Robust Prediction Research Articles

Understanding EMS response times: a machine learning-based analysis

BackgroundEmergency Medical Services (EMS) response times are critical for optimizing patient outcomes, particularly in time-sensitive emergencies. This study explores the multifaceted determinants of EMS response times, leveraging machine learning (ML) techniques to identify key factors such as urgency levels, environmental conditions, and geographic variables. The findings aim to inform strategies for enhancing resource allocation and operational efficiency in EMS systems.MethodsA retrospective analysis was conducted using over one million EMS missions from Stockholm, Sweden, between 2017 and 2022. Advanced ML techniques, including Gradient Boosting models, were applied to evaluate the influence of diverse variables such as call handling times, travel times, weather patterns, and resource availability. Feature engineering was employed to extract meaningful insights, and statistical models were used to validate the relationships between key predictors and response times.ResultsThe study revealed a complex interplay of factors influencing EMS response times, aligning with the study’s aim to deepen the understanding of these determinants. Key drivers of response time variability included weather conditions, call priority, and resource constraints. ML models, particularly Gradient Boosting, proved effective in quantifying these impacts and provided robust predictions of response times across scenarios. By providing a comprehensive evaluation of these influences, the results support the development of adaptive resource allocation models and evidence-based policies aimed at enhancing EMS efficiency and equity across all call priorities.ConclusionsThis study underscores the potential of ML-driven insights to revolutionize EMS resource allocation strategies. By integrating real-time data on weather, call types, and workload, EMS systems can transition to adaptive deployment models, reducing response times and enhancing equity across priority levels. The research provides a blueprint for implementing predictive analytics in EMS operations, paving the way for evidence-based policies that improve emergency care efficiency and outcomes.Clinical trial numberNot applicable.

Primary and Low-Strain Creep Models for 9Cr Tempered Martensitic Steels Including the Effects of Irradiation Softening and High-Helium Re-Hardening

Primary and low-strain creep represents a very important integrity challenge to large, complex structures, like fusion reactors. Here, we develop a predictive empirical primary creep model for 9Cr tempered martensitic steels (TMS), relating the applied stress (σ) to strain (ε), time (t) and temperature (T). The most accurate model is based on the applied σ normalized by the steel’s T-dependent ultimate tensile stress (σo), σ/σo(T). The model, fit to 17 heats of 9Cr TMS, yielded a σ root mean square error (RMSE) of ≈±11 MPa. Notably, the model also provides robust predictions for all the other TMS, when calibrated only by the fusion candidate Eurofer97 database. The model was extended to explore two possible effects of neutron irradiation, which produces both displacements per atom (dpa) and helium (He in atomic parts per million, appm) damage. These effects, which have not been previously considered, include: (a) softening, as a function of dpa, at T > ≈400–450 °C, in low-He fission environments (<1 He/dpa); and (b) subsequent re-hardening in high-He (≥10 He/dpa) fusion first-wall environments. The irradiation effect models predict (a) accelerated primary creep due to irradiation softening; and (b) fully arrested creep due to high-He re-hardening.

Toward Reliable Post-Disaster Assessment: Advancing Building Damage Detection Using You Only Look Once Convolutional Neural Network and Satellite Imagery

Natural disasters continuously threaten populations worldwide, with hydrometeorological events standing out due to their unpredictability, rapid onset, and significant destructive capacity. However, developing countries often face severe budgetary constraints and rely heavily on international support, limiting their ability to implement optimal disaster response strategies. This study addresses these challenges by developing and implementing YOLOv8-based deep learning models trained on high-resolution satellite imagery from the Maxar GeoEye-1 satellite. Unlike prior studies, we introduce a manually labeled dataset, consisting of 1400 undamaged and 1200 damaged buildings, derived from pre- and post-Hurricane Maria imagery. This dataset has been publicly released, providing a benchmark for future disaster assessment research. Additionally, we conduct a systematic evaluation of optimization strategies, comparing SGD with momentum, RMSProp, Adam, AdaMax, NAdam, and AdamW. Our results demonstrate that SGD with momentum outperforms Adam-based optimizers in training stability, convergence speed, and reliability across higher confidence thresholds, leading to more robust and consistent disaster damage predictions. To enhance usability, we propose deploying the trained model via a REST API, enabling real-time damage assessment with minimal computational resources, making it a low-cost, scalable tool for government agencies and humanitarian organizations. These findings contribute to machine learning-based disaster response, offering an efficient, cost-effective framework for large-scale damage assessment and reinforcing the importance of model selection, hyperparameter tuning, and optimization functions in critical real-world applications.

