Accurate Temperature Prediction Research Articles

Human thermal comfort model and evaluation on building thermal environment

A healthy and comfortable thermal environment has become the core focus on building environment evaluation. The key is to realize room temperature regulation based on the demand for human thermal comfort. The study aims to build the core of building thermal environment regulation, building thermal environment evaluation system, to achieve accurate evaluation and prediction of thermal comfort temperature for different type buildings and occupants. Considering the differences between traditional and smart buildings in building intelligence, whose thermal environment evaluation frameworks are proposed respectively. Taking the traditional buildings in a typical city from the severe cold zone as an example, the thermal comfort models of different type buildings, heating periods, and occupants are established. Furthermore, the corresponding correction factors are proposed for age, gender, BMI and metabolic rate. This study provides theoretical support for the evaluation of building thermal environments.

Prediction of Wind Turbine Gearbox Oil Temperature Based on Stochastic Differential Equation Modeling

Aiming at the problem of high failure rate and inconvenient maintenance of wind turbine gearboxes, this paper establishes a stochastic differential equation model that can be used to fit the change of gearbox oil temperature and adopts an iterative computational method and Markov-based modified optimization to fit the prediction sequence in order to realize the accurate prediction of gearbox oil temperature. The model divides the oil temperature change of the gearbox into two parts, internal aging and external random perturbation, adopts the approximation theorem to establish the internal aging model, and uses Brownian motion to simulate the external random perturbation. The model parameters were calculated by the Newton–Raphson iterative method based on the gearbox oil temperature monitoring data. Iterative calculations and Markov-based corrections were performed on the model prediction data. The gearbox oil temperature variations were simulated in MATLAB, and the fitting and testing errors were calculated before and after the iterations. By comparing the fitting and testing errors with the ordinary differential equations and the stochastic differential equations before iteration, the iterated model can better reflect the gear oil temperature trend and predict the oil temperature at a specific time. The accuracy of the iterated model in terms of fitting and prediction is important for the development of preventive maintenance.

Computational and intelligence modeling analysis of pharmaceutical freeze drying for prediction of temperature in the process

Accurate temperature prediction is crucial for various scientific and engineering applications, yet it remains challenging due to the complex relationships between spatial coordinates and temperature variations. This study addresses this challenge by exploring advanced machine learning models to improve prediction accuracy, filling the research gap in optimizing predictive models for temperature estimation in freeze drying of pharmaceuticals. We employed Support Vector Regression (SVR), Poisson Regression (POR), and Adaptive Neuro-Fuzzy Inference System (ANFIS) models, each enhanced using the Cheetah Optimizer (CO), to estimate temperature based on spatial coordinates (X, Y, Z) in the domain of process. The methodology involved training and testing these models on a dataset comprising spatial and temperature data, with a focus on improving accuracy through optimization techniques. Validation of the models showed that the CO-SVR model outperformed the others, achieving an R2 score of 0.953, Mean Squared Error (MSE) of 9.893, and Mean Absolute Error (MAE) of 2.549. This represents a significant improvement over the CO-ANFIS model, which obtained an R2 of 0.863, MSE of 23.583, and MAE of 3.912. The CO-POR model showed the lowest predictive capability, with an R2 score of 0.753, MSE of 57.608, and MAE of 6.756. These findings underscore the effectiveness of the Cheetah Optimizer in enhancing the accuracy of SVR models for temperature prediction, suggesting its potential for broader applications in predictive modeling where accuracy is paramount.

Improving Module Temperature Prediction Models for Floating Photovoltaic Systems: Analytical Insights from Operational Data

Floating photovoltaic (FPV) systems are gaining popularity as a valuable means of harnessing solar energy on unused water surfaces. However, a significant gap persists in our comprehension of their thermal dynamics and the purported cooling benefits they provide. The lack of comprehensive monitoring data across different climatic regions and topographies aggravates this uncertainty. This paper reviews the applicability of established module temperature prediction models, originally developed for land-based PV systems, to FPVs. It then details the refinement of these models using FPV-specific data and their subsequent validation through large-scale, ongoing FPV projects. The result is a significant improvement in the accuracy of temperature predictions, as evidenced by the reduced Mean Absolute Error (MAE) and improved R-squared (R2) after parameter optimisation. This reduction means that the tailored models better reflect the distinct environmental influences and cooling processes characteristic of FPV systems. The results not only confirm the success of the proposed method in refining the accuracy of current models, but also indicate significant post-tuning changes in the parameters representing wind and convective effects. These adjustments highlight the increased responsiveness of FPVs to convective actions, especially when compared to ground-based systems, possibly due to the evaporative cooling effect of bodies of water. Through this research, we address a critical gap in our understanding of heat transfer in FPV systems and aim to enrich the knowledge surrounding the acknowledged cooling effect of FPVs.

