An Automated Conformalized Causal Learning System for Enhanced Mineral Prospectivity Mapping

The majority of machine learning algorithms that have been applied in data-driven predictive mapping of mineral prospectivity require a sufficient number of training samples (known mineral deposits) to obtain results with high performance and reliability. Semi-supervised learning can take advantage of the huge amount of unlabeled data to benefit the supervised learning tasks and hence provide a suitable scheme for mapping mineral prospectivity in cases where only few known mineral deposits are available. Semi-supervised random forest was used in this study to map mineral prospectivity in the southwestern Fujian metallogenic belt of China, where there is still excellent potential for mineral exploration due to the large proportion of areas covered by forest. The findings obtained from the current study include: (1) semi-supervised learning can make use of both the labeled and unlabeled samples to help improve the performance of mapping mineral prospectivity; (2) multi-dimensional scaling can be used to explore the clustering structure within the samples, which provides a tool to validate the usability of semi-supervised learning algorithms. In addition, the prospectivity map obtained in this study can be used to guide further mineral exploration in the southwestern Fujian of China.

This study applies machine learning (ML) techniques to classify fertile [for porphyry Cu and (or) Au systems] and barren adakites using geochemical data from New Brunswick, Canada. It emphasizes that not all intrusive units, including adakites, are inherently fertile and should not be directly used as the heat source evidence layer in mineral prospectivity mapping without prior analysis. Adakites play a crucial role in mineral exploration by helping distinguish between fertile and barren intrusive units, which significantly influence ore-forming processes. A dataset of 99 fertile and 66 barren adakites was analyzed using seven ML models: support vector machine (SVM), neural network, random forest (RF), decision tree, AdaBoost, gradient boosting, and logistic regression. These models were applied to classify 829 adakite samples from around the world into fertile and barren categories, with performance evaluated using area under the curve (AUC), classification accuracy, F1 score, precision, recall, and Matthews correlation coefficient (MCC). SVM achieved the highest performance (AUC = 0.91), followed by gradient boosting (0.90) and RF (0.89). For model validation, 160 globally recognized fertile adakites were selected from the dataset based on well-documented fertility characteristics. Among the tested models, SVM demonstrated the highest classification accuracy (93.75%), underscoring its effectiveness in distinguishing fertile from barren adakites for mineral prospectivity mapping. Statistical analysis and feature selection identified middle rare earth elements (REEs), including Gd and Dy, with Hf, as key indicators of fertility. A comprehensive analysis of 1596 scatter plots, generated from 57 geochemical variables, was conducted using linear discriminant analysis (LDA) to determine the most effective variable pairs for distinguishing fertile and barren adakites. The most informative scatter plots featured element vs. element combinations (e.g., Ga vs. Dy, Ga vs. Gd, and Pr vs. Gd), followed by element vs. major oxide (e.g., Fe2O3T vs. Gd and Al2O3 vs. Hf) and ratio vs. element (e.g., La/Sm vs. Gd, Rb/Sr vs. Hf) plots, whereas major oxide vs. major oxide, ratio vs. ratio, and major oxide vs. ratio plots had limited discriminatory power.

Mineral systems are composed of many interacting components that lead to complex, singular and rare properties of geo-data. In mineral prospectivity mapping (MPM), supervised machine learning algorithms, which have advantages in dealing with complex geo-data, usually involve uncertainty resulting from the discretization of continuous evidential maps into arbitrary classes as well as the large data imbalance caused by the rarity of deposit locations. Consequently, the predicted results may be biased. In this paper, a random forest (RF) algorithm based on the bagging technique is used to map the prospectivity of tungsten polymetallic deposits in the Nanling metallogenic belt. Data-driven logistic transformation is employed to obtain continuous evidential maps. Both discretized and continuous evidential maps are used to generate prospectivity models for comparison. To reduce the data imbalance, the under-sampling method and the synthetic minority over-sampling technique (SMOTE) are implemented to generate balanced datasets. The receiver operating characteristic (ROC) curve and improved prediction-area (P-A) plot are applied to evaluate the prospectivity models. The predictive results show that when using the RF algorithm in MPM, the application of continuous evidential maps can improve the performance of prospectivity models and reduce the uncertainty resulting from the discretization of evidential maps. The prospectivity model trained with a balanced SMOTE-generated dataset shows the best overall performance for improving the percentage of deposit locations that are correctly predicted and decreasing the percentage of non-deposit locations that are inaccurately identified as deposit locations to some extent. In addition, the improved P-A plot is superior to the ROC curve because the latter neglects the occupied area, which is critical for mineral exploration and may provide an overly optimistic performance with imbalanced data. However, further testing of the evaluation criteria and the SMOTE approach to reduce data imbalance is warranted to determine fully the universality in MPM from the perspective of data imbalance. Based on prospectivity models, four high-potential areas and five moderate-potential areas are delineated, which indicates good future prospecting for tungsten polymetallic deposits in this region.