PSE-Based Aerodynamic Flow Transition Prediction Using Automated Unstructured CFD Integration

The accurate, robust, and efficient prediction of transition in viscous flows is a significant challenge in computational fluid dynamics. We present a coupled high-fidelity iterative approach that leverages the FUN3D flow solver and the LASTRAC stability code to predict transition in low-disturbance environments, initiated by the linear growth of boundary-layer instability modes. Our method integrates the ability of FUN3D to compute mixed laminar–transitional–turbulent mean flows via transition-sensitized Reynolds-Averaged Navier–Stokes equations with the ability of LASTRAC to perform linear stability analysis, all within an automated framework that requires no intermediate user involvement. Unlike conventional frameworks that rely on classical stability theory or reduced-order metamodels, our approach employs parabolized stability equations to provide more accurate and reliable estimates of disturbance growth for multiple instability mechanisms, including Tollmien–Schlichting, Kelvin–Helmholtz, and crossflow modes. By accounting for the effects of mean-flow nonparallelism as well as the surface curvature, this approach lays the foundation for improved N-factor correlations for transition onset prediction in a broad class of flows. We apply this method to three distinct flow configurations: (1) flow over a zero-pressure-gradient flat plate, (2) the NLF-0416 airfoil with both natural and separation-induced transition, and (3) a 6:1 prolate spheroid, where transition is primarily driven by crossflow instability. For two-dimensional cases, a formulated intermittency distribution is used to model the transition zone between the laminar and fully turbulent flows. The results include comparisons with experimental measurements, similar numerical approaches, and transport-equation-based models, demonstrating good agreement in surface pressure coefficients, transition onset locations, and skin-friction coefficients for all three configurations. In addition to contributing a couple of new insights into boundary-layer transition in these canonical cases, this study presents a powerful tool for transition modeling in both research and design applications in aerodynamics.

Pattern Recognition-Driven Detection of Circadian-Disruptive Compounds from Gene Expressions: High-Throughput Screening and Experimental Verification.

Circadian rhythms regulate the timing of numerous biological functions in organisms. Besides well-known external stimuli like the light-dark cycle and temperature, circadian rhythms can also be modulated by environmental substances. However, this area remains largely underexplored. Here, we developed a robust Pattern Recognition-Driven Prediction Approach (PRD-PA) that enables the identification of circadian-disruptive compounds from large-scale zebrafish transcriptomic profiling. The approach utilizes a circadian gene panel consisting of over 270 Circadian-Indicating Genes (CIGs) with stable and robust periodicity and combines it with a predictive model, known as the Differential Gene Expression Values of an Individual Comparison Model (DGVICM), that can effectively predict internal circadian phases from transcriptomic samples. By analyzing 692 aggregated gene expression profiles across 40 environmental substances, several were identified as having significant circadian-disruptive potential. These include glucocorticoids (e.g., prednisone (PRE) and triamcinolone (TRI)), the antithyroid agent propylthiouracil (PTU), and the widely used UV filter benzophenone-3 (BP-3). Both glucocorticoids and PTU are well-documented disruptors of circadian rhythms, and BP-3's circadian-disrupting properties were validated through experimental exposures. Moreover, BP-3 analogs, including 2,4-dihydroxybenzophenone (BP-1) and 2,2'-dihydroxy-4-methoxybenzophenone (BP-8), were also found to exhibit similar circadian-disruptive effects. Overall, the present findings demonstrated the reliability of the PRD-PA approach for circadian disruption screening and highlighted the presence of diverse circadian-disruptive substances in our environment.