A Reduced-Order Model of the Coupled Venting-Thermal-Electrochemical Behavior to Predict First Venting Under External Short Circuit Conditions

Modeling abusive battery operation before thermal runaway (TR) can reduce the testing requirements and facilitate the development of effective and reliable early failure detection and fast discharge strategies [1] which require multiple types of sensor signals, including current, voltage, temperature, and pressure. We present a multi-physics model that can predict the rapidly evolving discharge behavior of cells undergoing an external short circuit, including hazards like first venting. First venting models account for gas generation due to SEI decomposition and electrolyte vaporization at high temperatures to calculate the build-up of internal cell pressure under constant-displacement conditions [2]. Modeling gas generation requires accurate temperature prediction, which subsequently requires accurate Joule heating calculated from current and voltage predictions. From the cascading chain of model input dependencies, the first challenge is managing error propagation through the submodels with appropriate parameterization. Previous modeling work parameterized a venting model for a cell undergoing an external short circuit (ESC) but did not include a thermal or electrical model [2]. The second challenge is modeling the diffusion-limited discharge behavior with currents approaching 50-80 C with a fast and accurate model that is feasible for detection and control applications. Diffusion-limited behavior occurs when the local Li concentration saturates, suddenly causing large concentration overpotentials that are observable in the terminal voltage and current (see Fig. 1) as well as numerical instability when solving the Butler-Volmer (BV) equation. Previous ESC modeling works either used the Doyle-Fuller-Newman (DFN) model with a limiting current density in the BV equation [3] or an equivalent circuit model (Eq-CM) [1]. However, solving the DFN is computationally intensive for a control application, while Eq-CMs cannot predict the diffusion-limited electrical behavior beyond the data they were parameterized on, requiring apriori experiments to be accurate. To balance the trade-offs, we instead look towards reduced-order modeling.In this work, we present a control-oriented, reduced-order, multi-physics model that captures the electrochemical, thermal, and venting behavior of four 4.6 Ah NMC pouch cells undergoing an external short circuit with different initial state-of-charge (SOC). The multi-physics model couples a first venting model with a lumped thermal model driven by Joule heating calculated through the overpotentials from the Single-Particle Model with electrolyte (SPMe). The combined model was parameterized through four experiments by fitting five key parameters in the submodels related to the SEI decomposition rate, cell thermal behavior, and solid electrode diffusion to capture the first venting timing, peak temperature, and diffusion-limited current-voltage drops. Additionally, two resistances were tuned to match the initial current and voltage with all other parameters were taken from the literature. Applying the same parameter set consisting of the average of the fitted values on all four cells, the combined multi-physics model correctly predicted that the fully-charged cells would vent and conservatively predicted the cell venting timing up to about 40 s before it occurred in the experiment. For high initial SOC cells, the SPMe also accurately predicted the current and voltage drops associated with diffusion limitations and SOC up until the cell vented. This is the first work that systematically parameterizes and couples a reduced-order, physics-based model to capture the electrical, thermal, and venting behavior under battery abuse conditions. Future work will explore applications for the model in early detection and response to critical safety events.REFERENCES[1] Tran, Vivian, Jason Siegel, and Anna Stefanopoulou. "Emergency Li-ion Battery Discharge using Nonlinear Model Predictive Control with Temperature and Venting Pressure Constraints." 2023 American Control Conference (ACC). IEEE, 2023.[2] Cai, Ting, et al. "Modeling li-ion battery first venting events before thermal runaway." IFAC-PapersOnLine 54.20 (2021): 528-533.[3] Rheinfeld, Alexander, et al. "Quasi-isothermal external short circuit tests applied to lithium-ion cells: Part ii. modeling and simulation." Journal of The Electrochemical Society 166.2 (2019): A151. Fig. 1: 15-min simulation of an external short circuit for cells at different initial SOC. Model results and experimental measurements are shown for four cells that were externally shorted. The measured current, voltage, temperature, and expansion force were measured at 10 Hz and plotted versus log time to highlight the dynamic current-voltage behavior in the first few minutes. The diffusion-limited current and voltage behavior are captured by the model. The two cells at 100% SOC, experienced venting and higher peak temperatures, which are well captured by the model. The cell venting timing was predicted to be 43 s and 7 s early for Cell 100A and 100B, respectively. The cells that were shorted at lower SOC did not vent. Figure 1

