Dynamic Prediction Model Research Articles

Research on dynamic and wear prediction models of compound planetary transmission systems

Under high speeds and heavy loads, gear tooth surfaces will be worn, which will lead to accidents. The current wear prediction model is not comprehensive, but the wear prediction model that considers the temperature field and dynamic response can provide more accurate gear wear fault early warning than previous methods. Therefore, according to the Archard model, the discrete wear prediction model of the tooth surface is deduced in this paper, and the wear evolution trend of the tooth surface is predicted and analyzed in each operation stage. The tooth surface temperature field was simulated by the finite-element method, and the tooth surface wear prediction model was improved considering its influence on materials. In addition, the dynamic model of the compound planetary transmission system was established, and the wear prediction model was improved again by using its nonlinear meshing force. Finally, the tooth wear prediction model under the interaction of the dynamic response and temperature field was obtained. A wear measurement method based on duplicate adhesive film was proposed. The wear evolution trend along the tooth length direction and the tooth width direction were measured, and the accuracy of the wear prediction model was verified. The results show that the wear depth along the tooth width direction is larger in the middle part and smaller on both sides under the influence of temperature. After the interference of the dynamic response, the wear depth along the tooth rectangle fluctuates, which is very similar to the results of the theoretical prediction model. It provides a theoretical basis for the early warning of gear health status in practical engineering.

Multidimensional effects of history, neighborhood, and proximity on urban land growth: A dynamic spatiotemporal rolling prediction model (STRM)

Multidimensional effects of history, neighborhood, and proximity on urban land growth: A dynamic spatiotemporal rolling prediction model (STRM)

MTdyg: Multi-scale transformers with continuous time dynamic graph model for link prediction

Link prediction through continuous dynamic graph neural networks is a challenging endeavour. Previous studies have considered historic interaction sequences among pairs of nodes. However, this approach does not sufficiently model the links between them. Thus, the frequency of historical common neighbours was proposed to obtain more information about node pairs. Nonetheless, this measure fails to consider the timing of interactions because the relative importance of different interactions shifts over time.Multi-scale transformers with a continuous time dynamic graph model (MTdyg) are our response to this challenge to enhance link prediction. The novel MTdyg model employs a multi-scale patching strategy that dynamically adjusts based on the interaction frequency, feeding segmented interaction sequences into the transformer. This methodology significantly improves the model’s ability to assimilate historical data. Furthermore, we developed a temporal attention-based historical common neighbour encoding technique to effectively identify linkages between source and target nodes in interaction sequences. Extensive testing on eight public datasets confirmed that MTdyg delivers superior performance on most datasets, demonstrating its effectiveness in capturing the nuances of node interactions over time.

Monitoring and Occurrence Prediction of the Migration Population of Helicoverpa armigera (Hübner) Based on Adult Semiochemical Attractants

Helicoverpa armigera (Hübner) is a destructive agricultural pest. Facultative migration usually causes regional catastrophes; therefore, developing a simple and easy new technology for the monitoring and early warning of immigrant populations is urgent. Between 2021 and 2023, we conducted a population-monitoring study on H. armigera immigrants in Xundian County, Yunnan Province, where the migration pathway for pests from southeast Asia extends to southwest China. Based on the differences in the reproductive organ development parameters of H. armigera at different ages, we established an adult age discrimination model. The monitoring results of field populations with semiochemical attractants and sex pheromones between 2021 and 2023 showed that the daily average age of the adult population of H. armigera fluctuated above 6 days, and the trapping dynamics with semiochemical attractants and sex pheromones were the same. Both trapping methods yielded H. armigera males of different ages and had identical age structures, indicating that the H. armigera population primarily migrated from other regions. The trajectory analysis showed that the H. armigera population that migrated to Xundian between May and September was primarily from South Kunming, and after October, it was primarily the southward-migrating population north of Qujing City, Yunnan Province. Based on the relationship between the daily average fecundity and the age of H. armigera, a dynamic prediction model for the fecundity of the immigrant population was established. In this study, the prediction models and methods based on semiochemical attractants could potentially be used in the surveillance and population alerting of H. armigera.