CancerFusionPrompt: A Novel Framework for Multimodal Cancer Subtype Classification Using Vision‐Language Model

ABSTRACTBackgroundCancer subtype classification plays a pivotal role in personalised medicine, requiring the integration of diverse data types. Traditional prompting methods in vision‐language models fail to fully leverage multimodal data, particularly when working with minimal labelled data.MethodsTo address these limitations, we propose a novel framework that introduces the CancerFusionPrompt, a specialised prompting method for integrating imaging and multi‐omics data. Our proposed approach extends the few‐shot learning paradigm by incorporating in‐context learning for cancer subtype classification.ResultsThe proposed method significantly outperforms state‐of‐the‐art techniques in cancer subtype classification, achieving notable improvements in both accuracy and generalisation. These results demonstrate the superior capability of CancerFusionPrompt in handling complex multimodal inputs compared to existing prompting methods.ConclusionsThe CancerFusionPrompt framework offers a powerful solution for integrating multimodal data in cancer subtype classification tasks. By overcoming the limitations of current prompting methods, CancerFusionPrompt approach enables more accurate and robust predictions with minimal labelled data.

Deep Learning Fusion for Student Academic Prediction Using ARLMN Ensemble Model

The realization of accurate student performance prognostication within the educational domain presents a critical capability for the timely implementation of intervention strategies and supplementary support mechanisms. This research proposes the Adaptive Recurrent Logistic Memory Network (ARLMN), an innovative approach for student academic prediction. The ARLMN combines Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM) network, and Sigmoid Plus - Adaptive Activation Function(S-AAF). The integrated system achieves an impressive accuracy of approximately 98%. By incorporating these methodologies, this model captures temporal dependencies and patterns in student data, including academic, demographic, and emotional information. Pre-processing involves standardizing features before feeding them into the RNN and LSTM models, which are then combined using S-AAF classifier for robust predictions. Experimental results demonstrate the effectiveness of this approach, achieving high accuracy in forecasting student academic performance. By identifying factors that impact performance, this model empowers educators to proactively intervene and ensure student success.

Hybrid Physics-Infused Deep Learning for Enhanced Real-Time Prediction of Human Upper Limb Movements in Collaborative Robotics

Human–robot collaboration is crucial in various industries, making accurate prediction of human arm movements essential for seamless interaction. This paper presents a significant advancement in collaborative robotics by developing a hybrid model that enhances the accuracy and interpretability of human motion predictions. By integrating a Physics-Infused Model with Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) networks, our approach effectively captures intricate temporal dependencies while incorporating physical constraints, leading to more robust and realistic predictions. The hybrid model was successfully implemented on an ABB IRB 120 robot, demonstrating its practical applicability in real-world scenarios. Our results show that this model outperforms conventional methods, particularly in predicting human arm positions during collaborative tasks. The key contribution of this work lies in the integration of deep learning with physics-based principles, setting a new benchmark for predictive accuracy in human–robot collaboration. This research not only enhances the performance of collaborative robots but also opens the door for similar hybrid models to be applied in other fields where accurate motion prediction is critical.

Deep learning approaches for robust prediction of large-scale renewable energy generation: A comprehensive comparative study from a national context

Precise forecasting of renewable energy generation is crucial for ensuring grid stability and enhancing the efficiency of energy management systems. This research develops and rigorously evaluates a range of deep learning models—such as Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRUs), and Bidirectional LSTM (BiLSTM) architectures—for predicting solar, wind, and total renewable energy production at a national scale. These models are systematically benchmarked against traditional machine learning approaches and gradient boosting methods to determine their predictive capabilities. The findings demonstrate that deep learning models incorporating memory mechanisms consistently surpass conventional methods, with BiLSTM standing out as the most precise and dependable model. Furthermore, the study investigates fully connected artificial neural networks (ANNs) and ConvLSTM2D models, reinforcing the advantages of memory-based architectures in modeling temporal relationships. By introducing a robust deep learning framework for large-scale renewable energy forecasting, this research represents a considerable leap forward compared to traditional machine learning techniques. The results highlight the transformative potential of deep learning in improving forecasting accuracy, thereby facilitating more effective energy planning and the smooth integration of renewable energy into national power grids.