Fuzzy analytical hierarchy (AHP) approach is a method for mineral prospectivity mapping (MPM) that is generally used for mineral exploration. This method is feasible for multi-criteria decision-making (MCDM) issues. Geographical information system (GIS) and fuzzy AHP have been applied in this paper to obtain prospectivity model for Calcic Iron Skarn (CIS) mineralization. Several thematic (such as geological, geophysical, and geochemical) geo-datasets have been collected, analysed and integrated based on fuzzy AHP method, in Varan area, central of Iran. Three professional economic geologists with the experience on exploration of CIS mineralization have been used to allocate appropriate weights to layers. Then fuzzy operator was used to integrate weighted evidence layers and mineral prospectivity map of CIS mineralization in Varan area was generated. Eventually for confirming the accuracy of the applied manner, locations of recognized mineral deposits in the Varan area were compared with the generated mineral prospectivity map. The results presented acceptable responses. For detailed assessment of the CIS mineralization model and due to the fact that geological features have fractal dimensions, we used C-A model for classification of prospectivity model to determine thresholds for the final prospectivity map. C-A fractal model, determine thresholds for classifying values in evidential maps. The final prospectivity map was confirmed by checking field of three target areas.

Data-driven logistic-based weighting of geochemical and geological evidence layers in mineral prospectivity mapping

Porphyry-type mineral prospectivity mapping with imbalanced data via prior geological transfer learning

In mineral exploration, proposing new prospects is a main issue and geospatial information system (GIS) offers different techniques for this procedure. Mineral prospectivity maps (MPMs) can reduce costs and errors for predicting mineral potentials. In this research, data layers have been analyzed and integrated for porphyry copper mineral prospectivity mapping in Chahargonbad sheet of Kerman Province, Central Iran. First of all, geological, geochemical, geophysical, and satellite imagery have been processed separately and assigned according to their favorability in porphyry copper mineralization using index overlay and fuzzy logic methods which was lead to introduce two priorities for further exploration. Eight hundred forty-six geochemical stream sediment samples were analyzed using multifractal concentration-number model to generate geochemical anomaly maps. Afterward, airborne magnetic data was used to extract magnetic edges which can represent structures (faults and fractures) and lithological contacts. Airborne radiometric data is also used to identify felsic units based on K, Th, and U (RGB) ternary image. Thereafter, satellite imagery (ASTER, ETM+ images) was processed based on relative absorption band depth (RBD), principle component analysis (PCA) and Crosta methods in order to separate alteration zones in the study area. Totally, 80 km2 has been detected as the first priority that is located in the northwest (Kuh Panj), center (south of Hamid Abad and east of Sorkhgino), southeast (Chenar Kaf), and southwest (north of Alimoradi) of this sheet. Also, the second priority (97 km2) is located in the center (southeast of Syloieh), southeast (Chenar Kaf), east (Cheheltan), and northwest (south of Kuh Panj).

Mineral prospectivity mapping (MPM) is a powerful approach for identifying mineralization zones with high potential for economically viable mineral deposits. This study proposes a hybrid framework combining a Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP), a Convolutional Neural Network (CNN) and a Fuzzy-Kernel Extreme Learning Machine (FKELM) to address the challenges of imbalanced and uncertain datasets in mineral exploration. The approach was applied to the G.R. Halli gold prospect, in the Chitradurga Schist Belt, Western Dharwar Craton, India, using nine geochemical pathfinder elements. WGAN-GP generated high-quality negative samples, balancing the dataset and reducing overfitting. Compared with Support Vector Machines, Gradient Boosting, and a baseline CNN, FKELM (AUC = 0.976, accuracy = 92%) and WGAN-GP + CNN (AUC = 0.973, accuracy = 91%) showed superior performance and produced geologically coherent prospectivity maps. Promising gold targets were delineated, closely aligned with known mineralized zones and geochemical anomalies. This hybrid framework provides a robust, cost-effective, and scalable MPM solution for structurally controlled geological tracts, insufficient data terrains, and integration with additional geoscience datasets for other complex mineral systems.