Modeling wax disappearance temperature using robust white-box machine learning

Wax deposition is one of the major operational problems encountered in the upstream petroleum production system. The deposition of this undesirable scale can cause a variety of challenging problems. In order to avoid the latter, numerous parameters associated with the mechanism of wax deposition should be determined precisely. In this study, a new smart correlation was proposed for the accurate prediction of Wax disappearance temperature (WDT) using a robust explicit-based machine learning (ML) approach, namely gene expression programming (GEP). The correlation was developed using comprehensive experimental measurements. The obtained results revealed the promising degree of accuracy of the suggested GEP-based correlations. In this context, the newly-introduced correlations provided excellent statistical metrics (R2 = 0.9647 and AARD = 0.5963 %). Furthermore, performance of the developed correlation outperformed that of many existing approaches for predicting WDT. In addition, the trend analysis performed on the outcomes of the proposed GEP-based correlations divulged their physical validity and consistency. Lastly, the findings of this study provide a promising benefit, as the newly developed correlations can notably improve the adequate estimation of WDT, thus facilitating the simulation of wax deposition-related phenomena. In this context, the proposed correlations can supply the effective management of the production facilities and improvement of project economics since the provided correlation is a simple-to-use decision-making tool for production and chemical engineers engaged in the management of organic deposit-related issues.

Enhanced Atlantic Meridional Mode predictability in a high-resolution prediction system.

Accurate prediction of sea surface temperatures (SSTs) in the tropical North Atlantic on multiyear timescales is of paramount importance due to its notable impact on tropical cyclone activity. Recent advances in high-resolution climate predictions have demonstrated substantial improvements in the skill of multiyear SST prediction. This study reveals a notable enhancement in high-resolution tropical North Atlantic SST prediction that stems from a more realistic representation of the Atlantic Meridional Mode and the associated wind-evaporation-SST feedback. The key to this improvement lies in the enhanced surface wind response to changes in cross-equatorial SST gradients, resulting from Intertropical Convergence Zone bias reduction when atmospheric model resolution is increased, which, in turn, amplifies the positive feedback between latent and sensible surface heat fluxes and SST anomalies. These advances in high-resolution climate prediction hold promise for extending tropical cyclone forecasts at multiyear timescales.

Reaction rate of HO2+ 5-methyl-2-furanyl methyl/2-furanyl methyl and its effect on combustion of 2, 5-dimethylfuran/2-methylfuran

A valuable alternative to traditional fuels, bio-oxygenated fuels provide benefits. Oxygenated fuels 2,5-dimethylfuran (DMF) and 2-methylfuran (2MF) perform well. This study used quantum chemical calculations and combustion simulations to evaluate the combustion characteristics of low and medium temperature combustion mechanisms. Conclusions: In the combustion reaction of DMF and 2MF, the H-abstraction reaction occurs mainly at the methyl site. The reaction between macromolecular radicals and HO2 at low and middle temperatures plays a critical role in fuel auto-ignition. Thus, R∙+HO2 ↔ ROOH→R-CHO+H2O and R∙+HO2 → vdw complex → R+3O2 were added to the mechanism. Modified mechanism improves temperature prediction accuracy. The HOMO-LUMO gap is narrowed by the methyl group, which is closely related to the reaction sites and the molecular structure. After H-abstraction, the methyl site is the most likely to react, followed by the C3 and C5 sites.