Similarity-Informed Matrix Completion Method for Predicting Activity Coefficients.

Accurate prediction of thermodynamic properties of mixtures, such as activity coefficients, is essential for designing and optimizing chemical processes. While established physics-based methods face limitations in prediction accuracy and scope, emerging machine learning approaches, such as matrix completion methods (MCMs), offer promising alternatives. However, their performance can suffer in data-sparse regions. To address this issue, we propose a novel hybrid MCM for predicting activity coefficients at infinite dilution at 298 K that not only uses experimental training data but also includes synthetic training data from two sources: predictions obtained from the physics-based modified UNIFAC (Dortmund) and from a similarity-based approach developed in previous work. The resulting hybrid method combines the broad applicability of MCMs with the precision of the similarity-based approach, resulting in a more robust prediction framework that excels even in regions with limited data. Additionally, our analysis provides valuable insights into how different types of training data affect the prediction accuracy. When experimental data are sparse, incorporating synthetic training data from modified UNIFAC (Dortmund) and the similarity-based approach significantly improves the performance of the MCMs. Conversely, even with abundant experimental data, high accuracy is achieved only if the training set includes mixtures similar to those of interest.

Data-Driven Modeling and Design of Sustainable High Tg Polymers

This paper develops a machine learning methodology for the rapid and robust prediction of the glass transition temperature (Tg) for polymers for the targeted application of sustainable high-temperature polymers. The machine learning framework combines multiple techniques to develop a feature set encompassing all relative aspects of polymer chemistry, to extract and explain correlations between features and Tg, and to develop and apply a high-throughput predictive model. In this work, we identify aspects of the chemistry that most impact Tg, including a parameter related to rotational degrees of freedom and a backbone index based on a steric hindrance parameter. Building on this scientific understanding, models are developed on different types of data to ensure robustness, and experimental validation is obtained through the testing of new polymer chemistry with remarkable Tg. The ability of our model to predict Tg shows that the relevant information is contained within the topological descriptors, while the requirement of non-linear manifold transformation of the data also shows that the relationships are complex and cannot be captured through traditional regression approaches. Building on the scientific understanding obtained from the correlation analyses, coupled with the model performance, it is shown that the rigidity and interaction dynamics of the polymer structure are key to tuning for achieving targeted performance. This work has implications for future rapid optimization of chemistries

Proteomic Learning of Gamma-Aminobutyric Acid (GABA) Receptor-Mediated Anesthesia.

Anesthetics are crucial in surgical procedures and therapeutic interventions, but they come with side effects and varying levels of effectiveness, calling for novel anesthetic agents that offer more precise and controllable effects. Targeting Gamma-aminobutyric acid (GABA) receptors, the primary inhibitory receptors in the central nervous system, could enhance their inhibitory action, potentially reducing side effects while improving the potency of anesthetics. In this study, we introduce a proteomic learning of GABA receptor-mediated anesthesia based on 24 GABA receptor subtypes by considering over 4000 proteins in protein-protein interaction (PPI) networks and over 1.5 millions known binding compounds. We develop a corresponding drug-target interaction network to identify potential lead compounds for novel anesthetic design. To ensure robust proteomic learning predictions, we curated a data set comprising 136 targets from a pool of 980 targets within the PPI networks. We employed three machine learning algorithms, integrating advanced natural language processing (NLP) models such as pretrained transformers and autoencoder embeddings. Through a comprehensive screening process, we evaluated the side effects and repurposing potential of over 180,000 drug candidates targeting the GABRA5 receptor. Additionally, we assessed the ADMET (absorption, distribution, metabolism, excretion, and toxicity) properties of these candidates to identify those with near-optimal characteristics. This approach also involved optimizing the structures of existing anesthetics. Our work presents an innovative strategy for the development of new anesthetic drugs, optimization of anesthetic use, and a deeper understanding of potential anesthesia-related side effects.

Machine learning-based prediction reveals kinase MAP4K4 regulates neutrophil differentiation through phosphorylating apoptosis-related proteins.