Brain tumor is one of the most aggressive diseases nowadays, resulting in a very short life span if it is diagnosed at an advanced stage. The treatment planning phase is thus essential for enhancing the quality of life for patients. The use of Magnetic Resonance Imaging (MRI) in the diagnosis of brain tumors is extremely widespread, but the manual interpretation of large amounts of images requires considerable effort and is prone to human errors. Hence, an automated method is necessary to identify the most common brain tumors. Convolutional Neural Network (CNN) architectures are successful in image classification due to their high layer count, which enables them to conceive the features effectively on their own. The tuning of CNN hyperparameters is critical in every dataset since it has a significant impact on the efficiency of the training model. Given the high dimensionality and complexity of the data, manual hyperparameter tuning would take an inordinate amount of time, with the possibility of failing to identify the optimal hyperparameters. In this paper, we proposed a Bayesian Optimization-based efficient hyperparameter optimization technique for CNN. This method was evaluated by classifying 3064 T-1-weighted CE-MRI images into three types of brain tumors (Glioma, Meningioma, and Pituitary). Based on Transfer Learning, the performance of five well-recognized deep pre-trained models is compared with that of the optimized CNN. After using Bayesian Optimization, our CNN was able to attain 98.70% validation accuracy at best without data augmentation or cropping lesion techniques, while VGG16, VGG19, ResNet50, InceptionV3, and DenseNet201 achieved 97.08%, 96.43%, 89.29%, 92.86%, and 94.81% validation accuracy, respectively. Moreover, the proposed model outperforms state-of-the-art methods on the CE-MRI dataset, demonstrating the feasibility of automating hyperparameter optimization.

Geochemical exploration of stream sediments is an important step for the identification of areas of interest with potential mineralization, particularly in the early stages of mineral exploration. A total of 407 sample points for 15 different geochemical traces were collected from Central Wales and classified into two groups: a training group consisting of 285 samples and a testing group consisting of 122 samples. Geospatial characterization of each parameter at stream level was performed using two different prediction models; the inverse distance weighting and the geostatistical kriging. Several variations of the IDW model was applied based on the power function and the number of the sample points, and the best one selected based on “root mean square prediction error” statistic. The same statistic was also used in the best-fitted semivariogram models including the circular, spherical, exponential and Gaussian for each geochemical parameter in Kriging. Finally, the mineral prospectivity map of the area was developed based on the geochemical accumulation index (GAI) using multivariate overlay analysis. The experimental results show that there is no single method that can be used independently to predict the spatial distribution of geochemical elements in streams. Instead, a combinatory approach of IDW and kriging is advised in order to generate more accurate predictions. The mineral prospectivity map based on GAI showed that most of the mineral-enriched streams were found in northwest, northeast, and south part of the study area which was also confirmed with the existing mining activities in the region.

In machine learning applications, the reliability of predictions is significant for assisted decision and risk control. As an effective framework to quantify the prediction reliability, conformal prediction (CP) was commonly developed with <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula> -nearest neighbor, known as CPKNN. However, the conventional CPKNN suffers from high variance and bias, and long computational time as the feature dimensionality increases. To address these limitations, a new CP framework-CP with shrunken centroids (CPSC) is proposed. It regularizes the class centroids to attenuate the irrelevant features and shrink the sample space for predictions and reliability quantification. We have also compared the CPSC with CP based on SVM, LightGBM, RF on the herbal medicine dataset, with the electronic nose as a case and assessed them in two tasks: 1) off-line prediction: the training set was fixed, and the accuracy on the testing set was evaluated and 2) online prediction with data augmentation: CPKNN and CPSC filtered unlabeled data to augment the training data based on the prediction reliability, and the final accuracy of the testing set was compared. The result shows that CPSC significantly outperformed CPKNN in both two tasks: 1) CPSC reached a significantly higher accuracy with lower computation cost, and with the same credibility output, CPSC generally achieved higher accuracy and 2) the data augmentation process with CPSC robustly manifested a statistically significant improvement in prediction accuracy with different reliability thresholds, and the augmented data were more balanced in classes. This novel CPSC provides higher prediction accuracy and better reliability quantification, which can assist in reliable decision support.

Black-box zero-th order optimizationis a central primitive for applications in fields as diverse as finance, physics, and engineering. In a common formulation of this problem, a designer sequentially attempts candidate solutions, receiving noisy feedback on the value of each attempt from the system. In this paper, we study scenarios in which feedback is also provided on the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">safety</i> of the attempted solution, and the optimizer is constrained to limit the number of unsafe solutions that are tried throughout the optimization process. Focusing on methods based on Bayesian optimization (BO), prior art has introduced an optimization scheme – referred to as <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SafeOpt</small> – that is guaranteed not to select <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">any</i> unsafe solution with a controllable probability over feedback noise as long as strict assumptions on the safety constraint function are met. In this paper, a novel BO-based approach is introduced that satisfies safety requirements irrespective of properties of the constraint function. This strong theoretical guarantee is obtained at the cost of allowing for an arbitrary, controllable but non-zero, rate of violation of the safety constraint. The proposed method, referred to as <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Safe-Bocp</small>, builds on online conformal prediction (CP) and is specialized to the cases in which feedback on the safety constraint is either noiseless or noisy. Experimental results on synthetic and real-world data validate the advantages and flexibility of the proposed <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Safe-Bocp</small>.