An Optimized Framework Based on Data Exploration and Dynamic Ensemble-Based Models for Breast Cancer Prediction

An Optimized Framework Based on Data Exploration and Dynamic Ensemble-Based Models for Breast Cancer Prediction

An Optimized Framework Based on Data Exploration and Dynamic Ensemble-Based Models for Breast Cancer Prediction

Breast cancer (BC) is a major global health concern. Detecting BC at an early stage gives more treatment options and can help avoid more aggressive treatments. The use of machine learning (ML) in BC prediction offers significant potential for improving the accuracy and speed of diagnosis, personalizing treatment, and identifying high-risk patients. However, there are significant challenges associated with the use of ML, including the need for high-quality data and more flexible models with optimal parameters to achieve high efficiency. In this paper, we propose an optimized framework based on multi-stage data exploration. This framework is designed to provide a comprehensive approach to data exploration, ensuring that the data is well-prepared for ML. In addition, the framework includes dynamic ensemble-based classifiers, which combine multiple independent classifiers to improve accuracy and mitigate the risk of overfitting in conjunction with the cross-validation techniques. These classifiers are optimized using Bayesian hyperparameter tuning, which involves selecting the optimal values for the various hyperparameters of the model. This approach can significantly improve the prediction accuracy of the resulting model. The study evaluates the framework using the publicly available Wisconsin Diagnostic Breast Cancer (WDBC) dataset and compares our results with other state-of-the-art models. The experimental results show that the best result is 100% for accuracy and recall with hyperparameters of (Ensemble Method = AdaBoost, Number of learners = 322, learning rate = 0.9350, and the Maximum number of splits = 1). The highest performance has been achieved with the proposed framework compared with the other models in terms of accuracy (mean = 99.35%, best = 100%, worst = 98.7%, and Standard Deviation = 0.325). The framework can potentially improve the accuracy and efficiency of BC prediction, ultimately leading to better outcomes for patients.

The Serum NLRP1 Level and Coronary Artery Calcification: From Association to Development of a Risk-Prediction Nomogram.

To investigate the correlation between inflammasomes and coronary artery calcification (CAC), and develop and validating a nomogram for predicting the risk of CAC in patients with coronary artery disease (CAD). A total of 626 patients with CAD at the Affiliated Hospital of Xuzhou Medical University were enrolled in this study. The patients were divided into the calcification group and the non-calcification group based on the assessment of coronary calcification. We constructed a training set and a validation set through random assignment. The least absolute shrinkage and selection operator (LASSO) regression and multivariate analysis were performed to identify independent risk factors of CAC in patients with CAD. Based on these independent predictors, we developed a web-based dynamic nomogram prediction model. The area under the receiver operating characteristic curve (AUC-ROC), calibration curves, and decision curve analysis (DCA) were used to evaluate this nomogram. Age, smoking, diabetes mellitus (DM), hyperlipidemia, the serum level of nucleotide-binding oligomerization domain (NOD)-like receptor protein 1 (NLRP1), alkaline phosphatase (ALP) and triglycerides (TG) were identified as independent risk factors of CAC. The AUC-ROC of the nomogram is 0.881 (95% confidence interval (CI): 0.850-0.912) in the training set and 0.825 (95% CI: 0.760-0.876) in the validation set, implying high discriminative ability. Satisfactory performance of this model was confirmed using calibration curves and DCA. The serum NLRP1 level is an independent predictor of CAC. We established a web-based dynamic nomogram, providing a more accurate estimation and comprehensive perspective for predicting the risk of CAC in patients with CAD.

Development and Validation of a Machine Learning Algorithm to Predict the Risk of Blood Transfusion after Total Hip Replacement in Patients with Femoral Neck Fractures: A Multicenter Retrospective Cohort Study.

Total hip arthroplasty (THA) remains the primary treatment option for femoral neck fractures in elderly patients. This study aims to explore the risk factors associated with allogeneic blood transfusion after surgery and to develop a dynamic prediction model to predict post-operative blood transfusion requirements. This will provide more accurate guidance for perioperative humoral management and rational allocation of medical resources. We retrospectively analyzed data from 829 patients who underwent total hip arthroplasty for femoral neck fractures at three third-class hospitals between January 2017 and August 2023. Patient data from one hospital were used for model development, whereas data from the other two hospitals were used for external validation. Logistic regression analysis was used to screen the characteristic subsets related to blood transfusion. Various machine learning algorithms, including logistic regression, SVA (support vector machine), K-NN (k-nearest neighbors), MLP (multilayer perceptron), naive Bayes, decision tree, random forest, and gradient boosting, were used to process the data and construct prediction models. A 10-fold cross-validation algorithm facilitated the comparison of the predictive performance of the models, resulting in the selection of the best-performing model for the development of an open-source computing program. BMI (body mass index), surgical duration, IBL (intraoperative blood loss), anticoagulant history, utilization rate of tranexamic acid, Pre-Hb, and Pre-ALB were included in the model as well as independent risk factors. The average area under curve (AUC) values for each model were as follows: logistic regression (0.98); SVA (0.91); k-NN (0.87) MLP, (0.96); naive Bayes (0.97); decision tree (0.87); random forest (0.96); and gradient boosting (0.97). A web calculator based on the best model is available at: (https://nomo99.shinyapps.io/dynnomapp/). Utilizing a computer algorithm, a prediction model with a high discrimination accuracy (AUC > 0.5) was developed. The logistic regression model demonstrated superior differentiation and reliability, thereby successfully passing external validation. The model's strong generalizability and applicability have significant implications for clinicians, aiding in the identification of patients at high risk for postoperative blood transfusion.