Predictive Modeling of Solar PV Panel Operating Temperature over Water Bodies: Comparative Performance Analysis with Ground-Mounted Installations

Solar panel efficiency is significantly influenced by its operating temperature. Recent advancements in emerging renewable energy alternatives have enabled photovoltaic (PV) module installation over water bodies, leveraging their increased efficiency and associated benefits. This paper examines the operational performance of solar panels placed over water bodies, comparing them to ground-mounted solar PV installations. Regression models for panel temperature are developed based on experimental setups at BITS Pilani, India. Developed regression models, including linear, quadratic, and exponential, are utilized to predict the operating temperature of solar PV installations above water bodies. These models incorporated parameters such as ambient temperature, solar insolation, wind velocity, water temperature, and humidity. Among these, the one-degree regression models with three parameters outperformed the models with four or five parameters with a prediction error of 5.5 °C. Notably, the study found that the annual energy output estimates from the best model had an error margin of less than 0.2% compared to recorded data. Research indicates that solar PV panels over water bodies produce approximately 2.59% more annual energy output than ground-mounted systems. The newly developed regression models provide a predictive tool for estimating the operating temperature of solar PV installations above water bodies, using only three meteorological parameters: ambient temperature, solar insolation, and wind velocity, for accurate temperature prediction.

A numerical oxidation model for SiC‐coated thermal protection systems in hypersonic applications

AbstractSilicon carbide (SiC) is a widely used component for thermal protection system (TPS) design. This material is often used either as a coating layer to protect beneath carbon‐based material against oxidation or as a ceramic matrix for composite materials used in the hypersonic leading edges. A numerical equilibrium model for SiC‐coated material ablation is developed in this study to compute the material response of coated TPS in hypersonic relevant aerothermal environment. The developed model is based on an equilibrium approach similar to the carbon graphite oxidation framework for ablative charring materials. The equilibrium wall composition is calculated based on the minimization of the Gibbs free energy. The proposed method can capture numerically the transition from passive to active oxidation while maintaining a low computational cost and good numerical stability. Implementation of the model in the Porous Material Analysis Toolbox based on OpenFOAM code permits to compare against previous literature test cases. By comparing the surface temperature obtained from the model with the experimental data, it is observed that the numerical model gives a good estimation providing accurate surface temperature prediction.

Nondestructive and accurate prediction of IGBT junction temperature in wind power converters: based on IDMOA-ELM prediction method

ABSTRACT This study has made significant advancements in predicting junction temperature of IGBTs in wind power converters. An improved dwarf mongoose optimisation algorithm (IDMOA) with superior performance was developed. The IDMOA improves the initial solution quality through Hammersley initialisation, balances global search and local optimisation with nonlinear dynamic decreasing weight factors, and enhances population diversity via differential evolution strategy to avoid local optima. The IDMOA optimizes random parameters of extreme learning machine (ELM), overcoming the limitations of traditional manual parameter setting and constructing a high-precision IDMOA optimised ELM (IDMOA-ELM) model. Simulation results indicate that the IDMOA-ELM excels in predicting the IGBT junction temperature, achieving a low RMSE value of 0.1034 ℃. This significantly surpasses existing technologies and provides robust support for temperature management in wind power converters. Furthermore, to verify the performance of the DMOA-ELM in practical application scenarios, IGBT accelerated ageing experiments were conducted, yielding a comprehensive validation dataset. The high accuracy and effectiveness of the IDMOA-ELM were confirmed through comparative analysis with experimental data, enhancing the credibility of the research. This study achieved non-destructive and high-precision prediction of IGBT junction temperature in wind power converters and significantly improving the reliability of wind power converters.

Assessing the accuracy of two steady‐state temperature models for onboard passenger vehicle photovoltaics applications

AbstractWe assess the accuracy of two steady‐state temperature models, namely, Ross and Faiman, in the context of photovoltaics (PV) systems integrated in vehicles. Therefore, we present an analysis of irradiance and temperature data monitored on a PV system on top of a vehicle. Next, we have modeled PV cell temperatures in this PV system, representing onboard vehicle PV systems using the Ross and Faiman model. These models could predict temperatures with a coefficient of determination (R2) in the range of 0.61–0.88 for the Ross model and 0.63–0.93 for the Faiman model. It was observed that the Ross and Faiman model have high errors when instantaneous data are used but become more accurate when averaged to timesteps of greater than 1000–1500 s. The Faiman model's instantaneous response was independent of the variations in the weather conditions, especially wind speed, due to a lack of thermal capacitance term in the model. This study found that the power and energy yield calculations were minimally affected by the errors in temperature predictions. However, a transient model, which includes the thermal mass of the vehicle and PV modules, is necessary for an accurate instantaneous temperature prediction of PV modules in vehicle‐integrated (VIPV) applications.

Advancing Ionic Liquid Research with pSCNN: A Novel Approach for Accurate Normal Melting Temperature Predictions.

