substantially from June to July while yield prediction accuracy increases, suggesting that mitigation efforts are most effective prior to July. The final component of the research involved creating operational risk maps that integrate the yield vulnerability assessment with the CDM. These maps were applied in a case study to demonstrate their utility in providing actionable, real-time information for agricultural stakeholders. Overall, this study contributes to the body of knowledge regarding crop sensitivities to varying drought conditions and represents a methodological advancement by enabling high-resolution, operational agricultural risk assessments at scale. By integrating detailed vulnerability data with drought hazard monitoring from the CDM, the information provided by these risk maps can be leveraged by agricultural stakeholders in near real-time to make well-informed decisions that mitigate the impacts of drought on wheat production, enhancing the resilience of agricultural systems to climatic variability.

Optimizing recombinant antibody fragment production: A comparison of artificial intelligence and statistical modeling.

Maximizing the recombinant protein yield necessitates optimizing the production medium. This can be done using a variety of methods, including the conventional "one-factor-at-a-time" approach and more recent statistical and mathematical methods such as artificial neural network (ANN), genetic algorithm, etc. Every approach has advantages and disadvantages of its own, yet even when a technique has flaws, it is nevertheless used to get the best results. Here, one categorical variable and four numerical parameters, including post-induction time, inducer concentration, post-induction temperature, and pre-induction cell density, were optimized using the 232 experimental assays of the central composite design. The direct and indirect effects of factors on the yield of anti-epithelial cell adhesion molecule extracellular domain fragment antibody were examined using statistical methods. The analysis of variance results indicate that the response surface methodology (RSM) model is effective in predicting the amount of produced single-chain fragment variable (p-value = 0.0001 and R2 = 0.905). For ANN modeling, the evaluation using normalized root mean square error (NRMSE) and R2 values shows a good fit (R2 = 0.942) and accurate predictions (NRMSE = 0.145). The analysis of error parameters and R2 of a dataset, which contained 30 data points randomly selected from the complete dataset, showed that the ANN model had a higher R2 value (0.968) compared to the RSM model (0.932). Furthermore, the ANN model demonstrated stronger predictive ability with a lower NRMSE (0.048vs. 0.064). Induction at the cell density of 0.7 and an isopropyl β-D-1-thiogalactopyranoside concentration of 0.6mM for 32 h at 30°C in BW25113 was the ideal culture condition leading to the protein yield of 259.51mg/L. Under the optimum conditions, the output values predicted by the ANN model (259.83mg/L) were more in line with the experimental data (259.51mg/L) than the RSM (276.13mg/L) expected value. This outcome demonstrated that the ANN model outperforms the RSM in terms of prediction accuracy.

Comparative analysis of machine learning techniques for predicting drilling rate of penetration (ROP) in geothermal wells: A case study of FORGE site

Enhanced Geothermal Systems (EGS) present a compelling means to unlock the considerable yet largely untapped thermal energy within the earth's crust globally. The EGS drilling cost constitutes a substantial portion, up to 60 %, of the overall expenses. Consequently, streamlining and optimizing the drilling processes for these systems hold immense economic significance, with the potential to substantially lower costs, advance the utilization of geothermal energy, and contribute significantly to the reduction of carbon emissions. This research aims to enhance EGS drilling operations by seeking ways of reducing drilling cost.In this research, we harnessed the predictive power of 10 state-of-the-art machine learning (ML) algorithms to anticipate a crucial drilling parameter: ROP. Using the FORGE dataset, we developed a code tailored for the intensive preprocessing of drilling data. This code offers many options, including various noise-removing techniques and scaling approaches. However, the primary focus of our work extends to quantifying uncertainties intrinsic to the predictions of the 10 algorithms employed. To achieve this, a comprehensive approach involved subjecting each algorithm to 40 runs, utilizing the best model from the tuning process.The results show that unaddressed uncertainties may lead to unstable model behavior, where small changes in the input data or random initialization result in significant prediction variations. Thus, models that do not account for uncertainty may be overfit to the noise in the training data, leading to poor generalization to new, unseen data. Remarkably, the results highlight the superiority of the Extreme Tree, Light Gradient Boost, Random Forest, and Gradient Boosting algorithms, showcasing mean absolute error (MAE) and R2 values within the ranges of 3.5–4.5 and 0.9–0.95, respectively. Conversely, artificial neural networks and support vector machine algorithms demonstrate comparatively lower performance, with MAE ranging from 4.7 to 6.3 and R2 from 0.85 to 0.91.Although the results presented in this work are only based on the drilling parameters from one well of the FORGE site and do not include rock properties or geological parameters, however, the proposed nuanced understanding of algorithmic performance is valuable for refining predictive models in geothermal drilling applications, ensuring robustness and reliability in the face of diverse operational scenarios. Navigating a successful workflow, adeptly processing data, and meticulously quantifying uncertainties linked to each predictive algorithm emerge as formidable yet indispensable tasks. Our research not only sheds light on these complexities but also paves the way for a strategic optimization approach based on data-driven ROP models. Therefore, the potential for substantial savings in real-time drilling operations becomes apparent, unlocking a new realm of possibilities for the geothermal energy sector.