Identification of failure behaviors of underground structures under dynamic loading using machine learning

Understanding the dynamic responses of hard rocks is crucial during deep mining and tunneling activities and when constructing nuclear waste repositories. However, the response of deep massive rocks with openings of different shapes and orientations to dynamic loading is not well understood. Therefore, this study investigates the dynamic responses of hard rocks of deep underground excavation activities. Split Hopkins Pressure Bar (SHPB) tests on granite with holes of different shapes (rectangle, circle, vertical ellipse (elliptical short (ES) axis parallel to the impact load direction), and horizontal ellipse (elliptical long (EL) axis parallel to the impact load direction)) were carried out. The influence of hole shape and location on the dynamic responses was analyzed to reveal the rocks' dynamic strengths and cracking characteristics. We used the ResNet18 (convolutional neural network-based) network to recognize crack types using high-speed photographs. Moreover, a prediction model for the stress-strain response of rocks with different openings was established using Deep Neural Network (DNN). The results show that the dynamic strengths of the granite with EL and ES holes are the highest and lowest, respectively. The strength-weakening coefficient decreases first and then increases with an increase of thickness-span ratio (h/L). The weakening of the granite with ES holes is the most obvious. The ResNet18 network can improve the analyzing efficiency of the cracking mechanism, and the trained model's recognition accuracy reaches 99%. Finally, the dynamic stress-strain prediction model can predict the complete stress-strain curve well, with an accuracy above 85%.

Aero-engine direct thrust control based on nonlinear model predictive control with composite predictive model

Abstract A novel NMPC (Nonlinear Model Predictive Control) based on composite predictive model is proposed and applied to direct engine thrust control. To improve the real-time of NMPC, an adaptive composite model based on SVM (State Variable Model), KF (Kalman Filter), and CLM (Component Level Model) is proposed as predictive model. The correction theory is adopted to establish a full envelope adaptive on-board predictive dynamic model and reduce the data storage of predictive model. At each sampling time, the CLM is calculated only once in the proposed NMPC, instead of many times in the popular NMPC based on EKF (extended Kalman filler). Therefore, the proposed NMPC has better real-time performance than the popular one. The simulations that consist of the proposed NMPC, the popular NMPC based on EKF, and the traditional controller PID are conducted. The simulations demonstrate that the proposed NMPC not only has greatly better real time performance than popular NMPC, but also has faster response speed than traditional controller PID.

A dynamic prediction model for preeclampsia using the sFlt-1/PLGF ratio combined with multiple factors

ObjectivePreeclampsia (PE) is a pregnancy-related multi-organ disease and a significant cause of incidence rate and mortality of pregnant women and newborns worldwide. Delivery remains the only available treatment for PE. This study aims to establish a dynamic prediction model for PE.MethodsA total of 737 patients who visited our hospital from January 2021 to June 2022 were identified according to the inclusion and exclusion criteria, forming the primary dataset. Additionally, 176 singleton pregnant women who visited our hospital from July 2022 to November 2022 comprised the verification set. We investigated different gestational weeks of sFlt-1/PLGF (soluble FMS-like tyrosine kinase-1, placental growth factor) ratio combined with maternal characteristics and routine prenatal laboratory results in order to predict PE in each trimester. Multivariate logistic regression was used to establish the prediction model for PE at different gestational weeks. The discrimination, calibration, and clinical validity were utilized to evaluate predictive models as well as models in external validation queues.ResultsAt 20–24 weeks, the obtained prediction model for PE yielded an area under the curve of 0.568 (95% confidence interval, 0.479–0.657). At 25–29 weeks, the obtained prediction model for PE yielded an area under the curve of 0.773 (95% confidence interval, 0.703–0.842)and 0.731 (95% confidence interval, 0.653–0.809) at 30–34 weeks. After adding maternal factors, uterine artery pulsation index(Ut-IP), and other laboratory indicators to the sFlt-1/PLGF ratio, the predicted performance of PE improved. It found that the AUC improved to 0.826(95% confidence interval, 0.748 ∼ 0.904) at 20–24 weeks, 0.879 (95% confidence interval, 0.823 ∼ 0.935) at 25–29 weeks, and 0.862(95% confidence interval, 0.799 ∼ 0.925) at 30–34 weeks.The calibration plot of the prediction model indicates good predictive accuracy between the predicted probability of PE and the observed probability. Furthermore, decision-curve analysis showed an excellent clinical application value of the models.ConclusionUsing the sFlt-1/PLGF ratio combined with multiple factors at 25–29 weeks can effectively predict PE, but the significance of re-examination in late pregnancy is not significant.