Neutrophils, an essential innate immune cell type with a short lifespan, rely on continuous replenishment from bone marrow (BM) precursors. Although it is established that neutrophils are derived from the granulocyte-macrophage progenitor (GMP), the molecular regulators involved in the differentiation process remain poorly understood. Here we developed a random forest-based machine-learning pipeline, NeuRGI (Neutrophil Regulatory Gene Identifier), which utilized Positive-Unlabeled Learning (PU-learning) and neural network-based in silico gene knockout to identify neutrophil regulators. We interrogated features including gene expression dynamics, physiological characteristics, pathological relatedness, and gene conservation for the model training. Our identified pipeline leads to identifying Mitogen-Activated Protein Kinase-4 (MAP4K4) as a novel neutrophil differentiation regulator. The loss of MAP4K4 in hematopoietic stem cells and progenitors in mice induced neutropenia and impeded the differentiation of neutrophils in the bone marrow. By modulating the phosphorylation level of proteins involved in cell apoptosis, such as STAT5A, MAP4K4 delicately regulates cell apoptosis during the process of neutrophil differentiation. Our work presents a novel regulatory mechanism in neutrophil differentiation and provides a robust prediction model that can be applied to other cellular differentiation processes.

DTIAM: a unified framework for predicting drug-target interactions, binding affinities and drug mechanisms

Accurate and robust prediction of drug-target interactions (DTIs) plays a vital role in drug discovery but remains challenging due to limited labeled data, cold start problems, and insufficient understanding of mechanisms of action (MoA). Distinguishing activation and inhibition mechanisms is particularly critical in clinical applications. Here, we propose DTIAM, a unified framework for predicting interactions, binding affinities, and activation/inhibition mechanisms between drugs and targets. DTIAM learns drug and target representations from large amounts of label-free data through self-supervised pre-training, which accurately extracts their substructure and contextual information, and thus benefits the downstream prediction based on these representations. DTIAM achieves substantial performance improvement over other state-of-the-art methods in all tasks, particularly in the cold start scenario. Moreover, independent validation demonstrates the strong generalization ability of DTIAM. All these results suggest that DTIAM can provide a practically useful tool for predicting novel DTIs and further distinguishing the MoA of candidate drugs.

Risk factors and a predictive model of diabetic foot in hospitalized patients with type 2 diabetes.

The risk factors and prediction models for diabetic foot (DF) remain incompletely understood, with several potential factors still requiring in-depth investigations. To identify risk factors for new-onset DF and develop a robust prediction model for hospitalized patients with type 2 diabetes. We included 6301 hospitalized patients with type 2 diabetes from January 2016 to December 2021. A univariate Cox model and least absolute shrinkage and selection operator analyses were applied to select the appropriate predictors. Nonlinear associations between continuous variables and the risk of DF were explored using restricted cubic spline functions. The Cox model was further employed to evaluate the impact of risk factors on DF. The area under the curve (AUC) was measured to evaluate the accuracy of the prediction model. Seventy-five diabetic inpatients experienced DF. The incidence density of DF was 4.5/1000 person-years. A long duration of diabetes, lower extremity arterial disease, lower serum albumin, fasting plasma glucose (FPG), and diabetic nephropathy were independently associated with DF. Among these risk factors, the serum albumin concentration was inversely associated with DF, with a hazard ratio (HR) and 95% confidence interval (CI) of 0.91 (0.88-0.95) (P < 0.001). Additionally, a U-shaped nonlinear relationship was observed between the FPG level and DF. After adjusting for other variables, the HRs and 95%CI for FPG < 4.4 mmol/L and ≥ 7.0 mmol/L were 3.99 (1.55-10.25) (P = 0.004) and 3.12 (1.66-5.87) (P < 0.001), respectively, which was greater than the mid-range level (4.4-6.9 mmol/L). The AUC for predicting DF over 3 years was 0.797. FPG demonstrated a U-shaped relationship with DF. Serum albumin levels were negatively associated with DF. The prediction nomogram model of DF showed good discrimination ability using diabetes duration, lower extremity arterial disease, serum albumin, FPG, and diabetic nephropathy (Clinicaltrial.gov NCT05519163).