Understanding and Predicting the Spatially Resolved Adsorption Properties of Nanoporous Materials.

Using knowledge from statistical thermodynamics and crystallography, we develop an image-image translation model, called SorbIIT, that uses three-dimensional grids of adsorbate-adsorbent interaction energies as input to predict the spatially resolved loading surface of nanoporous materials over a broad range of temperatures and pressures. SorbIIT consists of a closed-form differential model for loading-surface prediction and a U-Net to generate spatial differential distributions from the energy grids. SorbIIT is trained using the energy grids and adsorbate distributions (obtained from high-throughput simulations) of 50 synthesized and 70 hypothetical zeolites and applied for predicting the adsorption of carbon dioxide, hydrogen sulfide, n-butane, 2-methylpropane, krypton, and xenon in other zeolites from 256 to 400 K. Employing a quadratic isotherm model for the local differentiation, SorbIIT yields mean R2 values of 0.998 for total adsorption and 0.6904 for local adsorption with a resolution of 0.2 Å, and a value of 0.721 for the structural similarity of the local loading distribution.

Application of deep learning model incorporating domain knowledge in international migration forecasting

PurposeForecasting population movement trends is crucial for implementing effective policies to regulate labor force growth and understand demographic changes. Combining migration theory expertise and neural network technology can bring a fresh perspective to international migration forecasting research.Design/methodology/approachThis study proposes a conditional generative adversarial neural network model incorporating the migration knowledge – conditional generative adversarial network (MK-CGAN). By using the migration knowledge to design the parameters, MK-CGAN can effectively address the limited data problem, thereby enhancing the accuracy of migration forecasts.FindingsThe model was tested by forecasting migration flows between different countries and had good generalizability and validity. The results are robust as the proposed solutions can achieve lesser mean absolute error, mean squared error, root mean square error, mean absolute percentage error and R2 values, reaching 0.9855 compared to long short-term memory (LSTM), gated recurrent unit, generative adversarial network (GAN) and the traditional gravity model.Originality/valueThis study is significant because it demonstrates a highly effective technique for predicting international migration using conditional GANs. By incorporating migration knowledge into our models, we can achieve prediction accuracy, gaining valuable insights into the differences between various model characteristics. We used SHapley Additive exPlanations to enhance our understanding of these differences and provide clear and concise explanations for our model predictions. The results demonstrated the theoretical significance and practical value of the MK-CGAN model in predicting international migration.

Assessment of environmental water strategies for improving fringing vegetation health by modelling vegetation condition in a connected floodplain lakes system

AbstractAcross the globe, environmental water has been allocated with the purpose of preserving the health and vitality of floodplain vegetation. However, the influences of environmental water volume and environmental water delivery strategies have not been studied widely because of shortage of on‐ground monitoring data. Remotely sensed data can bridge this gap by providing long‐term and continuous information; Landsat imagery from 1988 to 2020 was used in this research. We used the normalized difference vegetation index (NDVI) as an indicator of physiological condition of lake‐fringing trees on the Hattah Lakes floodplain, south‐east Australia. We employed the random forest (RF) regression method to model the relationship between NDVI and various climate and hydrological factors, such as the volume of water delivered to the connected lakes system as environmental water allocations or natural floods. The RF models performed well overall, with a mean R2 value of 0.73. The analysis identified the monthly total of environmental water delivered 3 months prior to the Landsat image date as a more crucial factor than natural floods over the same period for driving vegetation condition. Environmental water from 3 months previously exerts a positive influence on NDVI until the volume reaches a specific threshold. We have observed significant improvements in floodplain vegetation through the current environmental water strategy, particularly since the construction of pumping infrastructure in 2013. We suggest that managers aim to inundate the lake fringing area every 3 years, specifically from August to September, by delivering environmental water up to the modelled threshold volume. Finally, the use of infrastructure has proven to be an effective and efficient method for irrigating floodplain lakes, leading to improvements in vegetation condition while conserving water resources.