Dynamic Prediction of Overall Survival for Patients with Osteosarcoma: A Retrospective Analysis of the EURAMOS-1 Clinical Trial Data.

Current prediction models for patients with ostosarcoma are restricted to predictions from a single, static point in time, such as diagnosis or surgery. These approaches discard information which becomes available during follow-up and may have an impact on patient's prognosis. This study aims at developing a dynamic prediction model providing 5-year overall survival (OS) predictions from different time points during follow-up. The developed model considers relevant baseline prognostic factors, accounting for where appropriate time-varying effects and time-varying intermediate events such as local recurrence (LR) and new metastatic disease (NM). A landmarking approach is applied to 1965 patients with high-grade resectable osteosarcoma from the EURAMOS-1 trial (NCT00143030). Results show that LR and NM negatively affected 5-year OS (HRs: 2.634, 95% CI 1.845-3.761; 8.558, 95% CI 7.367-9.942, respectively). Baseline factors with strong prognostic value (HRs > 2) included poor histological response (≥10% viable tumor), axial tumor location, and the presence of lung metastases. The effect of poor versus good histological response changed over time, becoming non-significant from 3.25 years post-surgery onwards. This time-varying effect, as well as the strong impact of disease-related time-varying variables, show the importance of including updated information collected during follow-up in the model to provide more accurate survival predictions.

Data-driven and knowledge-guided denoising diffusion probabilistic model for runoff uncertainty prediction

The existing medium and long-term runoff prediction methods, which are based on data-driven and knowledge-guided methods, are associated with inherent limitations, and chaotic phenomena in runoff prediction models often leads to oscillation in the prediction error, affecting the robustness of the prediction. A knowledge-guided denoising diffusion probabilistic model (DK-RDDPM) that introduces physical theory to guide constraint quantification and obtain effective runoff uncertainty prediction results is therefore proposed in this study. The main advantage of this model is that the physical randomness in the runoff prediction process can be captured and combined with the Saint-Venant process to guide model optimization and realize more accurate medium- and long-term runoff prediction. The main contributions of this study are the establishment of a dynamic runoff probabilistic prediction model with stochastic quantification characteristics that includes the prediction uncertainty over time, and modelling of the physical constraint boundary of runoff prediction from the perspective of partial differentiation. The effectiveness of the DK-RDDPM was verified by predicting runoff in the Qijiang and Tunxi Basins in China. The results show that: 1) Encoding the physical random uncertainty operator in runoff prediction into the network of the denoising diffusion probabilistic model (DDPM) effectively captures the physically complex implicit randomness of the process, thus reducing the error that results from randomness in runoff prediction. 2) The constraint matrix that is formed using the Saint-Venant equation and the prediction matrix are layered and projected, with the fluctuation range of the constraints in each step adjusted in the optimization direction within a certain random threshold range. 3) The DK-RDDPM shows superior performance to the benchmark models, even under the influence of different noise interference factors.