Forecasting dengue across Brazil with LSTM neural networks and SHAP-driven lagged climate and spatial effects

BackgroundDengue fever is a mosquito-borne viral disease that poses significant health risks and socioeconomic challenges in Brazil, necessitating accurate forecasting across its 27 federal states. With the country’s diverse climate and geographical spread, effective dengue prediction requires models that can account for both climate variations and spatial dynamics. This study addresses these needs by using Long Short-Term Memory (LSTM) neural networks enhanced with SHapley Additive exPlanations (SHAP) integrating optimal lagged climate variables and spatial influence from neighboring states.MethodAn LSTM-based model was developed to forecast dengue cases across Brazil’s 27 federal states, incorporating a comprehensive set of climate and spatial variables. SHAP was used to identify and select the most important lagged climate predictors. Additionally, lagged dengue cases from neighboring states were included to capture spatial dependencies. Model performance was evaluated using MAE, MAPE, and CRPS, with comparisons to baseline models.ResultsThe LSTM-Climate-Spatial model consistently demonstrated superior performance, effectively integrating temporal, climatic, and spatial information to capture the complex dynamics of dengue transmission. SHAP-enhanced variable selection improved accuracy by focusing on key drivers such as temperature, precipitation and humidity. The inclusion of spatial effects further strengthened forecasts in highly connected states showcasing the model’s adaptability and robustness.ConclusionThis study presents a scalable and robust framework for dengue forecasting across Brazil, effectively integrating temporal, climatic, and spatial information into an LSTM-based model. The model’s successful application across Brazil’s diverse regions demonstrates its generalizability to other dengue-endemic areas with varying climatic and epidemiological conditions. By integrating diverse data sources, the framework captures key transmission drivers, demonstrating the potential of LSTM neural networks for robust predictions. These findings provide valuable insights to enhance public health strategies and outbreak preparedness in Brazil.

The Practice and Application of Machine Learning in Data Analysis

Currently, the data - driven decision - making model has emerged as the core impetus for the development of various industries. Machine learning technology, leveraging its robust pattern recognition and prediction capabilities, is reshaping the boundaries of traditional data analysis. This research focuses on the technical implementation paths of machine learning algorithms in the processing of structured and unstructured data, and reveals its value - transformation mechanisms in scenarios such as financial risk control, medical diagnosis, and intelligent manufacturing. In response to pain - point issues like data noise interference, insufficient model generalization ability, and excessive consumption of computing resources, innovative solutions such as feature engineering optimization, construction of ensemble learning frameworks, and deployment of edge computing are systematically explored. Through a comparative analysis of the differential performances of supervised learning and unsupervised learning in data modeling, the correlation rules between algorithm selection and business scenario adaptability are demonstrated, providing methodological support for cross - domain data value mining.

Battery Life Prediction for Ensuring Robust Operation of IoT Devices in Remote Metering

Primary batteries are extensively employed as power sources in Internet of Things (IoT) devices for remote metering. However, primary batteries maintain a relatively consistent discharge voltage curve over a long period before experiencing a full discharge, making it challenging to predict the battery’s life. In this study, we introduce a battery life prediction method to ensure the robust operation of IoT devices in remote metering applications. The robust battery life prediction process is divided into two stages. The first stage involves predicting the state of charge (SOC) to enable real-time remote monitoring of the battery status of metering devices. In the second stage, IoT devices implement a hardware-based alerting mechanism to provide warnings prior to complete discharge, leveraging a custom-designed Multi-Stage Discharge battery architecture. In the first stage, we developed the CNN-Series Decomposition Transformer (C-SDFormer) model, which is capable of accurately predicting the SOC of primary batteries. This model was specifically designed to support the real-time monitoring of battery status in large-scale IoT deployments, enabling proactive maintenance and enhancing system reliability. To validate the performance of the C-SDFormer model, data were collected from smart remote meters installed in households. The model was trained using the collected data and evaluated through a series of experiments. The performance of the C-SDFormer model was compared with existing methods for SOC prediction. The results indicate that the C-SDFormer model outperformed the traditional methods. Specifically, the SOC prediction achieved a mean absolute error (MAE) of less than 4.1%, a root mean square error (RMSE) of less than 5.2%, a symmetric mean absolute percentage error (SMAPE) of less than 7.0%, and a coefficient of determination (R2) exceeding 0.96. These results demonstrate the effectiveness of the C-SDFormer model in accurately predicting the SOC of primary batteries. For the second stage, a Multi-Stage Discharge (MSD) primary battery was developed to ensure a hardware-based low battery alert before the battery is fully discharged. This battery was designed to ensure the reliable operation of IoT devices, especially those whose batteries are not proactively managed through real-time monitoring in the first stage. By providing a low battery alert, the MSD battery reduces the risk of unexpected device shutdowns. This feature enhances the overall reliability of IoT devices, ensuring their continuous operation in remote metering applications.