Introduction: The 30–50% non-response rate to cardiac resynchronization therapy (CRT) calls for improved patient selection and optimized pacing lead placement. The study aimed to develop a novel technique using patient-specific cardiac models and machine learning (ML) to predict an optimal left ventricular (LV) pacing site (ML-PS) that maximizes the likelihood of LV ejection fraction (LVEF) improvement in a given CRT candidate. To validate the approach, we evaluated whether the distance DPS between the clinical LV pacing site (ref-PS) and ML-PS is associated with improved response rate and magnitude.Materials and methods: We reviewed retrospective data for 57 CRT recipients. A positive response was defined as a more than 10% LVEF improvement. Personalized models of ventricular activation and ECG were created from MRI and CT images. The characteristics of ventricular activation during intrinsic rhythm and biventricular (BiV) pacing with ref-PS were derived from the models and used in combination with clinical data to train supervised ML classifiers. The best logistic regression model classified CRT responders with a high accuracy of 0.77 (ROC AUC = 0.84). The LR classifier, model simulations and Bayesian optimization with Gaussian process regression were combined to identify an optimal ML-PS that maximizes the ML-score of CRT response over the LV surface in each patient.Results: The optimal ML-PS improved the ML-score by 17 ± 14% over the ref-PS. Twenty percent of the non-responders were reclassified as positive at ML-PS. Selection of positive patients with a max ML-score >0.5 demonstrated an improved clinical response rate. The distance DPS was shorter in the responders. The max ML-score and DPS were found to be strong predictors of CRT response (ROC AUC = 0.85). In the group with max ML-score > 0.5 and DPS< 30 mm, the response rate was 83% compared to 14% in the rest of the cohort. LVEF improvement in this group was higher than in the other patients (16 ± 8% vs. 7 ± 8%).Conclusion: A new technique combining clinical data, personalized heart modelling and supervised ML demonstrates the potential for use in clinical practice to assist in optimizing patient selection and predicting optimal LV pacing lead position in HF candidates for CRT.

The rapid advancement of large language models has raised significant concerns regarding their potential misuse by malicious actors.As a result, developing effective detectors to mitigate these risks has become a critical priority.However, most existing detection methods focus excessively on detection accuracy, often neglecting the societal risks posed by high false positive rates (FPRs).This paper addresses this issue by leveraging Conformal Prediction (CP), which effectively constrains the upper bound of FPRs.While directly applying CP constraints FPRs, it also leads to a significant reduction in detection performance.To overcome this trade-off, this paper proposes a Zero-Shot Machine-Generated Text Detection Framework via Multiscaled Conformal Prediction (MCP), which both enforces the FPR constraint and improves detection performance.This paper also introduces RealDet, a high-quality dataset that spans a wide range of domains, ensuring realistic calibration and enabling superior detection performance when combined with MCP.Empirical evaluations demonstrate that MCP effectively constrains FPRs, significantly enhances detection performance, and increases robustness against adversarial attacks across multiple detectors and datasets.

Purpose of research. The purpose of the study is to evaluate certain machine learning models in data processing based on speed and efficiency related to the analysis of sentiment or consumer opinions in business intelligence. To highlight the existing developments, an overview of modern methods and models of sentiment analysis is given, demonstrating their advantages and disadvantages.Materials and methods. In order to improve the semester analysis process, organized using existing methods and models, it is necessary to adjust it in accordance with the growing changes in information flows today. In this case, it is crucial for researchers to explore the possibilities of updating certain tools, either to combine them or to develop them to adapt them to modern tasks in order to provide a clearer understanding of the results of their treatment. We present a comparison of several deep learning models, including convolutional neural networks, recurrent neural networks, and long-term and shortterm bidirectional memory, evaluated using different approaches to word integration, including Bidirectional Encoder Representations from Transformers (BERT) and its variants, FastText and Word2Vec. Data augmentation was conducted using a simple data augmentation approach. This project uses natural language processing (NLP), deep learning, and models such as LSTM, CNN, SVM TF-IDF, Adaboost, Naive Bayes, and then combinations of models.The results of the study allowed us to obtain and verify model results with user reviews and compare model accuracy to see which model had the highest accuracy results from the models and their combination of CNN with LSTM model, but SVM with TF-IDF vectoring was most effective for this unbalanced data set. In the constructed model, the result was the following indexes: ROC AUC - 0.82, precision - 0.92, F1 - 0.82, Precision - 0.82, and Recall - 0.82. More research and model implementation can be done to find a better model.Conclusion. Natural language text analysis has advanced quite a bit in recent years, and it is possible that such problems will be completely solved in the near future. Several different models in ML and CNN with the LSTM model, but SVM with the TF-IDF vectorizer proved most effective for this unbalanced data set. In general, both deep classification algorithm. A combination of both approaches can also learning and feature-based selection methods can be used to solve be used to further improve the efficiency of the algorithm. some of the most pressing problems. Deep learning is useful when the most relevant features are not known in advance, while feature-based