Modeling, prediction and analysis of natural gas consumption in China using a novel dynamic nonlinear multivariable grey delay model

Accurately predicting natural gas consumption is essential for developing a clean, low-carbon, safe, and efficient energy system. Therefore, this paper integrates the idea of the extended logistic model into multivariable grey prediction theory. Considering the delay effect and nonlinear characteristics of the system, a novel dynamic nonlinear multivariate grey delay prediction model is constructed. Meanwhile, the algorithmic framework for solving the parameters of the new model is provided to identify and optimize the parameters of the time-delay effect of the model. The genetic algorithm was identified as the best matching optimization algorithm for the new model. Furthermore, the new model is applied to fitting and forecasting China's natural gas consumption, and the validity of the model is fully verified. Compared with other forecasting models, the new model has a lower average relative error in the fitting and forecasting stage, and, in particular, achieves a better forecasting effect with the lowest MAPEpre value (0.001 % for one-step ahead, 0.005 % for two-step ahead, and 0.746 % for three-step ahead). Moreover, the model is employed to forecast China's natural gas consumption for the next five years, providing a robust foundation for government policies related to the supply of natural gas.

Online interpretable dynamic prediction models for clinically significant posthepatectomy liver failure based on machine learning algorithms: A retrospective cohort study.

Posthepatectomy liver failure (PHLF) is the leading cause of mortality in patients undergoing hepatectomy. However, practical models for accurately predicting the risk of PHLF are lacking. This study aimed to develop precise prediction models for clinically significant PHLF. A total of 226 patients undergoing hepatectomy at a single center were recruited. The study outcome was clinically significant PHLF. Five pre- and postoperative machine learning (ML) models were developed and compared with four clinical scores, namely, the MELD, FIB-4, ALBI, and APRI scores. The robustness of the developed ML models was internally validated using 5-fold cross-validation by calculating the average of the evaluation metrics and was externally validated on an independent temporal dataset, including the area under the curve (AUC) and the area under the precision‒recall curve (AUPRC). SHapley Additive exPlanations analysis was performed to interpret the best performance model. Clinically significant PHLF was observed in 23 of 226 patients (10.2%). The variables in the preoperative model included creatinine, total bilirubin, and Child‒Pugh grade. In addition to the above factors, the extent of resection was also a key variable for the postoperative model. The pre- and postoperative artificial neural network (ANN) models exhibited excellent performance, with mean AUCs of 0.766 and 0.851, respectively, and mean AUPRC values of 0.441 and 0.645, whereas the MELD, FIB-4, ALBI, and APRI scores reached AUCs of 0.714, 0.498, 0.536 and 0.551, respectively, and AUPRC values of 0.204, 0.111, 0.128 and 0.163, respectively. In addition, the AUCs of the pre- and postoperative ANN models were 0.720 and 0.731, respectively, and the AUPRC values were 0.380 and 0.408, respectively, on the temporal dataset. Our online interpretable dynamic ML models outperformed common clinical scores and could function as a clinical decision support tool to identify patients at high risk of PHLF pre- and postoperatively.

New online dynamic nomograms to predict recurrence-free and overall survival after resection of endometrial cancer: a single-institution retrospective cohort study

PurposeThe significant global burden of endometrial cancer (EC) and the challenges associated with predicting EC recurrence indicate the need for a dynamic prediction model. This study aimed to propose nomograms based on clinicopathological variables to predict recurrence-free survival (RFS) and overall survival (OS) after surgical resection for EC.MethodsThis single-institution retrospective cohort study included patients who underwent surgical resection for EC. Web-based nomograms were developed to predict RFS and OS following resection for EC, and their discriminative and calibration abilities were assessed.ResultsThis study included 289 patients (median age, 56 years). At a median follow-up of 51.1 (range, 4.1–128.3) months, 13.5% (39/289) of patients showed relapse or died, and 10.7% (31/289) had non-endometrioid tumors (median size: 2.8 cm). Positive peritoneal cytology result (hazard ratio [HR], 35.06; 95% confidence interval [CI], 1.12–1095.64; P = 0.0428), age-adjusted Charlson comorbidity index (AACCI) (HR, 52.08; 95% CI, 12.35–219.61; P < 0.001), and FIGO (Federation of Gynecology and Obstetrics) stage IV (HR, 138.33; 95% CI, 17.38–1101.05; P < 0.001) were predictors of RFS. Similarly, depth of myometrial invasion ≥ 1/2 (HR, 1; 95% CI, 0.46–2.19; P = 0.995), AACCI (HR, 93.63; 95% CI, 14.87–589.44; P < 0.001), and FIGO stage IV (HR, 608.26; 95% CI, 73.41–5039.66; P < 0.001) were predictors of OS. The nomograms showed good predictive capability, positive discriminative ability, and calibration (RFS: 0.895 and OS: 0.891).ConclusionThe nomograms performed well in internal validation when patients were stratified into prognostic groups, offering a personalized approach for risk stratification and treatment decision-making.