Research on Real Estate Market Prediction Models Based on Big Data and Artificial Intelligence

The intersection of big data and artificial intelligence has significantly transformed computational techniques for predicting real estate market trends, aligning closely with the thematic scope of “Frontiers in Computer Science.” Traditional real estate forecasting models often fail to capture the intricate spatial, temporal, and economic dependencies essential for robust prediction. Challenges such as data sparsity, nonlinearity, and market volatility remain inadequately addressed, limiting their scalability and adaptability in dynamic market conditions. To address these gaps, we propose a novel framework comprising the Dynamic Relational Price Network (DRPN) and the Market Adaptive Optimization Strategy (MAOS). DRPN integrates graph-based reasoning for spatial dependencies, temporal forecasting with recurrent networks, and hierarchical feature learning to improve interpretability and predictive accuracy. Meanwhile, MAOS dynamically adjusts model parameters and regularization strategies based on real-time market conditions, ensuring robust generalization across diverse scenarios. Experimental results demonstrate the superior performance of our approach in predictive accuracy, stability, and scalability compared to conventional methods, providing actionable insights into market dynamics. This research offers a scalable and adaptive solution to real estate forecasting, contributing to the broader applications of AI in computational market analysis.

A Small-Scale Investigation into the Viability of Detecting Canopy Damage Caused by Acantholyda posticalis Disturbance Using High-Resolution Satellite Imagery in a Managed Pinus sylvestris Stand in Central Poland

As the effects of climate change progressively worsen, many scientists are concerned over the expanding geographic range and impact of forest-defoliating insects. Many are currently pointing to this form of disturbance becoming a key focus of remote sensing research in the coming decades; however, the available body of research remains lacking. This study investigated the viability of detecting and quantifying damage caused to a managed Scots pine forest in central Poland by insect defoliation disturbance using high-resolution multispectral satellite imagery. Observed leaf area index (LAI) values were compared to frass observations (insect detritus) to assess the relationship between LAI and defoliating insect activity across a single life cycle of A. posticalis Mats. Across four managed plots, four vegetative indices (NDVI, GNDVI, EVI, and MSAVI2) were calculated using multispectral satellite imagery from a PlanetScope (PSB.SD instrument) satellite system. Then, 1137 point-sampled digital number (DN) values were extracted from each index, and a correlation analysis compared each to 40 ground-observed LAI data points. LAI was modeled on the basis of NDVI values. Three models were assessed for their performance in predicting LAI. They were fit using a variety of regression techniques and assessed using several goodness-of-fit measures. A relationship between observed LAI and frass observations was found to be statistically significant (p-value = 0.000303). NDVI was found to be the correlated LAI values (rho = 0.612). Model 3, which was based on concepts of the Beer–Lambert law, resulted in the most robust predictions of LAI. All parameters were found to be significant post fitting of the model using a nonlinear least squares method. Despite the success of the Beer’s law model in predicting LAI, detection of A. posticalis damage was not achieved. This was predominately due to issues of resolution and plot condition, among others. The results of this analysis address many interesting facets of remote sensing analysis and challenge the commonly held view of the impeachability of these methods.