Ionic liquids (ILs), known for their distinct and tunable properties, offer a broad spectrum of potential applications across various fields, including chemistry, materials science, and energy storage. However, practical applications of ILs are often limited by their unfavorable physicochemical properties. Experimental screening becomes impractical due to the vast number of potential IL combinations. Therefore, the development of a robust and efficient model for predicting the IL properties is imperative. As the defining feature, it is of practice significance to establish an accurate yet efficient model to predict the normal melting point of IL (T m), which may facilitate the discovery and design of novel ILs for specific applications. In this study, we presented a pseudo-Siamese convolution neural network (pSCNN) inspired by SCNN and focused on the T m. Utilizing a data set of 3098 ILs, we systematically assess various deep learning models (ANN, pSCNN, and Transformer-CNF), along with molecular descriptors (ECFP fingerprint and Mordred properties), for their performance in predicting the T m of ILs. Remarkably, among the investigated modeling schemes, the pSCNN, coupled with filtered Mordred descriptors, demonstrates superior performance, yielding mean absolute error (MAE) and root-mean-square error (RMSE) values of 24.36 and 31.56 °C, respectively. Feature analysis further highlights the effectiveness of the pSCNN model. Moreover, the pSCNN method, with a pair of inputs, can be extended beyond ionic liquid melting point prediction.

Experimentally validated thermal modeling for temperature prediction of photovoltaic modules under variable environmental conditions

In this work, a detailed analysis and thermal modeling for temperature prediction of a stand-alone photovoltaic module is performed. The study aims to present precise estimation of module temperature, since it is an important parameter for power output calculation. Hence, the required data were collected via experiments. Accounting for all heat transfer mechanisms, and following model validation, a proposed algorithm was implemented to investigate heat transfer from the module to its surrounding and predict different layers’ temperature. Results indicate that accurate energy distribution and temperature prediction was achieved by the adopted thermal model, only about 16% of the received energy is converted to electrical power while the rest is released by heat. Moreover, the proposed simulation algorithm provided one of the best results in comparison to literature models, achieving an R2 of 0.963 and a MAE of 1.883, which is very close to the best overall model by King at R2=0.973 and MAE=1.663. Additionally, two new models for module temperature prediction were proposed. After testing on new data, the explicit model provided a reasonable first approximation attaining an adjusted R2 of 0.97 and a MSE of 3.505, and an accurate implicit model, achieving a MSE of only 1.268.

Absolute heat sources as a method to check the accuracy of temperature prediction in underground structures within cryolithozone

The appearance of the penis is often an important aspect for men, and dissatisfaction with it distorts the perception of their body and makes them seek surgical help.The approach to this problem should be based on the objective needs of patients, assessed after analysis of their requests, anamnesis, emotional background and anatomical features. A non-systematic literature review was conducted using PubMed and Scopus to search for papers on penile aesthetic surgery published in the last 15 years.The main parameters evaluated were changes in penile length and girth, and postoperative complications.

Comparative Study on the Accuracy of Surface Air Temperature Prediction based on selection of land use and initial meteorological data

Comparative Study on the Accuracy of Surface Air Temperature Prediction based on selection of land use and initial meteorological data

Ensemble learning soft sensor method of endpoint carbon content and temperature of BOF based on GCN embedding supervised ensemble clustering

Abstract The endpoint control of Basic Oxygen Furnace (BOF) steelmaking depends on the prediction of the endpoint carbon content and temperature. However, predicting these variables is challenging because of the numerous working conditions in the industrial field and the volatility of the sensor data collected during BOF steelmaking. The accuracy of prediction models in ensemble learning depends significantly on the initial distribution of data. However, the complex nature of BOF steelmaking data makes it challenging to generate diverse subsets, which ultimately affects the accuracy of predictions. This paper presents a new approach called Graph Convolutional Network Node Embedding Supervised Ensemble Clustering (GESupEC) for soft sensor modelling in ensemble learning to tackle these issues. GESupEC utilizes a similarity graph derived from a co-association matrix and employs graph convolutional networks to extract structural information among nodes. By optimising the clustering loss within the network, GESupEC learns compact node representations that are useful for the clustering task. Furthermore, it generates a reconstruction matrix based on the similarity of node embeddings. This matrix helps with the extraction of a suitable subset of data for BOF steelmaking through matrix decomposition. After that, the gradient boosting decision tree regression sub-model is established based on the data subset. An ensemble strategy called Gray Relational Analysis Weighted Average is proposed, which assigns weights based on the grey relation similarity between test samples and different data subsets. This weighted average strategy aims to enhance the accuracy of carbon content and temperature predictions. When tested with actual BOF steelmaking generation process data, the prediction accuracy of carbon content reached 88.6% within the error range of ±0.02%, and the prediction accuracy of temperature reached 92.6% within the error range of ±10 °C.