Strong El Niño Events Lead to Robust Multi‐Year ENSO Predictability

AbstractThe El Niño‐Southern Oscillation (ENSO) phenomenon—the dominant source of climate variability on seasonal to multi‐year timescales—is predictable a few seasons in advance. Forecast skill at longer multi‐year timescales has been found in a few models and forecast systems, but the robustness of this predictability across models has not been firmly established owing to the cost of running dynamical model predictions at longer lead times. In this study, we use a massive collection of multi‐model hindcasts performed using model analogs to show that multi‐year ENSO predictability is robust across models and arises predominantly due to skillful prediction of multi‐year La Nina events following strong El Niño events.

Assessment of two approaches for very short range precipitation prediction for a convection-dominant period at different scales

Extreme precipitation plays a crucial role in managing weather-related risks, particularly flooding, and has a significant impact on various sectors such as hydrology, agriculture, and economy. It is important to evaluate precipitation forecast outputs to help refining prediction models, especially for heavy events. This study examines the performance of two weather models, both designed to provide frequently updated forecasts for a short time range, but using different approaches: extrapolation-based and fully dynamical 3D numerical weather prediction (NWP) models. These models are assessed over a two-month period with several heavy thunderstorms, using data from Austria and a smaller catchment in southeast Austria. We addressed the errors and uncertainties in these models using different verification metrics and two different observational datasets. In general, both models performed well in the first hour of the forecast at both large and small scales. However, performance decreased with lead time after the first hour, with a faster decline in the extrapolation-based model. The performance of the models changed when considering different precipitation thresholds. For higher thresholds (heavier precipitation), the NWP model performed better than the extrapolation-based model, whereas it performed worse for lower thresholds. When using the object-oriented Structure Amplitude Location (SAL) metric, the dynamical NWP model performed better regarding the structure of precipitation, while the extrapolated-based model had a better performance when considering the amplitude parameter, i.e., the total amount of precipitation. With a lower error in the first hours of each run, the dynamical NWP model showed that an hourly update cycle helps to reduce the forecast errors noticeably. The results highlight the need of considering forecast model performance at different intensity thresholds and spatial scales.

A dynamic response prediction of ultra-high strain rates of composite materials based on a surrogate model

Based on the propagation of laser-induced tensile waves in materials and the principle of material ply cracking, nondestructive testing technology for measuring the interfacial bonding force of composite materials can be developed. The study of the ultra-high strain rate dynamic response model of composite materials under the action of laser shock waves is crucial to this technique. Therefore, this paper proposes a method for constructing a dynamic response prediction model for composites based on data and a physical model driven by comprehensively considering the strain rate effect of materials. The constructed model can accurately predict the peak velocity and duration of the initial pulse of the velocity curve under the condition of ultra-high strain rate. The relative error between the predicted and simulated peak values is within 3%, and the relative error between the predicted and simulated initial pulse durations is within 5%. In addition, laser impact experiments were conducted on specimens of various thicknesses to validate the accuracy of the predicted data at ultra-high strain rates. The results show that the relative errors between the predicted and experimental peak values are all within 2%, and the relative errors of the initial pulse duration are within 9%.

InSAR-CTPIM-Based 3D Deformation Prediction in Coal Mining Areas of the Baisha Reservoir, China

Time series dynamic prediction of surface deformation in mining areas can provide reference data for coal mine safety and production, which has important impacts. The combination of interferometric synthetic aperture radar (InSAR) technology and the probability integral method (PIM) is commonly used for predicting deformation. However, most surface subsidence prediction in mining areas is based on the static PIM parameters, failing to achieve the three-dimensional (3D) dynamic deformation prediction. This paper proposed a 3D deformation dynamic prediction model (InSAR-3D-CTPIM) between InSAR deformation observations and dynamic coordinate-time PIM (CTPIM) parameters, which can realize the prediction of east–west, north–south, and vertical series deformation caused by mining. The method has been validated by simulation experiments and real experiments in the mining area of Jiansheng Coal Mine in Baisha Reservoir, Henan Province, China. The results showed that the modeling accuracy was improved by 34.3% compared to the traditional multi-rate model, and the accuracy was improved by 28.5% compared to the vertical deformation obtained by the traditional static PIM method. The InSAR-3D-CTPIM model can be used to predict the evolutionary history of basin-wide surface deformation dynamics in coal mining areas, and provide a reference for the early warning and prediction of geological hazards in coal mining areas.