Lumped Parameter Thermal Network Modeling and Thermal Optimization Design of an Aerial Camera.

The quality of aerial remote sensing imaging is heavily impacted by the thermal distortions in optical cameras caused by temperature fluctuations. This paper introduces a lumped parameter thermal network (LPTN) model for the optical system of aerial cameras, aiming to serve as a guideline for their thermal design. By optimizing the thermal resistances associated with convection and radiation while considering the camera's unique internal architecture, this model endeavors to improve the accuracy of temperature predictions. Additionally, the proposed LPTN framework enables the establishment of a heat leakage network, which offers a detailed examination of heat leakage paths and rates. This analysis offers valuable insights into the thermal performance of the camera, thereby guiding the refinement of heating zones and the development of effective active control strategies. Operating at a total power consumption of 26 W, the thermal system adheres to the low-power limit. Experimental data from thermal tests indicate that the temperatures within the optical system are maintained consistently between 19 °C and 22 °C throughout the flight, with temperature gradients remaining below 3 °C, satisfying the temperature requirements. The proposed LPTN model exhibits swiftness and efficacy in determining thermal characteristics, significantly facilitating the thermal design process and ensuring optimal power allocation for aerial cameras.

Enhanced Thermal Modeling of Electric Vehicle Motors Using a Multihead Attention Mechanism

The rapid advancement of electric vehicles (EVs) accentuates the criticality of efficient thermal management systems for electric motors, which are pivotal for performance, reliability, and longevity. Traditional thermal modeling techniques often struggle with the dynamic and complex nature of EV operations, leading to inaccuracies in temperature prediction and management. This study introduces a novel thermal modeling approach that utilizes a multihead attention mechanism, aiming to significantly enhance the prediction accuracy of motor temperature under varying operational conditions. Through meticulous feature engineering and the deployment of advanced data handling techniques, we developed a model that adeptly navigates the intricacies of temperature fluctuations, thereby contributing to the optimization of EV performance and reliability. Our evaluation using a comprehensive dataset encompassing temperature data from 100 electric vehicles illustrates our model’s superior predictive performance, notably improving temperature prediction accuracy.

Utilizing a CNN-RNN machine learning approach for forecasting time-series outlet fluid temperature monitoring by long-term operation of BHEs system

The Borehole Heat Exchanger (BHE) plays a pivotal role in enhancing heat exchange efficiency within Ground Source Heat Pump (GSHP) systems. The accurate prediction of the BHE's outlet fluid temperature is crucial for optimizing GSHP performance, energy storage, and resource conservation. However, conventional machine learning methods encounter challenges in manual feature extraction, learning complex nonlinear relationships, and adapting to real-world scenarios. To address these limitations, this research proposes a crossbreed model integrating Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) architectures to forecast long-term outlet fluid temperature in BHE systems. The model framework encompasses data preprocessing, utilizing refined data in the CNN module for temporal feature extraction, subsequently passed to the RNN module to capture sequential and temporal patterns from each dataset. Specifically, the advanced CNN-RNN architecture is designed to establish a comprehensive input-output mapping, leveraging essential input features such as inlet fluid, ambient air, and subsurface temperatures at varying depths (0, 10, and 20 m). Performance evaluation metrics, including R2, RMSE, MAE, and AARE, are employed to compare and assess prediction accuracy across various models, including LSTM, CNN, and SimpleRNN. The obtained results demonstrate the superior performance of the proposed model, achieving an RSME of 0.818, MAE of 0.642, AARE of 0.0305, and an R2 value of 98.75 %. This surpasses the performance of traditional prediction models (LSTM, CNN, and SimpleRNN) by 3.01 %, 5.80 %, and 19.52 %, respectively. Notably, the remarkably low MAE of 0.642 exhibited by a CNN-RNN model underscores its capability to outperform traditional approaches, especially when handling large datasets. These findings emphasize the significance of the developed model in facilitating efficient operation, positioning it as a valuable tool for advancing the long-term sustainability of BHE systems.